Detailed Description
The following describes the detailed implementation of the embodiments of the present invention with reference to the drawings. It should be understood that the detailed description and specific examples, while indicating and illustrating the invention, are not intended to limit the invention.
Fig. 1 is a flowchart of a method for predicting plant production electricity consumption according to an embodiment of the present invention, referring to fig. 1, the method for predicting plant production electricity consumption may include the following steps:
Step S110, historical electricity consumption data of each electricity consumption unit is obtained, wherein the historical electricity consumption data comprises historical electricity consumption and values of electricity consumption factor.
Wherein the electricity meter of the factory may be divided into a plurality of electricity usage units, each of which may include one or more electricity meters. The historical electricity usage data is historical electricity usage data for a preset period of time, for example, three months, one year, or three years.
Preferably, before step S110, the method for predicting the electricity consumption of the factory may further include dividing the electricity meters corresponding to the same type of production equipment into one electricity consumption unit according to the type of the production equipment, or dividing the electricity meters of the same area into one electricity consumption unit according to the electricity meter distribution.
The electricity meter can be divided into one electricity unit according to the type of the production equipment, the divided electricity units comprise a PU electricity unit, an SCR electricity unit, a cooling system electricity unit, other electricity units and the like, the electricity meter can be divided into a plurality of electricity units according to electricity meter distribution, the divided electricity units comprise an A area electricity unit, a P area electricity unit, a T area electricity unit and the like, the electricity meters can be divided according to the electricity meter distribution, the electricity meters corresponding to the production equipment with the same type in each area can be divided into one electricity unit according to the type of the production equipment, and the divided electricity units comprise an A area electricity unit, a T area rack electricity unit, a T area SCR electricity unit, a T area cooling system electricity unit, a PU area electricity unit and the like.
The preferable power utilization factor in the embodiment of the invention comprises the output quantity or the ambient temperature of the production equipment corresponding to the power utilization unit.
The output of the production equipment corresponds to an economic influence factor of electricity consumption, and the output of the production equipment (for example, the number of finished products, semi-finished products or assembled products) for producing products is equal to the environmental influence factor of electricity consumption. For example, the power consumption factor of the PU power consumption unit, the SCR power consumption unit, etc. is the output of the production equipment, and the power consumption factor of the cooling system power consumption unit, gao Wenwei waste treatment system power consumption unit, etc. is the ambient temperature.
And step S120, determining the correlation between the historical electricity consumption and the electricity consumption factor.
Preferably, the step S120 includes steps S121-S123, wherein the step S121 is divided into corresponding N production time periods according to N working condition modes of each electricity utilization unit, N is more than or equal to 1, the step S122 is used for counting the historical electricity utilization amount and the value of an electric influence factor of each unit time period according to the historical electricity utilization data of each production time period, and the step S123 is used for obtaining the correlation coefficient between the historical electricity utilization amount and the electric influence factor of each production time period through the counted partial data or all data in the historical electricity utilization amount and the value of the electric influence factor of each unit time period.
The working condition modes of the power utilization units can be classified by day (24 hours) according to the working conditions of corresponding production equipment. The working condition modes preferred by the embodiment of the invention can comprise a production-free mode, a production mode, a warm-up air circulation mode and the like.
Step S121 may be correspondingly divided into N production time periods for N working condition modes of each power utilization unit. By way of example, each power usage unit may include different operating modes, such as operating mode of power usage unit A including a production mode (e.g., 8:00-17:00 a day) and a no-production mode (e.g., other times a day), operating mode of power usage unit B including a production mode (e.g., 8:00-17:00 a day) and a warm-up air circulation mode (e.g., other times a day), operating mode of power usage unit C including a production mode (e.g., 8:00-17:00 a day), a warm-up air circulation mode (e.g., 6:00-8:00 a day and 17:00-22:00 a day) and a no-production mode (e.g., other times a day), operating mode of power usage unit D including only a production mode (e.g., 24 hours). According to the working condition mode of each electricity utilization unit, the electricity utilization unit is divided into N corresponding production time periods, for example, the divided time periods in the brackets can be correspondingly marked as no-production time periods, warm-up empty circulation time periods and the like.
Step S122, for the historical electricity consumption data of each production period, statistics are made of the historical electricity consumption amount and the value of the electricity consumption factor of each unit period. The unit time period is preferably hour, which is beneficial to identifying the difference of electricity consumption peaks, wave troughs and the like and the influence of the change of 24-hour air temperature on the electricity consumption. For example, for the production period of the electricity usage unit a, the sum of the historical electricity usage amounts per hour is calculated from the historical electricity usage data for a preset period (for example, three months, one year, or three years), and the value of the electricity usage factor is calculated (for example, the output per hour is calculated or the average value of the temperature per hour is calculated).
In step S123, a correlation coefficient between the historical electricity consumption of the production period and the electricity consumption factor is preferably obtained from the pearson correlation. For example, for a production period of the electricity consumption unit a, a correlation coefficient r (X, Y) of the historical electricity consumption amount X and the output amount Y or the ambient temperature Y of the production period is calculated by:
Wherein X represents an array vector of historical electricity consumption per hour, Y represents an array vector of output per hour or ambient temperature in the production period, cov (X, Y) represents covariance of X and Y, and Var represents variance.
Preferably, the correlation coefficient r (X, Y) can be calculated from the counted historical power consumption per unit time period and part of the data in the value of the power consumption factor to quickly obtain the correlation coefficient. For example, for the production period of the electricity consumption unit a, the sum of the historical electricity consumption amounts per hour is calculated by any three days, and the value of the electricity consumption factor is calculated, and the correlation coefficient between the historical electricity consumption amounts and the electricity consumption factor for the production period is calculated by the formula (1).
Preferably, in step S120, the method may further include determining that the correlation between the historical electricity consumption and the active electricity consumption factor of the production period is uncorrelated when the obtained correlation coefficient between the historical electricity consumption and the active electricity consumption factor of the production period is less than a first threshold, determining that the correlation between the historical electricity consumption and the active electricity consumption factor of the production period is weakly correlated when the obtained correlation coefficient between the historical electricity consumption and the active electricity consumption factor of the production period is between the first threshold and a second threshold, and determining that the correlation between the historical electricity consumption and the active electricity consumption factor of the production period is strongly correlated when the obtained correlation coefficient between the historical electricity consumption and the active electricity consumption factor of the production period is greater than the second threshold.
With the above example, for the production period of the electricity consumption unit a, if the correlation coefficient is greater than the first threshold (e.g., the threshold a), the historical electricity consumption amount of the production period is strongly correlated with the electricity consumption factor (output amount or ambient temperature), if the correlation coefficient is between the first threshold and the second threshold (e.g., between the threshold a and the threshold B), the historical electricity consumption amount of the production period is weakly correlated with the electricity consumption factor (output amount or ambient temperature), and if the correlation coefficient is less than the second threshold (e.g., the threshold B), the historical electricity consumption amount of the production period is not correlated with the electricity consumption factor (output amount or ambient temperature).
Preferably, prior to step S120, the method of predicting plant production electricity usage further includes determining an electricity usage factor for each electricity usage unit, i.e., the electricity usage factor for that electricity usage unit is a production volume or an ambient temperature.
And step S130, determining the electricity consumption quantitative analysis strategy of each electricity consumption unit based on the determined correlation and through the historical electricity consumption and the value of the electricity consumption factor.
Preferably, the step S130 may include 1) when the correlation between the historical electricity consumption of the production time period and the electric influence factor is strong, establishing a corresponding linear regression model through the counted values of the historical electricity consumption of each unit time period and the electric influence factor to obtain a predicted value of the electricity consumption of the production time period through the linear regression model, 2) when the correlation between the historical electricity consumption of the production time period and the electric influence factor is weak, establishing a corresponding probability distribution model graph through the counted historical electricity consumption of each unit time period to obtain a predicted value of the electricity consumption of the production time period through the counted characterization value determined through the dispersion degree of the probability distribution model graph, and 3) when the correlation between the historical electricity consumption of the production time period and the electric influence factor is irrelevant, obtaining a predicted value of the electricity consumption of the production time period through the counted average value of the historical electricity consumption of each unit time period.
By way of illustration, 1) a strong yield correlation is established for the production pattern (corresponding production period) of the power usage unit (T-zone rack as shown in fig. 2), and a corresponding linear regression model can be established by the counted values of the historical power usage Z and yield M per hour. For example, by inputting the counted values of the historical electricity consumption Z and the output M per hour into matlab, a linear regression model of the historical electricity consumption Z and the output M per hour as shown in fig. 2 can be obtained, and after linear fitting, the following formula can be obtained:
Z=C1M+ C0 (2)
Wherein C0 and C1 are coefficients obtained by matlab fitting.
The linear regression model or equation (2) shows the relationship between the electricity consumption amount (per unit time period) and the electricity consumption factor, and thus the expected output amount per hour in the production time period can be input to the linear regression model or equation (2) to predict the electricity consumption amount per hour in the production time period. The linear regression model or the formula (2) can also be used for representing the relation between the electricity consumption of the production time period and the electricity consumption factor, so that the expected output of the production time period can be input into the linear regression model or the formula (2) to predict the electricity consumption of the production time period, and further, the expected output of the production time period and one year can be input into the linear regression model or the formula (2) to predict the electricity consumption of the production time period for one year and the like.
If the production mode (corresponding to the production period) of the electricity utilization unit a is strongly related to the ambient temperature, a linear regression model or formula (2) similar to the above can be obtained, where M is the ambient temperature. Preferably, the relationship between the electricity consumption of each unit time period and each unit time period (ambient temperature) can also be obtained through a nesting model, for example, the relationship between each hour and the ambient temperature (for example, the average value of the ambient temperature of each hour) is determined through a first model, the first model is nested through a second model, the relationship between the electricity consumption of each hour and the ambient temperature of each hour is obtained, and the electricity consumption of the production time period can be directly predicted by inputting time (for example, 15 days of 5 months, 7-9 months, etc.) into the nesting module.
2) For the production mode (corresponding production period) of the electricity utilization unit (shown in fig. 3) is that the yield is weakly related, a corresponding probability distribution model diagram can be established through the counted values of the historical electricity utilization amount Z and the yield M per hour, as shown in fig. 3.
Preferably, the characterization value determined by the dispersion of the probability distribution model graph is a median or average value of the probability distribution model graph.
The straight line shown in fig. 3 shows the average value R of the electricity consumption per hour in the fitted production period, which is used as the predicted value of the electricity consumption per hour, and the predicted value g=t×r of the electricity consumption in the production period T (for example, t=8 hours) can be obtained from the predicted value of the electricity consumption per hour. Further, the electricity usage for the production period of one month, three months, or one year can be predicted.
3) Similarly to 2), when the correlation between the historical electricity consumption of the production time period and the electric influence factor is uncorrelated, calculating to obtain an average value of the electricity consumption per hour in the production time period according to the counted historical electricity consumption of each unit time period, wherein the average value is used as a predicted value of the electricity consumption per hour, and the predicted value of the electricity consumption of the production time period can be obtained according to the predicted value of the electricity consumption per hour.
And step 140, predicting the production electricity consumption of each electricity consumption unit and the production electricity consumption of the factory through the electricity consumption quantitative analysis strategy of each electricity consumption unit.
Preferably, step S140 may include predicting, for each electricity usage unit, a production electricity usage amount of the electricity usage unit by setting a value of the electricity usage factor based on the electricity usage quantitative analysis policy, and predicting a production electricity usage amount of the plant by a sum of the predicted production electricity usage amounts of each electricity usage unit
As described above, based on the electricity usage quantitative analysis policy of each electricity usage unit obtained in step S130, the production electricity usage amount of each electricity usage unit may be predicted by setting the value of the electricity usage factor, and further, the production electricity usage amount of the plant may be predicted. By way of illustration, for each electricity usage unit, the relationship between the electricity usage amount of the electricity usage unit and the electricity usage factor may be obtained through the above-described prediction manner corresponding to each production time period (or production condition). For example, the operating mode of the electricity unit a includes a production mode (e.g., 8:00-17:00 a day) and a no production mode (e.g., other times a day), wherein the production mode is a strong yield correlation, and the no production mode is a non-yield correlation, and the electricity consumption predicted value z=t1(C1M+C0)+T2 ×r of the electricity unit (a day), wherein T1 =9 (hours), T2＝15,C1、C0 is a parameter of formula (2), and R is a fitting parameter as illustrated in fig. 3. The predicted value of the electricity consumption amount can be obtained by setting the value of M, which may be, for example, a one-day output, a one-month output, a three-month output, or a one-year output. For example, the prediction of the power consumption per month of each power consumption unit in a certain year shown in table 1 is that the sum of each column is the predicted value of the power consumption per year of each power consumption unit, the sum of each row (i.e., ATPU) is the predicted value of the power consumption per month of the plant, and the total sum is the predicted value of the power consumption per year of the plant.
TABLE 1 prediction of the power consumption for each year of power consumption units
| Label (Label) | Zone A | PU | SCR | Cooling system | T zone | Other T zone | ATPU |
| 2301 | 108720 | 218880 | 174960 | 154080 | 409680 | 81360 | 737280 |
| 2302 | 113040 | 259200 | 184320 | 210960 | 479520 | 83520 | 844560 |
| 2303 | 95040 | 226080 | 174240 | 147600 | 400320 | 78480 | 721440 |
| 2304 | 110160 | 236880 | 173520 | 84240 | 341280 | 83520 | 689040 |
| 2305 | 122400 | 234000 | 164880 | 50400 | 299520 | 84960 | 655920 |
| 2306 | 96480 | 195120 | 162000 | 86400 | 330480 | 81360 | 622080 |
| 2307 | 116640 | 208080 | 141840 | 86400 | 309600 | 80640 | 633600 |
| 2308 | 123840 | 239040 | 210240 | 81360 | 303120 | 84240 | 665280 |
| 2309 | 113760 | 236160 | 231840 | 72720 | 303120 | 77760 | 652320 |
| 2310 | 118080 | 197280 | 162720 | 89280 | 337680 | 85680 | 653040 |
| 2311 | 113760 | 182880 | 178560 | 97200 | 359280 | 83520 | 655920 |
| 2312 | 105840 | 205920 | 165600 | 112320 | 282960 | 77760 | 666720 |
| Mean value of | 111600 | 217440 | 164160 | 109440 | 354960 | 81360 | 684000 |
As shown in table 1, the embodiment of the invention can obtain energy key points and waste points according to analysis, for example, the energy key points (for example, T areas) are obtained through sequencing of the electricity consumption of each electricity consumption unit, and the waste points are determined through transverse comparison (for example, comparison of the electricity consumption of plants in different years and in the same month of each electricity consumption unit) or longitudinal comparison (for example, comparison of the value and the average value of each column in table 1) so as to formulate effective electricity saving measures and pertinently develop energy saving and consumption reduction actions.
Preferably, the actual electricity consumption data of each electricity consumption unit may be continuously acquired, and the parameters (or the characterization values) of the calculation model in the electricity consumption quantitative analysis strategy in step S130 are optimized.
Accordingly, the embodiment of the invention determines the corresponding electricity consumption quantitative analysis strategy through the correlation between the electricity consumption and the electricity consumption factor so as to accurately predict the factory production electricity consumption of the day, month, year and the like. And the energy cost of the production line can be effectively controlled, the energy key points and the waste points are identified, and the energy saving and consumption reduction actions are developed in a targeted manner.
The embodiment of the invention also provides a control device for the method for predicting the power consumption of the factory, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to realize the method for predicting the power consumption of the factory.
The embodiment of the invention also provides a machine-readable storage medium, wherein the machine-readable storage medium is stored with instructions, and the instructions enable a machine to execute the method for predicting the electricity consumption of the factory.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.