Control parameter adjusting method based on time sequence model, server, medium and product

Abstract

The invention discloses a control parameter adjusting method based on a time sequence model, a server, a medium and a product. The method comprises the following steps: acquiring real-time operation data and real-time control data of equipment, and determining predicted operation data; if the real-time operation data is not matched with the predicted operation data, obtaining a control parameter table through a preset time sequence model; acquiring abnormal parameter data of the abnormal operation parameters; when the abnormal parameter data is within a preset controllable data range, obtaining first operation data in a control parameter table; determining second operation data based on the abnormal parameter data and the first operation data; if the second operation data is not matched with the first operation data, determining a control data set; determining the product qualification rate after the equipment is adjusted according to each control data in the control data set; modifying the target control data in the control parameter table according to the control data corresponding to the highest product qualification rate; and sending the control parameter table to the equipment. By implementing the technical scheme, the product percent of pass during equipment failure is improved.

Description

Technical Field

[0001] This application relates to the field of parameter adjustment, and in particular to a control parameter adjustment method, server, medium and product based on a time series model. Background Technology

[0002] Modern industrial production, especially in precision manufacturing and continuous production, places increasingly higher demands on product quality stability. Automated production lines, by integrating various sensors and control systems, achieve real-time monitoring of the production process and real-time adjustment of equipment control parameters, ensuring that equipment operates in optimal condition and guaranteeing the final product qualification rate.

[0003] Currently, in industrial practice, when a sudden failure is detected during normal equipment operation, the standard emergency response procedure is usually to immediately trigger the safety interlock protection mechanism to quickly stop the equipment from operating, in order to prevent the failure from escalating or causing a safety accident.

[0004] However, in certain scenarios where the continuity of the processing is extremely important (such as heat treatment, chemical reaction, precision coating, etc.), this emergency shutdown method can cause products that are being processed or in the process to be scrapped directly due to the sudden interruption of the process flow, thereby reducing the product qualification rate of that batch or time period. Summary of the Invention

[0005] This application provides a control parameter adjustment method, server, medium, and product based on a timing model, which can improve the product qualification rate when equipment fails.

[0006] In a first aspect, this application provides a method for adjusting control parameters. The method includes: acquiring real-time operating data and real-time control data of a device; predicting, based on the real-time control data and historical operating data, predicting the predicted operating data of the device under normal operating conditions, according to the real-time control data; if the real-time operating data does not match the predicted operating data, inputting the real-time operating data into a preset time series model to obtain a control parameter table, the control parameter table including control data and adjustment time; acquiring abnormal parameter data corresponding to abnormal operating parameters at various adjustment times, the abnormal operating parameters being parameters whose values ​​do not match the operating parameters in the real-time operating data and the current operating data; when the abnormal parameter data is within a preset controllable data range, acquiring first operating data corresponding to a target adjustment time in the control parameter table, the target adjustment time being one of the adjustment times among all adjustment times. In any case, the first operating data is the operating data after the equipment is adjusted according to the target adjustment parameter data corresponding to the target adjustment time; the abnormal operating parameter data in the first operating data is replaced with the corresponding abnormal parameter data to obtain the second operating data; if the second operating data does not match the first operating data, the control parameter data associated with the abnormal operating parameter in the target control data is modified to the corresponding data in the real-time control data, and the control parameters unrelated to the abnormal operating parameter in the target control data are adjusted according to the preset parameter adjustment scheme to obtain a control data set; based on historical production data, the product qualification rate after the equipment is adjusted according to each control data in the control data set is determined; the target control data in the control parameter table is modified according to the control data corresponding to the highest product qualification rate; and the control parameter table is sent to the equipment.

[0007] By adopting the above technical solution, after detecting an anomaly in the equipment, a control parameter table for adjusting the equipment under normal conditions is generated using a preset timing model. This table is then adaptively modified to ensure the control data is suitable for the current abnormal situation. During this modification, the parameter values ​​of control parameters associated with the abnormal operating parameters are updated to match the corresponding values ​​in the equipment's real-time control data. This ensures the equipment operates according to the adjusted control data, preventing any impact on the abnormal module's operational status. This avoids exacerbating equipment malfunctions or introducing new problems due to improper control parameters, which could lead to unpredictable abnormal operating data and affect the accuracy of control data adjustments. Simultaneously, the parameter values ​​of control parameters unrelated to the abnormal operating parameters are adaptively corrected to obtain multiple control data sets. The product qualification rate after the equipment operates according to each control data set is calculated. The control data with the highest product qualification rate is selected to modify the control parameter table. This ensures that the equipment's operating data under abnormal conditions, adjusted according to the control parameters in the parameter table, most closely matches normal production requirements, improving the product qualification rate during equipment malfunctions.

[0008] In conjunction with some embodiments of the first aspect, in some embodiments, if the real-time operating data does not match the predicted operating data, the real-time operating data is input into a preset time series model to obtain a control parameter table. Specifically, this includes: if the real-time operating data does not match the predicted operating data, determining the transmission duration range from the current time point to the time point when the device starts operating according to the control parameters based on abnormal operating parameters, real-time network status, and historical data transmission data; calculating an adjustment time set based on the transmission duration range, where the adjustment time is the time when the device starts operating according to the control parameters; and inputting the real-time operating data and the adjustment time set into the preset time series model to obtain the control parameter table.

[0009] By adopting the above technical solution, when real-time operating data and predicted operating data do not match, the transmission duration range is determined based on abnormal operating parameters, real-time network status, and historical data transmission. This fully considers various influencing factors during data transmission, avoiding delays that could prevent control parameters from taking effect in a timely manner. The real-time operating data and adjustment time set are input into a preset timing model to obtain a control parameter table that closely matches actual transmission and operating conditions. This ensures that the equipment can be adjusted at appropriate times based on accurate control parameters, reducing adjustment deviations caused by unreasonable time planning or data transmission delays. This improves the timeliness and accuracy of equipment fault adjustment and increases the product qualification rate during equipment failures.

[0010] In conjunction with some embodiments of the first aspect, in some embodiments, if the real-time operating data does not match the predicted operating data, based on abnormal operating parameters, real-time network status, and historical data transmission data, the transmission duration range from the current time point to the time point when the device begins to operate according to the control parameters is determined. Specifically, this includes: determining the data transmission duration range between different devices based on real-time network status and historical data transmission data; determining the model calculation duration range based on the historical processing data of the time series model; determining the number of parameter adjustments based on abnormal operating parameters and preset parameter adjustment schemes; adding the product of the number of parameter adjustments and the preset duration range corresponding to each parameter adjustment to a preset base duration range to obtain the parameter adjustment duration range; and adding the data transmission duration range, the model calculation duration range, and the data adjustment duration range to obtain the transmission duration range.

[0011] By adopting the above technical solution, the transmission time range is determined by comprehensively considering the time range of data transmission, the time range required for the time series model to process the data, and the time range required for control data adjustment. This makes the determined time range comprehensive and accurate, providing a more reliable basis for subsequent calculation of adjustment time sets. It ensures that the equipment can start operating according to the control parameters at the appropriate time, improves the timeliness and effectiveness of equipment fault adjustment, and thus improves the product qualification rate when the equipment fails.

[0012] In conjunction with some embodiments of the first aspect, in some embodiments, after the step of sending the control parameter table to the device, the method further includes: after the first product is processed, obtaining production parameter data of a second product whose production sequence follows that of the first product, wherein the first product is the product being processed by the device; determining the non-conformity of the second product based on the product pass rate corresponding to the production parameter data and the current control data of the device; determining the processing value and product value of the second product based on the non-conformity, the current control data, and a preset cost correspondence table of the second product; when the processing value is greater than the product value, sending a stop processing command to the device, and controlling a preset transportation device to transport the second product to a preset area.

[0013] By adopting the above technical solution, after the equipment completes the processing of the first product, the processing value and product value of the second product, which follows the first product in the production sequence, are determined. When the processing value is greater than the product value, the product is not processed; the processing flow is terminated and the product is transferred in a timely manner. This avoids the continuous input of raw materials, energy, and manpower for ineffective processing when the equipment is in a faulty or abnormal state, thereby reducing the waste of production resources and lowering production costs.

[0014] In conjunction with some embodiments of the first aspect, in some embodiments, determining the processing value and product value of the second product based on the non-conformity, the current control data, and the preset cost correspondence table of the second product specifically includes: determining the degree of impact of the non-conformity on the use of the second product based on the non-conformity; determining the total loss value of the second product based on the degree of impact and the preset product loss value correspondence table; calculating the product value of the second product based on the preset total product value and the total loss value; obtaining the consumption value corresponding to the current control data; and adding the consumption value to the product cost value of the second product in the preset cost correspondence table to obtain the processing value of the second product.

[0015] By employing the above technical solution, the impact of non-conformities on the use of the second product is determined. Then, by combining this with a pre-set product loss value correspondence table, the total loss value is accurately determined, leading to the product value of the second product. This allows for an accurate assessment of the product's ultimate achievable value. Simultaneously, the consumption value corresponding to the current control data is obtained, and this consumption value is added to the product cost value in a pre-set cost correspondence table to obtain the processing value. This comprehensively considers all cost inputs during product processing, making the calculated processing value more accurate. Through this value calculation method, the processing value and product value can be compared more accurately. Therefore, when the processing value exceeds the product value, it is timely to determine whether to continue processing, reducing waste of production resources.

[0016] In conjunction with some embodiments of the first aspect, in some embodiments, after the step of sending the control parameter table to the device, the method further includes: after the current batch of products is produced, if the rate of change of the abnormal parameter data is within a preset range of no change, acquiring the historical control data of the device; determining whether there is control parameter data matching the abnormal parameter data in the historical control data; if so, controlling a preset intelligent robot to press the reset button of the device; after the device is reset, acquiring the third operating data of the device; if the third operating data matches the preset operating data, determining that the abnormality of the abnormal parameter is due to a disconnection of the network data transmission link, and switching the device's control parameter adjustment method to a preset button control, wherein the button control is a method of adjusting control parameters through a preset physical line.

[0017] By employing the above technical solution, the system determines whether the equipment is not faulty, but rather that the network communication link between the device sending and receiving the abnormal control parameter data is broken, by judging whether the rate of change of the abnormal parameter data is within a preset range of no change and whether there is matching control parameter data in the historical control data. If the abnormality is detected as being caused by a broken network communication link, the equipment control mode is switched to the more stable button control, and production continues. This avoids parameter loss due to a broken network communication link, reduces equipment downtime for maintenance, and ensures efficient and continuous operation of the production process.

[0018] In conjunction with some embodiments of the first aspect, in some embodiments, after the step of acquiring the real-time operating data and real-time control data of the device, the method further includes: acquiring the acquisition environment characteristic data of a preset data acquisition device; calculating the confidence level of the real-time operating data based on the acquisition environment characteristic data; if the confidence level is lower than a preset threshold, correcting the real-time operating data according to a preset correction strategy based on the degree of influence of the acquisition environment on each operating parameter in the real-time operating data.

[0019] The above technical solution determines data confidence levels based on the environmental characteristics of the pre-defined data acquisition equipment, taking into account the impact of factors such as temperature, humidity, and electromagnetic interference generated during the normal operation of other production equipment in the factory on the accuracy of data acquisition and transmission. For data with confidence levels below a threshold, a pre-defined correction strategy is implemented based on the degree of influence of the acquisition environment on each operating parameter to eliminate environmental noise interference, improve the accuracy and reliability of the acquired operating data, avoid erroneous judgments caused by data deviations due to environmental factors, and ensure the stable and efficient operation of the production process.

[0020] In a second aspect, embodiments of this application provide a parameter adjustment server, including: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code including computer instructions, and the one or more processors call the computer instructions to cause the parameter adjustment server to perform the method described in the first aspect and any possible implementation thereof.

[0021] Thirdly, embodiments of this application provide a computer-readable storage medium including instructions that, when executed on a parameter adjustment server, cause the parameter adjustment server to perform the method described in the first aspect and any possible implementation thereof.

[0022] Fourthly, this application provides a computer program product that, when run on a parameter adjustment server, causes the parameter adjustment server to perform the method described in the first aspect and any possible implementation thereof.

[0023] Understandably, the parameter adjustment server provided in the second aspect, the storage medium provided in the third aspect, and the computer program product provided in the fourth aspect are all used to execute the method provided in this application. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: 1. This application generates a control parameter table for adjusting the equipment under normal conditions by using a preset timing model to adapt to the current abnormal situation, and makes adaptive modifications to the control parameter table so that the control data in the control parameter table is suitable for the current abnormal situation of the equipment. This makes the operating data of the equipment under abnormal conditions, which adjusts the control parameters according to the control data in the parameter table, closer to the requirements of normal production, and improves the product qualification rate when the equipment fails.

[0025] 2. This application determines the processing value and product value of the second product, which follows the first product in the production sequence, after the equipment completes the processing of the first product. When the processing value is greater than the product value, the product is not processed; the processing flow is terminated and the product is transferred in a timely manner. This avoids the equipment from continuously investing resources such as raw materials, energy, and manpower in ineffective processing under faulty or abnormal conditions, thereby reducing the waste of production resources and lowering production costs.

[0026] 3. This application determines whether the equipment is not faulty, but rather that the network communication link between the device sending and receiving the abnormal control parameter data is broken, by judging whether the rate of change of the abnormal parameter data is within a preset range of no change and whether there is control parameter data matching the abnormal parameter data in the historical control data. If the abnormality is detected to be caused by the network communication link being broken, the control mode of the equipment is switched to the more stable button control, and production continues, avoiding parameter loss caused by the network communication link being broken, reducing equipment downtime for maintenance, and ensuring the efficient and continuous operation of the production process. Attached Figure Description

[0027] Figure 1 This is a schematic diagram of a system architecture to which the control parameter adjustment method in the embodiments of this application can be applied; Figure 2 This is a flowchart illustrating a control parameter adjustment method in an embodiment of this application; Figure 3 This is another flowchart illustrating the control parameter adjustment method in this application embodiment; Figure 4 This is a schematic diagram of an exemplary hardware structure of the parameter adjustment server in this application embodiment. Detailed Implementation

[0028] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification and appended claims of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to any or all possible combinations including one or more of the listed items.

[0029] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0030] Figure 1 This is a schematic diagram of a system architecture to which the control parameter adjustment method in the embodiments of this application can be applied.

[0031] Please see Figure 1 The control parameter adjustment system includes sensors, equipment, and a parameter adjustment server.

[0032] The parameter control server, as the core component of the system, analyzes and processes the operational data collected by sensors and the control data transmitted by the equipment, and sends control parameter tables to the equipment. Sensors collect operational data during equipment operation and transmit the collected data to the parameter control server. The equipment receives the control parameter tables transmitted by the parameter control server and operates according to the control parameters in the tables.

[0033] Through the above system architecture, the control parameter adjustment system can determine the control parameter data that the equipment needs to adjust by collecting operating data from sensors, and send the control parameter data to the equipment so that the equipment can adjust the control parameters according to the control parameter data, thereby improving the equipment's operating efficiency and stability, and reducing production failures and product quality problems caused by improper parameters.

[0034] In related technologies, when a sudden malfunction is detected during normal equipment operation, the standard emergency response procedure usually involves immediately triggering a safety interlock protection mechanism to quickly stop the equipment and prevent the malfunction from escalating or causing a safety accident. However, in certain scenarios where the continuity of the processing is extremely important (such as heat treatment, chemical reactions, and precision coating), this emergency shutdown method can cause products being processed or in the process to be scrapped due to the sudden interruption of the process flow, thereby reducing the product qualification rate of that batch or time period.

[0035] The control parameter adjustment method in this application, after detecting an abnormality in the equipment, generates a control parameter table that adapts to the current abnormal situation and is used to adjust the equipment under normal conditions through a preset timing model, and makes adaptive modifications to the control parameter table so that the control data in the control parameter table is suitable for the current abnormal situation of the equipment. This makes the operating data of the equipment under abnormal conditions, which adjusts the control parameters according to the control data in the parameter table, more closely match the requirements of normal production and improves the product qualification rate when the equipment fails.

[0036] The following is combined Figure 2 The method of the embodiments of this application will be described below.

[0037] Please see Figure 2 This is a flowchart illustrating a control parameter adjustment method in an embodiment of this application.

[0038] S201. Obtain real-time operating data and real-time control data of the equipment.

[0039] Real-time operational data includes key indicators reflecting the current operating status of the equipment, such as its rotational speed, temperature, pressure, and vibration frequency. Real-time control data includes control information that directly affects the equipment's operational behavior, such as the setpoints of its control parameters.

[0040] Specifically, real-time operational data is acquired by communicating with various sensors installed on the equipment. These sensors include speed sensors, temperature sensors, pressure sensors, vibration frequency sensors, etc.

[0041] For real-time control data, a communication connection is first established with the equipment's control system, and then a request to obtain control data is sent to the equipment. Upon receiving the request, the equipment transmits the real-time control data to the server via the communication link.

[0042] In some embodiments, if the device has a control screen, image data of the control screen can be acquired by an image acquisition device, and then real-time control data in the image data can be identified by image recognition technology.

[0043] S202. Based on real-time control data and historical operating data, predict the predicted operating data of the equipment under normal operating conditions, according to the real-time control data.

[0044] Specifically, the server first retrieves historical operating data from a local database or cloud storage system for a preset time period prior to the start time of real-time control data processing. This historical operating data consists of real-world data accumulated over a long period of operation by the device under various control parameter settings, including historical records of the device's operation under different operating environments and combinations of control parameters.

[0045] Then, a pre-trained prediction model is obtained. This prediction model can be built based on algorithms such as Long Short-Term Memory (LSTM) networks, gradient boosting decision trees, and deep neural networks. During model training, the model is trained using a large amount of historical data, enabling it to learn the changing patterns and interrelationships of various operating parameters under different operating environments and control data. The historical data includes the equipment's operating data under different control parameter settings and environmental parameters (such as temperature, humidity, air pressure, and power grid fluctuations).

[0046] Historical operating data, along with their corresponding operating environment and control data, real-time operating environment data, and real-time control data, are input into the trained prediction model. The model first preprocesses the input data. After preprocessing, the model compares the control data corresponding to the last historical operating data in the time series with the real-time control data. If the control data matches the real-time control data, it indicates that the equipment control parameters have not changed. The model will then focus on the impact of environmental data changes on the equipment's operating state, directly predicting the operating data based on these environmental data changes and the learned patterns and interrelationships of various operating parameters under different operating environments.

[0047] If the control data is inconsistent with the real-time control data, it indicates that the equipment control parameters have changed. The model will further evaluate the impact of the control parameter changes on the equipment's operating status. Combining the characteristics of operating data under different control parameters in historical operating data, real-time operating environment data, and the interaction relationship between control parameters and operating parameters under different environments learned by the model, the model will predict the operating data through comprehensive analysis and calculation of these factors. Specifically, the model will look for similar control parameter changes and their corresponding operating data changes in historical operating data based on the magnitude and direction of the control parameter changes. At the same time, it will consider the differences between the current real-time operating environment data and historical environment data, and use the patterns learned by the model to adjust and weight these historical data to obtain the predicted operating data.

[0048] Predictive operating data is based on historical operating data, real-time environmental data, and real-time control data. It is the operating data that should be monitored by the equipment under normal conditions in the current real-time control data and operating environment, which is inferred by the predictive model after learning the changing patterns and mutual influence relationships of various operating parameters under different operating environments and control data.

[0049] S203. If the real-time operating data does not match the predicted operating data, input the real-time operating data into the preset time series model to obtain the control parameter table.

[0050] The control parameter table includes control data and adjustment time.

[0051] Specifically, the values ​​of each first operating parameter in the real-time operating data are compared with the corresponding values ​​of the second operating parameters in the predicted operating data to determine whether there is a difference between the values ​​of the first and second operating parameters that exceeds the preset error range corresponding to the operating parameters. If so (i.e., the real-time operating data and the predicted operating data do not match), it indicates that there is an abnormal operating part of the equipment. The mismatched parameters are recorded as abnormal operating parameters, and abnormal operating data of the abnormal operating parameters within a preset time period are obtained.

[0052] Then, preset prediction features are extracted from the abnormal operation data, including time-related features (such as the periodic information of hours, days, weeks, months, etc. corresponding to the timestamp), statistical features (such as the mean, variance, standard deviation, maximum value, and minimum value over a period of time), and trend features (the slope of the data is calculated by sliding window to determine the upward or downward trend of the data).

[0053] Next, based on the characteristics of the abnormal operating parameters and the data pattern, a suitable prediction model is selected. If the data shows a clear linear trend, a linear regression model can be used; for data with complex nonlinear relationships, recurrent neural network models such as Long Short-Term Memory (LSTM) or Gated Recurrent Unit (GRU) are employed. Taking the LSTM model as an example, the model is trained using a large amount of data containing historical data of abnormal operating parameters, timestamp information, and various derived features. The data trains the model, enabling it to learn the patterns of abnormal parameter changes over time, the correlations between different parameters, and the evolution trends under abnormal conditions.

[0054] The model inputs real-time abnormal operation data at the current time point to predict abnormal parameter data for each adjustment time within a preset time period after the current time point. Taking the LSTM model as an example, after the data is input into the model, the model first normalizes and transforms the input real-time abnormal operation data into a 3D tensor format. Then the data enters the LSTM cell unit. The forget gate calculates the degree of forgetting of historical cell states based on the current input and the hidden state of the previous time step using the sigmoid function; the input gate also uses the sigmoid function to evaluate the degree of acceptance of new information and uses the tanh function to generate candidate cell states, and the two work together to update the cell state. Next, the output gate determines the output selection degree based on the updated cell state, the current input, and the hidden state of the previous time step using the sigmoid function, multiplies it with the cell state processed by tanh, and outputs the hidden state of the current time step. After processing the input data step by step in this way, the hidden state of the last time step is taken and fed into the fully connected layer. After weighted summation and transformation by a linear activation function, the predicted value of the abnormal parameters for the first adjustment time is output. To obtain the predicted values ​​of subsequent adjustment times within a preset time period, a rolling prediction strategy is adopted. The previous prediction value is added to the time window and the earliest data is removed. The above calculation process is repeated until the prediction of the entire preset time period is completed.

[0055] Obtain the preset time series model. This time series model is built based on a Long Short-Term Memory (LSTM) network. During training, a large amount of data containing changes in device operating data under different control data and operating environment data is used, enabling the model to learn the changing patterns of device operating data under different control data and operating environment data.

[0056] Real-time operating data, abnormal parameter data for each adjustment time within a preset time period after the current time point, real-time control data, and operating environment data are input into a preset time series model to obtain a control parameter table and the equipment operating according to the control parameter table. After the data is input into the model, the model first predicts the normal operating data for each adjustment time based on the learned variation patterns of the equipment's operating data under different control data and operating environment data. Then, the abnormal operating parameter values ​​in the normal operating data for each adjustment time are replaced with the corresponding parameter values ​​in the abnormal parameter data to obtain the actual operating data for each adjustment time.

[0057] Next, for each adjustment period, the model applies different combinations of control data (generated under the premise that the equipment is operating normally) to the corresponding actual operating data, and predicts the changes in the operating state of the equipment under these control measures through an internal state transition mechanism. For example, if the control data involves the speed adjustment of the equipment, the model will simulate the changing trends of these parameters under different speed adjustments based on the learned relationship between the speed, control data, and operating environment (such as temperature, pressure, etc.).

[0058] The model then sets a series of evaluation metrics to measure the merits of different control strategies. These metrics include, but are not limited to, the speed at which the equipment's operating state approaches the ideal state represented by normal parameter data, the stability of equipment operation during adjustment, and the energy consumption of adjustment. For each simulated control strategy, the model calculates its score on each evaluation metric, and then sums these scores according to preset weights to obtain the comprehensive evaluation score of the control strategy.

[0059] Subsequently, based on the evaluation results, the model determines the optimal control data for each adjustment period. This control data takes into account factors such as the severity of the abnormal situation, the current state of the equipment, and the operating environment.

[0060] Finally, the model combines the control data for each determined adjustment time with the corresponding adjustment time to output a control parameter table. Simultaneously, the model records the adjusted operating data and actual operating data of the equipment after adjustment according to the control data for each adjustment time in these control parameter tables, and outputs this data.

[0061] S204. Obtain the abnormal parameter data corresponding to the abnormal operating parameters at each adjustment time.

[0062] Obtain the abnormal parameter data of the abnormal operating parameters predicted in step S203 at each adjustment time.

[0063] S205. When the abnormal parameter data is within the preset controllable data range, obtain the first operating data corresponding to the target adjustment time in the control parameter table.

[0064] The target adjustment time is any one of all adjustment times, and the first operating data is the operating data after the equipment has been adjusted according to the target adjustment parameter data corresponding to the target adjustment time.

[0065] Specifically, the parameter values ​​of each parameter in the abnormal parameter data are compared with the corresponding parameter value range in the preset controllable data range to determine whether any parameter values ​​exceed the parameter value range. If so, it indicates that the equipment abnormality is serious, and a stop operation command is sent to the equipment. If not (i.e., the abnormal parameter data is within the preset controllable data range), the adjustment operation data (i.e., the first operation data) corresponding to the target adjustment time obtained in step S203 is acquired.

[0066] S206. Replace the abnormal running parameter data in the first running data with the corresponding abnormal parameter data to obtain the second running data.

[0067] Obtain the abnormal parameter data corresponding to the target adjustment time, replace the parameter values ​​of the abnormal operating parameters in the first operating data with the corresponding parameter values ​​in the abnormal parameter data, and obtain the second operating data after replacing the parameter values.

[0068] S207. If the second operating data does not match the first operating data, modify the data of the control parameters in the target control data that are associated with the abnormal operating parameters to the corresponding data in the real-time control data, and adjust the control parameters in the target control data that are not associated with the abnormal operating parameters according to the preset parameter adjustment scheme to obtain the control data set.

[0069] Specifically, if the second operating data does not match the first operating data, a preset set of first control parameters associated with the abnormal operating parameters is first obtained, and the parameter values ​​of each first control parameter in the target control data are replaced with the corresponding parameter values ​​in the real-time control data.

[0070] Then, a set of preset second control parameters (i.e., the set of control parameters other than the first control parameters) unrelated to the abnormal operating parameters and a preset parameter adjustment scheme corresponding to the abnormal operating parameters are obtained. The parameter adjustment scheme includes multiple adjustment rule groups, each of which is divided according to different operating conditions of the equipment (such as high load, low load, startup phase, stable operation phase, etc.) and the severity of the abnormality (minor abnormality, moderate abnormality, severe abnormality).

[0071] Next, determine the current operating condition and severity of the anomaly of the equipment. This is done based on indicators such as speed and load from real-time operating data. For example, if the speed is at the rated speed and the load reaches a certain proportion, the equipment is considered to be operating under high load; if the speed is low and the load is small, it is considered to be operating under low load. Simultaneously, the severity of the anomaly is determined based on the number of abnormal operating parameters, the degree of deviation from the normal range, and the preset impact on equipment operation.

[0072] Next, adjustment rule groups matching the operating conditions and severity of the anomalies are selected from the preset parameter adjustment schemes. Each adjustment rule group contains specific adjustment rules for each control parameter in the second set of control parameters. These rules specify the direction of parameter adjustment (increase, decrease, or remain unchanged) and the adjustment range.

[0073] For each second control parameter, based on the preset safety parameter range corresponding to the operating condition and severity of the anomaly, and the parameter value relationship between the second control parameter and other control parameters, adjustments are made according to the rules in the selected adjustment rule group to obtain all possible adjusted control data sets. Initial adjustments are first made according to the rules in the selected adjustment rule group. Then, the adjusted second control parameter is substituted into the parameter value relationship rules to calculate the theoretical values ​​of other relevant second control parameters, and these theoretical values ​​are checked to see if they are within their corresponding preset safety parameter ranges. If a value exceeds the range, the adjustment of the current second control parameter is corrected by reducing the adjustment step size or changing the adjustment direction and recalculating until all relevant control parameters satisfy the safety parameter range and parameter value relationship rules. During this process, the server uses an exhaustive method, iterating and adjusting each second control parameter within its safety parameter range according to different adjustment step sizes and directions. For each adjustment combination, the above checking and correction process is repeated to obtain all adjusted control data sets that meet the conditions.

[0074] The safety parameter range is preset based on the equipment's design specifications, historical operating data, and safety standards to ensure that the equipment will not be damaged or experience safety accidents when operating within this range. The parameter value relationships are the rules set between the parameters; for example, one parameter must be greater than, less than, or equal to another parameter, and the difference between parameter values ​​must be within a preset range.

[0075] S208. Based on historical production data, determine the product qualification rate after the equipment is adjusted according to each control data in the control data set.

[0076] Specifically, first, the actual operating data output by the model in S203 before the target adjustment time is obtained, resulting in actual operating data sorted chronologically. Then, the actual operating data, its corresponding control data, a certain control data from the control data set, and real-time operating environment data are input into the prediction model in S202 to obtain the second adjustment operating data after the equipment is adjusted according to each control data in the control data set.

[0077] Then, historical production records matching the second adjustment operation data are filtered from the historical production database, and these production records are traversed. During the traversal, for each historical production record, the server extracts its product qualification identifier. If the product qualification identifier indicates that the product is qualified, the server increments the qualified product counter by 1 and the total number of records by 1. If the product qualification identifier indicates that the product is unqualified, the server obtains the production operation data of other processing equipment during the product's production process. If there is no abnormal data in the production operation data, and the product's production equipment includes this equipment, the total number of records is incremented by 1; if there is abnormal data, no operation is performed.

[0078] After iterating through all matching historical production records, the number of qualified products and the total number of matching historical production records are calculated. The product qualification rate is then calculated using the formula: "Product qualification rate = Number of qualified products / Total number of matching historical production records".

[0079] S209. Modify the target control data in the control parameter table according to the control data corresponding to the highest product qualification rate.

[0080] Specifically, the control data are sorted from highest to lowest product qualification rate. After sorting, the control data corresponding to the highest product qualification rate is obtained, and the target control data corresponding to the target settling time in the control parameter table is replaced with this control data.

[0081] S210, Send the control parameter table to the device.

[0082] A communication connection is established with the device, and a control parameter table is sent to the device. After receiving the control parameter table, the device searches for the control data corresponding to the adjustment time that matches the received time in the control parameter table, and adjusts the device's current control data to that control data.

[0083] In this embodiment, after detecting an anomaly in the equipment, a control parameter table adapted to the current abnormal situation and the normal adjustment of the equipment is generated using a preset timing model. The control parameter table is then adaptively modified to ensure that the control data in the table is suitable for the current abnormal situation. During the modification process, the parameter values ​​of control parameters associated with the abnormal operating parameters in the control data are changed to the corresponding parameter values ​​in the equipment's real-time control data. This ensures that the equipment operates according to the adjusted control data, without affecting the operating state of the abnormal module. This avoids exacerbating equipment failures or causing new problems due to improper control parameters, preventing the abnormal operating data of the abnormal module from being accurately predicted and affecting the accuracy of control data adjustments. Simultaneously, the parameter values ​​of control parameters unrelated to the abnormal operating parameters in the control data are adaptively corrected to obtain multiple control data sets. The product qualification rate after the equipment operates according to each control data set is calculated. The control data corresponding to the highest product qualification rate is selected to modify the control parameter table. This ensures that the operating data of the equipment under abnormal conditions, adjusted according to the control data in the parameter table, most closely matches the requirements of normal production, improving the product qualification rate during equipment failures.

[0084] The following is combined Figure 3 The methods of the embodiments of this application will be further explained below.

[0085] Please see Figure 3 This is another flowchart illustrating the control parameter adjustment method in this application.

[0086] S301. Obtain real-time operating data and real-time control data of the equipment.

[0087] Step S301 and Figure 2 Step S201 in the illustrated embodiment is similar and can be found in the description of step S201, which will not be repeated here.

[0088] S302. Obtain the environmental characteristic data of the preset data acquisition device.

[0089] Specifically, first obtain the target production equipment (including the equipment and other production equipment besides the equipment) that is currently engaged in production activities within the factory area where the equipment is located, as well as its corresponding production status (including the equipment's operating power, operating speed, equipment's working mode, etc.) and production duration.

[0090] Next, retrieve the pre-stored production environment impact tables for each production device. These tables are constructed based on extensive experimental data and historical production experience, recording the impact data of each production device on other production devices within a preset range under different production states and durations. Find the production environment impact data list in the production environment impact table corresponding to the target production device, matching the production state and duration. This list includes the cumulative impact values ​​of factors such as production temperature, production humidity, and electromagnetic interference on other production devices within different influence ranges around the device.

[0091] Next, based on the preset locations of the target production equipment and the equipment, the distances between the target production equipment and the equipment are calculated using a preset distance calculation formula. Based on the distances between the target production equipment and the list of production environment impact data for the target production equipment, production environment impact data in the list whose impact range matches the distance are then searched.

[0092] Finally, the production environment impact data of all target production equipment are summed to obtain the collection environment characteristic data of the preset data acquisition equipment configured for the equipment.

[0093] S303. Calculate the confidence level of the real-time running data based on the collected environmental characteristic data.

[0094] Specifically, the parameter score values ​​corresponding to each feature parameter in the collected environmental feature data are obtained from a preset score table corresponding to the current weather conditions (including temperature, humidity, etc.). Based on the preset weights of each feature parameter and the parameter score values, the confidence level of the real-time running data is obtained through weighted calculation.

[0095] S304. If the confidence level is lower than the preset threshold, the real-time operating data is corrected according to the preset correction strategy based on the degree of influence of the acquisition environment on each operating parameter in the real-time operating data.

[0096] Specifically, if the confidence level is lower than a preset threshold, it indicates that the acquisition environment has a significant impact on the accuracy of the sensor-acquired data. First, determine the degree of influence of each feature parameter in the acquisition environment's characteristic data on each operating parameter in the real-time operating data. Obtain a pre-stored table mapping the degree of influence of each feature parameter to that of each operating parameter. For each operating parameter, obtain the degree of influence value of each feature parameter corresponding to its value in the degree of influence mapping table, thus obtaining a table of the degree of influence of each operating parameter.

[0097] Then, based on the impact degree table of each operating parameter, data correction is performed according to a preset correction strategy. The preset correction strategy includes multiple correction modes; for characteristic parameters and combinations of operating parameters with significant impact, a more complex nonlinear correction model is adopted. First, characteristic parameters and impact degree values ​​exceeding the corresponding preset thresholds in the impact degree table of each operating parameter are selected, resulting in the target impact degree table for each operating parameter after filtering.

[0098] For each operational parameter value correction, if the target influence table has only one feature parameter, the basic correction function corresponding to that feature parameter type and operational parameter is first retrieved from a pre-built correction function library. This function is usually stored in the form of a mathematical formula. Then, the collected original operational parameter value and the influence value of that feature parameter are substituted into the function for calculation to obtain the corrected operational parameter value. If the target influence table has two or more feature parameters, a multivariate correction model is used to correct the operational parameter value. First, the server performs principal component analysis on these feature parameters, calculating the covariance matrix between each feature parameter to identify the main components affecting the operational parameter, reducing the dimensionality of multiple feature parameters and minimizing the interference of correlations between parameters. Next, based on the dimensionality-reduced comprehensive index, the corresponding multivariate nonlinear correction model is called. This model can be a model trained based on a neural network or a function constructed through multivariate regression analysis. Taking the neural network model as an example, before use, it needs to be trained using a large amount of historical operational data and corresponding corrected real value data so that the model can learn the complex nonlinear mapping relationship between feature parameters and operational parameters. The comprehensive index and original operating parameter values ​​are input into the trained model. The model then performs layer-by-layer calculations and processing on the input data according to the pre-learned mapping relationship. Data enters from the input layer, undergoes nonlinear transformations through multiple hidden layers, and each neuron performs a weighted summation of the input and processes it through an activation function to extract and transform feature information. Finally, the corrected operating parameter values ​​are obtained at the output layer.

[0099] S305. Based on real-time control data and historical operating data, predict the operating data of the equipment under normal operating conditions, according to the real-time control data.

[0100] Step S305 and Figure 2 Step S202 in the illustrated embodiment is similar and can be found in the description of step S202, which will not be repeated here.

[0101] S306. Determine the data transmission duration range between different devices based on real-time network status and historical data transmission data.

[0102] Specifically, the server first acquires real-time network status. By establishing communication connections with network devices (such as routers and switches), it periodically sends status query commands to these devices and receives real-time network status data returned by the devices, including parameters such as network bandwidth, latency, and packet loss rate. Simultaneously, the server also obtains local network connection status information, such as network interface speed and connection stability, from monitoring programs deployed on various device nodes.

[0103] Next, historical data transmission data is retrieved from the storage module. This historical data contains records of data transmission between different devices over a period of time. Each record details the initiation time, end time, amount of data transmitted, source device, and target device of the data transmission.

[0104] For a preset network transmission link, a first data set is found where the source and target devices in historical data transmission data match those of the preset network transmission link. Based on real-time network status, a second data set is found where the similarity of network status in the first data set is higher than a preset threshold. The similarity is calculated using methods such as Euclidean distance, Manhattan distance, or cosine similarity, based on parameters such as network bandwidth, latency, and packet loss rate in real-time network status and historical data. For each second data set, historical transmission data within a preset time period after the transmission initiation time of the second data set is obtained to form a third data set. The data transmission duration of each transmission data set in the third data set is calculated to obtain a transmission duration set. Statistical characteristic values ​​of the transmission duration set are calculated, including minimum, maximum, average, median, and standard deviation. Based on these statistical characteristic values, a data transmission duration range is determined. A preliminary transmission duration range is formed by using a first proportion of the minimum value (which can be adjusted according to actual network stability) as the lower limit and a second proportion of the maximum value as the upper limit. Simultaneously, the distribution pattern of transmission duration in historical data is analyzed. If significant long-tail effects or outliers are found, robust statistical methods, such as quantile-based truncation, are employed to remove extreme data that could affect the accuracy of the range, and the adjusted duration range is recalculated. Finally, the transmission duration ranges corresponding to different transmission data volume ranges are integrated to obtain the first data transmission duration range.

[0105] The preset network transmission link includes the source device and the target device, reflecting the network data transmission route between physical devices after the server receives the data collected by the sensor and transmits the data from the server to various components of the device.

[0106] For a preset physical transmission link, obtain the preset physical transmission duration range to obtain the second data transmission duration range.

[0107] Finally, add all the first data transmission duration ranges to all the second data transmission duration ranges to obtain the data transmission duration range.

[0108] S307. Determine the range of model calculation time based on the historical processing data of the time series model.

[0109] Specifically, the historical processing data of the time-series model is first retrieved from the storage device. This data includes information such as input data characteristics, processing task type, start time, end time, and computational resource usage (e.g., CPU utilization, memory usage) for each model run. Then, abnormal operating parameters and their corresponding abnormal deviation values ​​are obtained. The abnormal deviation value is obtained by subtracting the predicted abnormal parameter value from the actual collected abnormal parameter value. Next, a first set of processing data is obtained that matches the abnormal operating parameters and abnormal deviation values ​​in the input data characteristics of the historical processing data with the aforementioned abnormal operating parameters and their corresponding abnormal deviation values. Finally, based on the processing time of each processing data in the first set of processing data, statistical feature values ​​of the processing time set are extracted, and the model computation time range is determined according to a preset range determination rule.

[0110] S308. Determine the number of parameter adjustments based on abnormal operating parameters and preset parameter adjustment plans.

[0111] Specifically, obtain all possible adjusted control data sets, count the number of control data points in each set, and determine the number of parameter adjustments. For details on obtaining the control data sets, please refer to [link to relevant documentation]. Figure 2 The steps in S207.

[0112] S309. Add the product of the number of parameter adjustments and the preset duration range corresponding to each parameter adjustment to the preset base duration range to obtain the parameter adjustment duration range.

[0113] Multiply the number of parameter adjustments by the preset duration range corresponding to each parameter adjustment, and then add the product to the preset base duration range to obtain the parameter adjustment duration range.

[0114] S310. Add the data transmission duration range, the model calculation duration range, and the data adjustment duration range together to obtain the transmission duration range.

[0115] The transmission duration range is obtained by adding the model calculation duration range, the data adjustment duration range, and the maximum and minimum values ​​within the data adjustment duration range.

[0116] S311. Based on the transmission duration range, the set of adjustment times is calculated.

[0117] The adjustment time is the point in time or period during which the equipment begins to operate according to the control parameters.

[0118] Specifically, the current time point is added to each transmission duration within the transmission duration range to obtain the adjustment time period. The effective duration is adjusted according to preset parameters, and the adjustment time period is divided into multiple sub-adjustment time periods with the effective duration adjusted by parameters, resulting in an adjustment time set.

[0119] S312. Input the real-time operating data and adjustment time set into the preset timing model to obtain the control parameter table.

[0120] S313. Obtain the abnormal parameter data corresponding to the abnormal operating parameters at each adjustment time.

[0121] S314. When the abnormal parameter data is within the preset controllable data range, obtain the first operating data corresponding to the target adjustment time in the control parameter table.

[0122] S315. Replace the abnormal running parameter data in the first running data with the corresponding abnormal parameter data to obtain the second running data.

[0123] S316. If the second operating data does not match the first operating data, determine the control data set.

[0124] S317. Determine the product qualification rate after the equipment is adjusted according to each control data in the control data set.

[0125] S318. Modify the target control data in the control parameter table according to the control data corresponding to the highest product qualification rate.

[0126] S319. Send the control parameter table to the device.

[0127] Steps S312-S319 and Figure 2 Steps S203-S210 in the illustrated embodiment are similar and can be found in the descriptions of steps S203-S210, which will not be repeated here.

[0128] S320. After the first product is processed, obtain the production parameter data of the second product whose production sequence follows that of the first product.

[0129] The first product is the product that the equipment is currently processing.

[0130] Specifically, the system acquires equipment operating data in real time. If the operating data matches the preset data for when processing is complete, the system determines that the first product being processed has been completed. After the first product is completed, the system retrieves the production parameter data for the second product, which follows the first product in the pre-stored product production table. The production parameter data records the operating data of the production equipment corresponding to various processing steps the product has undergone from the start of production to the current time, and is dynamically updated as the product production process progresses.

[0131] S321. Determine the non-conformity of the second product.

[0132] Based on the product qualification rate corresponding to the production parameter data and the current control data of the equipment, the non-conformity of the second product is determined.

[0133] Specifically, the normal production data range of the production equipment corresponding to each processing step the second product has undergone from the start of production to the current time is obtained. The production data of each production equipment in the production parameter data is compared with the corresponding normal production data to determine whether there are any abnormal operating parameters whose values ​​exceed the corresponding normal parameter range.

[0134] If so, obtain the abnormal operating parameters of the production equipment and the abnormal differences between the abnormal parameter values ​​and the normal parameter values. Find the first non-conformity case in the preset non-conformity table corresponding to the production equipment, where the abnormal parameters and ranges match the aforementioned abnormal parameters and values. This includes the impact values ​​on product function, product appearance, product lifespan, and safety performance. Simultaneously, obtain the current operating data corresponding to the current control data of the equipment (which can be collected in real-time by sensors or pre-calculated adjusted operating data after the equipment has been adjusted according to the current control data) and its corresponding product pass rate. Compare the current operating data with the corresponding normal operating data range to determine the abnormal parameters and the abnormal differences between the abnormal parameter values ​​and the normal parameter values. Obtain the second non-conformity case in the preset non-conformity table corresponding to the equipment, where the abnormal parameters and ranges match the aforementioned abnormal parameters and values. Multiply the impact values ​​of each influencing parameter in the second non-conformity case by the product non-conformity rate to obtain the third non-conformity case. Here, the product non-conformity rate = 1 - product pass rate. Finally, integrate the first and third non-conformity cases to obtain the second product non-conformity case.

[0135] If not, the third non-conformity in the above steps shall be regarded as a non-conformity of the second product.

[0136] S322. Based on the nonconformity, determine the extent to which the nonconformity affects the use of the second product.

[0137] Based on the weights of each influencing parameter preset in the non-conformance situation and the corresponding influence degree value of each influencing parameter, the influence degree value of the non-conformance situation on the use of the second product is obtained by weighted calculation.

[0138] S323. Based on the degree of impact and the pre-defined product loss value correspondence table, determine the total loss value of the second product.

[0139] Obtain the total loss value that matches the impact range in the preset product loss value correspondence table with the impact value of the second product's use.

[0140] S324. Calculate the product value of the second product.

[0141] The product value of the second product is obtained by subtracting the total loss value from the preset total product value.

[0142] S325. Obtain the consumption value corresponding to the current control data.

[0143] Obtain the consumption value that matches the current operating data and current time point corresponding to the current control data in the preset consumption value table of the equipment, based on the operating data range and operating time range.

[0144] S326. Calculate the processing value of the second product.

[0145] The processing value of the second product is obtained by adding the consumption value to the product cost value of the second product in the preset cost correspondence table.

[0146] Specifically, obtain the product cost value of the second product from the preset cost mapping table. This cost mapping table records the total consumption value of all production equipment corresponding to various processing steps performed by each product from the start of production to the current time point, and is dynamically updated as the product production process progresses. Adding the consumption value to the product cost value yields the processing value of the second product.

[0147] S327. When the processing value exceeds the product value, send a stop processing command to the equipment.

[0148] When the processing value exceeds the product value, a stop processing command is sent to the equipment, and the preset transport device is controlled to transport the second product to the preset area.

[0149] Specifically, when the processing value is greater than the product value, it is determined whether the product can be disassembled into raw materials for reprocessing based on the product type.

[0150] If the product can be disassembled into raw materials for remanufacturing, calculate the remanufacturing value. Obtain the product disassembly cost corresponding to the previous processing flow for the equipment. Subtract the sum of the product disassembly cost and the preset total production cost from the preset total product value to obtain the remanufacturing value. If the remanufacturing value is greater than or equal to a preset threshold, send a stop processing command to the equipment and a control command to the preset transport device. After receiving the control command, the preset transport device transports the second product to the remanufacturing area according to the preset transport route.

[0151] If the value of the product after reprocessing is less than a preset threshold or the product cannot be disassembled into raw materials for reprocessing, the preset recycling value corresponding to the previous processing step of the processing flow corresponding to the equipment and the total consumption value corresponding to the remaining processing steps are obtained. If the difference between the product value and the total consumption value is greater than the recycling value, the equipment is controlled to process the second product. If the difference between the product value and the total consumption value is less than or equal to the recycling value, a stop processing command is sent to the equipment, and a control command is sent to the preset transport device. After receiving the control command, the preset transport device transports the second product to the recycling area according to the preset transport route.

[0152] S328. After the current batch of products is produced, if the rate of change of abnormal parameter data is within the preset range of no change, obtain the historical control data of the equipment.

[0153] Specifically, the system retrieves the set of products whose processing flow in the product production table reaches the preset production equipment. It then filters out the target product with the latest production sequence from the product set. Once the equipment has finished producing the target product (i.e., the current batch of products has finished production), it first retrieves the abnormal parameter data of abnormal operating parameters collected by sensors within a preset time period prior to the current time point. Then, it calculates the rate of change of the abnormal parameter data. For each abnormal operating parameter, the data is arranged according to a time series, and a difference calculation method is used to subtract the parameter values ​​at adjacent time points and then divide by the time interval to obtain the change in value per unit time between adjacent time points, thus obtaining the rate of change. The server then compares the calculated rate of change per unit time between each adjacent time point with a preset range of no change to determine whether all rates of change fall within the preset range.

[0154] If so, it means that the equipment operating part corresponding to the abnormal operating parameters may not have a fault. Obtain the historical control data of the equipment within the pre-stored preset time range (the preset time period before the abnormal time point where the abnormal operating parameters are detected). The historical control data includes each control time point and its corresponding control data, operating data, and operating environment, etc.

[0155] S329. Determine whether there is control parameter data in the historical control data that matches the abnormal parameter data.

[0156] If yes, proceed with step S330; otherwise, proceed with step S333.

[0157] Specifically, the historical parameter values ​​of each first control parameter in the preset first control parameter set associated with abnormal operating parameters are extracted from the historical control data. Simultaneously, the abnormal control parameter values ​​of each first control parameter corresponding to the abnormal time point are obtained.

[0158] The historical parameter values ​​of each first control parameter are iterated sequentially from latest to earliest. The historical parameter value of each first control parameter at each time point is compared with the corresponding abnormal control parameter value. If the historical parameter value of a first control parameter at any time point exceeds a preset error range compared to the abnormal control parameter value, the historical parameter value of the first control parameter at that time point is obtained, thus obtaining the target control parameter value. The parameter values ​​of the first control parameters in the control data of all time points after that time point in the historical control data are replaced with the corresponding target control parameter values ​​to obtain new historical control data.

[0159] The new historical control data, real-time operating environment data, and real-time control data are input into the prediction model trained in S202 to obtain new predicted operating data. If the new predicted operating data matches the real-time operating data, it is determined that there is control parameter data in the historical control data that matches the abnormal parameter data. If they do not match, the above traversal operation steps are continued to determine whether there is control parameter data that matches the abnormal parameter data at an earlier time point. If, after the traversal is completed, there is still no control parameter data that matches the abnormal parameter data, it is determined that there is no control parameter data that matches the abnormal parameter data in the historical control data.

[0160] S330, control the preset intelligent robot to press the device's reset button.

[0161] Send a preset control command to the preset intelligent robot. After receiving the command, the intelligent robot controls the built-in robotic arm located above the reset button to move in a direction perpendicular to the button, thus pressing the device's reset button.

[0162] When the reset button is pressed, an electrical signal changes in the physical circuit connected to it. This signal change is transmitted along the physical circuit to the control circuit board inside the device. The microcontroller (such as a single-chip microcomputer) on the control circuit board monitors the electrical signal status of this circuit in real time. Once a signal change that meets a preset reset trigger condition (e.g., a change from low to high or from high to low) is detected, the microcontroller immediately responds and initializes the various systems and modules of the device according to the reset program pre-stored in the device's internal memory (such as flash memory).

[0163] S331. After the device is reset, obtain the third operating data of the device.

[0164] After receiving feedback from the intelligent robot (i.e., the device has been reset), the third operational data of the device collected by the sensors is acquired.

[0165] S332. If the third operating data matches the preset operating data, switch the device to adjust the control parameters and the control mode to the preset button control.

[0166] Among them, button control is a method of adjusting control parameters through preset physical circuits.

[0167] Specifically, the third operating data is compared with the preset reset operating data. If the third operating data matches the preset operating data, the cause of the abnormal parameter is determined to be a disconnection of the network data transmission link, and the device's control parameter adjustment method is switched to the preset button control. The common control method for this device is to transmit control commands to the controllers of the corresponding modules via a network link to control the operation of each module. When the network link between the controller and the device transmitting control commands is disconnected, the device control parameters can be adjusted through a preset physical line control method.

[0168] When the equipment is controlled by buttons, production and processing can continue. When adjusting the control parameters of the equipment, the robotic arms above different buttons can be controlled to press the buttons.

[0169] S333: Send maintenance tasks to preset maintenance personnel.

[0170] Based on the abnormal operating parameters of the equipment, the equipment's own information, and historical operating data, maintenance tasks are generated and sent to the mobile terminals of preset maintenance personnel through the built-in communication module.

[0171] In this embodiment, when real-time operating data does not match predicted operating data, the transmission duration range is determined based on abnormal operating parameters, real-time network status, and historical data transmission. This fully considers various influencing factors during data transmission, avoiding delays that could prevent control parameters from taking effect in a timely manner. This ensures the equipment can be adjusted at the appropriate time based on accurate control parameters, reducing adjustment deviations caused by unreasonable time planning or data transmission lag. This improves the timeliness and accuracy of equipment fault adjustment and increases the product qualification rate during equipment failures. During production by abnormal equipment, if the processing value exceeds the product value, the product is not processed; the processing flow is terminated and the product is transferred. This avoids the equipment continuously investing raw materials, energy, and manpower in ineffective processing under faulty or abnormal conditions, reducing waste of production resources and lowering production costs. Simultaneously, by judging whether the rate of change of abnormal parameter data is within a preset range of no change, and whether there is matching control parameter data in the historical control data, it is determined whether the equipment is not faulty, but rather that the network communication link between the device sending and receiving abnormal control parameter data is broken. If the anomaly is detected as being caused by a network communication link disconnection, the control method of the equipment will be switched to a more stable button control, and production will continue. This will prevent parameter loss due to the network communication link disconnection, reduce equipment downtime for maintenance, and ensure the efficient and continuous operation of the production process.

[0172] The control parameter adjustment method in the embodiments of this application has been described above. The parameter adjustment server in the embodiments of this application will be described in detail below in conjunction with the above control parameter adjustment method.

[0173] Please see Figure 4 This is a schematic diagram of an exemplary hardware structure of the parameter adjustment server in this application embodiment.

[0174] In some embodiments, the parameter adjustment server 400 includes a computer device, which may be a terminal device. The computer device includes a processor 401, a memory 402, a communication module 403, an input device 404, and an output device 405 connected via a system bus. The processor 401 provides computing and control capabilities. The memory 402 includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores data. The communication module 403 transmits operating data, control data, and image data to the server and sends control parameter tables to the device. The input device 404 receives collected operating data, control data, and image data. The output device 405 displays device operating data and control data. When the computer program is executed by the processor 401, it implements the control parameter adjustment method described in this embodiment.

[0175] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0176] In some embodiments of this application, a computer-readable storage medium is provided, including instructions that, when executed on the parameter adjustment server 400, cause the parameter adjustment server 400 to perform the control parameter adjustment method of the embodiments of this application.

[0177] In some embodiments of this application, a computer program product is also provided, which, when running on a parameter adjustment server 400, causes the parameter adjustment server 400 to execute the control parameter adjustment method in the embodiments of this application.

[0178] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

[0179] As used in the above embodiments, depending on the context, the term "when..." can be interpreted as meaning "if...", "after...", "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if (the stated condition or event) is interpreted as meaning "if determining...", "in response to determining...", "when (the stated condition or event) is detected", or "in response to detecting (the stated condition or event)".

[0180] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive), etc.

[0181] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for adjusting control parameters, characterized in that, include: Acquire real-time operating data and real-time control data of the equipment; Based on the real-time control data and historical operating data, predict the predicted operating data of the device under normal operating conditions, according to the real-time control data. If the real-time operating data does not match the predicted operating data, the real-time operating data is input into a preset time series model to obtain a control parameter table, which includes control data and adjustment time. Obtain abnormal parameter data corresponding to abnormal operating parameters at each adjustment time, wherein the abnormal operating parameters are parameters whose operating parameter values ​​do not match those in the real-time operating data and the current operating data; When the abnormal parameter data is within the preset controllable data range, the first operating data corresponding to the target adjustment time in the control parameter table is obtained. The target adjustment time is any one of all adjustment times. The first operating data is the operating data after the device is adjusted according to the target adjustment parameter data corresponding to the target adjustment time. Replace the abnormal operating parameter data in the first operating data with the corresponding abnormal parameter data to obtain the second operating data; If the second operating data does not match the first operating data, the data of the control parameters associated with the abnormal operating parameters in the target control data are modified to the corresponding data in the real-time control data, and the control parameters in the target control data that are not associated with the abnormal operating parameters are adjusted according to the preset parameter adjustment scheme to obtain a control data set; Based on historical production data, determine the product qualification rate after the equipment is adjusted according to each control data in the control data set; Modify the target control data in the control parameter table according to the control data corresponding to the highest product qualification rate; The control parameter table is sent to the device.

2. The method according to claim 1, characterized in that, If the real-time operating data does not match the predicted operating data, the real-time operating data is input into a preset time series model to obtain a control parameter table, specifically including: If the real-time operating data does not match the predicted operating data, the transmission duration range from the current time point to the time point when the device starts operating according to the control parameters is determined based on abnormal operating parameters, real-time network status and historical data transmission data. Based on the transmission duration range, an adjustment time set is calculated, where the adjustment time is the time when the device starts operating according to the control parameters; The real-time operating data and the set of adjustment times are input into a preset time series model to obtain a control parameter table.

3. The method according to claim 2, characterized in that, If the real-time operating data does not match the predicted operating data, based on abnormal operating parameters, real-time network status, and historical data transmission data, the transmission duration range from the current time point to the time point when the device begins to operate according to the control parameters is determined, specifically including: Based on real-time network status and historical data transmission data, determine the data transmission duration range between different devices; The calculation time range of the model is determined based on the historical processing data of the time series model; The number of parameter adjustments is determined based on abnormal operating parameters and preset parameter adjustment plans; Add the product of the number of parameter adjustments and the preset duration range corresponding to each parameter adjustment to the preset base duration range to obtain the parameter adjustment duration range; The transmission duration range is obtained by adding the data transmission duration range, the model calculation duration range, and the data adjustment duration range together.

4. The method according to claim 1, characterized in that, After the step of sending the control parameter table to the device, the method further includes: After the first product is processed, the production parameter data of the second product, which is produced after the first product, is obtained. The first product is the product being processed by the equipment. Based on the product pass rate corresponding to the production parameter data and the current control data of the equipment, determine the non-conformity of the second product; Based on the non-conformance situation, the current control data, and the preset cost correspondence table of the second product, determine the processing value and product value of the second product; When the processing value exceeds the product value, a stop processing command is sent to the equipment, and a preset transport device is controlled to transport the second product to a preset area.

5. The method according to claim 4, characterized in that, The determination of the processing value and product value of the second product based on the non-conformance situation, the current control data, and the preset cost correspondence table of the second product specifically includes: Based on the aforementioned non-compliance, determine the extent to which the non-compliance affects the use of the second product; Based on the degree of impact and the preset product loss value correspondence table, the total loss value of the second product is determined; The product value of the second product is calculated based on the preset total product value and the total loss value. Obtain the consumption value corresponding to the current control data; The processing value of the second product is obtained by adding the consumption value to the product cost value of the second product in the preset cost correspondence table.

6. The method according to claim 1, characterized in that, After the step of sending the control parameter table to the device, the method further includes: After the current batch of products is produced, if the rate of change of the abnormal parameter data is within a preset range of no change, the historical control data of the equipment is obtained. Determine whether there is control parameter data in the historical control data that matches the abnormal parameter data; If so, control the preset intelligent robot to press the reset button on the device; After the device is reset, the third operating data of the device is acquired; If the third operating data matches the preset operating data, the cause of the abnormal parameter is determined to be a disconnection of the network data transmission link, and the device is switched to the preset button control mode for adjusting control parameters. The button control mode is a method of adjusting control parameters through a preset physical line.

7. The method according to claim 1, characterized in that, After the step of acquiring the device's real-time operating data and real-time control data, the method further includes: Acquire environmental characteristic data from the preset data acquisition device; Calculate the confidence level of the real-time operating data based on the collected environmental characteristic data; If the confidence level is lower than a preset threshold, the real-time operating data is corrected according to a preset correction strategy based on the degree of influence of the acquisition environment on each operating parameter in the real-time operating data.

8. A parameter adjustment server, characterized in that, include: One or more processors and memory; The memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code including computer instructions, the one or more processors invoking the computer instructions to cause the parameter adjustment server to perform the method as described in any one of claims 1-7.

9. A computer-readable storage medium storing computer instructions, characterized in that, When the computer instructions are executed on the parameter adjustment server, the parameter adjustment server performs the method as described in any one of claims 1-7.

10. A computer program product, characterized in that, When the computer program product is run on the parameter adjustment server, the parameter adjustment server performs the method as described in any one of claims 1-7.

Images