Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
Example 1:
the embodiment provides a method for calculating inventory of key parts of a pure electric vehicle.
Referring to fig. 1, the method is shown to include steps S100, S200, S300, S400, S500, and S600.
Step S100, acquiring first information, second information and third information, wherein the first information comprises historical sales data and market trend information of key parts of the pure electric automobile, the second information comprises life cycle data and supply time data of the key parts, and the third information comprises historical purchase price, price discount information and transportation cost information provided by suppliers.
It is understood that the first information includes historical sales data and market trend information of key components of the power battery, the motor, the BMS system, and the like. By analyzing the historical sales data, sales of the parts, including sales quantity, sales trend, etc., can be known. At the same time, market trend information can provide insight about the trend of these aftermarket demands, helping us predict future demand situations. The second information covers life cycle data and supply time data of key parts such as a power battery, a motor, a BMS system and the like. The life cycle data comprises key indexes such as service life, life distribution, life change trend and the like of the parts. These data can help us evaluate the useful life of the parts and formulate corresponding inventory strategies based on their characteristics. Supply time data relates to the supply time period and stability of the supply of the parts, knowing which information allows for better planning of the supply chain and ensures timely replenishment of the inventory. The third information includes historical purchase price, price discount information, and transportation cost information provided by the provider. By knowing historical purchase price and price discount information, the purchase cost of these components can be assessed and discounts and offers can be sought during the purchase process to reduce inventory costs. In addition, transportation cost information needs to be taken into account as it has a significant impact on the design and inventory planning of the supply chain. By acquiring and analyzing the key information, demand prediction, inventory planning and purchasing decision can be more accurately carried out, so that the supply chain management efficiency of key parts such as power batteries, motors, BMS systems and the like is improved.
And step 200, carrying out time sequence analysis according to the first information to obtain a demand prediction result, wherein the demand prediction result comprises demand fluctuation data of key parts in a preset time period in the future.
It will be appreciated that in this step, by analysis of historical sales data and market trend information, the volatility characteristics of critical component demands are identified and future demand trends and fluctuations are predicted. The step S200 includes a step S210, a step S220, a step S230, a step S240, and a step S250.
Step S210, preprocessing is carried out according to the historical sales data to obtain preprocessed data.
It will be appreciated that this step performs data cleansing on historical sales data, including removing duplicate data, repairing missing values, handling outliers, and the like. These purging operations can eliminate noise and errors in the data, ensuring the accuracy and integrity of the data.
And step S220, carrying out trend analysis and smoothing treatment according to the market demand change trend and the competitor sales situation in the market trend information to obtain market trend data.
It can be appreciated that in this step, the periodic and trending changes of the market demand can be understood by first observing the trend of the market demand, including seasonal changes, long-term trends, etc., which helps to capture the periodic fluctuations and long-term trends of the market. The market trend data is then smoothed to eliminate short term fluctuations and noise disturbances. Preferably, the smoothing process uses a moving average, exponential smoothing, or the like. And more stable and reliable market trend data can be obtained through smoothing treatment, so that subsequent demand prediction and analysis are facilitated. In the trend analysis and smoothing process, sales of competitors are also considered. Through observation and analysis of competitor sales data, sales trends and market share changes of other manufacturers in the market can be known. This helps to more accurately grasp the competitive situation of the market and consider the impact of competitors in demand forecasting.
And step S230, carrying out fluctuation analysis and heteroscedasticity test according to the preprocessing data and the market trend data to obtain characteristic information, wherein the characteristic information comprises fluctuation characteristics and heteroscedasticity characteristics of the key spare and accessory parts requirements.
It will be appreciated that the volatility analysis is first performed using the pre-processing data and market trend data to understand the extent of volatility of critical component requirements. The volatility characteristics of the critical component requirements can be obtained by analyzing the volatility of the historical sales data. Further, the fluctuation degree of the demand is evaluated by calculating the standard deviation, the coefficient of variation, and the like of the sales data. This helps us to understand the uncertainty and volatility of critical component demands, thus providing an important basis for inventory management. Meanwhile, a heteroscedasticity test is needed to know whether the demand of the key parts has heteroscedasticity or not. Heteroscedasticity refers to the characteristic that the variance of demand changes over time. Preferably, the demand heteroscedasticity feature is evaluated using an autoregressive conditional heteroscedasticity model. This helps us identify the pattern of change in demand, especially for critical parts that have heteroplasmy, and can take corresponding inventory management strategies. The processing method of the step provides important reference information for subsequent demand prediction and inventory management, and helps us better understand and cope with the uncertainty and variability of the critical spare and accessory part demands.
And step 240, performing model construction according to the characteristic information and a preset autoregressive conditional heteroscedastic mathematical model to obtain a demand prediction model.
It can be understood that the demand prediction model is constructed according to a preset autoregressive conditional heteroscedastic mathematical model and by combining characteristic information. An autoregressive conditional heteroscedastic (ARCH) model is a commonly used time series model for describing the variability and variance of time series data. It takes into account the effect of the residual of the past moment on the variance of the current moment and captures the volatility characteristics of the time series by introducing an heteroscedastic term. When the demand prediction model is constructed, a preset autoregressive conditional heteroscedastic mathematical model is used as a basis, and model parameters and structures are adjusted according to the characteristic information. By fitting the model and estimating parameters, an accurate demand prediction model can be obtained, and the change rule of the fluctuation and variance of the demand of the key parts can be better described. The demand prediction model is used for predicting demand fluctuation data of key parts in a preset time period in the future. The method can provide probability distribution information of the requirements of the key parts, help us predict the possible range and probability distribution of the requirements, and support the formulation and optimization of inventory management decisions. By constructing the demand prediction model, the demand fluctuation of the key parts can be predicted more accurately, and a more reliable prediction result is provided for inventory management. This helps to improve the efficiency and accuracy of inventory management, reduce the risk of inventory starvation and overstock, thereby better meeting customer needs and reducing costs.
And S250, taking market trend information and a preset future time point as input values of a demand prediction model, and deducing and predicting the demand fluctuation data of the key parts in the future preset time period through the demand prediction model.
It can be understood that in this step, the market trend information and the preset future time point are used as inputs to perform mathematical calculation and model analysis by using the previously established demand prediction model. Parameter estimation and model fitting are performed by using an ARCH model, and future demand volatility is predicted by considering demand change trend and volatility in historical data and according to the modes and rules. The goal of model inference is to predict future demand trend and volatility using past experience and trends. For example, if the forecast results indicate that future demand is fluctuating, the enterprise may take more flexible inventory management strategies, maintaining a higher safety inventory level to cope with the demand fluctuations. Conversely, if the forecast results indicate that future demand is less fluctuating, the enterprise may adjust inventory levels appropriately to reduce inventory costs and increase the efficiency of the supply chain.
And step S300, a demand-supply model is constructed according to the second information and the demand prediction result, and a service level target is obtained by performing simulation calculation according to the demand-supply model, wherein the service level target represents the probability that a customer can obtain required parts in a preset time period.
It can be understood that this step can construct a mathematical model describing the relationship between demand and supply by analyzing the life cycle distribution pattern of the critical components and features such as volatility, seasonal nature, etc. of the supply time. Simulation calculations are then performed using the demand-supply model to evaluate the impact of different inventory levels on service levels by simulating different supply chain instances and scenarios. In the simulation calculation process, service level targets are determined according to calculation results of the model by considering different inventory levels, supply time changes, demand fluctuation and other factors. The service level objective is to measure supply chain performance and an important indicator of meeting customer needs. The step S300 includes step S310, step S320, step S330, step S340, and step S350.
Step S310, carrying out pattern recognition processing according to the life cycle data and a preset life cycle distribution algorithm to obtain a life cycle distribution pattern, wherein the life cycle distribution pattern comprises the average life, life probability distribution and life variation trend of key parts.
It can be appreciated that the life cycle distribution pattern of the critical parts can be identified by processing the history of the life of the parts in this step. In addition, by applying a life cycle distribution algorithm, the probability distribution of the service life of the key parts is deduced, and the service life probability of the key parts in a given time range can be estimated, so that the reliability and the fault probability of the key parts can be better known. Finally, by observing and analyzing the trend of the change in the life of the key parts, the possible trend of life change, such as the increase or decrease of the life, can be identified. Specifically, taking management of battery packs as an example, the sum of the service lives of all the battery packs is calculated first, and divided by the total number of the battery packs to obtain the average life. Next, a life cycle distribution algorithm is applied to infer a probability distribution of battery pack life. Preferably, the weber distribution is used to fit the probability distribution of the battery pack lifetime, resulting in a probability distribution curve suitable for the battery pack lifetime. By fitting a curve, the probability of battery pack life over a given time frame can be estimated. This may help us predict the probability of battery assembly failure occurring within a particular time period in order to take appropriate inventory management and maintenance measures. Finally, the trend of the life of the battery assembly can be known by observing and analyzing the trend of the life cycle data. Such trends may be captured by trend analysis and regression models and used to predict future life changes of the battery assembly.
And step S320, carrying out regression analysis according to the supply time data, and obtaining statistical characteristics by determining the relation between the supply time and other factors, wherein the statistical characteristics comprise average supply time, supply time fluctuation and seasonality of key parts.
It will be appreciated that data relating to the time of supply of critical parts, including supplier delivery time, time of logistics transportation, etc., is first collected and used as input to regression analysis. With the supply time as a dependent variable and other factors that may affect the supply time as independent variables, such as the supplier's delivery capacity, logistics transportation efficiency, order processing time, etc., may have an effect on the supply time. By regression analysis, the specific degree of influence of these factors on the supply time can be determined and a corresponding mathematical model established. On the basis of regression analysis, the average supply time of the key parts can be obtained, and the average predicted value of the supply time is obtained by solving a regression model. Further, by analyzing the regression residual, i.e. the difference between the actual supply time and the predicted supply time. The volatility of the supply time can be estimated by calculating the standard deviation or variance of these residuals. A larger residual value indicates a higher volatility of the supply time, while a smaller residual value indicates a lower volatility of the supply time. Finally, the supply time is subjected to seasonal analysis, and the change modes of the supply time in different seasons or specific time periods are observed, so that the existing seasonal change can be identified. For example, during certain periods of time, the supply time may change as affected by holidays or seasonal demands. Regression analysis and statistical property calculation can help us to understand the supply time characteristics of critical parts.
And step S330, carrying out gray correlation analysis according to the life cycle distribution mode and the statistical characteristics to obtain a correlation index, and sorting the life cycle distribution mode and the statistical characteristics based on the correlation index to obtain a sorting result.
It will be appreciated that gray correlation analysis is a method of comparing and ranking a plurality of factors, the importance of which is determined based on the degree of correlation between the factors. In the step, firstly, the life cycle distribution mode and the statistical characteristics are converted into numerical values so as to analyze gray correlation degree. Preferably, this is achieved by means of normalization and normalization, ensuring that the individual factors are compared on the same scale. Then, a gray correlation calculation formula is used to calculate a correlation index between the life cycle distribution pattern and the statistical characteristics. The higher the association index, the stronger the association between the two, indicating that they are also of higher importance in the demand-supply model. And finally, sorting the life cycle distribution mode and the statistical characteristics according to the relevancy index to obtain a sorting result. The sequencing result guides the construction process of the demand-supply model, so that factors with higher relevance are considered more seriously and accurately. The calculation process is as follows:
Step S331, setting life cycle distributionThe pattern is a sequenceStatistical properties are sequencesWherein n represents the length of the time period;
step S332, calculating the variation among each data point, and combining the statistical characteristics of the Gaussian distribution, such as the weight, the mean value, the standard deviation and the like, so as to obtain a relevance index for measuring the relevance between the sequences X and Y. The calculation formula is as follows:
wherein,as a correlation index, representing the degree of correlation between sequences X and Y; n is the length of the sequence, representing the number of data points in the sequence; i is the index value of the data point in the sequence; />As a weight factor, for adjusting the weight of each data point; />The variable quantity between two adjacent moments of the sequence X is used for measuring the variation trend of the sequence X; />The variable quantity between two adjacent moments of the sequence Y is used for measuring the variation trend of the sequence Y; />Is the average value of the sequence X and represents the average level of the sequence X; />Is the average value of the sequence Y and represents the average level of the sequence Y; />The standard deviation of the sequence X represents the fluctuation or variation degree of the sequence X; />The standard deviation of the sequence Y represents the fluctuation or variation degree of the sequence Y;
and step 340, performing model construction and parameter setting according to the sequencing result and a preset system dynamics model to obtain a demand-supply model, and performing simulation calculation on the demand and supply conditions of key parts based on the demand-supply model to obtain a simulation result.
It will be appreciated that system dynamics is a method for studying system behavior and interactions that focuses on interactions and feedback mechanisms between factors within the system. In this step, a system dynamics algorithm is utilized to analyze and model the dynamic relationship between the demand and supply of critical components. Firstly, parameter setting is carried out on the life cycle distribution mode and the statistical characteristics based on the sorting result obtained in the previous step. These parameters will be used as inputs to the system dynamics model to describe the dynamic changes in the demand and supply of critical components. Then, a demand-supply model of the key parts is built according to a preset system dynamics model, and the model reflects the complexity in practical situations by considering time delay, feedback mechanism and interaction between the demand and the supply. After the model is constructed, parameter setting is carried out, parameters of the model are adjusted and optimized, so that the model is more in line with actual conditions, and the dynamic relationship between the requirements and the supply can be accurately described. Finally, based on the demand-supply model, simulation calculation is performed, and the change trend of the demand and supply of the key spare parts and the influence of the change trend on the stock level and the supply chain can be observed and predicted through the simulation calculation.
And step 350, calculating to obtain a service level target according to the ratio of the time point at which the requirement is met in the simulation result to the total simulation time.
It will be appreciated that the simulation results demonstrate the variation in demand and supply of critical components over the simulation period. In this step, attention is paid to the point in time when the demand is satisfied, that is, the point in time when the demand is satisfied in the simulation time, and then the ratio of the point in time when the demand is satisfied to the total simulation time is calculated. This ratio reflects how much of the supply chain meets demand during the simulation period, with higher ratios indicating higher service levels of the supply chain and greater capacity to meet customer demand. Finally, the service level objective is determined according to the ratio of the time point when the demand is satisfied to the total simulation time, and the setting of the service level objective is generally performed according to the actual service demand and the market demand, preferably, the service level objective can be determined based on factors such as importance of the customer demand, reliability requirement of the supply chain, and the like.
Step 400, calculating to obtain safety stock data according to the demand prediction result, the service level target and a preset dynamic planning mathematical model, and calculating to obtain an order point according to the safety stock data, wherein the order point represents the stock level triggering re-order.
It will be appreciated that in this step, the demand forecast provides information on the amount of critical parts required, the service level objective determines the probability requirement to meet customer demand, and the pre-set dynamic planning mathematical model is used to optimize inventory costs and supply risk. The safety stock data represents the additional stock quantity required to be able to meet customer needs in the event of supply uncertainty. The order point is the stock level that reaches or triggers the re-order, when the stock level falls below the order point, the re-order is triggered to ensure that the stock can be timely replenished, and the future requirement is met. The step S400 includes a step S410, a step S420, a step S430, and a step S440.
Step S410, according to the demand prediction result and a preset dynamic planning mathematical model, safety stock data is obtained through optimization processing of minimizing stock cost and supply risk.
It will be appreciated that a pre-set dynamic programming mathematical model is introduced in this step that takes into account the trade-off between inventory costs and supply risk, and that an optimal inventory level is found by the optimization process to minimize inventory costs and supply risk. Further, in the optimization process, the influence of inventory holding cost, backorder cost and supply uncertainty on supply risk is considered, a mathematical model is used for describing the relation between inventory level and cost and risk, and an optimal solution is found through a numerical calculation method. Finally, through an optimization process, safety stock data is obtained, wherein the safety stock data represents the required additional stock quantity under the condition of supply uncertainty, so as to ensure that the requirements of customers can be met and the supply risk is reduced.
Step S420, according to the safety stock data and the service level target, a Markov chain Monte Carlo simulation algorithm is applied to simulate a plurality of supply chain instances and calculate corresponding service levels, and a service level simulation result is obtained.
It will be appreciated that the Markov chain Monte Carlo simulation algorithm is used in this step to evaluate the service level performance in different situations by simulating the operation of the supply chain multiple times based on randomness and probability. Various factors in the supply chain need to be considered in the simulation process, including supply delays, demand fluctuations, inventory management policies, etc. Each simulation instance represents one possible supply chain scenario, and by simulating multiple instances, the performance and service level of the supply chain can be more fully assessed. And finally, calculating a service level simulation result based on the simulation example, so that the service level simulation result can help us evaluate the performance of the supply chain and provide decision support. Through simulation and service level calculations for different supply chain instances, the potential risk and room for improvement of the supply chain can be better understood, thereby optimizing inventory management and improving customer satisfaction.
And S430, adjusting safety stock data by using a Bayesian optimization algorithm according to the service level simulation result, and performing iterative optimization to obtain optimized stock data.
It will be appreciated that a bayesian optimization algorithm is an iterative optimization algorithm that progressively finds the optimal solution by continually trying new combinations of parameters and learning from previous results. In the iterative optimization process, different safety stock data values are tried continuously, and evaluation is carried out according to the result of each attempt. The Bayesian optimization algorithm uses the existing simulation results and service level targets to guide the direction of parameter adjustment and gradually approaches the optimal inventory data. Finally, optimized inventory data is obtained through this iterative optimization process. These data are adjusted to a level that provides a higher level of service to better meet customer needs and reduce supply chain risk. In inventory management, various uncertainties such as demand fluctuation, supply delay and the like are faced, and a Bayesian optimization algorithm can optimize under the uncertainty conditions by deducing based on the existing simulation results and service level targets, so that the robustness and reliability of decision making are improved.
Step S440, calculating to obtain an order point according to the optimized inventory data and the preset inventory consumption mathematical model.
It will be appreciated that the optimized inventory data reflects the adjusted and optimized safety inventory levels, enabling more accurate satisfaction of demand and service level objectives. The inventory consumption mathematical model provides a method for quantifying and predicting inventory consumption. By combining the optimized inventory data with the inventory consumption mathematical model, a proper ordering point can be calculated, so that the re-ordering decision of the supply chain can be guided more accurately, the supply chain can be timely restocked according to the actual demand condition, inventory shortage or overage is avoided, and the flexibility and response capability of the supply chain are improved. Further, the construction and calculation process of the inventory consumption mathematical model comprises the following steps:
Step S441, determining the form of a basic model, wherein the basic model comprises baseline consumption and chaotic disturbance. Baseline consumption is the average trend of inventory consumption, fitted and predicted by time series analysis. Chaotic disturbance is a part of introducing chaotic theory and is used for simulating randomness and nonlinearity characteristics of inventory consumption.
Step S442, constructing a chaotic disturbance model, wherein the chaotic disturbance model comprises an initial value, seasonal variation and chaotic mapping. The initial value is a starting point of inventory consumption and can be determined from historical data. Seasonal fluctuations are periodic fluctuations in inventory consumption that can be extracted by time series decomposition. The chaotic map is a nonlinear function based on the chaos theory and is used for introducing the chaos effect. Preferably, a logistic map or an Enlong map or the like is used.
Step S443, parameters of the model, including initial values, amplitude and period of seasonal variation, and parameters of the chaotic map, are determined through fitting and optimization of historical data, and parameter adjustment is performed according to actual conditions.
Step S444, based on different initial values, seasonal variation and chaotic mapping parameters, different inventory consumption scenes are simulated and corresponding simulation calculation is performed, and a prediction result of inventory consumption is obtained.
Through this process, the inventory consumption mathematical model is able to capture the randomness and non-linearity characteristics of inventory consumption, providing more accurate inventory management predictions and decision support. The construction and parameter adjustment of the model can be optimized according to actual conditions so as to meet inventory management requirements in different scenes.
And S500, calculating according to the third information to obtain an economic ordering batch, wherein the economic ordering batch represents the optimal quantity of the ordered key spare parts in each ordering period.
It can be appreciated that the purchasing cost, the discount provided by the supplier, the transportation cost and other factors are comprehensively considered in the step, so that the purchasing cost is reduced to the greatest extent while the requirement is met, and the economic benefit maximization of the supply chain is realized. The step S500 includes a step S510, a step S520, a step S530, a step S540, and a step S550.
And S510, constructing an economic batch mathematical model according to the price discount information and the transportation cost information.
Optimally, this step uses a supply chain optimization-based approach to model construction to take into account the supplier's ordering constraints, inventory cost functions, and supply time impact. The following steps of the method are as follows:
Step S511, obtaining a subscription constraint according to the subscription policy and contractual agreement of the provider, wherein the subscription constraint includes minimum and maximum subscription numbers allowed by the provider, and a subscription period and a frequency of subscription.
Step S512, an inventory cost function is established, wherein the inventory cost function comprises holding cost and stock-out cost, the holding cost comprises warehouse expense and capital occupation cost, and the stock-out cost comprises sales loss and customer satisfaction reduction. The inventory cost function is as follows:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein C (x) represents an inventory cost function; h represents a unit holding cost; x represents the order number or batch size; s represents unit backorder cost; d represents a demand or sales quantity; f represents the amplitude of seasonal costs; ω represents the frequency of seasonal variation; t represents time; ϕ the phase difference.
Step S513, determining an appropriate safety stock level in the model taking into account the effect of the supply time on the stock demand. In particular, longer supply times require higher safety stock to cope with potential supply uncertainties.
Step S514, selecting a proper optimization objective function according to the economic batch targets. Such as minimizing total cost or maximizing service level.
Step S515, converting the optimization objective into an integer programming model by defining the influence of decision variables, which are integer variables representing the number of orders or lots per order period, the order constraints of the suppliers, the inventory cost function and the supply time. In this model, the goal of minimizing the total cost or maximizing the service level is considered while satisfying the vendor constraints.
Step S520, obtaining the order quantity through optimization and parameter adjustment calculation based on the economic batch model.
It will be appreciated that the economic batch model has taken into account the impact of the supplier's subscription constraints, inventory cost functions and supply time, while the process of optimization and parameter adjustment aims to find the number of subscriptions that will minimize the total cost or maximize the service level.
Step S530, carrying out feasibility evaluation according to the order quantity to obtain order batch.
It will be appreciated that this step evaluates whether the supplier is able to meet the calculated order quantity supply demand by taking into account the supplier's capacity, delivery capacity and commitment period. Meanwhile, the productivity and efficiency of the production line, the available capacity of the warehouse and the logistics transportation capability are also required to be evaluated, so that the production, storage and transportation requirements of the calculated ordering quantity can be met. By comprehensively evaluating these factors, the final ordering batches can be determined, supporting proper operation and optimization of the supply chain. This evaluation process is based on data and numerical analysis to ensure that the ordered batch can be efficiently executed in the actual supply chain.
Step S540, according to the minimum order number and supply time of the suppliers in the third information, comprehensively considering the requirement and supply condition of the supply chain, and calculating to obtain the economic order point.
It will be appreciated that in calculating the economic order point, the minimum number of orders for the suppliers is considered, ensuring that the number of orders per time meets the supplier requirements. At the same time we comprehensively consider the supply time, i.e. the time required from the order to the supply collection, to ensure that the order point can trigger in advance to cope with potential supply delays or uncertainties. The economic ordering point is calculated by comprehensively considering the demand and supply conditions of the supply chain, which is a key decision point for triggering the re-ordering process in the supply chain. By reasonably setting the economic order point, effective control of inventory can be achieved in the supply chain, timely supply is ensured, and meanwhile, the occurrence of excessive inventory or out-of-stock conditions is avoided. This may increase the efficiency and operational reliability of the supply chain, thereby enabling optimization of the supply chain and minimizing costs.
Step S550, obtaining the economic ordering batch according to the ordering batch and the economic ordering point.
It will be appreciated that by combining an economic ordering point with an ordering batch, inventory in the supply chain can be effectively managed, enabling control of inventory levels and minimizing costs.
Step S600, final inventory data is obtained according to the safety inventory data, the order points and the economic order batch calculation.
It will be appreciated that this step integrates the safety inventory data, the order points and the economic order batches, and calculates the final inventory data. These data will guide inventory management of the supply chain, ensure that inventory levels meet expectations, and achieve cost minimization and maximization of service levels. By accurately calculating and accurately controlling inventory, the supply chain can operate more efficiently, providing quality products and services. The step S600 includes step S610, step S620, step S630, and step S640.
Step S610, comparing the difference between the current stock level and the safety stock. If the inventory is lower than the safety inventory, indicating that replenishment is required; if the inventory is higher than the safety inventory, it may be desirable to reduce the amount of orders or stop orders. Such a comparison may help us determine whether an adjustment in inventory levels is required.
Step S620, dynamically adjusting the value of the order point according to the demand and the supply condition of the supply chain. The demand and supply conditions in the supply chain may vary, such as seasonal demand fluctuations, supply delays, etc. By adjusting the order point, the changing demand and supply conditions can be better satisfied, and the occurrence of stock shortage or excessive stock is avoided.
Step S630, calculating the optimal economic ordering batch by utilizing an economic ordering batch model and an optimization algorithm and combining the ordering constraint of the supplier and the inventory cost function. This batch can minimize subscription and inventory costs based on balancing costs and service levels. The calculation of the economic ordering batches requires taking into account the characteristics and requirements of the supply chain, ensuring an efficient functioning and good supply capacity of the supply chain.
Step S640, updating final inventory data according to the current inventory difference, the ordering point and the economic ordering batch. If an order is required, the impact of order quantity and supply time on inventory will be considered. Meanwhile, the change situation of the stock, including sales, returns, losses and other factors, is considered to ensure that the final stock data accurately reflects the actual situation of the supply chain.
Through the dynamic adjustment process, the calculation and adjustment of the ordering points and the economic ordering batch can be flexibly carried out according to the actual demands and changes of the supply chain. In this way, inventory management of the supply chain can be optimized, and the rationality of inventory level and the stability of supply capacity can be ensured, thereby improving the operation efficiency and response capacity of the supply chain.
Example 2:
as shown in fig. 2, the present embodiment provides a system for calculating inventory of critical parts of a pure electric vehicle, where the system includes:
the acquiring module 1 is configured to acquire first information, second information and third information, where the first information includes historical sales data and market trend information of key parts of the electric vehicle, the second information includes life cycle data and supply time data of the key parts, and the third information includes historical purchase price, price discount information and transportation cost information provided by a provider.
And the prediction module 2 is used for carrying out time sequence analysis according to the first information to obtain a demand prediction result, wherein the demand prediction result comprises demand fluctuation data of key parts in a preset time period in the future.
And the construction module 3 is used for constructing a demand-supply model according to the second information and the demand prediction result, and carrying out simulation calculation according to the demand-supply model to obtain a service level target, wherein the service level target represents the probability that a customer can obtain required parts in a preset time period.
And the planning module 4 is used for calculating to obtain safety stock data according to the demand prediction result, the service level target and a preset dynamic planning mathematical model, and calculating to obtain an order point according to the safety stock data, wherein the order point represents the stock level triggering re-ordering.
And the calculating module 5 is used for calculating and obtaining an economic ordering batch according to the third information, wherein the economic ordering batch represents the optimal quantity of the ordered key spare parts in each ordering period.
And the output module 6 is used for calculating final inventory data according to the safety inventory data, the ordering points and the economic ordering batch.
In one embodiment of the present disclosure, the prediction module 2 includes:
the first processing unit 21 is configured to perform preprocessing according to the historical sales data to obtain preprocessed data.
The first analysis unit 22 is configured to perform trend analysis and smoothing processing according to the market demand change trend and the competitor sales situation in the market trend information, so as to obtain market trend data.
The first extraction unit 23 is configured to perform a volatility analysis and a heteroscedasticity test according to the preprocessing data and the market trend data to obtain feature information, where the feature information includes a volatility feature and a heteroscedasticity feature of the critical component requirements.
The first construction unit 24 is configured to perform model construction according to the feature information and a preset autoregressive conditional heteroscedastic mathematical model to obtain a demand prediction model.
The first prediction unit 25 is configured to infer and predict, using the market trend information and a preset future time point as input values of a demand prediction model, the demand prediction model to obtain the demand fluctuation data of the key parts in the future preset time period.
In one embodiment of the present disclosure, the build module 3 includes:
the first identifying unit 31 is configured to perform a pattern recognition process according to the life cycle data and a preset life cycle distribution algorithm to obtain a life cycle distribution pattern, where the life cycle distribution pattern includes an average life, a life probability distribution, and a life variation trend of the key parts.
The second analysis unit 32 is configured to perform regression analysis according to the supply time data, and obtain statistical characteristics by determining a relationship between the supply time and other factors, where the statistical characteristics include average supply time, supply time volatility, and seasonality of the critical components.
And a third analysis unit 33, configured to perform gray correlation analysis according to the lifecycle distribution pattern and the statistical characteristics to obtain a correlation index, and rank the lifecycle distribution pattern and the statistical characteristics based on the correlation index to obtain a ranking result.
The second construction unit 34 is configured to perform model construction and parameter setting according to the sequencing result and a preset system dynamics model to obtain a demand-supply model, and calculate the demand and supply conditions of the key parts based on the demand-supply model simulation to obtain a simulation result.
The first calculating unit 35 is configured to calculate a service level target according to a ratio of a time point at which the demand is satisfied in the simulation result to the total simulation time.
In one embodiment of the present disclosure, planning module 4 includes:
the first optimizing unit 41 is configured to obtain safety inventory data through an optimizing process that minimizes inventory cost and supply risk according to a demand prediction result and a preset dynamic planning mathematical model.
The first simulation unit 42 is configured to apply a markov chain monte carlo simulation algorithm according to the safety stock data and the service level target, simulate a plurality of supply chain instances and calculate corresponding service levels, so as to obtain a service level simulation result.
The second optimizing unit 43 is configured to adjust the safety inventory data using a bayesian optimizing algorithm according to the service level simulation result, and perform iterative optimization to obtain optimized inventory data.
A second calculation unit 44, configured to calculate an order point according to the optimized inventory data and the preset inventory consumption mathematical model.
In one embodiment of the present disclosure, planning module 4 includes:
a third construction unit 51 for constructing an economic batch mathematical model based on the price discount information and the transportation cost information.
The third calculation unit 52 calculates the order quantity by optimization and parameter adjustment based on the economic batch model.
The first evaluation unit 53 is configured to perform feasibility evaluation according to the subscription number to obtain a subscription batch.
And a fourth calculating unit 54, configured to calculate an economic ordering point according to the minimum ordering number and the supply time of the suppliers in the third information, by comprehensively considering the requirement and the supply condition of the supply chain.
And a second processing unit 55 for obtaining an economic ordering lot based on the ordering lot and the economic ordering point.
It should be noted that, regarding the system in the above embodiment, the specific manner in which the respective modules perform the operations has been described in detail in the embodiment regarding the method, and will not be described in detail herein.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.