Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the invention. Rather, they are merely examples of apparatus and methods consistent with aspects of the invention as detailed in the accompanying claims.
It is to be understood that the same or similar parts in the above embodiments may be referred to each other, and that in some embodiments, the same or similar parts in other embodiments may be referred to.
It should be noted that in the description of the present invention, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Furthermore, in the description of the present invention, unless otherwise indicated, the meaning of "plurality" means at least two.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and further implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
FIG. 1 is a schematic block diagram of a remote control system of a numerically-controlled machine tool, according to an exemplary embodiment, including a numerically-controlled machine tool device, an edge computing device, a cloud device, and a remote terminal control device, as shown in FIG. 1;
the numerical control machine tool equipment is used for acquiring field data and transmitting the field data to the edge computing equipment or the cloud equipment, wherein the field data at least comprises one of the following:
machine tool sensor data, machine tool image data, and machine tool positioning data;
The edge computing device is used for performing edge computing on the field data, generating target data and uploading the target data to the cloud device;
The cloud device is used for carrying out data processing on the target data to obtain a data processing result, and transmitting the data processing result to the remote terminal control device;
The remote terminal control device is used for outputting the data processing result, and responding to a control instruction received on the man-machine interaction interface, and remote control interaction operation with the numerical control machine tool device is realized through the cloud device.
The operation site comprises two types of equipment, namely edge computing equipment and numerical control machine tool equipment. The numerical control machine tool equipment can support network communication, and communication connection is established between the numerical control machine tool equipment and edge computing equipment or cloud equipment. And the numerical control machine tool equipment can collect data of various dimensions such as sensor data, positioning data, video monitoring data and the like, report the data to edge computing equipment or cloud equipment for data processing, and realize various functions such as data visual display, equipment health state management, abnormal early warning and the like. The edge computing equipment can perform preliminary processing on the data, report the data after the preliminary processing to the cloud processing, and also can directly perform equipment control on the numerical control machine equipment based on the preliminary data processing of the local edge computing equipment, and meanwhile, the local control and the cloud control are realized. By the cloud edge cooperative computing mode, delay can be reduced, and network congestion of a cloud data center can be relieved. And the offline local control operation is supported, so that the flexibility and the reliability of the system are improved. Through edge calculation, the operation can be continued under the condition of no network, and the risk resistance is improved.
Specifically, the edge computing device can perform preliminary processing on data such as speed, acceleration, rotation speed and the like acquired by the sensor, and generate needed advanced data (such as average speed, maximum speed and the like). Through edge calculation, the data processing process is placed at a position close to a data source, delay is reduced, and real-time performance of data feedback is improved. The data transmission quantity is reduced, the network congestion of the cloud data center is reduced, and the stability and reliability of the whole system are improved. Under the condition of no network connection, the edge computing equipment can still process the data, and the flexibility and the reliability of the system are improved. In the edge computing device, the maximum value of the speed can be obtained by using a sequencing algorithm, average speed, acceleration and the like are calculated by using a statistical algorithm, real-time data monitoring is performed by using a fault detection algorithm, abnormal conditions are detected, and early warning information is generated.
The remote terminal control equipment can realize a data display interface, including numerical values, charts and the like, and can design common operation instructions to the interface, including parameter adjustment, fault investigation and the like;
Optionally, the operation data and the state of the numerical control machine tool can be checked in real time, and optionally, control instructions such as parameter adjustment, tool replacement and the like can be sent, and fault checking and remote debugging can be performed.
The cloud end device can store data uploaded from the numerical control machine system and perform corresponding data processing, the data processing comprises data cleaning, statistical analysis, model construction and the like, the cloud end device can support AI analysis including fault prediction, optimizing processing codes and the like, and the cloud end device can realize remote updating including version management of application programs and firmware. The cloud AI module can adopt an advanced AI algorithm to carry out statistical analysis on a large amount of uploaded data and generate a data model, so that a user can be helped to clearly check data information, identify potential faults, predict the maintenance period of equipment, optimize processing codes and shorten processing time. Through the cloud platform, operating personnel can remote monitoring the running state, the production condition and the like of the numerical control machine tool, and also can remotely send instructions to a numerical control machine tool system through the cloud platform so as to adjust parameters, replace cutters and the like. Through integrating the AI module on the cloud platform, data are analyzed, a corresponding data model is created, data information is checked in an auxiliary mode, potential faults are found, the maintenance period of equipment is predicted, the machining process is optimized, and the intelligent degree is higher. And providing a map interface on the cloud platform to display the position information of the device.
Specifically, the cloud artificial intelligence AI may obtain the uploaded data from the edge computing device. And carrying out visual automatic layout and generation on the acquired source data, generating a data visual model, and displaying data characteristics and change trend by using a chart. The generated data model can help the user to more intuitively and clearly know the state of the equipment, such as generating a speed curve, a temperature change trend and the like. The generated visual model can be checked on remote equipment, and the machine tool state can be grasped dynamically. When the data are abnormal, for example, the temperature of the numerical control machine exceeds the normal range, the AI can perform early warning to remind operators of performing fault investigation.
As an alternative implementation mode, the numerical control machine tool equipment comprises an M2M module, a picture monitoring module, a positioning system module and a sensor module;
The M2M module is configured to implement communication with the edge computing device or the cloud device;
The picture monitoring module is used for collecting the machine tool image data and uploading the machine tool image data to the cloud end equipment so that the cloud end equipment outputs the machine tool image data to the remote terminal control equipment for remote picture monitoring;
the positioning system module is used for collecting the machine tool positioning data of the fault equipment and reporting the machine tool positioning data to the edge computing equipment;
The sensor module is used for collecting the machine tool sensor data and reporting the machine tool sensor data to the edge computing equipment, wherein the machine tool sensor data comprises at least one of position data, speed data, acceleration data, motor rotation speed data, temperature data, pressure data and load data of each shaft of the numerical control machine tool equipment.
In this embodiment, the inside of the numerically-controlled machine tool device may include four modules, namely, an M2M module, a sensor module, a positioning system module, and a screen monitoring module. The M2M module can enable the numerical control machine tool to have networking capability and remote communication, transmits data to the edge computing equipment through 5G communication, and forms an M2M application system to realize intelligent and interactive communication. The sensor module can collect parameters such as position, speed, acceleration, motor rotation speed and the like of each shaft of the numerical control machine tool, and collect data such as temperature, pressure, load and the like through the temperature sensor, the pressure sensor, the load sensor and the like. The positioning system module can acquire the exact position of the fault equipment, calculate the optimal route and help the staff to quickly arrive at the fault site. The picture monitoring module can collect real-time pictures of the vicinity of the machine tool and the processing process, the pictures are uploaded to the cloud end, and an operator views the field pictures through the remote terminal, so that real-time accurate control of field industrial equipment is realized. The method comprises the steps of acquiring data by adopting a scheme based on an M2M technology, and carrying out high-speed transmission on the basis of 5G communication to realize data monitoring of a digital control machine tool system device on a cloud platform. The M2M module enables the numerical control machine tool system to have networking and remote communication capabilities, and high-speed and low-delay data transmission is realized through a 5G communication technology. And meanwhile, the data acquired by the sensor module and the positioning system module are uploaded to the edge computing equipment. The data is uploaded by using 5G transmission preferentially, and other alternatives (such as 4G, wi-Fi and wired connection) can be adopted. In cases where 5G is not available or is costly, a 4G network may be used for data transmission. Wi-Fi may be used for data transmission in a fixed location or in a small range. In scenarios where data transmission security and stability requirements are high, a wired connection may be used.
For the positioning system module, a GPS positioning device is arranged on the numerical control machine tool, the specific position of the numerical control machine tool can be obtained through the GPS positioning device, and the current position of the equipment can be checked through a mobile phone. When a problem occurs in a certain device, the specific position of the fault device can be determined through the positioning system, so that people can be quickly dispatched to repair the fault device. Positioning can be realized by installing a GPS module and an antenna in the numerical control machine tool equipment.
For the picture monitoring module, a high-definition camera is installed to collect a field picture, and a real-time picture is transmitted to the cloud through 5G communication. The remote terminal control equipment provides an intuitive interface, and is convenient for operators to check real-time pictures and send control instructions.
The remote control of the numerical control machine tool equipment can be realized through interaction of the remote terminal control equipment, the cloud end and the operation site, and the numerical control machine tool equipment is more convenient and faster. The remote terminal control device is used for an operator to remotely check and control the running state of the numerical control machine tool, the cloud end is used for storing and processing data, and the operation site is the actual position of the numerical control machine tool device. The staff can use equipment such as PC computer or smart mobile phone to carry out remote control. And transmitting the position data to the edge computing equipment through the M2M module, and uploading the position data to the cloud. And the real-time pictures of the scene are collected through the camera and uploaded to the cloud. The staff can log in the cloud platform through the remote equipment to view the real-time picture of the scene. And the remote equipment sends an instruction to adjust parameters of the numerical control machine tool, so that real-time accurate control of the field industrial equipment is realized.
As an optional implementation manner, the cloud device is specifically configured to:
performing data analysis on the target data, and extracting a first target parameter value;
generating an equipment health assessment result based on the equipment health assessment model which is trained in advance and the first target parameter value;
generating a visual equipment state display interface based on the equipment health evaluation result and the target parameter value;
And transmitting the visual equipment state display interface to the remote terminal control equipment as the data processing result.
In the embodiment, the numerical control machine tool acquires various operation data in real time through the sensor module, such as position parameters (e.g. positions of shafts and positions of cutters), motion parameters (e.g. speed, acceleration, rotating speed and the like), environment parameters (e.g. temperature, pressure, load and the like). The obtained original data is subjected to preliminary processing by edge computing equipment, including abnormal value screening, data smoothing and data complement. Therefore, error analysis caused by noise and errors can be avoided, and target data can be obtained after processing and reported to the cloud device. The cloud device can analyze multidimensional data (such as speed, temperature, load and the like) of the numerical control machine tool, and extract important characteristics of the running state of the device. For example, the process analysis analyzes the influence of heat generation, vibration and other factors in the process based on the motion data and the temperature data. The wear condition and the service life of the cutter can be predicted by analyzing data such as temperature change, speed change and the like when the cutter is used.
Furthermore, the cloud device can construct a device health evaluation model in advance based on a classification algorithm and a regression algorithm. And generating the health state score of the equipment according to the real-time data, and helping operators to evaluate whether the equipment is in a normal working state or not and whether maintenance is needed or not. And generating a corresponding visual interface, and creating a real-time status panel for the numerical control machine tool, wherein the related parameters can comprise key parameters (such as displacement, speed, load, temperature and the like of each axis) of the numerical control machine tool, and equipment health scores (current health scores or residual life of the display equipment). Wherein the health score may be indicated by a color (e.g., green for normal, yellow for warning, red for failure).
Specifically, when training a model, data can be firstly cleaned and preprocessed, so that the data quality is ensured, noise is removed, missing values are filled, and the model can be learned from effective data. For less data loss, linear interpolation can be used for padding. The linear interpolation is based on values before and after the data, and is suitable for time series data with stable trend. For features that are more common to the absence, mean or median padding may be used. In particular temperature, pressure, etc., this is often used. Or fill in missing values based on the distance between similar data points. In multidimensional data, KNN can infer missing values from known sample data, and is suitable for scenes with complex data. Outlier detection may then be performed, specifically, detection and removal of outliers using the Z-score method, samples with Z-score values greater than 3 or less than-3 are considered outliers. Or using the IQR (quartile range) method, a range is calculated based on the upper and lower quartiles of the data (1.5 times the data outside the IQR are abnormal). This method is effective for data such as machine tool vibration. Or an abnormal value detection algorithm based on decision tree can be adopted, so that the method is particularly suitable for high-dimensional data, and extreme abnormal values in the data can be effectively removed. Thereafter, the data (e.g., speed, temperature, pressure) of different units are converted to the same range, typically [0,1], to eliminate the effect of dimensional differences. And then, changing the data into 0 as the mean value and 1 as the standard deviation, and being particularly suitable for scenes with different data distribution. Further, after the initial data processing is completed, key information can be extracted, meaningful features are generated, and complex original data is converted into a form which is easy to process by the model. The operation data of the numerically-controlled machine tool is usually time-series data, including changes of parameters such as temperature, speed, load and the like. The data analysis may be performed using a Moving Average (MA) that smoothes the noise by calculating the average of the data over a time window to obtain the overall trend of the data. Autoregressive models (AR) are used to analyze the trends and periodicity of the device operation. For example, a trend of change in the health state of the device is predicted. The exponential smoothing method Exponential Smoothing is applied to short-term prediction, emphasizing the most recent data by weighted averaging of historical data. Then, a proper machine learning algorithm is selected, and training is performed according to the equipment data of the numerical control machine tool. SVR can be used for the running state prediction of the numerical control machine, and is suitable for processing high-dimensional data and complex nonlinear relations. The SVR can predict the residual service life (RUL) or health status score of the equipment, or predict through integrating a plurality of decision trees, has stronger robustness, can process nonlinear data relationship, and is suitable for data analysis of various characteristics. Or by linear regression, is suitable for predicting the gradual change trend of equipment, such as the long-term health trend of the equipment.
Besides the visual equipment display interface, the remote control terminal equipment can also display the motion state of the machine tool by utilizing a dynamic chart, such as displaying the motion speed change trend of each shaft through a speed curve and displaying the real-time change of the load of each shaft, so as to help analyze whether the overload operation risk exists. The temperature and vibration data of different parts of the machine tool are displayed through a thermodynamic diagram or a histogram. The possible high temperature area is clearly marked by using color gradient (such as cold tone indicates low temperature and warm tone indicates high temperature), and the possible overheating problem of the equipment is early warned in advance. Through multiple show forms, realize the swift show of data.
As an optional implementation manner, the cloud device is further configured to:
performing data analysis on the target data, and extracting a second target parameter value;
generating a device fault prediction result based on a pre-trained fault prediction model and the second target parameter value;
And adding the equipment failure prediction result to the visual equipment state display interface, and transmitting the visual equipment state display interface to the remote terminal control equipment as the data processing result.
In this embodiment, the historical data and the real-time data of the device may be analyzed to generate a failure prediction model. For example, based on data of temperature, pressure, load, vibration, etc. of the equipment, the AI system can predict whether the tool is excessively worn, whether there are components that may fail (e.g., bearing damage, drive train failure, etc.).
For fault prediction, SVM can be adopted to process high-dimensional data, and the method is suitable for fault prediction tasks. It divides data into normal and fault states, enabling efficient identification of fault modes. Or adopting random forest classification to realize multi-category prediction of equipment faults. Or under small sample data, the KNN algorithm can effectively classify the state of the equipment and is suitable for real-time fault classification. Further, for complex pattern recognition, since numerical control machine tool data is mostly time-series data, LSTM is very suitable for learning a state change pattern of an apparatus. LSTM is capable of capturing time-series dependencies of long-time series data, and is particularly suitable for equipment failure prediction. Or in image data processing through CNN, can be used for feature extraction of time series data to help identify complex equipment failure modes.
As an optional implementation manner, the cloud device is further configured to:
generating early warning data according to the equipment fault prediction result, the equipment health evaluation result, the first target parameter value and/or the second target parameter value, and transmitting the early warning data to the remote terminal control equipment as the data processing result.
In this embodiment, various data may be monitored in real time, and if the device parameter is abnormal (such as temperature exceeding, load being too high, etc.), the system may trigger an alarm to automatically notify the operator. At the moment, the system feeds back early warning information on an interface in real time through modes of color change, icon flickering and the like, and reminds operators to carry out corresponding adjustment or inspection. By detecting equipment abnormality in real time and carrying out fault early warning, equipment shutdown is avoided in advance. When abnormality detection is performed, the self-encoder can detect data inconsistent with the normal behavior pattern by reconstructing the input data. For example, if operational data of the device such as temperature, vibration, etc. fluctuates greatly, the model may detect an abnormality. Or based on Isolation Forest (a tree-based anomaly detection algorithm), anomaly data can be found by randomly partitioning the feature space of the dataset. Any data that does not conform to the normal pattern is marked as anomalous in the industrial data.
In addition, fault prediction can be performed based on machine learning or deep learning, and a regression algorithm (such as SVR and random forest regression) is used for predicting the health state score of the equipment, or a classification method (such as SVM and random forest classification) is used for predicting whether the equipment can fail. The use of LSTM can be used for long-term trend prediction to help predict the probability of failure of a device in the future for a certain period of time.
As an optional implementation manner, the cloud device is further configured to:
determining a fault type according to the equipment fault prediction result;
Generating a fault handling suggestion based on the fault type, and transmitting the fault handling suggestion to the remote terminal control device as the data processing result.
As an optional implementation manner, the cloud device is further configured to:
And generating a data statistics report according to the equipment fault prediction result, the equipment health evaluation result, the first target parameter value, the second target parameter value and/or the target data, and transmitting the data statistics report to the remote terminal control equipment as the data processing result.
In this embodiment, the cloud may store all data, including sensor data, processed advanced data, historical data, and the like. Advanced AI algorithm is adopted to process and analyze data, including data cleaning, statistical analysis, anomaly detection, model construction, etc.
As an alternative embodiment, the remote terminal control device is specifically configured to:
Outputting the data processing result, wherein the data processing result comprises a visual equipment state display interface;
if the control instruction received on the man-machine interaction interface is a display control instruction, adjusting a display view in the visual equipment state display interface;
And if the control instruction received on the man-machine interaction interface is an equipment control instruction, issuing the equipment control instruction to the numerical control machine tool equipment through the cloud equipment to realize remote control interaction operation.
In the embodiment, the remote terminal control device can provide a remote control interface, and an operator can adjust parameters of the numerical control machine tool in real time through the remote control interface, such as cutting speed adjustment and tool changing control. Specifically, the cutting speed can be adjusted according to the cutting temperature and the load condition monitored in real time under the condition of not influencing the work so as to avoid overheating or too fast abrasion of the cutter. And when AI predicts that the cutter is seriously worn, an operator can send a cutter replacement instruction through a remote control interface, so that the reduction of machining precision or production shutdown caused by cutter damage is avoided.
The interface design adopts a graphical mode, so that an operator can check key parameters and data through simple clicking operation. For example, an operator can check the temperature change of different parts of the machine tool by clicking on the temperature module, and check the vibration frequency and amplitude of the current machine tool by clicking on the vibration module.
Wherein, according to the demand of operating personnel, the user can customize different views. For example, a process engineer may choose to view process parameters of a machine tool, while a serviceman may view fault prediction data and historical service records to optimize a maintenance plan.
In addition, the working environment of the machine tool is monitored in real time through the high-definition camera, and the video is uploaded to the cloud. And an operator views the field picture through the remote terminal to conduct operation guidance or problem diagnosis. Through video monitoring and data visualization, operators can adjust equipment at a remote terminal and even quickly conduct fault investigation through the assistance of AI. For example, when the remote terminal displays equipment temperature and vibration data, a worker can view the live video at the same time, and make timely adjustments according to visual feedback.
Specifically, the data statistics report may be generated by collecting data from different modules (such as a sensor module, a positioning system, a picture monitoring module, etc.) and different sensors, and combining the data into a unified format for subsequent processing. For example, parameters such as temperature, speed, pressure and the like acquired by the sensor need to be unified on a time stamp to ensure consistency and comparability of data. And removing noise data, filling up missing values, ensuring the quality of the data, and avoiding inaccurate data from affecting statistical results. Conventional statistical indicators of the operating parameters of the device, such as mean, standard deviation, maximum, minimum, quartile, skewness, kurtosis, and the like, are calculated. These indicators can help analyze the distribution of various parameters of the machine tool and find the normal range of the equipment. For example, the data from the temperature sensor may generate statistical reports of average temperature, temperature fluctuation amplitude, maximum temperature, and minimum temperature, reflecting whether the device is within a normal operating range. For time series data (such as rotational speed, temperature, etc. of a machine tool), trend lines, seasonal variations, fluctuation amplitudes, etc. can be calculated and variations of the respective parameters over different time periods are shown. For example, a daily average temperature change trend or a periodic vibration mode of the machine tool is generated through time series analysis, so that the working state of equipment is analyzed. And then the linear relation among a plurality of variables is quantized through the pearson correlation coefficient. By calculating the correlation between the various sensor data (e.g., speed, temperature, pressure, etc.) of the machine tool, it is identified whether there is commonality or correlation. For example, there is a positive correlation between temperature and rotational speed, which may lead to an increase in temperature when the rotational speed increases under certain conditions, which is critical to the control decisions of the machine operator.
In addition, when abnormality detection and fault prediction are performed, a data point with a large difference from the historical data is found through statistical analysis, for example, when temperature fluctuation exceeds a set threshold value, the statistical report automatically marks the abnormal point. In addition, the report may provide some predictions based on historical data calculations, such as equipment failure probabilities, remaining useful life, etc.
The specific content of the data statistics report may include key parameter statistics, such as equipment operation parameters, including average value, maximum value, minimum value, standard deviation, etc., of the key operation parameters (such as rotation speed, temperature, pressure, etc.) of the numerical control machine tool and statistical results thereof. Such as a rotational speed of 1500RPM average, 2000RPM maximum, 1200RPM minimum, 45 ℃ average, 65 ℃ maximum, and 30 ℃ minimum. By generating a fluctuation map of the plant operational data, it is demonstrated whether the machine is operating within an acceptable range. For example, a temperature fluctuation map is generated to display the change condition of the machine tool temperature in different time periods.
The report may also include an analysis of the health status of the device, and the health status of the device may be calculated by setting a health scoring model. The score is derived by integrating the plurality of sensor data, using a score range of 0-100, with a larger value indicating a healthier device. For example, a device health status score of 80/100 indicates that the device is functioning properly, but there may be a few anomalies that require attention. Based on historical operating data and current operating conditions of the device, a probability prediction of a failure of the device within days or weeks of the device's future is generated. For example, "device A has a 12% probability of failing within 7 days of the future" which facilitates maintenance decisions.
The report may further include an abnormal event record and early warning, which lists all abnormal conditions occurring in the reporting period, including conditions in which the device parameter exceeds a preset range (such as too high rotational speed, too high vibration, etc.). And marks the occurrence time, the type of abnormality, the influence range and other information of each abnormal event. Based on the abnormality detected by the algorithm, early warning information is automatically generated, for example, the equipment A rotating speed exceeds a set threshold value, and shutdown checking is recommended. "
The report can also contain trend and forecast, show the running trend of the equipment in a certain time range, and analyze the performance change of the equipment. For example, a gradual rise in temperature or pressure may suggest that the device is about to fail. Future operational trends of the device, such as remaining useful life of the device, health scores, etc., are generated using predictive algorithms.
In addition, the display interface can also generate an intuitive chart to help an operator to quickly understand the statistical result. If the line graph shows the trend of the device parameters over time, the bar graph shows the comparison of different devices or parameters. The pie chart shows the distribution of the operating conditions of the device (e.g., the proportion of the health of the device). The thermodynamic diagram shows the correlation between different parameters of the device to help the operator understand the relationship between the parameters of the device.
Further, the control instructions may be used to instruct adjustment parameters, tool change, etc.
According to the application, the production efficiency of a modern workshop is obviously improved by the remote control system, and the intelligent remote control system can save a large amount of manpower and material resources for factories and improve the production efficiency. The remote control system is excellent in data monitoring, the numerical control system carrying the remote control system can realize real-time monitoring, acquire the data of the equipment, conveniently count the data information of the current day or a certain stage, automatically make adjustment through AI, make reasonable planning and conveniently conduct the arrangement of the next step. And master the site information more swiftly, optimize operational environment, concentrate manpower resources, avoid causing the waste of manpower resources. And a series of functions of remote upgrading and downloading of firmware/application, remote monitoring, debugging, fault checking and the like are realized.
The remote monitoring technology is realized through a network, the equipment data of the current numerical control machine tool is directly checked remotely, the operation data of the numerical control machine tool is processed by combining the computing capacity of cloud equipment, the remote interactive control is realized, and the problem of lower control efficiency of the numerical control machine tool in the prior art is solved.
Based on the same inventive concept, fig. 2 is a flowchart of a remote control method of a numerical control machine tool according to an exemplary embodiment, and as shown in fig. 2, the method is applicable to a cloud device, and includes:
s21, acquiring target data reported by numerical control machine tool equipment;
step S22, carrying out data processing on the target data to obtain a data processing result, and transmitting the data processing result to a remote terminal control device so that the remote terminal control device outputs the data processing result;
And S23, receiving a control instruction returned by the remote terminal control equipment, and realizing remote control interactive operation with the numerical control machine tool equipment.
Referring to fig. 3 together, fig. 3 is a flowchart illustrating another remote control method of a numerical control machine according to an exemplary embodiment, and when a device fails, fault information is reported to a cloud through an M2M module. And (5) carrying out fault analysis by the cloud AI to generate a processing suggestion. The operator performs fault diagnosis through the remote terminal, and dispatches a field service person if necessary. And the on-site service personnel quickly arrive at the position of the fault equipment according to the optimal route provided by the cloud. After the data is uploaded to the cloud, the AI module performs diagnostic analysis on the equipment operation data, and judges whether the equipment is abnormal or not by setting reasonable thresholds, rules or performing real-time monitoring by using a statistical method (such as Z-score, standard deviation and the like). For example, an alarm is triggered when the temperature exceeds 70 ℃, a warning is given when the rotational speed deviates from a predetermined range, a pressure abnormality value, etc. By learning the historical data, the AI can identify a "normal" operating mode of the device and detect deviations from this mode (e.g., vibration data, temperature data, etc. of the device). For example, if the temperature of a numerical control machine fluctuates around 60 ℃ in the past one week and the temperature suddenly rises to 80 ℃ at a certain time, AI is regarded as abnormal data. Or machine learning models (such as decision trees, support Vector Machines (SVMs) and the like) can be used for detecting abnormal points, model training is performed based on historical operation data and fault records of equipment, and potential abnormal modes are identified. Through a trained prediction model, the AI can predict the potential faults of the equipment. For example, the AI may predict whether the device is likely to fail within the next few hours based on the current device's operating state (e.g., temperature, rotational speed, pressure, etc.) and historical data. Based on the fault analysis described above, the AI will generate specific process recommendations and transmit them in the form of reports to the operator or maintenance team. For example, depending on the type of fault, the AI will automatically generate a set of treatment plans or recommendations that ensure that the device can be quickly repaired and production resumed. For example:
cooling problems if AI detects that the equipment temperature is continuously getting higher, it is recommended to check the cooling system and adjust the cooling parameters or clean the cooling device.
Mechanical failure if AI identifies an abnormal rotational speed and is related to vibration data, which may be a symptom of mechanical failure, it is recommended to check the motor and transmission.
And (3) overload of the equipment, namely if the AI monitors that the load of the equipment is close to the maximum value, suggesting to stop operation, and carrying out load balancing and pressure adjustment.
In addition, in addition to handling faults, AI may also provide some preventive maintenance advice to reduce the likelihood of faults occurring and extend the service life of the device. For example:
Periodic inspections suggest that the operator examine key components of the machine tool (e.g., motor, cooling system, drive train, etc.) monthly.
Component replacement-depending on the operating conditions of the device, AI may recommend replacement of certain vulnerable components (e.g., tools, bearings, etc.) depending on the time of use or frequency of failure.
The AI can recommend to adjust the operation parameters of the equipment according to the analysis result so as to improve the efficiency or reduce the energy consumption.
The generated processing advice is displayed in the cloud control platform, and a notification can be sent through an automatic system to remind an operator or a maintenance team, for example, the processing advice and the machine tool position are notified to related personnel in real time through mail, short messages or APP pushing. The AI may also give priority to direct the operator to handle the most urgent fault first, depending on the severity of the fault. After the processing suggestion is implemented, an operator can monitor the equipment in real time through the cloud platform, and the AI can track the processing result to confirm whether the fault is repaired or not. If the problem still exists, the AI will continue to optimize the process advice and feed back the current fault status to the operator in real time.
The remote monitoring technology is realized through a network, the equipment data of the current numerical control machine tool is directly checked remotely, the operation data of the numerical control machine tool is processed by combining the computing capacity of cloud equipment, the remote interactive control is realized, and the problem of lower control efficiency of the numerical control machine tool in the prior art is solved.
The implementation manner and the beneficial effects of each method step in this embodiment may be described with reference to the cloud device module corresponding to the foregoing embodiment, which is not described in detail in this embodiment.
Based on the same inventive concept, fig. 4 is a schematic diagram of an internal control circuit of a cloud device according to an exemplary embodiment, as shown in fig. 4, where the cloud device includes:
at least one processor 401, a communication interface 402, and
A memory 403 communicatively coupled to the at least one processor 401;
wherein the processor 401, the communication interface 402 and the memory 403 complete the communication with each other via the communication bus 404, and wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to enable the at least one processor to perform the method as described above.
A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the above-described method is shown according to an exemplary embodiment.
The computer readable storage medium of the present embodiment includes, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.