Equipment parameter collaborative control system and control method

Abstract

The present invention discloses a device parameter collaborative control system and control method, belonging to the field of device parameter collaborative control technology, which includes: performing sudden disturbance monitoring by performing multi-level comparative analysis on the degree of deviation between real-time production parameters and initial production parameter values; when a sudden disturbance is detected in a target device, reverse reasoning is performed to locate the abnormal device operating parameters that cause the abnormal disturbance, generate control instructions for the abnormal device operating parameters, and dynamically update the control instructions for the abnormal device operating parameters based on the abnormal production parameter values; after completing the production task, perform quality inspection on the product; if the product quality inspection fails, issue a product quality warning and generate a product quality production report. This solves the problem that the target device relies on preset process parameters in production, lacks real-time dynamic compensation capabilities in the face of sudden disturbances in the production process, and thus affects production quality.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment parameter collaborative control, and more specifically to an equipment parameter collaborative control system and control method. Background Art

[0002] In modern industrial production, traditional production equipment mostly relies on preset process parameters for production during operation. However, the actual production environment is complex and changeable, and there are many uncontrollable factors. For example, during the production process, sudden disturbances such as fluctuations in the composition of raw materials, wear and aging of equipment components, and changes in ambient temperature and humidity often occur. When these situations occur, existing production equipment lacks real-time dynamic compensation capabilities and cannot adjust operating parameters in time to adapt to these changes. As a result, quality problems such as uneven internal structure, inconsistent density, and dimensional accuracy deviation are prone to occur during the production process. At the same time, due to the inability to flexibly adjust according to actual production conditions, production efficiency is also greatly limited, and the scrap rate remains high. Therefore, in order to overcome these limitations, the present invention proposes a collaborative control system and control method for equipment parameters. Summary of the Invention

[0003] In response to the shortcomings of the existing technology, the purpose of the present invention is to provide an equipment parameter collaborative control system and control method, which solves the problem that production equipment relies on preset process parameters in production, lacks real-time dynamic compensation capabilities in the face of sudden disturbances in the production process, and affects production quality.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A collaborative control system for equipment parameters, including a parameter acquisition module, an analysis and decision module, an equipment control module, and a quality detection module;

[0006] The parameter acquisition module is used to determine the initial production parameter value based on the production task of the target device, and to collect the real-time production parameter value during the target device's execution of the production task. By performing multi-level comparative analysis on the real-time production parameter and its deviation degree, sudden disturbance monitoring is performed to determine whether the target device has a sudden disturbance;

[0007] The analysis and decision module is used to construct a parameter anomaly propagation path map to locate abnormal production parameters based on Bayesian theorem when a sudden disturbance is detected in the target equipment. Based on the abnormal production parameters, reverse reasoning is performed to locate the abnormal equipment operating parameters that are the cause of the sudden disturbance.

[0008] The equipment control module is used to sequentially generate control instructions for the abnormal equipment operating parameters according to the arrangement order of the abnormal equipment operating parameters, and dynamically update the control instructions for the abnormal equipment operating parameters based on the real-time deviation degree of the abnormal production parameter values;

[0009] The quality inspection module is used to collect quality parameter values ​​and perform quality inspection on the product after the target equipment completes the production task. According to the product quality inspection results, it determines whether to issue a product quality warning and generate a product quality production report.

[0010] Specifically, the specific steps of sudden disturbance monitoring include:

[0011] For each production parameter, the variance of historical production parameters under the same production task is extracted from the historical production task database. Combined with its initial production parameter value, the production parameter threshold is set, including the upper threshold and the lower threshold of the production parameter.

[0012] Based on the production parameter threshold, the collected real-time production parameter values ​​are judged for potential disturbances, and each real-time production parameter value is compared with the corresponding production parameter threshold in real time;

[0013] If the real-time production parameter value is greater than the upper threshold value of the production parameter or less than the lower threshold value of the production parameter, the real-time production parameter is marked as an abnormal production parameter, the real-time production parameter value is marked as an abnormal production parameter value, and the time when the abnormal production parameter value occurs is recorded; otherwise, no processing is performed;

[0014] Configure the deviation degree threshold, and calculate the ratio of the absolute value of the difference between the abnormal production parameter value and the initial production parameter value to the initial production parameter value as the deviation degree of the abnormal production parameter value. If the deviation degree of the abnormal production parameter value is greater than the deviation degree threshold, a sensor abnormality warning is issued, otherwise abnormal monitoring is started for the real-time production parameters marked as abnormal production parameters.

[0015] Specifically, the specific steps of abnormal monitoring include:

[0016] Configure an abnormality duration threshold to obtain the abnormal duration of production parameters marked as abnormal production parameters. If the abnormal duration is greater than the abnormality duration threshold, use the time series fitting algorithm to fit and predict the production parameter value marked as abnormal production parameter to obtain the predicted value of the production parameter within the abnormality duration threshold in the future.

[0017] Configure the mutation threshold, compare the production parameter prediction value with the corresponding production parameter threshold in real time, and count the number of production parameter prediction values ​​marked as abnormal production parameter values. If the number is greater than the mutation threshold, it is determined that there is a sudden disturbance. Otherwise, continue to monitor the real-time production parameters marked as abnormal production parameters for abnormalities.

[0018] Specifically, the steps for obtaining the predicted value of the production parameter within the future abnormality persistence threshold include:

[0019] Obtain the production parameter values ​​marked as abnormal production parameters from the start time of the production task of the target device to the current time, and arrange them in chronological order to construct an abnormal prediction set;

[0020] After data preprocessing, the anomaly prediction set is divided into a training set and a test set. A time series fitting algorithm is selected to build an anomaly prediction model. The anomaly prediction model is fitted using the training set and the test set.

[0021] According to the abnormality duration threshold, the production parameter prediction value within the future abnormality duration threshold time period is predicted through the fitted abnormality prediction model.

[0022] Specifically, the steps for constructing a parameter anomaly propagation path map include:

[0023] According to the production task type, the historical production task data of the target equipment is filtered from the historical production task database to construct an anomaly propagation dataset. The variables in the anomaly propagation dataset include historical production parameter variables and historical equipment operation parameter variables.

[0024] Perform data cleaning on the anomaly propagation dataset to remove noise data, duplicate data, and erroneous data; and align the timestamps of the anomaly propagation dataset based on the collection time of each variable value in the anomaly propagation dataset;

[0025] Initially set the preliminary causal relationship between each historical production parameter variable and each historical equipment operation parameter variable in the abnormal propagation data set. Based on the Granger causality test, by comparing the temporal sequence and correlation of different variables in the abnormal propagation data set, calculate the causal relationship strength and significance level between each parameter, set the significance level threshold, and screen the causal relationship parameter pairs with a significance level greater than the significance level threshold;

[0026] The abnormality of each production parameter is defined as an abnormal event. The frequency of each production parameter being marked as an abnormal production parameter is counted based on the abnormal propagation dataset, which is used as the prior probability of the production parameter being abnormal.

[0027] For parameter pairs with causal relationships, according to Bayes' theorem, by calculating the prior probability of each parameter pair with causal relationships, the conditional probability that one parameter is abnormal is calculated under the condition that the other parameter is abnormal.

[0028] Specifically, the specific steps of constructing the parameter anomaly propagation path map also include:

[0029] A parameter anomaly propagation path graph framework is constructed, with each production parameter as a node in the graph. Each node represents the abnormal state of a specific production parameter. Edges are added to connect parameter pairs with causal relationships. The direction of the edge represents the direction of the causal relationship, from the cause node to the result node. The conditional probability of the parameter pair with causal relationship is used as the weight of the edge.

[0030] Specifically, the specific steps of locating the abnormal equipment operating parameters that cause the abnormal cause of the sudden disturbance include:

[0031] The node of the parameter anomaly propagation path graph corresponding to the abnormal production parameter of the target device is used as the starting node;

[0032] Starting from the starting node, trace back along the edges in the parameter anomaly propagation path graph, and calculate the posterior probability of each cause node causing the starting node anomaly based on the edge weights;

[0033] Configure a probability threshold and, based on the calculated posterior probability, select the cause nodes whose posterior probability is greater than the probability threshold as potential anomaly causes.

[0034] The operating parameters of the abnormal equipment are determined according to the potential abnormal causes, and the operating parameters of the abnormal equipment are sorted in descending order according to the posterior probability of the potential abnormal causes.

[0035] Specifically, the steps of generating a control instruction for abnormal equipment operating parameters include:

[0036] Obtain the order of abnormal production parameters and generate control instructions for abnormal equipment operating parameters based on the order of arrangement, namely:

[0037] Filter the extreme values ​​of historical equipment operating parameters of the current production task from the historical production task database according to the production task type, so as to set the operating standard range of abnormal equipment operating parameters;

[0038] Determine the preliminary control direction based on the deviation direction of the abnormal production parameter value and the initial production parameter value, including: if the abnormal production parameter value is greater than the initial production parameter value, then reduce the abnormal equipment operating parameter value; if the abnormal production parameter value is less than the initial production parameter value, then increase the abnormal equipment operating parameter value;

[0039] A basic step length is set for each equipment operating parameter, and the deviation degree of abnormal production parameter values ​​is divided into segments. Each deviation degree is matched with a mapping coefficient. A segmented mapping function is used to determine the mapping coefficient based on the deviation degree between the current abnormal production parameter value and the initial production parameter value to control the step length.

[0040] Obtain the abnormal device operating parameter value of the current target device, and generate a control instruction sequence based on the operating standard range, preliminary control direction and step length after control of the abnormal device operating parameter.

[0041] Specifically, the specific steps of dynamically updating the control instructions of the abnormal equipment operating parameters include:

[0042] According to the arrangement order of the abnormal equipment operating parameters, the control instruction sequence of the abnormal equipment operating parameters is executed in sequence;

[0043] Configure a stop threshold. For any control instruction sequence of abnormal equipment operating parameters, monitor the deviation degree of the abnormal production parameter after executing each control instruction in the control instruction sequence. If the deviation degree of the abnormal production parameter is greater than the stop threshold, determine whether the deviation degree has been alleviated.

[0044] When the deviation degree of the abnormal production parameter decreases or remains unchanged, it is determined that the deviation degree has been alleviated, otherwise it is determined that it has not been alleviated. If the deviation degree has been alleviated, the next control instruction in the control instruction sequence will continue to be executed until the control instruction sequence of the current abnormal equipment operating parameter is completed;

[0045] If the degree of deviation is not alleviated, the current control instruction is marked as a control instruction abnormal point, and the next control instruction in the control instruction sequence is continued to be executed to monitor the control instructions, configure the abnormal point threshold, and count the number of control instruction abnormal points. If it is greater than the abnormal point threshold, the control direction is updated to the opposite direction of the initial control direction. Combined with the current abnormal equipment operating parameter value, according to the operating standard range of the abnormal equipment operating parameter and the step length after control, an updated control instruction sequence is obtained, and the updated control instruction sequence is monitored for abnormalities; otherwise, the next control instruction in the control instruction sequence is continued to be executed until the control instruction sequence of the current abnormal equipment operating parameter is completed;

[0046] If the deviation degree of the abnormal production parameters is less than or equal to the stop threshold, the equipment operation parameter control is stopped.

[0047] Specifically, the specific steps of monitoring the update control instruction sequence for abnormalities include:

[0048] After executing the control instruction of the update control instruction sequence, obtain the deviation degree of the abnormal production parameter. If the deviation degree is alleviated, continue to execute the next control instruction of the update control instruction sequence until the update control instruction sequence of the current abnormal production parameter is completed.

[0049] If the degree of deviation is not alleviated, the abnormal point of the updated control instruction is marked, and the updated control instruction is monitored. The number of abnormal points of the updated control instruction is counted. If it is greater than the abnormal point threshold, the control is stopped and an abnormal control warning is issued. Otherwise, the next control instruction in the updated control instruction sequence is continued to be executed until the updated control instruction sequence of the current abnormal production parameter is completed.

[0050] When all control instruction sequences for executing abnormal equipment operating parameters are completed, if the deviation degree of the abnormal production parameters is greater than the stop threshold, a control abnormality warning will be issued.

[0051] A method for collaboratively controlling device parameters comprises the following steps:

[0052] Step S1: Determine initial production parameter values ​​based on the production task of the target device, and collect real-time production parameter values ​​while the target device is executing the production task. Perform a multi-level comparative analysis of the real-time production parameters and their deviations to monitor sudden disturbances and determine whether the target device has sudden disturbances.

[0053] Step S2: When a sudden disturbance is detected in the target equipment, a parameter anomaly propagation path map is constructed using Bayesian theorem to locate the abnormal production parameters. Based on the abnormal production parameters, reverse reasoning is performed to locate the abnormal equipment operating parameters that are the cause of the sudden disturbance.

[0054] Step S3: Generate control instructions for the abnormal equipment operating parameters in sequence according to the order of arrangement of the abnormal equipment operating parameters that cause the sudden disturbance, and dynamically update the control instructions for the abnormal equipment operating parameters based on the real-time deviation of the abnormal production parameter values;

[0055] Step S4: After the target equipment completes the production task, the quality parameter values ​​are collected and the product quality is tested. If the product quality test fails, a product quality warning is issued and a product quality production report is generated.

[0056] Beneficial effects of the present invention:

[0057] The equipment parameter collaborative control system and control method effectively addresses the issue of production equipment relying on preset process parameters and lacking the ability to compensate for sudden disturbances in real time, thus impacting production quality. The parameter acquisition module uses multi-level comparative analysis of real-time production parameters to accurately monitor sudden disturbances and promptly detect anomalies in the production process. The analysis and decision-making module uses Bayesian theorem to construct graph-based reverse reasoning to quickly locate abnormal equipment operating parameters that cause sudden disturbances. The equipment control module generates and dynamically updates control instructions based on these parameters, achieving real-time dynamic compensation for sudden disturbances and effectively reducing their impact on production. After production is completed, the quality inspection module comprehensively inspects product quality, issues warnings for substandard products, and generates reports based on multi-module data. This provides strong data support for optimizing initial production parameter settings, adjusting production parameter thresholds, and improving the overall production process in subsequent production, thereby comprehensively improving product quality and production efficiency and ensuring production stability and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 Flowchart of specific steps for sudden disturbance monitoring of the present invention;

[0059] Figure 2 Flowchart of the specific steps of abnormality monitoring of the present invention;

[0060] Figure 3 A flowchart of the specific steps of dynamically updating the control instructions for abnormal equipment operating parameters according to the present invention;

[0061] Figure 4 A flowchart of the specific steps of the present invention for performing abnormal monitoring on an update control instruction sequence;

[0062] Figure 5 This is a flow chart of a device parameter collaborative control method of the present invention;

[0063] Figure 6 This is a structural diagram of a device parameter collaborative control system of the present invention. DETAILED DESCRIPTION

[0064] Example 1

[0065] See also Figure 1 ,This embodiment introduces a device parameter collaborative control system, including: a parameter acquisition module, an analysis and decision module, a device control module and a quality detection module;

[0066] The parameter acquisition module is used to determine the initial production parameter values ​​based on the production tasks of the target equipment and to collect the real-time production parameter values ​​during the execution of the production tasks by the target equipment. By performing multi-level comparative analysis on the real-time production parameters and their deviation degree, the module monitors the sudden disturbance to determine whether the target equipment has a sudden disturbance.

[0067] In this embodiment, the target equipment is a vertical roller centrifuge and its key execution units, including the drum system, mold assembly, and molten metal pouring system. Based on the current production task of the vertical roller centrifuge, the initial production parameters matching the current task are determined from a database of historical production tasks. These parameters include drum speed, mold preheat temperature, molten metal pouring flow rate, and molten metal temperature. During the execution of the vertical roller centrifuge's production task, the parameter acquisition module establishes a comprehensive data acquisition network using multiple types of high-precision sensors. Speed ​​sensors, temperature sensors, pressure sensors, and vibration sensors are deployed in key locations of the vertical roller centrifuge, including the drum, feed pipe, and cooling system. Real-time production parameters are collected continuously and at high frequency to ensure data timeliness and integrity. Real-time production parameters are compared against dynamic thresholds set based on historical data and process standards. If the data exceeds the threshold, a sudden disturbance is preliminarily determined. Simultaneously, the changing trends and characteristics of the real-time production parameters are analyzed to further determine whether a sudden disturbance has occurred, providing a solid data foundation for subsequent analytical decisions.

[0068] See also Figure 2 Preferably, the specific steps of sudden disturbance monitoring include:

[0069] For each production parameter, the variance of the historical production parameters under the same production task is extracted from the historical production task database, and combined with its initial production parameter value, the production parameter threshold is set, including the upper threshold and the lower threshold of the production parameter. For example, according to the statistical principle 3σ criterion, the production parameter threshold is set, and the initial production parameter value plus 3 times the standard deviation is used as the upper threshold of the production parameter, and the initial production parameter value minus 3 times the standard deviation is used as the lower threshold of the production parameter. The historical production task database is a database system specifically used to store and manage various historical production parameter data generated during the production process of the vertical roller centrifuge, including production parameter data, production task data, equipment operation data, quality inspection data, and personnel operation data.

[0070] Based on the production parameter threshold, the collected real-time production parameter values ​​are judged for potential disturbances, and each real-time production parameter value is compared with the corresponding production parameter threshold in real time. If the real-time production parameter value is greater than the upper threshold of the production parameter or less than the lower threshold of the production parameter, the real-time production parameter is marked as an abnormal production parameter, the real-time production parameter value is marked as an abnormal production parameter value, and the time when the abnormal production parameter value occurs is recorded; otherwise, no processing is performed; the collected production parameter values ​​are compared with the pre-set production parameter threshold in real time, which can timely capture abnormal changes in parameters in the production process, and provide detailed time series information for subsequent in-depth analysis and processing, which is convenient for tracing and troubleshooting potential production failures, and effectively reducing the losses caused by sudden disturbances to production.

[0071] Based on production process requirements and equipment characteristics, a deviation threshold is configured. The deviation of the abnormal production parameter value is calculated as the ratio of the absolute value of the difference between the abnormal production parameter value and the initial production parameter value to the initial production parameter value. If the deviation of the abnormal production parameter value exceeds the deviation threshold, a sensor anomaly warning is issued. Otherwise, anomaly monitoring is initiated for the real-time production parameter marked as abnormal. Configuring the deviation threshold and calculating the deviation of the abnormal production parameter value can further distinguish between parameter deviations caused by sensor anomalies and true potential disturbances in the production process. When the deviation exceeds the threshold, a sensor anomaly warning is issued, allowing sensor failures to be detected and addressed in a timely manner, avoiding misjudgments caused by sensor errors. Initiating anomaly monitoring for abnormal production parameters that do not meet the sensor anomaly criteria allows for continuous tracking of potential problems in the production process, ensuring that no possible sudden disturbances are missed.

[0072] See also Figure 3 Preferably, the specific steps of abnormality monitoring include:

[0073] Configure an abnormality duration threshold to obtain the duration of real-time abnormal production parameter anomalies marked as abnormal. If the duration is greater than the abnormality duration threshold, a time series fitting algorithm is used to fit and predict the production parameter value marked as abnormal, obtaining future production parameter forecasts within the abnormality duration threshold. Otherwise, no processing is performed. Time series fitting algorithms include ARIMA models or LSTM neural networks. The production parameter values ​​from the start time of the vertical roller centrifuge's production task to the current time marked as abnormal are obtained to construct an abnormality prediction set. After preprocessing operations such as data cleaning and normalization, the abnormality prediction set is input into the fitted abnormality prediction model, which models and analyzes the changing trends of the abnormal production parameters and predicts future production parameter forecasts within the abnormality duration threshold period.

[0074] Preferably, the specific steps of predicting the production parameter prediction value within the future abnormality duration threshold time period include:

[0075] Obtain the production parameter values ​​marked as abnormal production parameters from the start time of the production task of the vertical roller centrifuge to the current moment, and arrange them in chronological order to construct an abnormal prediction set;

[0076] After data preprocessing, the abnormal prediction set is divided into training set and test set. Data preprocessing includes data cleaning and missing value processing.

[0077] Select a time series fitting algorithm, build an anomaly prediction model, and fit the anomaly prediction model using the training set and test set. If the anomaly prediction set data is stationary and mainly exhibits a linear trend, select the ARIMA model. If the data has complex nonlinear characteristics and long-term dependencies, select the LSTM neural network.

[0078] Based on the anomaly persistence threshold, the length of the future time period to be predicted is determined. Specifically, the production parameter values ​​for the period exceeding the anomaly persistence threshold are predicted. The production parameter values ​​prior to the current moment are input into the fitted anomaly prediction model to predict future production parameter values. This yields the predicted values ​​for the period exceeding the anomaly persistence threshold. Determining the length of the predicted future time period based on the anomaly persistence threshold ensures that the prediction results are closely aligned with actual production conditions, allowing for a reasonable estimation of future changes in production parameters. The resulting production parameter predictions can provide forward-looking guidance for adjusting and controlling the production process.

[0079] By configuring a mutation threshold, the predicted production parameter values ​​are compared with the corresponding production parameter thresholds in real time. The number of predicted production parameter values ​​marked as abnormal is counted. If this number exceeds the mutation threshold, a sudden disturbance is determined to have occurred. Otherwise, abnormality monitoring of the real-time production parameters marked as abnormal continues. The number of predicted production parameter values ​​marked as abnormal is counted and compared with the mutation threshold, providing a quantitative judgment standard, making the judgment of sudden disturbances more objective and accurate. When the mutation threshold is exceeded, a sudden disturbance is determined to have occurred, and an alarm can be issued in a timely manner, prompting the company to take appropriate measures to address it. Otherwise, abnormality monitoring continues, ensuring continuous attention to the production process and not missing any potential risks.

[0080] The analysis and decision-making module is used to construct a parameter anomaly propagation path map to locate abnormal production parameters when a sudden disturbance is detected in the vertical roller centrifuge. Based on the abnormal production parameters, reverse reasoning is performed to locate the abnormal equipment operating parameters that caused the sudden disturbance.

[0081] Preferably, the specific steps of constructing a parameter anomaly propagation path map include:

[0082] Based on the production task type, historical production task data for vertical roller centrifuges was filtered from the historical production task database to construct an anomaly propagation dataset. The variables in the anomaly propagation dataset include historical production parameter variables and historical equipment operation parameter variables. Historical production parameter variables include drum speed, mold preheating temperature, molten metal pouring flow rate, and molten metal temperature. Historical equipment operation parameter variables include motor voltage, current, and frequency, mold heating power and heating time, molten metal pouring port size, pouring pressure and pouring time, and molten metal furnace power and holding time. The filtered data was integrated to construct the anomaly propagation dataset. To ensure the completeness and accuracy of the dataset, each data item was recorded and annotated in detail, including information such as the data source, collection time, and data meaning.

[0083] The anomaly propagation dataset is cleaned to remove noise, duplicate data, and erroneous data. Timestamps are aligned based on the acquisition time of each variable in the dataset. A combination of filtering algorithms, including median filtering and Kalman filtering, is used to tailor data processing to different types of data. For high-frequency fluctuating data, such as equipment vibration signals, Kalman filtering effectively removes noise interference and preserves true signal characteristics. For low-frequency varying data, such as ambient temperature, median filtering is used to smooth the data and reduce the impact of random noise. Key information in the data records within the anomaly propagation dataset, such as timestamps, parameter values, and data sources, is compared to accurately identify and remove duplicate data. Obvious erroneous data, such as parameter values ​​outside the physical range, is corrected based on business logic and historical data. If correction is not possible, it is marked as invalid and removed from the dataset. For parameter values ​​with different acquisition frequencies, such as production parameters collected every 1 second and equipment operating parameters collected every 5 seconds, linear interpolation is used to interpolate the low-frequency data to the high-frequency time points to ensure temporal consistency across all data.

[0084] Based on empirical knowledge, preliminary causal relationships are established between historical production parameter variables and historical equipment operating parameter variables in the anomaly propagation dataset. The causal relationships between these parameters are analyzed based on the experience and expertise of experts in the relevant fields. For example, changes in drum speed can affect the distribution of molten metal and the molding effect, thus impacting product quality; mold preheat temperature can affect the cooling rate of molten metal, which in turn affects the microstructure of the product. These causal relationships based on domain knowledge serve as the initial basis for judgment. Granger causality tests are then used to determine whether one variable Granger causes another by comparing the temporal sequence and correlation of different variables. The causal relationships between the variables are further verified, and the causal relationship strength and significance level between each parameter are calculated. A significance threshold is set to select causal parameter pairs with significance levels exceeding the threshold. Parameter pairs with weak causal relationship strength and low significance levels are eliminated to reduce unnecessary interference and computational complexity.

[0085] Each production parameter anomaly is defined as an abnormal event. The frequency of each production parameter being marked as an abnormal production parameter is counted based on the anomaly propagation dataset, serving as the prior probability of the production parameter anomaly. Based on the abnormal production parameter determination criteria, an abnormal event is defined. A comprehensive statistical analysis is performed on each production parameter in the anomaly propagation dataset, recording the number of abnormal occurrences and the total number of data samples for each production parameter. By calculating the ratio of the number of abnormal occurrences to the total number of samples, the prior probability of each production parameter anomaly is obtained.

[0086] For the parameter pairs with causal relationship, according to Bayes' theorem, by calculating the prior probability of each parameter pair with causal relationship, the conditional probability of abnormality of one parameter is calculated under the condition that the other parameter is abnormal;

[0087] A parameter anomaly propagation path graph framework is constructed, with each production parameter as a node in the graph, and each node represents the abnormal state of a specific production parameter. Edges are added to connect parameter pairs with causal relationships, and the direction of the edge represents the direction of the causal relationship, from the cause node to the result node. The conditional probability of the parameter pair with causal relationship is used as the weight of the edge, indicating the possibility of the result node abnormality when the cause node is abnormal.

[0088] Preferably, the specific steps of locating the abnormal equipment operating parameters that cause the abnormal cause of the sudden disturbance include:

[0089] The node in the parameter anomaly propagation path map corresponding to the abnormal production parameters of the vertical roller centrifuge is used as the starting node; this starting node represents the current abnormal production parameter and serves as the starting point for subsequent reverse reasoning and analysis. By clearly defining the starting node, we focus on the causal network related to the current abnormal production parameter, improving the pertinence and accuracy of the analysis.

[0090] Starting from the starting node, trace back along the edges in the parameter anomaly propagation path graph, and calculate the posterior probability of each possible cause node causing the starting node anomaly based on the edge weight.

[0091] Configure a probability threshold and, based on the calculated posterior probability, filter out cause nodes with posterior probabilities greater than the probability threshold as potential anomaly causes. By filtering out cause nodes with posterior probabilities greater than the probability threshold, you can focus on the causes most likely to cause anomalies at the starting node, reducing unnecessary analysis and troubleshooting, and improving problem-solving efficiency.

[0092] The operating parameters of the abnormal equipment are determined according to the potential abnormal causes, and the operating parameters of the abnormal equipment are sorted in descending order according to the posterior probability of the potential abnormal causes.

[0093] The equipment control module is used to generate control instructions for the abnormal equipment operating parameters in sequence according to the order of arrangement of the abnormal equipment operating parameters that cause the abnormal disturbance, and dynamically update the control instructions for the abnormal equipment operating parameters based on the real-time deviation degree of the abnormal production parameter values;

[0094] Preferably, the specific steps of generating a control instruction for abnormal equipment operating parameters include:

[0095] Obtain the arrangement order of abnormal production parameters, and generate control instructions for abnormal equipment operating parameters based on the arrangement order;

[0096] Preferably, the specific steps of the control instructions for abnormal production parameters include:

[0097] Filter the extreme values ​​of historical equipment operating parameters of the current production task from the historical production task database according to the production task type, so as to set the operating standard range of abnormal equipment operating parameters;

[0098] Determine the preliminary control direction based on the deviation direction of the abnormal production parameter value and the initial production parameter value, including: if the abnormal production parameter value is greater than the initial production parameter value, then reduce the abnormal equipment operating parameter value; if the abnormal production parameter value is less than the initial production parameter value, then increase the abnormal equipment operating parameter value;

[0099] A basic step size is set for each equipment operating parameter. The deviation degree of abnormal production parameter values ​​is segmented, and each deviation degree is matched with a mapping coefficient. A segmented mapping function is used to determine the mapping coefficient based on the deviation degree between the current abnormal production parameter value and the initial production parameter value to adjust the step length. For example, the deviation degree can be divided into multiple intervals, including a slight deviation interval, a moderate deviation interval, and a severe deviation interval. A mapping coefficient is matched to each interval, such as a mapping coefficient of 0.5 for the slight deviation interval, a mapping coefficient of 1 for the moderate deviation interval, and a mapping coefficient of 2 for the severe deviation interval. Based on the calculated deviation degree, the interval to which it belongs is determined. Then, the basic step size is multiplied by the corresponding mapping coefficient to obtain the adjusted step length.

[0100] Obtain the current abnormal equipment operating parameter value of the vertical roller centrifuge as the initial value, and generate a control instruction sequence according to the operating standard range, preliminary control direction and post-control step length of the abnormal equipment operating parameter;

[0101] See also Figure 4 Preferably, the specific steps of dynamically updating the control instructions of the abnormal equipment operating parameters include:

[0102] According to the arrangement order of the abnormal equipment operating parameters, the control instruction sequence of the abnormal equipment operating parameters is executed in sequence; the arrangement order is usually arranged from high to low based on the posterior probability of the potential abnormal cause, and the control instruction sequence of the equipment operating parameters that have a greater impact on the abnormality is executed first.

[0103] Configure the stop threshold. For any control instruction sequence of abnormal equipment operating parameters, monitor the deviation degree of the abnormal production parameters after executing each control instruction in the control instruction sequence. If the deviation degree of the abnormal production parameters is greater than the stop threshold, determine whether the deviation degree has been alleviated; and timely obtain the changes in abnormal production parameters during equipment operation, providing data basis for control effect evaluation, accurately judging whether the control is effective, and thus deciding on subsequent control strategies.

[0104] When the degree of deviation of the abnormal production parameters decreases or remains unchanged, it is determined that the degree of deviation has eased, otherwise it is determined that it has not eased. If the degree of deviation has eased, the next control instruction in the control instruction sequence will continue to be executed until the control instruction sequence of the current abnormal equipment operating parameters is completed; for effective control, the control process will continue to be promoted to gradually restore the equipment operating parameters to normal.

[0105] If the degree of deviation is not alleviated, the current control instruction is marked as a control instruction abnormal point, and the next control instruction in the control instruction sequence is executed. If the degree of deviation is still not alleviated, the next control instruction is marked as a control instruction abnormal point. During the execution of the control instruction sequence, the control instruction is monitored, the abnormal point threshold is configured, and the number of control instruction abnormal points is counted. If the number of abnormal points in the control instruction sequence is greater than the abnormal point threshold, the control direction is updated to the opposite direction of the initial control direction. Combined with the current abnormal equipment operating parameter value, the operating standard range of the abnormal equipment operating parameter and the step length after control are updated to obtain an updated control instruction sequence, and the updated control instruction sequence is monitored for abnormalities. Otherwise, the next control instruction in the control instruction sequence is executed until the control instruction sequence of the current abnormal equipment operating parameter is completed. For invalid control, the control strategy is adjusted in time to avoid the continuation of invalid operations and improve the pertinence and effectiveness of control.

[0106] If the deviation degree of the abnormal production parameters is less than or equal to the stop threshold, the equipment operation parameter control is stopped;

[0107] See also Figure 5 Preferably, the specific steps of performing abnormal monitoring on the update control instruction sequence include:

[0108] After executing the control instruction of the updated control instruction sequence, obtain the degree of deviation of the abnormal production parameter. If the deviation degree is alleviated, continue to execute the next control instruction of the updated control instruction sequence until the updated control instruction sequence of the current abnormal production parameter is completed; continuously track the effect of the updated control instruction to ensure that the new control strategy can effectively improve the equipment operation status.

[0109] If the degree of deviation is not alleviated, the abnormal points of the updated control instructions will be marked, and the updated control instructions will be monitored and the number of abnormal points of the updated control instructions will be counted. If it is greater than the abnormal point threshold, the control will be stopped and an abnormal control warning will be issued. Otherwise, the next control instruction in the updated control instruction sequence will continue to be executed until the updated control instruction sequence of the current abnormal production parameters is completed. If the updated control instruction is still invalid, it will be discovered in time to attract the attention of relevant personnel through the early warning mechanism so that further measures can be taken.

[0110] When all control instruction sequences for abnormal equipment operating parameters have completed execution, if the deviation of abnormal production parameters exceeds the stop threshold, a control anomaly warning is issued. A comprehensive assessment of the final results of the entire control process ensures that equipment operating parameters are stable and meet production requirements. If control targets are not met, timely warnings are issued, providing a basis for subsequent in-depth analysis and resolution, ensuring smooth production.

[0111] The quality inspection module collects quality parameter values ​​after the vertical roller centrifuge completes its production task and performs quality inspection on the roller products. If the roller product quality inspection fails, a product quality warning is issued. Combining the real-time production parameter values ​​obtained by the parameter acquisition module during the production process, the abnormal equipment operating parameters that caused the sudden disturbance, identified by the analysis and decision-making module, and the records of the abnormal equipment operating parameter control instructions recorded by the equipment control module, a product quality production report is generated. This provides data support for the initial production parameter setting, production parameter threshold adjustment, and overall production process optimization for subsequent production tasks, thereby continuously improving product quality and production efficiency.

[0112] Preferably, the specific steps of performing quality inspection on the roll product include:

[0113] After the vertical roller centrifuge completes its production task, the quality inspection process is initiated to collect quality parameter values ​​for the key quality characteristics of the roller products. This includes: using a profilometer to measure the surface roughness of the roller, and using a three-dimensional coordinate measuring machine to obtain the dimensional accuracy of the roller, including diameter, length, and cylindricity; using a hardness tester to test the hardness values ​​at different locations on the surface and inside the roller; and using ultrasonic flaw detectors and magnetic particle flaw detectors for non-destructive testing to check for defects such as cracks and sand holes inside and on the surface.

[0114] The collected values ​​of various quality parameters are recorded in real time, and a quality parameter database is established. Each quality parameter is associated with its corresponding product batch, production time, and equipment number to ensure the accuracy and completeness of the data.

[0115] According to the quality standards for roll products, quality parameter ranges are set, and the collected quality parameter values ​​are compared one by one with the corresponding quality parameter ranges. If all quality parameters meet the quality standards, the roll product is deemed qualified, the quality inspection process ends, and the product is marked as qualified and enters the next stage. If any one or more quality parameters exceed the standard range, the roll product is deemed unqualified, the quality problem analysis process is initiated, and a product quality production report is generated.

[0116] Preferably, the specific steps of generating a product quality production report include:

[0117] When the roll product quality inspection fails, it connects with the parameter acquisition module to obtain the real-time production parameter values ​​and abnormal production parameters during the roll product production process, as well as whether there are sudden disturbances;

[0118] By analyzing the decision-making module, the abnormal equipment operating parameters that lead to sudden disturbances are located; for example, whether the motor voltage, current and frequency are stable, whether the mold heating power and heating time meet the requirements, whether the molten metal pouring port size, pouring pressure and pouring time are accurate, whether the molten metal furnace power and holding time are appropriate, etc., to determine the impact mechanism of abnormal equipment operation on product quality.

[0119] Retrieve the record of control instructions for abnormal equipment operating parameters from the equipment control module, including the control instructions taken for abnormal equipment operating parameters during the production process, as well as the execution time and execution results of the control instructions;

[0120] Based on the information obtained above, a product quality production report is generated. The report content includes basic product information, including batch, number, production time, quality inspection results, production process parameter review, equipment operating parameter abnormality analysis, and control instructions. The generated product quality production report and related quality data are summarized and stored in a long-term quality database. It provides a historical reference for the initial production parameter setting of subsequent production tasks. By analyzing the relationship between the quality of different batches of products and the initial production parameters, the values ​​of the initial parameters are optimized to make them more consistent with the requirements of high-quality production. Based on a large amount of quality data and production process data, the production parameter thresholds are dynamically adjusted. Based on the frequency and type of quality issues, the threshold range of certain parameters can be reasonably expanded or narrowed to improve the stability of the production process and the consistency of product quality.

[0121] Example 2

[0122] See also Figure 6 This embodiment introduces a device parameter collaborative control method, including the following steps:

[0123] Step S1: Determine initial production parameter values ​​based on the production task of the target device, and collect real-time production parameter values ​​while the target device is executing the production task. Perform a multi-level comparative analysis of the real-time production parameters and their deviations to monitor sudden disturbances and determine whether the target device has sudden disturbances.

[0124] Step S2: When a sudden disturbance is detected in the target equipment, a parameter anomaly propagation path map is constructed using Bayesian theorem to locate the abnormal production parameters. Based on the abnormal production parameters, reverse reasoning is performed to locate the abnormal equipment operating parameters that are the cause of the sudden disturbance.

[0125] Step S3: Generate control instructions for the abnormal equipment operating parameters in sequence according to the order of arrangement of the abnormal equipment operating parameters that cause the sudden disturbance, and dynamically update the control instructions for the abnormal equipment operating parameters based on the real-time deviation of the abnormal production parameter values;

[0126] Step S4: After the target equipment completes the production task, the quality parameter values ​​are collected and the product quality is inspected. If the product quality inspection fails, a product quality warning is issued. In combination with the real-time production parameter values ​​in the production process, the abnormal equipment operating parameters that cause the sudden disturbance, and the abnormal equipment operating parameter control instruction records, a product quality production report is generated.

[0127] Preferably, the specific steps of sudden disturbance monitoring include:

[0128] For each production parameter, the variance of historical production parameters under the same production task is extracted from the historical production task database. Combined with its initial production parameter value, the production parameter threshold is set, including the upper threshold and the lower threshold of the production parameter.

[0129] Based on the production parameter threshold, the collected real-time production parameter values ​​are judged for potential disturbances, and each real-time production parameter value is compared with the corresponding production parameter threshold in real time;

[0130] If the real-time production parameter value is greater than the upper threshold value of the production parameter or less than the lower threshold value of the production parameter, the real-time production parameter is marked as an abnormal production parameter, the real-time production parameter value is marked as an abnormal production parameter value, and the time when the abnormal production parameter value occurs is recorded; otherwise, no processing is performed;

[0131] Configure the deviation degree threshold, and calculate the ratio of the absolute value of the difference between the abnormal production parameter value and the initial production parameter value to the initial production parameter value as the deviation degree of the abnormal production parameter value. If the deviation degree of the abnormal production parameter value is greater than the deviation degree threshold, a sensor abnormality warning is issued, otherwise abnormal monitoring is started for the real-time production parameters marked as abnormal production parameters.

[0132] Preferably, the specific steps of abnormality monitoring include:

[0133] Configure an abnormality duration threshold to obtain the abnormal duration of production parameters marked as abnormal production parameters. If the abnormal duration is greater than the abnormality duration threshold, use the time series fitting algorithm to fit and predict the production parameter value marked as abnormal production parameter to obtain the predicted value of the production parameter within the abnormality duration threshold in the future.

[0134] Configure the mutation threshold, compare the production parameter prediction value with the corresponding production parameter threshold in real time, and count the number of production parameter prediction values ​​marked as abnormal production parameter values. If the number is greater than the mutation threshold, it is determined that there is a sudden disturbance. Otherwise, continue to monitor the real-time production parameters marked as abnormal production parameters for abnormalities.

[0135] Preferably, the specific steps of obtaining the predicted value of the production parameter within the future abnormality persistence threshold include:

[0136] Obtain the production parameter values ​​marked as abnormal production parameters from the start time of the production task of the target device to the current time, and arrange them in chronological order to construct an abnormal prediction set;

[0137] After data preprocessing, the anomaly prediction set is divided into a training set and a test set. A time series fitting algorithm is selected to build an anomaly prediction model. The anomaly prediction model is fitted using the training set and the test set.

[0138] According to the abnormality duration threshold, the production parameter prediction value within the future abnormality duration threshold time period is predicted through the fitted abnormality prediction model.

[0139] Preferably, the specific steps of locating the abnormal equipment operating parameters that cause the abnormal cause of the sudden disturbance include:

[0140] The node of the parameter anomaly propagation path graph corresponding to the abnormal production parameter of the target device is used as the starting node;

[0141] Starting from the starting node, trace back along the edges in the parameter anomaly propagation path graph, and calculate the posterior probability of each cause node causing the starting node anomaly based on the edge weights;

[0142] Configure a probability threshold and, based on the calculated posterior probability, select the cause nodes whose posterior probability is greater than the probability threshold as potential anomaly causes.

[0143] The operating parameters of the abnormal equipment are determined according to the potential abnormal causes, and the operating parameters of the abnormal equipment are sorted in descending order according to the posterior probability of the potential abnormal causes.

[0144] Preferably, the specific steps of generating a control instruction for abnormal equipment operating parameters include:

[0145] Obtain the order of abnormal production parameters and generate control instructions for abnormal equipment operating parameters based on the order of arrangement, namely:

[0146] Filter the extreme values ​​of historical equipment operating parameters of the current production task from the historical production task database according to the production task type, so as to set the operating standard range of abnormal equipment operating parameters;

[0147] Determine the preliminary control direction based on the deviation direction of the abnormal production parameter value and the initial production parameter value, including: if the abnormal production parameter value is greater than the initial production parameter value, then reduce the abnormal equipment operating parameter value; if the abnormal production parameter value is less than the initial production parameter value, then increase the abnormal equipment operating parameter value;

[0148] A basic step length is set for each equipment operating parameter, and the deviation degree of abnormal production parameter values ​​is divided into segments. Each deviation degree is matched with a mapping coefficient. A segmented mapping function is used to determine the mapping coefficient based on the deviation degree between the current abnormal production parameter value and the initial production parameter value to control the step length.

[0149] Obtain the abnormal device operating parameter value of the current target device, and generate a control instruction sequence based on the operating standard range, preliminary control direction and step length after control of the abnormal device operating parameter.

[0150] Working principle and its effect:

[0151] The equipment parameter collaborative control system and control method of the present invention has a parameter acquisition module that determines the initial production parameter value and sets the threshold value based on the production task. During production, the real-time production parameters are collected and compared with the threshold value and the degree of deviation for multi-level analysis to achieve sudden disturbance monitoring. This can promptly detect abnormal situations in production that deviate from the preset parameters, solving the problem of relying on preset process parameters and being unable to detect sudden disturbances in a timely manner. Once a sudden disturbance is detected, the analysis and decision-making module uses Bayes' theorem to filter data from the historical production task database to construct an abnormal propagation data set. After cleaning and causal relationship analysis, a parameter abnormal propagation path map is constructed to locate abnormal production parameters. Reverse reasoning is used to locate the abnormal equipment operating parameters that cause the sudden disturbance, providing a basis for subsequent precise control. This changes the previous situation where it was difficult to locate the root cause of the problem when facing sudden disturbances. The equipment control module generates control instructions based on the order of the abnormal equipment operating parameters located, and dynamically updates them based on the real-time deviation degree of the abnormal production parameter values ​​to achieve real-time dynamic compensation for sudden disturbances, effectively improving the ability to cope with sudden disturbances and ensuring stable production. After production is completed, the quality inspection module collects quality parameter values ​​through various inspection methods to detect product quality. If the product is unqualified, it generates a report based on data from other modules to provide data support for optimizing the initial production parameter settings, adjusting production parameter thresholds, and improving the overall production process in subsequent production, continuously improving product quality and production efficiency, and solving the problem of production quality affected by the lack of real-time dynamic compensation capabilities.

[0152] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiment. All technical solutions based on the concept of the present invention are within the scope of protection of the present invention. It should be noted that for those skilled in the art, various improvements and modifications that do not depart from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. A device parameter collaborative control system, characterized in that: It includes parameter acquisition module, analysis and decision module, equipment control module and quality inspection module; The parameter acquisition module is used to determine the initial production parameter value based on the production task of the target device, and to collect the real-time production parameter value during the target device's execution of the production task. By performing multi-level comparative analysis on the real-time production parameter and its deviation degree, sudden disturbance monitoring is performed to determine whether the target device has a sudden disturbance; The analysis and decision module is used to construct a parameter anomaly propagation path map to locate abnormal production parameters based on Bayesian theorem when a sudden disturbance is detected in the target equipment. Based on the abnormal production parameters, reverse reasoning is performed to locate the abnormal equipment operating parameters that are the cause of the sudden disturbance. The equipment control module is used to sequentially generate control instructions for the abnormal equipment operating parameters according to the arrangement order of the abnormal equipment operating parameters, and dynamically update the control instructions for the abnormal equipment operating parameters based on the real-time deviation degree of the abnormal production parameter value; The quality inspection module is used to collect quality parameter values ​​and perform quality inspection on the product after the target equipment completes the production task. According to the product quality inspection results, it determines whether to issue a product quality warning and generate a product quality production report.

2. The device parameter collaborative control system according to claim 1, characterized in that: The specific steps of the sudden disturbance monitoring include: For each production parameter, the variance of historical production parameters under the same production task is extracted from the historical production task database. Combined with its initial production parameter value, the production parameter threshold is set, including the upper threshold and the lower threshold of the production parameter. Based on the production parameter threshold, the collected real-time production parameter values ​​are judged for potential disturbances, and each real-time production parameter value is compared with the corresponding production parameter threshold in real time; If the real-time production parameter value is greater than the upper threshold value of the production parameter or less than the lower threshold value of the production parameter, the real-time production parameter is marked as an abnormal production parameter, the real-time production parameter value is marked as an abnormal production parameter value, and the time when the abnormal production parameter value occurs is recorded; otherwise, no processing is performed; Configure the deviation degree threshold, and calculate the ratio of the absolute value of the difference between the abnormal production parameter value and the initial production parameter value to the initial production parameter value as the deviation degree of the abnormal production parameter value. If the deviation degree of the abnormal production parameter value is greater than the deviation degree threshold, a sensor abnormality warning is issued, otherwise abnormal monitoring is started for the real-time production parameters marked as abnormal production parameters.

3. The device parameter collaborative control system according to claim 2, characterized in that: The specific steps of the abnormality monitoring include: Configure an abnormality duration threshold to obtain the abnormal duration of production parameters marked as abnormal production parameters. If the abnormal duration is greater than the abnormality duration threshold, use the time series fitting algorithm to fit and predict the production parameter value marked as abnormal production parameter to obtain the predicted value of the production parameter within the abnormality duration threshold in the future. Configure a mutation threshold, compare the predicted production parameter value with the corresponding production parameter threshold in real time, and count the number of predicted production parameter values ​​marked as abnormal production parameter values. If the number is greater than the mutation threshold, it is determined that a sudden disturbance exists. Otherwise, continue to monitor the real-time production parameters marked as abnormal production parameters for abnormalities. The specific steps of obtaining the predicted value of the production parameter within the future abnormality duration threshold include: Obtain the production parameter values ​​marked as abnormal production parameters from the start time of the production task of the target device to the current time, and arrange them in chronological order to construct an abnormal prediction set; After data preprocessing, the anomaly prediction set is divided into a training set and a test set. A time series fitting algorithm is selected to build an anomaly prediction model. The anomaly prediction model is fitted using the training set and the test set. According to the abnormality duration threshold, the production parameter prediction value within the future abnormality duration threshold time period is predicted through the fitted abnormality prediction model.

4. The device parameter collaborative control system according to claim 1, wherein: The specific steps of constructing the parameter anomaly propagation path map include: According to the production task type, the historical production task data of the target equipment is filtered from the historical production task database to construct an anomaly propagation dataset. The variables in the anomaly propagation dataset include historical production parameter variables and historical equipment operation parameter variables. Perform data cleaning on the anomaly propagation dataset to remove noise data, duplicate data, and erroneous data; and align the timestamps of the anomaly propagation dataset based on the collection time of each variable value in the anomaly propagation dataset; Initially set the preliminary causal relationship between each historical production parameter variable and each historical equipment operation parameter variable in the abnormal propagation data set. Based on the Granger causality test, by comparing the temporal sequence and correlation of different variables in the abnormal propagation data set, calculate the causal relationship strength and significance level between each parameter, set the significance level threshold, and screen the causal relationship parameter pairs with a significance level greater than the significance level threshold; The abnormality of each production parameter is defined as an abnormal event. The frequency of each production parameter being marked as an abnormal production parameter is counted based on the abnormal propagation dataset, which is used as the prior probability of the production parameter being abnormal. For parameter pairs with causal relationships, according to Bayes' theorem, by calculating the prior probability of each parameter pair with causal relationships, the conditional probability that one parameter is abnormal is calculated under the condition that the other parameter is abnormal.

5. The device parameter collaborative control system according to claim 4, characterized in that: The specific steps of constructing the parameter anomaly propagation path map also include: Construct a parameter anomaly propagation path graph framework, using each production parameter as a node in the graph. Each node represents the abnormal state of a specific production parameter. Add edges to connect parameter pairs with causal relationships. The direction of the edge expresses the direction of the causal relationship, from the cause node to the result node. The conditional probability of a pair of parameters with causal relationship is used as the weight of the edge.

6. The device parameter collaborative control system according to claim 1, wherein: The specific steps of locating the abnormal equipment operating parameters that cause the abnormal cause of the sudden disturbance include: The node of the parameter anomaly propagation path graph corresponding to the abnormal production parameter of the target device is used as the starting node; Starting from the starting node, trace back along the edges in the parameter anomaly propagation path graph, and calculate the posterior probability of each cause node causing the starting node anomaly based on the edge weights; Configure a probability threshold and, based on the calculated posterior probability, select the cause nodes whose posterior probability is greater than the probability threshold as potential anomaly causes. The operating parameters of the abnormal equipment are determined according to the potential abnormal causes, and the operating parameters of the abnormal equipment are sorted in descending order according to the posterior probability of the potential abnormal causes.

7. The device parameter collaborative control system according to claim 1, wherein: The specific steps of generating the control instruction of the abnormal equipment operating parameters include: Obtain the order of abnormal production parameters and generate control instructions for abnormal equipment operating parameters based on the order of arrangement, namely: Filter the extreme values ​​of historical equipment operating parameters of the current production task from the historical production task database according to the production task type, so as to set the operating standard range of abnormal equipment operating parameters; Determine the preliminary control direction based on the deviation direction of the abnormal production parameter value and the initial production parameter value, including: if the abnormal production parameter value is greater than the initial production parameter value, then reduce the abnormal equipment operating parameter value; if the abnormal production parameter value is less than the initial production parameter value, then increase the abnormal equipment operating parameter value; A basic step length is set for each equipment operating parameter, and the deviation degree of abnormal production parameter values ​​is divided into segments. Each deviation degree is matched with a mapping coefficient. A segmented mapping function is used to determine the mapping coefficient based on the deviation degree between the current abnormal production parameter value and the initial production parameter value to control the step length. Obtain the abnormal device operating parameter value of the current target device, and generate a control instruction sequence based on the operating standard range, preliminary control direction and step length after control of the abnormal device operating parameter.

8. The device parameter collaborative control system according to claim 7, characterized in that: The specific steps of dynamically updating the control instructions for the abnormal equipment operating parameters include: According to the arrangement order of the abnormal equipment operating parameters, the control instruction sequence of the abnormal equipment operating parameters is executed in sequence; Configure a stop threshold. For any control instruction sequence of abnormal equipment operating parameters, monitor the deviation degree of the abnormal production parameter after executing each control instruction in the control instruction sequence. If the deviation degree of the abnormal production parameter is greater than the stop threshold, determine whether the deviation degree has been alleviated. When the deviation degree of the abnormal production parameter decreases or remains unchanged, it is determined that the deviation degree has been alleviated, otherwise it is determined that it has not been alleviated. If the deviation degree has been alleviated, the next control instruction in the control instruction sequence will continue to be executed until the control instruction sequence of the current abnormal equipment operating parameter is completed; If the degree of deviation is not alleviated, the current control instruction is marked as a control instruction abnormal point, and the next control instruction in the control instruction sequence is continued to be executed to monitor the control instructions, configure the abnormal point threshold, and count the number of control instruction abnormal points. If it is greater than the abnormal point threshold, the control direction is updated to the opposite direction of the initial control direction. Combined with the current abnormal equipment operating parameter value, according to the operating standard range of the abnormal equipment operating parameter and the step length after control, an updated control instruction sequence is obtained, and the updated control instruction sequence is monitored for abnormalities; otherwise, the next control instruction in the control instruction sequence is continued to be executed until the control instruction sequence of the current abnormal equipment operating parameter is completed; If the deviation degree of the abnormal production parameters is less than or equal to the stop threshold, the equipment operation parameter control is stopped.

9. The device parameter collaborative control system according to claim 8, characterized in that: The specific steps of performing abnormal monitoring on the update control instruction sequence include: After executing the control instruction of the update control instruction sequence, obtain the deviation degree of the abnormal production parameter. If the deviation degree is alleviated, continue to execute the next control instruction of the update control instruction sequence until the update control instruction sequence of the current abnormal production parameter is completed. If the degree of deviation is not alleviated, the abnormal point of the updated control instruction is marked, and the updated control instruction is monitored. The number of abnormal points of the updated control instruction is counted. If it is greater than the abnormal point threshold, the control is stopped and an abnormal control warning is issued. Otherwise, the next control instruction in the updated control instruction sequence is continued to be executed until the updated control instruction sequence of the current abnormal production parameter is completed. When all control instruction sequences for executing abnormal equipment operating parameters are completed, if the deviation degree of the abnormal production parameters is greater than the stop threshold, a control abnormality warning will be issued.

10. A device parameter collaborative control method, which is implemented based on the device parameter collaborative control system according to any one of claims 1 to 9, characterized in that: The following steps are involved: Step S1: Determine initial production parameter values ​​based on the production task of the target device, and collect real-time production parameter values ​​while the target device is executing the production task. Perform a multi-level comparative analysis of the real-time production parameters and their deviations to monitor sudden disturbances and determine whether the target device has sudden disturbances. Step S2: When a sudden disturbance is detected in the target equipment, a parameter anomaly propagation path map is constructed using Bayesian theorem to locate the abnormal production parameters. Based on the abnormal production parameters, reverse reasoning is performed to locate the abnormal equipment operating parameters that are the cause of the sudden disturbance. Step S3: Generate control instructions for the abnormal equipment operating parameters in sequence according to the order of arrangement of the abnormal equipment operating parameters that cause the sudden disturbance, and dynamically update the control instructions for the abnormal equipment operating parameters based on the real-time deviation of the abnormal production parameter values; Step S4: After the target equipment completes the production task, the quality parameter values ​​are collected and the product quality is tested. If the product quality test fails, a product quality warning is issued and a product quality production report is generated.

Images