A production scheduling control method, system and storage medium for device status perception

Abstract

The present invention relates to a production scheduling control method, system and storage medium for device status perception, belonging to the technical field of production management, and includes: monitoring the operating temperature and operating amplitude of multiple devices to obtain an array of device temperatures and an array of device amplitudes, performing temperature and amplitude verification analysis to obtain an array of perception accuracy parameters; obtaining an array of service information, predicting and classifying to obtain an ideal array of perception accuracy parameters, and calculating to obtain an array of perception anomaly parameters; based on the array of device temperatures and the array of device amplitudes, predicting the device load to obtain an array of predicted device loads, and compensating to obtain an array of compensated device loads; obtaining the current production planning information, combining it with the array of compensated device loads, optimizing the production scheduling to obtain the optimal production scheduling information, and performing control. The present invention solves the technical problems of inaccurate and unreliable production scheduling management based on device status monitoring in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of production management, and particularly to a production scheduling control method, system and storage medium for device status perception. Background Art

[0002] In modern industrial production management, production scheduling and shift scheduling based on device status monitoring have become important means to improve production efficiency and reduce costs. However, the existing technologies mainly rely on information such as sensor data and device operation logs to judge the operation status of devices, and perform production management accordingly. However, due to problems such as aging, wear, and potential faults during the long-term operation of devices, the accuracy of device status monitoring is affected. For example, situations such as decreased sensor sensitivity, data drift, false alarms and missed alarms may lead to deviations in device status evaluation, thereby affecting the rationality of production plans, resulting in waste of resources or insufficient production capacity. Therefore, there are technical problems in the existing technologies that production scheduling management based on device status monitoring is inaccurate, unreliable, and affects production quality. Summary of the Invention

[0003] The present invention aims at the technical problems of inaccurate and unreliable production scheduling management based on device status monitoring in the existing technologies, and provides a production scheduling control method, system and storage medium for device status perception to solve them.

[0004] The technical solutions of the present invention to solve the above technical problems are as follows:

[0005] In a first aspect, the present invention provides a production scheduling control method for device status perception, including: monitoring the operating temperature and operating amplitude of multiple devices to obtain a device temperature array and a device amplitude array, respectively performing temperature-amplitude verification analysis on each device to obtain a perception accuracy parameter array;

[0006] Obtaining a service information array of the multiple devices, predicting and classifying to obtain an ideal perception accuracy parameter array, and combining the perception accuracy parameter array to calculate and obtain a perception anomaly parameter array;

[0007] According to the device temperature array and the device amplitude array, performing device load prediction to obtain a predicted device load array, and based on the perception anomaly parameter array, compensating the predicted device load array to obtain a compensated device load array;

[0008] Obtaining the current production planning information, combining the compensated device load array, performing production scheduling optimization to obtain the optimal production scheduling information, and performing control.

[0009] In a second aspect, the present invention provides a production scheduling control system for device status perception, including: a device perception module, configured to monitor the operating temperature and operating amplitude of multiple devices, obtain a device temperature array and a device amplitude array, and respectively perform temperature-amplitude verification analysis on each device to obtain a perception accuracy parameter array;

[0010] A perception anomaly analysis module, configured to obtain a service information array of the multiple devices, predict and classify to obtain an ideal perception accuracy parameter array, and combine the perception accuracy parameter array to calculate and obtain a perception anomaly parameter array;

[0011] A device load prediction module, configured to perform device load prediction according to the device temperature array and the device amplitude array, obtain a predicted device load array, and compensate the predicted device load array based on the perception anomaly parameter array to obtain a compensated device load array;

[0012] A production scheduling optimization module, configured to obtain current production planning information, combine the compensated device load array, perform production scheduling optimization to obtain optimal production scheduling information, and perform control.

[0013] In a third aspect, the present invention provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, it implements the production scheduling control method for device status perception as described in the first aspect.

[0014] The beneficial effects of the present invention are as follows: By monitoring the device temperature array and the device amplitude array, the present invention can reflect the operating state of the device in real time, providing basic data for subsequent analysis. Secondly, temperature amplitude verification analysis is carried out to obtain the perception accuracy parameter array. Through comparison with historical data and index classification, the credibility of the monitoring data is improved, and the error degree caused by problems such as sensor aging and data drift is known. On this basis, the service information array of the device is obtained, the ideal perception accuracy parameter is predicted, and the perception anomaly parameter array is calculated, which can quantify the error and anomaly degree of device status monitoring and provide a correction basis for subsequent device load prediction and production scheduling. The present invention also predicts the device load array and compensates based on the perception anomaly parameter, effectively making up for the inaccurate load prediction caused by the device status perception error and improving the rationality of load prediction. Finally, by combining the compensated device load array to optimize production scheduling, it is ensured that the production scheduling plan can fully consider the real operating ability of the device, improve the device utilization rate, avoid the scheduling imbalance problem caused by misjudgment of the status, and comprehensively reduce problems such as device damage and production quality decline caused by inappropriate scheduling as much as possible, thereby optimizing production efficiency and reducing production losses. In summary, through multi-level data monitoring, error correction, and optimization calculation, the present invention realizes more accurate device status perception and production scheduling control, solves the problem of inaccurate scheduling management caused by device status monitoring errors in the prior art, and improves the intelligence and adaptability of production scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 FIG. is a schematic flowchart of a production scheduling control method for device status perception provided by the present invention;

[0016] Figure 2 FIG. is a schematic structural diagram of a production scheduling control system for device status perception provided by the present invention.

[0017] In the drawings, the components represented by the reference numerals are described as follows:

[0018] Device perception module 11, perception anomaly analysis module 12, device load prediction module 13, production scheduling optimization module 14. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0020] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality of" means two or more unless otherwise specifically defined.

[0021] In the description of the present invention, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to implement and use the present invention. In the following description, details are set forth for purposes of explanation. It should be understood that those of ordinary skill in the art can recognize that the present invention can be implemented without the use of these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

[0022] Embodiment 1, as Figure 1 shown, the embodiment of the present invention provides a production scheduling control method for device status perception, which specifically includes the following steps:

[0023] S10: Monitor the operating temperature and operating amplitude of multiple devices to obtain a device temperature array and a device amplitude array, and respectively perform temperature amplitude verification analysis on each device to obtain a perception accuracy parameter array.

[0024] In the embodiment of the present application, first, monitor the operating temperature and operating amplitude of multiple devices currently undergoing production scheduling to obtain a device temperature array and a device amplitude array. The temperature and amplitude of the device can reflect the current load level of the device operation and the change in lubrication status.

[0025] Further, according to the monitored device temperature array and device amplitude array, respectively perform temperature amplitude verification analysis on each device to determine whether the temperature and amplitude of each monitored device are accurate, and obtain a perception accuracy parameter array.

[0026] The step S10 in the method provided by the embodiment of the present application includes:

[0027] Monitor the operating temperature and operating amplitude of multiple devices to obtain an operating temperature set and an operating amplitude set;

[0028] Obtain the sequence of the multiple devices, arrange the operating temperature set and the operating amplitude set, and obtain a device temperature array and a device amplitude array.

[0029] In the embodiments of the present application, the multiple devices are, for example, multiple numerically controlled machine tools of the same model. During operation, the temperature and amplitude of the numerically controlled machine tools will change significantly with the increase of the operation time and load.

[0030] First, perform operating temperature monitoring and operating amplitude monitoring on the multiple devices, respectively obtain an operating temperature set and an operating amplitude set, and provide basic data support for subsequent state analysis. The operating temperature refers to the temperature value measured during the operation of the device, which is usually collected in real time through an infrared temperature sensor, a thermocouple or other temperature detection devices. For example, the operating temperature of a certain device may be 65°C. The operating amplitude refers to the vibration amplitude generated by the mechanical movement or load change of the device during operation, which can be measured by an acceleration sensor or a vibration monitoring system. For example, the operating amplitude of a certain device may be 0.15 mm or 0.25 mm. Optionally, the temperature and amplitude of the spindle bearing, tool or motor in the numerically controlled machine tool can be monitored and collected.

[0031] Furthermore, after obtaining the temperature and amplitude data of each device, it is necessary to arrange these data in sequence to form a device temperature array and a device amplitude array. Among them, obtain the sequence of the multiple devices, for example, obtain the spatial sequence of the multiple devices in the factory building or the sequence of the pre-numbered devices, arrange the operating temperature set and the operating amplitude set. For example, if the measured temperatures of devices A, B, and C are 65°C, 72°C, and 68°C in sequence, then the device temperature array can be expressed as [65, 72, 68]. In this way, a device temperature array and a device amplitude array are obtained.

[0032] Step S10 in the method provided by the embodiments of the present application includes:

[0033] Obtain the historical temperature and amplitude monitoring data of the same type of devices, collect the sample device temperature set, and collect the average amplitude of the devices at different sample device temperatures to obtain the sample device amplitude set;

[0034] Construct a device verification index table with the sample device temperature set as the index header and the sample device amplitude set as the index value;

[0035] Input the multiple temperatures in the device temperature array into the device verification index table, and obtain an indexed device amplitude array through index classification;

[0036] Calculate and obtain a verified amplitude deviation amplitude array according to the indexed device amplitude array and the device amplitude array;

[0037] According to the verified amplitude deviation magnitude array, a perceived accuracy parameter array is calculated, wherein the magnitude of the perceived accuracy parameter is negatively correlated with the magnitude of the verified amplitude deviation magnitude.

[0038] In the embodiments of the present application, in order to know the accuracy of currently monitoring the temperatures and amplitudes of multiple devices, it is necessary to perform temperature-amplitude verification analysis for each device according to the device temperature array and the device amplitude array.

[0039] In the embodiments of the present application, first, historical temperature-amplitude monitoring data of the same type of devices is obtained. These data can be from the device operation data logs recorded during long-term operation, including the temperature-amplitude correspondence relationship during the operation of the same type of devices. First, the temperatures of the sample devices are collected. For example, the device operation temperature data of different devices are collected at different time points, such as [42°C, 55°C, 65°C, 72°C], to form a sample device temperature set.

[0040] Furthermore, the average amplitudes of the devices at different sample device temperatures are collected. For example, when the temperature of the same type of device is monitored multiple times to be 40°C, the device amplitude of the same type of device is calculated to be 0.08 mm. Then, the sample device amplitude corresponding to 40°C is 0.08 mm. In this way, the average amplitudes of the devices at different sample device temperatures are collected to obtain a sample device amplitude set.

[0041] Furthermore, with the sample device temperature set as the index header and the sample device amplitude set as the index value, based on the mapping relationship between each sample device temperature and the corresponding sample device amplitude, a device verification index table is constructed. The device verification index table includes the mapping relationships between multiple sample device temperatures and multiple sample device amplitudes. When a sample device temperature is input, the corresponding sample device amplitude can be mapped and indexed. Exemplarily, part of the data in the device verification index table is shown in Table 1.

[0042]

[0043] In this way, multiple temperatures in the current device temperature array are input into the device verification index table. When there is the same sample device temperature, the corresponding device amplitude is indexed and output. If there is no same sample device temperature, the device amplitude corresponding to the sample device temperature with the smallest difference is obtained and indexed and output. For example, when 39°C is input, the sample device temperature with the smallest difference is 40°C, then the device amplitude corresponding to 40°C is indexed and output. In this way, an indexed device amplitude array is obtained by indexing and output.

[0044] Further, temperature amplitude verification analysis and calculation are performed based on the index device amplitude array and the device amplitude array. Specifically, the index device amplitude array includes the ideal device amplitude sizes of multiple devices under the current device temperature array, while the device amplitude array includes the actually monitored device amplitude sizes of multiple devices. Due to possible errors of the sensors and potential hidden faults that may occur due to the long operation time of the devices, the actual device amplitude is inconsistent with the index device amplitude. By calculating the deviation amplitude between the actual device amplitude and the index device amplitude, the accuracy degree of detecting and perceiving the temperature and amplitude of the current multiple devices can be analyzed, that is, the perception accuracy parameter.

[0045] Exemplarily, based on the index device amplitude array and the device amplitude array, calculate the amplitude difference between the index device amplitude and the device amplitude of each device, and calculate the ratio of the absolute value of the amplitude difference to the index device amplitude as the verified amplitude deviation amplitude. In this way, a verified amplitude deviation amplitude array is calculated. Exemplarily, if the device amplitude of a certain device is 0.10 mm and the index device amplitude is 0.08 mm, then the verified amplitude deviation amplitude is (0.10 - 0.08) / 0.08 = 0.25.

[0046] Then, based on the verified amplitude deviation amplitude array, calculate the perception accuracy parameter array. Among them, the larger the verified amplitude deviation amplitude, the less accurate the perception, and the smaller the perception accuracy parameter. The size of the perception accuracy parameter is negatively correlated with the size of the verified amplitude deviation amplitude. For example, use 1 minus the verified amplitude deviation amplitude as the perception accuracy parameter. For example, if the verified amplitude deviation amplitude is 0.25, then the perception accuracy parameter is 1 - 0.25 = 0.75. In this way, a perception accuracy parameter array is calculated. The larger the perception accuracy parameter, the more accurate the monitoring and perception of the device state parameters. Conversely, it may be due to sensor errors or hidden device faults (such as lubrication failure) that lead to inaccurate monitoring and perception of the device state parameters.

[0047] Through the above steps, the accuracy of perceiving the operating state of the device can be effectively evaluated, and then used as the data basis for subsequent production scheduling of multiple devices. Furthermore, in production scheduling, not only the monitored operating parameters of the devices can be considered, but also the accuracy degree of the operating parameters caused by monitoring errors or hidden device faults can be analyzed, improving the reliability and accuracy of production scheduling.

[0048] S20: Obtain the service information array of the multiple devices, predict and classify to obtain the ideal perception accuracy parameter array, and combine the perception accuracy parameter array to calculate and obtain the perception anomaly parameter array.

[0049] In the embodiments of the present application, as the service time of the device increases, the device will gradually age, which will lead to inaccurate monitoring and perception of the device state parameters, that is, the perception accuracy parameter decreases. The embodiments of the present application obtain the service information arrays of multiple devices, predict the ideal perception accuracy parameters under different service information, obtain the ideal perception accuracy parameter arrays, and then combine the perception accuracy parameter arrays calculated by the current verification analysis to analyze whether the perception accuracy parameters of the current multiple devices are reasonable, and further analyze whether there are abnormalities, such as abnormal situations where premature aging leads to inaccurate perception, to obtain the perception abnormal parameter arrays.

[0050] Step S20 in the method provided by the embodiments of the present application includes:

[0051] Obtain the service time of the multiple devices as service information to obtain a service information array;

[0052] According to each service information, predict and classify to obtain an ideal perception accuracy parameter array;

[0053] According to the ideal perception accuracy parameter array and the perception accuracy parameter array, calculate the deviation amplitude between each ideal perception accuracy parameter and each perception accuracy parameter as the perception abnormal parameter to obtain the perception abnormal parameter array.

[0054] In the embodiments of the present application, the service time of the multiple devices is obtained. The service time is the running time of the device from the time of being put into use to the present, which has a direct impact on the state perception accuracy of the device. Generally, as the use time of the device increases, component aging and wear intensify, resulting in an increase in the volatility of state parameters such as temperature and amplitude, leading to a decrease in perception accuracy, that is, the perception accuracy parameter decreases.

[0055] To quantitatively analyze the perception accuracy parameters under different service times, the service times of multiple devices are obtained as service information, and a service information array is constructed, which records the running time data of multiple devices. For example, the service times of devices A, B, and C are 12 months, 24 months, and 36 months.

[0056] Further, according to each service information, predict and classify to obtain the perception accuracy parameters of the devices in the ideal state under different service information to obtain the ideal perception accuracy parameter array.

[0057] The step "According to each service information, predict and classify to obtain the ideal perception accuracy parameter array" in the method provided by the embodiments of the present application includes:

[0058] According to the perception monitoring data of the same type of devices under different service times, collect a sample service information set, and collect the average perception accuracy parameters of the devices under different sample service information to obtain a sample ideal perception accuracy parameter set;

[0059] Construct an equipment perception index table with the sample service information set as the index header and the sample ideal perception accuracy parameter set as the index value;

[0060] Input each service information in the service information array into the equipment perception index table, and obtain the ideal perception accuracy parameter array through index classification.

[0061] In the embodiments of the present application, during the long-term operation of similar equipment, as the service time (i.e., the cumulative usage duration of the equipment) increases, factors such as the measurement accuracy of sensors and the mechanical stability of the equipment will change. Therefore, equipment with different service times may exhibit different accuracies in state perception. For example, the greater the service time, the smaller the perception accuracy parameter.

[0062] Collect the perception monitoring data of similar equipment at different service times. First, collect the different service times of similar equipment as sample service information to obtain the sample service information set. And extract the average perception accuracy parameters of similar equipment under different sample service information (i.e., service times), which can be obtained by calculating the mean value of the perception accuracy parameters of similar equipment with the same service time. In this way, the sample ideal perception accuracy parameter set is collected.

[0063] Furthermore, to facilitate querying the ideal perception accuracy parameters of different service times, construct an equipment perception index table with the current service information set as the index header and the sample ideal perception accuracy parameter array as the index value. The equipment perception index table includes the mapping index relationship between the sample service information set and the sample ideal perception accuracy parameter set. Exemplarily, part of the data in the equipment perception index table is shown in Table 2.

[0064]

[0065] In the embodiments of the present application, based on the constructed equipment perception index table, input each service information in the current service information array for index prediction classification to obtain the ideal perception accuracy parameter corresponding to each service information, or the ideal perception accuracy parameter corresponding to the sample service information with the closest index. In this way, the ideal perception accuracy parameter array is obtained.

[0066] The ideal perception accuracy parameter array reflects the perception accuracy parameters of multiple current devices under normal conditions based on their service time. If the actual perception accuracy parameter of a device is less than this perception accuracy parameter, it indicates an implicit fault caused by premature aging or excessive current production load of the device, resulting in an abnormal perception accuracy parameter. The probability of damage to this device is relatively high, and it needs to be considered as a key factor in subsequent production scheduling to avoid damaging the device or affecting the processing quality. Conversely, if the actual perception accuracy parameter of the device is consistent with the perception accuracy parameter, it indicates that the monitoring perception accuracy of the device is normal and the device is operating normally, and only general consideration is required in subsequent production scheduling.

[0067] The embodiments of the present application can reasonably calculate the perception accuracy of a device based on its service time, providing data support for subsequent production scheduling optimization.

[0068] In the embodiments of the present application, based on the ideal perception accuracy parameter array obtained by prediction classification and the perception accuracy parameter array actually obtained through verification and analysis calculation, perception anomaly analysis of multiple devices is performed as perception anomaly parameters.

[0069] Exemplarily, the deviation amplitude between the ideal perception accuracy parameter and the perception accuracy parameter of each device is calculated as the perception anomaly parameter. For example, if the ideal perception accuracy parameter of a certain device is 0.95 and the perception accuracy parameter obtained through actual verification and analysis calculation is 0.92, then the deviation amplitude is (0.95 - 0.92) / 0.95 = 3.1%. As the perception anomaly parameter. The larger the perception anomaly parameter, the higher the probability of a fault occurring in the device operation and state monitoring perception, and it needs to be considered as a key factor in subsequent production scheduling.

[0070] S30: Based on the device temperature array and the device amplitude array, perform device load prediction to obtain a predicted device load array, and based on the perception anomaly parameter array, compensate the predicted device load array to obtain a compensated device load array.

[0071] In the embodiments of the present application, in order to perform production scheduling for multiple devices, it is also necessary to perform load prediction for multiple devices as reference data for production scheduling. Among them, based on the device temperature array and the device amplitude array, device load prediction is performed to obtain a predicted device load array.

[0072] Furthermore, the larger the perception anomaly parameter of a device, the higher the probability that its previous production load was too high, resulting in a fault or inaccurate monitoring perception. Therefore, based on the perception anomaly parameter array, the predicted device load of each device is compensated and corrected, so that the load of the device with a larger perception anomaly parameter is amplified, improving the rationality of subsequent production scheduling and avoiding excessive scheduling load on devices with a larger perception anomaly degree, which may cause device damage.

[0073] Step S30 in the method provided by the embodiment of this application includes:

[0074] Using the sample device temperature set and the sample device amplitude set as input features, using the sample device load set as output features, and using machine learning to train a device load predictor;

[0075] According to the device temperature array and the device amplitude array, divide and combine to obtain the load prediction input features of each device, input them into the device load predictor, and output to obtain a predicted device load array;

[0076] According to the perceived anomaly parameter array, compensate the predicted device load array to obtain a compensated device load array.

[0077] In the embodiment of this application, in order to accurately predict the operating load of a device, it is necessary to establish a device load predictor using machine learning based on the historical load monitoring data of similar devices, and compensate the predicted load in combination with the perceived anomaly parameters, so as to obtain a more accurate compensated device load array.

[0078] In the embodiment of this application, the operating load monitoring data of similar devices is collected, specifically, the temperature and amplitude during the operation of similar devices are collected, and the load degree of the device operation under different sample device temperatures and sample device amplitudes is collected. Among them, the load degree can be the proportional coefficient of the proportion of devices that need to be repaired under different sample device temperatures and sample device amplitudes, and used as the device load. In this way, the sample device load set is collected and labeled.

[0079] Exemplarily, among the operating parameters of similar devices, the number of devices under a certain sample device temperature and sample device amplitude monitored is 10, and the number of devices that need to be repaired is found to be 6 during subsequent maintenance. Then the sample device load corresponding to the sample device temperature and sample device amplitude is 6 / 10 = 0.6.

[0080] Further, using the sample device temperature set and the sample device amplitude set as input features, using the sample device load set as output features, and using machine learning to train a device load predictor for predicting the device load. Exemplarily, a feedforward neural network in machine learning is used to construct a device load predictor, which includes an input layer, a hidden layer, and an output layer. The dimensions of the input layer and the output layer are 2 and 1 respectively, and the hidden layer uses a ReLU activation function. During the training process, the sample device temperature and the sample device amplitude are input, the output device load is obtained, the difference from the corresponding sample device load is calculated as the loss, and then the network parameters such as weights are adjusted according to the loss to reduce the loss until it is less than a preset requirement, such as less than 0.05, then the training is completed.

[0081] Based on the currently collected device temperature array and device amplitude array, perform division and combination to obtain the current device temperature and device amplitude of each device, which are used as input data and input into the trained device load predictor to output the corresponding device load, thereby obtaining the predicted device load array.

[0082] Further, according to the sensed anomaly parameter array, perform compensation and correction on the predicted device load array to obtain the compensated device load array of multiple devices after compensation and correction.

[0083] The step "According to the sensed anomaly parameter array, perform compensation on the predicted device load array to obtain the compensated device load array" in the method provided by the embodiments of the present application includes:

[0084] Generate a device load compensation coefficient array according to the sensed anomaly parameter array;

[0085] Perform compensation calculation on the predicted device load array according to the device load compensation coefficient array to obtain the compensated device load array.

[0086] In the embodiments of the present application, a device load compensation coefficient array for device load compensation and correction is generated according to the sensed anomaly parameter array. Exemplarily, use 1 plus each sensed anomaly parameter as the device load compensation coefficient. For example, if the sensed anomaly parameter is 3.1%, then the device load compensation coefficient is 1 + 3.1% = 1.031. In this way, the larger the sensed anomaly parameter, the larger the device load compensation coefficient, and the larger the compensated device load. The device load with sensed anomalies, that is, the device load that may have faults, can be amplified, reducing its production volume in subsequent production scheduling, optimizing the rationality of scheduling, and minimizing equipment damage and ensuring production quality.

[0087] Further, use multiple device load compensation coefficients in the device load compensation coefficient array to perform compensation and correction calculation on multiple predicted device loads in the predicted device load array. For example, multiply the device load compensation coefficient by the predicted device load to obtain the compensated device load array after compensation and correction. For example, if the device load compensation coefficient is 1.031 and the predicted device load is 0.6, then the compensated device load is .

[0088] S40: Obtain the current production planning information, combine it with the compensated device load array, perform optimization of production scheduling, obtain the optimal production scheduling information, and perform control.

[0089] In the embodiments of the present application, obtain the production planning information for current production scheduling, combine it with the compensated device load arrays of multiple predicted and compensated devices, perform optimization of production scheduling for multiple devices, obtain the optimal production scheduling information, and perform production control.

[0090] Step S40 in the method provided by the embodiments of the present application includes:

[0091] Obtain the current production planning information, where the production planning information includes the production volume;

[0092] Based on the compensation equipment load array and the perceived anomaly parameter array, construct a production scheduling function as follows:

[0093] ;

[0094] where is the scheduling fitness, N is the number of multiple devices, is the weight of the i-th device assigned according to the perceived anomaly parameter of each device in the perceived anomaly parameter array, is the proportion of the equipment production volume assigned to the i-th device in the production planning information, is the equipment production coefficient assigned according to the compensation equipment load of the i-th device, where the magnitude of the equipment production coefficient is negatively correlated with the compensation equipment load;

[0095] Randomly assign the production planning information to multiple devices to obtain multiple first equipment production volumes as the first production scheduling information;

[0096] Based on the production scheduling function, calculate the first scheduling fitness of the first production scheduling information;

[0097] Continue the random assignment and optimization of the production scheduling information until convergence, and output the optimal production scheduling information with the maximum scheduling fitness for control.

[0098] In the embodiments of the present application, first, obtain the current production planning information, which includes the total production volume. For example, it is required to produce 10,000 products.

[0099] Further, based on the compensation equipment load array and the perceived anomaly parameter array, construct a production scheduling function as follows:

[0100] ;

[0101] where is the scheduling fitness, N is the number of multiple devices, for example, N is 10, is the weight of the i-th device assigned according to the perceived anomaly parameter of each device in the perceived anomaly parameter array. Specifically, calculate the ratio of the perceived anomaly parameter of each device to the sum of the perceived anomaly parameter array as the weight. The greater the perceived anomaly parameter of the device, the greater the weight, and the greater the emphasis in the production scheduling optimization. It is the ratio of the production volume allocated to the i-th device to the production planning information, for example, the ratio of the production capacity allocated to the i-th device to the total production capacity.

[0102] It is the equipment production coefficient allocated according to the compensation equipment load of the i-th device. Among them, the size of the equipment production coefficient is negatively correlated with the compensation equipment load. That is, the greater the compensation equipment load, the smaller the production volume that the equipment needs to be allocated, so as to avoid equipment failure and damage due to excessive load. Therefore, the greater the compensation equipment load, the smaller the equipment production coefficient. For example, the reciprocals of the compensation equipment loads of multiple devices can be calculated, and then the ratio of each reciprocal to the sum of multiple reciprocals can be calculated as the equipment production coefficient. In this way, multiple equipment production coefficients of multiple devices are obtained.

[0103] Furthermore, the production planning information is randomly allocated to multiple devices, that is, the total production volume is randomly allocated to multiple devices to obtain multiple first equipment production volumes as the first production scheduling information. The sum of multiple first equipment production volumes is the production volume in the production planning information.

[0104] Furthermore, calculate the ratio of each first equipment production volume to the total production volume as the multiple first equipment production ratios, and then combine the equipment production coefficients of multiple devices and substitute them into the production scheduling function to calculate the first scheduling fitness. Among them, the closer the production ratio and the equipment production coefficient of each device are, the more reasonable the production scheduling allocation is, and the greater the scheduling fitness is.

[0105] Furthermore, continue to randomly allocate the production planning information to generate new production scheduling information, calculate the scheduling fitness, and optimize the production scheduling information until convergence. For example, after randomly generating 100 production scheduling information, convergence occurs, the optimization ends, and the production scheduling information with the largest scheduling fitness is output as the optimal production scheduling information to complete the optimization and perform the control of production scheduling.

[0106] In the embodiment of the present application, by allocating the equipment production coefficient according to the compensation equipment load of multiple devices and optimizing the scheduling information, the equipment with a greater load can produce a smaller quantity, and the greater the perceived abnormal parameter, the greater the weight concerned in the optimization, that is, the greater the weight of the equipment that may be prematurely aged or faulty. In this way, the reliability and rationality of equipment production scheduling control are improved, equipment damage due to excessive load is avoided, and production efficiency and quality are guaranteed.

[0107] A production scheduling control method for equipment status perception provided by an embodiment of the present invention has at least the following technical effects:

[0108] In the embodiments of the present invention, by monitoring the device temperature array and the device amplitude array, the operating state of the device can be reflected in real time, providing basic data for subsequent analysis. Secondly, temperature amplitude verification analysis is carried out to obtain the perception accuracy parameter array. Through comparison with historical data and index classification, the credibility of the monitoring data is improved, and the error degree caused by problems such as sensor aging and data drift is known. On this basis, the service information array of the device is obtained, the ideal perception accuracy parameter is predicted, and the perception anomaly parameter array is calculated, which can quantify the error anomaly degree of device state monitoring and provide a correction basis for subsequent device load prediction and production scheduling. The present invention also predicts the device load array and compensates based on the perception anomaly parameter, effectively making up for the inaccurate load prediction caused by the device state perception error and improving the rationality of load prediction. Finally, by combining the compensated device load array to optimize production scheduling, it is ensured that the production scheduling plan can fully consider the actual operating capacity of the device, improve device utilization rate, avoid scheduling imbalance problems caused by misjudgment of the state, and comprehensively reduce problems such as device damage and production quality decline caused by inappropriate scheduling as much as possible, thereby optimizing production efficiency and reducing production losses. In summary, through multi-level data monitoring, error correction and optimization calculation, the present invention realizes more accurate device state perception and production scheduling control, solves the problem of inaccurate scheduling management caused by device state monitoring error in the prior art, and improves the intelligence and adaptability of production scheduling.

[0109] Embodiment 2, as Figure 2 shown, based on the same inventive concept as the production scheduling control method for device state perception provided in Embodiment 1, the embodiments of the present invention also provide a production scheduling control system for device state perception, including:

[0110] A device perception module 11, configured to monitor the operating temperature and operating amplitude of multiple devices, obtain a device temperature array and a device amplitude array, and perform temperature amplitude verification analysis on each device respectively to obtain a perception accuracy parameter array;

[0111] A perception anomaly analysis module 12, configured to obtain the service information array of the multiple devices, predict and classify to obtain an ideal perception accuracy parameter array, and combine the perception accuracy parameter array to calculate and obtain a perception anomaly parameter array;

[0112] A device load prediction module 13, configured to predict the device load according to the device temperature array and the device amplitude array, obtain a predicted device load array, and compensate the predicted device load array based on the perception anomaly parameter array to obtain a compensated device load array;

[0113] The production scheduling optimization module 14 is used to obtain the current production planning information, combine with the compensation equipment load array, optimize the production scheduling, obtain the optimal production scheduling information, and perform control.

[0114] Furthermore, the production scheduling control system for equipment status perception is also used for:

[0115] Monitor the operating temperature and operating amplitude of multiple devices to obtain an operating temperature set and an operating amplitude set;

[0116] Obtain the sequence of the multiple devices, arrange the operating temperature set and the operating amplitude set to obtain an equipment temperature array and an equipment amplitude array.

[0117] Furthermore, the production scheduling control system for equipment status perception is also used for:

[0118] Obtain the historical temperature and amplitude monitoring data of similar devices, collect a sample equipment temperature set, and collect the average amplitude of the equipment at different sample equipment temperatures to obtain a sample equipment amplitude set;

[0119] Construct an equipment verification index table with the sample equipment temperature set as the index header and the sample equipment amplitude set as the index value;

[0120] Input the multiple temperatures in the equipment temperature array into the equipment verification index table, and obtain an indexed equipment amplitude array through index classification;

[0121] Calculate and obtain a verification amplitude deviation magnitude array based on the indexed equipment amplitude array and the equipment amplitude array;

[0122] Calculate and obtain a perception accuracy parameter array based on the verification amplitude deviation magnitude array, where the size of the perception accuracy parameter is negatively correlated with the size of the verification amplitude deviation magnitude.

[0123] Furthermore, the production scheduling control system for equipment status perception is also used for:

[0124] Obtain the service time of the multiple devices as service information to obtain a service information array;

[0125] Predict and classify to obtain an ideal perception accuracy parameter array based on each service information;

[0126] Calculate the deviation magnitude between each ideal perception accuracy parameter and each perception accuracy parameter based on the ideal perception accuracy parameter array and the perception accuracy parameter array as a perception anomaly parameter to obtain a perception anomaly parameter array.

[0127] Furthermore, the production scheduling control system for equipment status perception is also used for:

[0128] Collect a sample service information set based on the perception monitoring data of similar devices at different service times, and collect the average perception accuracy parameters of the devices under different sample service information to obtain a sample ideal perception accuracy parameter set;

[0129] Construct a device perception index table with the sample service information set as the index header and the sample ideal perception accuracy parameter set as the index value;

[0130] Input each service information in the service information array into the device perception index table, and index and classify to obtain an ideal perception accuracy parameter array.

[0131] Furthermore, the production scheduling control system for device status perception is also used for:

[0132] Collect a sample device temperature set and a sample device amplitude set based on the operation load monitoring data of similar devices, and label the load degree of the devices under different sample device temperatures and sample device amplitudes to obtain a sample device load set;

[0133] Use the sample device temperature set and the sample device amplitude set as input features, use the sample device load set as output features, and use machine learning to train a device load predictor;

[0134] According to the device temperature array and the device amplitude array, divide and combine to obtain the load prediction input features of each device, input them into the device load predictor, and output to obtain a predicted device load array;

[0135] Compensate the predicted device load array according to the perception anomaly parameter array to obtain a compensated device load array.

[0136] Furthermore, the production scheduling control system for device status perception is also used for:

[0137] Generate a device load compensation coefficient array according to the perception anomaly parameter array;

[0138] Perform compensation calculation on the predicted device load array according to the device load compensation coefficient array to obtain a compensated device load array.

[0139] Furthermore, the production scheduling control system for device status perception is also used for:

[0140] Obtain the current production planning information, where the production planning information includes the production volume;

[0141] Based on the compensated device load array and the perception anomaly parameter array, construct a production scheduling function as follows:

[0142] ;

[0143] Among them, is the scheduling fitness, N is the number of multiple devices, is the weight of the i-th device assigned according to the sensing anomaly parameter of each device in the sensing anomaly parameter array, is the ratio of the device production volume assigned to the i-th device to the production planning information, is the device production coefficient assigned according to the compensation device load of the i-th device, where the size of the device production coefficient is negatively correlated with the compensation device load;

[0144] Randomly assign the production planning information to multiple devices to obtain multiple first device production volumes as the first production scheduling information;

[0145] Based on the production scheduling function, calculate the first scheduling fitness of the first production scheduling information;

[0146] Continue the random assignment and optimization of the production scheduling information until convergence, output the optimal production scheduling information with the maximum scheduling fitness, and perform control.

[0147] Embodiment 3. This embodiment provides a computer-readable storage medium. A computer program is stored in the computer storage medium. When the computer program is executed by a processor, it implements a production scheduling control method for device state perception as in Embodiment 1.

[0148] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they know the basic creative concept.

[0149] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A production scheduling control method based on equipment status perception, characterized in that: The method comprises: Perform operating temperature monitoring and operating amplitude monitoring on multiple devices to obtain device temperature arrays and device amplitude arrays, perform temperature amplitude verification analysis on each device respectively, and obtain a perception accuracy parameter array; Acquire the service information array of the plurality of devices, predict and classify to obtain an ideal perception accuracy parameter array, and calculate and obtain a perception abnormality parameter array by combining the perception accuracy parameter array; According to the device temperature array and the device amplitude array, device load prediction is performed to obtain a predicted device load array, and based on the sensed abnormality parameter array, the predicted device load array is compensated to obtain a compensated device load array; Obtain the current production planning information, combine it with the compensation equipment load array, optimize the production schedule, obtain the optimal production schedule information, and perform control, including: Acquire current production planning information, wherein the production planning information includes production volume; Based on the compensation equipment load array and the abnormal perception parameter array, a production scheduling function is constructed as follows: ； in, is the scheduling adaptability, N is the number of multiple devices, The first The weight of the device, For the The proportion of the equipment production volume allocated to each equipment to the production planning information, According to The equipment production coefficient of the compensation equipment load distribution of each equipment, wherein the size of the equipment production coefficient is negatively correlated with the compensation equipment load; Randomly assigning the production planning information to a plurality of devices to obtain a plurality of first device production quantities as first production scheduling information; Based on the production scheduling function, calculating and obtaining a first scheduling fitness of the first production scheduling information; Continue to randomly allocate and optimize the production schedule information until convergence, and output the optimal production schedule information with the largest schedule fitness for control.

2. The production scheduling control method based on equipment status perception according to claim 1 is characterized in that: Perform operating temperature monitoring and operating amplitude monitoring on multiple devices to obtain device temperature arrays and device amplitude arrays, including: Perform operating temperature monitoring and operating amplitude monitoring on multiple devices to obtain an operating temperature set and an operating amplitude set; The sequence of the plurality of devices is obtained, and the operating temperature sets and the operating amplitude sets are arranged to obtain a device temperature array and a device amplitude array.

3. The production scheduling control method based on equipment status perception according to claim 1 is characterized in that: Perform temperature amplitude validation analysis on each device separately to obtain an array of perception accuracy parameters, including: Obtain historical temperature amplitude monitoring data of similar equipment, collect a sample equipment temperature set, and collect the average amplitude of the equipment at different sample equipment temperatures to obtain a sample equipment amplitude set; Using the sample device temperature set as an index header and the sample device amplitude set as an index value, constructing a device verification index table; Inputting a plurality of temperatures in the device temperature array into the device verification index table, and obtaining an index device amplitude array by index classification; Calculating and obtaining a verification amplitude deviation amplitude array according to the index device amplitude array and the device amplitude array; According to the verification amplitude deviation magnitude array, a perception accuracy parameter array is calculated and obtained, wherein the magnitude of the perception accuracy parameter is negatively correlated with the magnitude of the verification amplitude deviation magnitude.

4. The production scheduling control method based on equipment status perception according to claim 1 is characterized in that: Acquiring the service information array of the plurality of devices, predicting and classifying to obtain an ideal perception accuracy parameter array, and combining the perception accuracy parameter array to calculate and obtain a perception abnormality parameter array, including: Obtaining the service time of the plurality of devices as service information, and obtaining a service information array; According to each service information, the prediction classification obtains an array of ideal perception accuracy parameters; According to the ideal perception accuracy parameter array and the perception accuracy parameter array, the deviation amplitude of each ideal perception accuracy parameter and each perception accuracy parameter is calculated as a perception abnormality parameter to obtain a perception abnormality parameter array.

5. The production scheduling control method based on equipment status perception according to claim 4 is characterized in that: Based on each service information, the prediction classification obtains an array of ideal perception accuracy parameters, including: According to the perception monitoring data of the same type of equipment at different service times, a sample service information set is collected, and the average perception accuracy parameters of the equipment under different sample service information are collected to obtain a sample ideal perception accuracy parameter set; Constructing a device perception index table using the sample service information set as an index header and the sample ideal perception accuracy parameter set as an index value; Each service information in the service information array is input into the device perception index table, and the index classification is performed to obtain an ideal perception accuracy parameter array.

6. The production scheduling control method based on equipment status perception according to claim 1 is characterized in that: According to the device temperature array and the device amplitude array, device load prediction is performed to obtain a predicted device load array, and based on the sensed abnormality parameter array, the predicted device load array is compensated to obtain a compensated device load array, including: According to the operating load monitoring data of similar equipment, a sample equipment temperature set and a sample equipment amplitude set are collected, and the load degree of the equipment under different sample equipment temperatures and sample equipment amplitudes is collected and marked to obtain a sample equipment load set; Using the sample device temperature set and the sample device amplitude set as input features, using the sample device load set as output features, and using machine learning to train a device load predictor; According to the device temperature array and the device amplitude array, the load prediction input characteristics of each device are obtained by dividing and combining, and the characteristics are input into the device load predictor, and the predicted device load array is obtained by output; The predicted equipment load array is compensated according to the perceived abnormality parameter array to obtain a compensated equipment load array.

7. The production scheduling control method based on equipment status perception according to claim 6 is characterized in that: According to the sensed abnormality parameter array, the predicted device load array is compensated to obtain a compensated device load array, including: Generating an array of equipment load compensation coefficients according to the array of abnormal perception parameters; According to the equipment load compensation coefficient array, compensation calculation is performed on the predicted equipment load array to obtain a compensated equipment load array.

8. A production scheduling control system based on equipment status perception, characterized in that: The steps for implementing the production scheduling control method of equipment status awareness as described in any one of claims 1 to 7 include: The device perception module is used to monitor the operating temperature and operating amplitude of multiple devices, obtain the device temperature array and the device amplitude array, perform temperature amplitude verification analysis on each device respectively, and obtain the perception accuracy parameter array; A perception anomaly analysis module, used to obtain the service information array of the plurality of devices, predict and classify to obtain an ideal perception accuracy parameter array, and calculate and obtain a perception anomaly parameter array in combination with the perception accuracy parameter array; An equipment load prediction module is used to perform equipment load prediction based on the equipment temperature array and the equipment amplitude array to obtain a predicted equipment load array, and to compensate the predicted equipment load array based on the sensed abnormality parameter array to obtain a compensated equipment load array; The production scheduling optimization module is used to obtain the current production planning information, combine the compensation equipment load array, optimize the production scheduling, obtain the optimal production scheduling information, and perform control.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, implements the production scheduling control method with equipment status awareness as described in any one of claims 1 to 7.

Images