Pushed slab kiln blocking fault prediction method and device, computer equipment and medium

Abstract

The invention relates to the technical field of fault prediction of pushed slab kilns. The method comprises the steps that operation information of a push rod is input into a sagger stacking and blocking fault prediction model, a stacking and blocking risk assessment value is obtained, the stacking and blocking risk assessment value is compared with a preset stacking and blocking risk threshold value, stacking and blocking risk state information is obtained, and the sagger stacking and blocking fault prediction model is established. If the stacking and blocking risk state information is high risk, a push rod operation parameter adjusting instruction is generated, adjusted operation information is obtained based on the push rod operation parameter adjusting instruction, the adjusted operation information is input into the sagger stacking and blocking fault prediction model, and a new stacking and blocking risk assessment value is obtained; if the new stacking and blocking risk assessment value is smaller than a preset stacking and blocking risk threshold value, operation of the push rod is controlled according to the adjusted operation parameters, and if the stacking and blocking risk state information is low risk, the original operation parameters of the push rod are kept. The pushing plate kiln has the effect of improving the operation stability of the pushing plate kiln.

Description

Technical Field

[0001] The present invention relates to the technical field of fault prediction of a push plate kiln, and in particular to a method, device, computer equipment and medium for predicting a blockage fault of a push plate kiln. Background Art

[0002] As an important heat treatment equipment in industrial production, pusher kiln is often used for sintering or high-temperature treatment of ceramics, glass and metal materials. However, pusher kiln often faces the problem of sagger blockage during operation. Blockage failure refers to the problem that the sagger is blocked at a certain position in the kiln due to abnormal fluctuations in mechanical parameters (such as abnormal changes in thrust, speed or displacement) during the operation of the push rod, which in turn causes material accumulation inside the kiln or equipment operation interruption. Summary of the invention

[0003] In order to improve the stability of the operation of a push-plate kiln, the present application provides a push-plate kiln blockage fault prediction method, device, computer equipment and medium.

[0004] The above-mentioned invention objective of the present application is achieved through the following technical solutions: A method for predicting a blockage fault of a push plate kiln, the method comprising: Get the operation information of the actuator; By inputting the operation information of the push rod into the sagger pile blockage fault prediction model, a pile blockage risk assessment value is obtained; Comparing the stack blockage risk assessment value with a preset stack blockage risk threshold to obtain stack blockage risk status information; If the stack blocking risk status information is high risk, generating a push rod operation parameter adjustment instruction; Based on the push rod operation parameter adjustment instruction, the operation state of the push rod is adjusted in real time to obtain adjusted operation information, and the adjusted operation information is input into the sagger pile blockage fault prediction model to obtain a new pile blockage risk assessment value, and if the new pile blockage risk assessment value is less than the preset pile blockage risk threshold, the operation of the push rod is controlled according to the adjusted operation parameters; If the stack blocking risk status information is low risk, the original operating parameters of the push rod are maintained.

[0005] By adopting the above technical solution, through the real-time analysis and risk assessment of the push rod operation information by the sagger pile blocking fault prediction model, it is possible to discover the abnormal operation that may lead to pile blocking fault in advance, so as to take targeted adjustment measures in time and effectively prevent the occurrence of pile blocking fault. When the pile blocking risk assessment value exceeds the threshold, timely generating the operation parameter adjustment instruction and dynamically optimizing the push rod operation state can quickly alleviate the pile blocking risk, avoid the equipment shutdown or production line interruption caused by the pile blocking fault, and ensure the continuity of production. The pile blocking fault often produces a large mechanical shock and load pressure on the push rod and related equipment. By dynamically adjusting the push rod operation parameters to reduce the pile blocking risk, the mechanical loss and unnecessary operating pressure of the equipment can be significantly reduced, and the service life of the equipment can be extended. Through the closed-loop control method of real-time monitoring, dynamic adjustment and risk assessment, it is ensured that the push rod operates within a reasonable range, the operation fluctuation caused by the pile blocking risk is eliminated, and the stability and reliability of the equipment operation are improved.

[0006] In a preferred example, the present application can be further configured as follows: the sagger pile blockage fault prediction model previously includes: Acquire historical operation information of a push plate kiln, and perform information preprocessing on the historical operation information of the push plate kiln to obtain the preprocessed historical operation information; The pre-processed historical operation information is labeled with state information of the occurrence of stack blockage faults according to the time series to form a training data set, and the training data set is input into a machine learning model to train the machine learning model to obtain an initial sagger stack blockage fault prediction model; The initial sagger pile blockage fault prediction model is verified by a cross-validation method, and after successful verification, the sagger pile blockage fault prediction model is obtained.

[0007] By adopting the above technical solution, by obtaining the historical operation information of the push plate kiln and performing information preprocessing, the noise data and abnormal data are removed to generate higher quality training data, thereby ensuring the accuracy of the model input data and improving the accuracy of fault prediction. The machine learning model is used to train the preprocessed historical operation data, and the state information of the pile blockage failure is annotated through the time series to capture the correlation between the push rod operation state and the pile blockage failure. The generated prediction model can automatically identify the pile blockage risk without relying on manual experience judgment, thereby improving the prediction efficiency. The initial sagger pile blockage failure prediction model is verified by cross-validation method to ensure the stable performance of the model on different data sets, thereby improving the reliability and generalization ability of the model in practical applications.

[0008] In a preferred example, the present application may be further configured as follows: the operation information of the push rod is input into the sagger pile blockage fault prediction model to obtain a pile blockage risk assessment value, including: Extracting features of the operation information of the push rod to obtain dynamic operation feature parameters of the push rod; The sagger blockage fault prediction model performs fault prediction calculation on the push rod dynamic operation characteristic parameters to obtain the blockage risk assessment value.

[0009] By adopting the above technical solution, by extracting the dynamic operation characteristics of the push rod and combining it with the sagger pile blockage fault prediction model for analysis and calculation, it is possible to achieve accurate quantification and efficient prediction of pile blockage risks, which not only improves the early warning capability of pile blockage failures, but also provides a scientific basis for subsequent operation adjustments and optimizations, effectively ensuring the safe and stable operation of the equipment and reducing the economic losses and production risks caused by pile blockage failures.

[0010] In a preferred example, the present application may be further configured as follows: the sagger blockage fault prediction model performs fault prediction calculation on the push rod dynamic operation characteristic parameters to obtain the blockage risk assessment value, including: The sagger pile blockage failure prediction model calculates the pile blockage risk assessment value based on the following formula: , wherein R represents the stack blockage risk assessment value, ΔF represents the instantaneous rate of change of the push rod thrust, ΔV represents the fluctuation amplitude of the push rod running speed, ΔS represents the change trend of the push rod displacement, and represents the interaction term between the thrust change rate and the speed fluctuation, W1 represents the weight coefficient of the instantaneous change rate of the push rod thrust, W2 represents the weight coefficient of the fluctuation amplitude of the push rod running speed, W3 represents the weight coefficient of the change trend of the push rod displacement, W4 represents the weight coefficient of the interaction term between the thrust change rate and the speed fluctuation, b represents the bias value, σ represents the nonlinear activation function, ΔF 2 represents the influence of the square of the thrust change rate on the stack blockage failure, It represents capturing the nonlinear influence of running speed fluctuation, and the log(1+|ΔS|) represents the influence on the sagger pile blockage fault prediction model when the displacement change is weakened.

[0011] By adopting the above technical scheme, the pile blockage risk assessment value is calculated based on the formula through the sagger pile blockage fault prediction model, and the instantaneous change rate of the push rod thrust, the fluctuation amplitude of the operating speed, the displacement change trend and their interactive relationship are comprehensively quantified using weighted analysis and nonlinear activation functions. It is possible to accurately assess the size of the pile blockage risk and provide an intuitive risk value.

[0012] In a preferred example, the present application may be further configured as follows: the stack blocking risk assessment value is compared with a preset stack blocking risk threshold to obtain stack blocking risk status information, including: The preset stack blockage risk threshold includes a low risk threshold, a high risk threshold and an intermediate risk range; The stack congestion risk assessment value is compared with a preset stack congestion risk threshold; when the stack congestion risk assessment value is < the low risk threshold, the stack congestion risk status information is generated as the low risk; if the low risk threshold is ≤ the stack congestion risk assessment value ≤ the high risk threshold, the stack congestion risk status information is generated as the medium risk; if the stack congestion risk assessment value is > the high risk threshold, the stack congestion risk status information is generated as the high risk.

[0013] By adopting the above technical solution, by setting low risk threshold, high risk threshold and intermediate risk range, and comparing the pile blockage risk assessment value with these thresholds, the pile blockage risk can be accurately classified (low risk, medium risk and high risk), so as to formulate targeted response measures for different risk levels to ensure the scientific and efficient treatment. According to the classification of pile blockage risk status information, the original operating parameters of the equipment are maintained in the low risk state, the operating status is continuously observed in the medium risk state, and the operating parameters are adjusted in time or early warning information is issued in the high risk state, so as to realize the dynamic and refined management of the equipment operating status, reduce unnecessary operations, and improve the equipment operation efficiency.

[0014] In a preferred example, the present application may be further configured as follows: the stack blockage risk status information is medium risk, and further includes: If the stack blockage risk status information is the medium risk, generating continuous observation operation status information; According to the continuously observed operation status information, if the stack blockage risk assessment value decreases to the low risk during the continuous observation period, restoring the original operation parameters of the push rod; If the stack blocking risk assessment value rises to the high risk during the continuous observation period, the push rod operation parameter adjustment instruction is generated.

[0015] By adopting the above technical solution, when the pile blocking risk status information is medium risk, the continuous observation operation status information is generated, the operation status of the push rod can be monitored in real time, the changing trend of the pile blocking risk assessment value can be dynamically grasped, and the risk status can be accurately assessed in dynamic changes, providing a more reliable basis for subsequent adjustments. In the medium risk state, by continuously observing the changes in the pile blocking risk assessment value, it is possible to avoid taking immediate adjustment measures, reduce unnecessary operating parameter modifications, reduce interference with equipment operation, and ensure the stability and efficiency of equipment operation. If the pile blocking risk assessment value is reduced to low risk during the continuous observation period, the original operating parameters of the push rod are restored to restore the equipment operation to the optimal state, avoiding resource waste and improving the equipment operation efficiency and economy. If the pile blocking risk assessment value rises to high risk during the continuous observation period, the push rod operation parameter adjustment instruction can be quickly generated, and the high risk state can be timely alleviated by dynamically optimizing the operating parameters, avoiding the occurrence of pile blocking failures, and reducing equipment damage or production interruptions caused by pile blocking.

[0016] In a preferred example, the present application may be further configured as follows: if the new stack blockage risk assessment value is less than the preset stack blockage risk threshold, the operation of the push rod is controlled according to the adjusted operation parameters, and further includes: If the new stack blocking risk assessment value is greater than the preset stack blocking risk threshold, a further operation parameter optimization instruction is generated, and the operation state of the push rod is adjusted based on the further operation parameter optimization instruction to obtain re-optimized operation information, and the re-optimized operation information is input into the sagger stack blocking fault prediction model to obtain a re-adjusted stack blocking risk assessment value; If the re-adjusted stack blockage risk assessment value is still greater than the preset stack blockage risk threshold, high-risk warning information is generated and sent to the operation terminal.

[0017] By adopting the above technical solution, when the new pile blocking risk assessment value is greater than the preset pile blocking risk threshold, by generating further operating parameter optimization instructions and adjusting the operating state of the push rod based on the optimization instructions, accurate control of high-risk states is achieved, ensuring that the pile blocking risk is effectively alleviated in the initial stage. The adjusted operating information is input into the sagger pile blocking fault prediction model for calculation again, forming a closed-loop control process from risk assessment to adjustment and optimization to re-evaluation, ensuring that the effect of each adjustment can be verified in real time. If the pile blocking risk assessment value after adjustment is still greater than the preset pile blocking risk threshold, a high-risk warning message will be automatically generated and sent to the operation terminal, which can quickly notify the operator to intervene, prevent the pile blocking risk from further escalating to a serious fault, and ensure the safety of equipment operation.

[0018] The second object of the invention is achieved by the following technical solutions: A push plate kiln blockage fault prediction device, the push plate kiln blockage fault prediction device comprising: A push rod operation information collection module is used to obtain the operation information of the push rod; A pile blocking risk assessment module, used for obtaining a pile blocking risk assessment value by inputting the operation information of the push rod into a sagger pile blocking fault prediction model; A stack blocking risk state judgment module, used for comparing the stack blocking risk assessment value with a preset stack blocking risk threshold to obtain stack blocking risk state information; A push rod operation parameter adjustment module, used for generating a push rod operation parameter adjustment instruction if the stack blocking risk status information is high risk; A dynamic adjustment and risk feedback module, which is used to adjust the operation state of the push rod in real time based on the push rod operation parameter adjustment instruction, obtain the adjusted operation information, input the adjusted operation information into the sagger pile blockage fault prediction model, obtain a new pile blockage risk assessment value, and if the new pile blockage risk assessment value is less than the preset pile blockage risk threshold, control the operation of the push rod according to the adjusted operation parameters; The operating parameter maintaining module is used to maintain the original operating parameters of the push rod if the stack blocking risk status information is low risk.

[0019] By adopting the above technical solution, through the real-time analysis and risk assessment of the push rod operation information by the sagger pile blocking fault prediction model, it is possible to discover the abnormal operation that may lead to pile blocking fault in advance, so as to take targeted adjustment measures in time and effectively prevent the occurrence of pile blocking fault. When the pile blocking risk assessment value exceeds the threshold, timely generating the operation parameter adjustment instruction and dynamically optimizing the push rod operation state can quickly alleviate the pile blocking risk, avoid the equipment shutdown or production line interruption caused by the pile blocking fault, and ensure the continuity of production. The pile blocking fault often produces a large mechanical shock and load pressure on the push rod and related equipment. By dynamically adjusting the push rod operation parameters to reduce the pile blocking risk, the mechanical loss and unnecessary operating pressure of the equipment can be significantly reduced, and the service life of the equipment can be extended. Through the closed-loop control method of real-time monitoring, dynamic adjustment and risk assessment, it is ensured that the push rod operates within a reasonable range, the operation fluctuation caused by the pile blocking risk is eliminated, and the stability and reliability of the equipment operation are improved.

[0020] The third objective of the present application is achieved through the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned push plate kiln blockage fault prediction method when executing the computer program.

[0021] The fourth objective of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned push plate kiln blockage fault prediction method.

[0022] In summary, the present application includes at least one of the following beneficial technical effects: 1. Through the real-time analysis and risk assessment of the push rod operation information by the sagger pile blockage fault prediction model, it is possible to detect abnormal operating conditions that may lead to pile blockage faults in advance, so as to take targeted adjustment measures in time and effectively prevent the occurrence of pile blockage faults. When the pile blockage risk assessment value exceeds the threshold, timely generate operating parameter adjustment instructions and dynamically optimize the push rod operation status, which can quickly alleviate the pile blockage risk, avoid equipment shutdown or production line interruption caused by pile blockage failure, and ensure production continuity. Pile blockage failures often cause greater mechanical shock and load pressure on push rods and related equipment. By dynamically adjusting the push rod operating parameters to reduce the risk of pile blockage, the mechanical loss of equipment and unnecessary operating pressure can be significantly reduced, and the service life of the equipment can be extended. Through the closed-loop control method of real-time monitoring, dynamic adjustment and risk assessment, ensure that the push rod operates within a reasonable range, eliminate operating fluctuations caused by pile blockage risks, and improve the stability and reliability of equipment operation; 2. The pile plugging fault prediction model is used to calculate the pile plugging risk assessment value based on the formula, and the push rod thrust instantaneous change rate, operating speed fluctuation amplitude, displacement change trend and their interactive relationship are integrated. The weighted analysis and nonlinear activation function are used to comprehensively quantify the influencing factors, which can accurately assess the size of the pile plugging risk and provide an intuitive risk value. 3. When the pile blocking risk status information is medium risk, the continuous observation operation status information is generated, which can monitor the operation status of the push rod in real time, dynamically grasp the changing trend of the pile blocking risk assessment value, ensure that the risk status is accurately assessed in dynamic changes, and provide a more reliable basis for subsequent adjustments. In the medium-risk state, by continuously observing the changes in the pile blocking risk assessment value, avoid taking immediate adjustment measures, reduce unnecessary operating parameter modifications, reduce interference with equipment operation, and ensure the stability and efficiency of equipment operation. If the pile blocking risk assessment value is reduced to low risk during the continuous observation period, the original operating parameters of the push rod are restored to restore the equipment operation to the optimal state, avoid resource waste, and improve equipment operation efficiency and economy. If the pile blocking risk assessment value rises to high risk during the continuous observation period, the push rod operating parameter adjustment instruction can be quickly generated. By dynamically optimizing the operating parameters, the high-risk state can be alleviated in time, the occurrence of pile blocking failures can be avoided, and equipment damage or production interruptions caused by pile blocking can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a flow chart of a method for predicting a blockage fault of a push plate kiln in an embodiment of the present application; Figure 2 It is a flowchart of the implementation before step S20 in the method for predicting the blockage fault of a push plate kiln in one embodiment of the present application; Figure 3 It is a flowchart for implementing step S20 in the method for predicting the blockage fault of a push plate kiln in one embodiment of the present application; Figure 4 It is a flowchart for implementing step S202 in the method for predicting the blockage fault of a push plate kiln in one embodiment of the present application; Figure 5 It is a flowchart for implementing step S30 in the method for predicting the blockage fault of a push plate kiln in one embodiment of the present application; Figure 6 It is a flowchart for implementing step S302 in the method for predicting the blockage fault of a push plate kiln in one embodiment of the present application; Figure 7 It is a flowchart for implementing step S40 in the method for predicting the blockage fault of a push plate kiln in one embodiment of the present application; Figure 8 This is a principle block diagram of a push plate kiln blockage fault prediction device in one embodiment of the present application; Fig. 9 It is a schematic diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The present application is further described in detail below in conjunction with the accompanying drawings.

[0025] In one embodiment, if Figure 1 As shown, the present application discloses a method for predicting blockage failure of a push plate kiln, which specifically includes the following steps: S10: Acquire the operation information of the push rod.

[0026] Specifically, high-precision sensors are installed on the push rod to collect the operation information of the push rod in real time. The sensors include pressure sensors, displacement sensors and speed sensors. The pressure sensor is used to monitor the force condition of the push rod, the displacement sensor is used to obtain the moving distance of the push rod, and the speed sensor obtains the operation speed of the push rod by calculating the change of displacement in unit time. The information sampling frequency of the sensor is set to 1 millisecond to 10 milliseconds, and the analog signal is converted into a digital signal and then transmitted to the information processing module. The information processing module performs noise filtering and signal amplification processing on the collected signal, and obtains the real-time operation information of the push rod after removing the sampling error, including the instantaneous value of the thrust, the changing trend of the operation speed, and the cumulative value of the displacement.

[0027] S20: The operation information of the push rod is input into the sagger pile blockage fault prediction model to obtain a pile blockage risk assessment value.

[0028] Specifically, the collected push rod operation information is divided into multiple time segments according to fixed time intervals, and each time segment is input into the sagger pile blockage fault prediction model as an independent sample. The model is calculated through previously trained parameters. First, the input sample data is preprocessed, including normalizing the operation information and scaling the thrust, speed and displacement parameters to the range between 0 and 1 to ensure that the characteristic values ​​of different data dimensions are at the same order of magnitude to avoid calculation deviation. Then the model uses the time series analysis method to extract features from the multiple input time segments. The feature extraction includes fitting the change trend of the thrust, counting the speed fluctuation, and calculating the increment of the displacement accumulation value. Finally, the extracted features are weighted and nonlinearly activated through the multi-layer computing units of the model. The output layer of the model generates a pile blockage risk assessment value. The pile blockage risk assessment value is a value between 0 and 1, which is used to represent the size of the pile blockage risk.

[0029] S30: Compare the stack blockage risk assessment value with a preset stack blockage risk threshold to obtain stack blockage risk status information.

[0030] Specifically, the calculated stack blockage risk assessment value is compared with a preset stack blockage risk threshold. The comparison process includes loading the stack blockage risk threshold from a database. The threshold is obtained based on historical operating data and multiple stack blockage failure test results, and is set to a safety critical value within a fixed range. The risk status is judged by calculating the difference between the stack blockage risk assessment value and the threshold. If the difference is greater than 0, it means that the assessment value exceeds the safety threshold range, and a high-risk status information is generated. If the difference is less than or equal to 0, it means that the assessment value is within the safety threshold range, and a low-risk status information is generated.

[0031] S40: If the stack blocking risk status information is high risk, a push rod operation parameter adjustment instruction is generated.

[0032] Specifically, after judging that the risk status of the stack blockage is high risk, a push rod operating parameter adjustment instruction is generated according to the current operating parameters. The generation of the adjustment instruction includes calculating the adjustment range according to the historical operating experience and the current parameters, wherein the thrust is adjusted to 70% to 80% of the current value, and the speed is adjusted to 50% to 70% of the current value. The adjustment range is automatically calculated by referring to the key parameter range when the stack blockage occurs in the historical data. The calculation method is to compare the current operating parameters with the parameters of similar operating conditions in the historical data, and extract the minimum safe operating parameters related to the occurrence of stack blockage as the adjustment target value. The generated adjustment instruction is sent to the push rod control unit through the instruction interface to change the actual operating parameters of the push rod, thereby reducing the risk of stack blockage.

[0033] Furthermore, the generation of push rod operation parameter adjustment instructions is based on the stack blockage risk assessment value R and the push rod operation information collected in real time. The generation of the instructions includes the following steps: First, according to the thrust, operation speed and displacement data collected in real time, the deviation between the current operation parameters and the historical safe operation parameters is calculated. The deviation value of the thrust is calculated by the following formula: , the speed deviation is calculated by the following formula: , where F current Indicates the current thrust, F safe represents the mean safe thrust value obtained based on historical fault data statistics, V current Indicates the current running speed, V safe It represents the average safe speed obtained based on historical data statistics. Then, according to the stack blockage risk assessment value R and the deviation value, the target thrust value and target speed value are calculated. The target thrust value is determined by the following formula: , the target speed value is calculated by the following formula: , where α represents the thrust adjustment coefficient, which is usually set based on historical data analysis and ranges from 0.5 to 0.9; β represents the speed adjustment proportional coefficient, which usually ranges from 0.2 to 0.6. The adjustment range increases with the increase of the stack blockage risk assessment value R, so that the adjustment is targeted; then, the adjustment execution time is calculated, and the adjustment execution time is calculated by the following formula: , where Ta djust Indicates the adjustment execution time, T baseline It represents the benchmark adjustment time, which is usually 3 to 5 seconds. It is dynamically adjusted through the risk assessment value R to balance the rapidity and stability of the adjustment response. Finally, according to the calculated target thrust value, target speed value and adjustment execution time, an operating parameter adjustment instruction is generated, and the instruction is formatted into an instruction sequence, including the thrust target value, speed target value and adjustment time parameters. The instruction is sent to the push rod drive module to adjust the operating status of the push rod.

[0034] S50: Based on the push rod operation parameter adjustment instruction, the operation status of the push rod is adjusted in real time to obtain the adjusted operation information, and the adjusted operation information is input into the sagger pile blockage fault prediction model to obtain a new pile blockage risk assessment value. If the new pile blockage risk assessment value is less than the preset pile blockage risk threshold, the operation of the push rod is controlled according to the adjusted operation parameters.

[0035] Specifically, the operating state of the push rod is adjusted in real time according to the generated push rod operating parameter adjustment instruction. The adjusted operating state includes reducing the thrust and speed of the push rod and maintaining the continuity of the displacement. The adjusted operating information is collected in real time. The adjusted operating information includes updated thrust, speed and displacement parameters. The adjusted operating information is re-input into the sagger pile blockage fault prediction model. The model recalculates the pile blockage risk assessment value based on the adjusted information. If the new assessment value is lower than the preset risk threshold, the adjustment is considered effective. The adjusted parameters are maintained and the operation of the push rod continues to be controlled in real time. The adjusted operating parameters and pile blockage risk assessment values ​​are recorded, and the push rod status is continuously monitored to ensure the stability of the adjusted operation.

[0036] S60: If the stack blocking risk status information is low risk, the original operating parameters of the push rod are maintained.

[0037] Specifically, when the risk status of stack blockage is judged to be low risk, the current push rod operating parameters are directly used to control the push rod without further adjustment. The operating parameters include the thrust, speed and displacement values ​​monitored in real time. These parameters are transmitted to the push rod control unit for output of control signals. At the same time, the current operating parameters and risk assessment results are written into the equipment operation database for archiving at fixed intervals. The operating parameters under the low-risk state are used as a reference benchmark for subsequent parameter optimization and operating condition analysis to maintain the stability and continuity of operation and avoid unnecessary adjustment actions that affect equipment efficiency.

[0038] In one embodiment, if Figure 2 As shown, before step S20, the sagger pile blockage fault prediction model includes: S11: Acquire historical operation information of the push plate kiln, perform information preprocessing on the historical operation information of the push plate kiln, and obtain the preprocessed historical operation information.

[0039] Specifically, the historical operation information obtained includes the operation parameters of the push rod, the occurrence time of the stack blockage fault, and the operation status data before and after the stack blockage fault. The operation parameters of the push rod include thrust, operation speed and displacement. The occurrence time of the stack blockage fault is obtained through the operation log records. The operation status data before and after the stack blockage fault is determined by segmented labeling of the historical operation data. When preprocessing the historical operation information, firstly, the missing values ​​in the historical operation data are filled by interpolation, in which the linear interpolation method is used to supplement the continuously missing numerical data, and the category with the highest occurrence frequency is used to fill the classified data; secondly, the outliers are processed, and the outliers in the operation parameters are detected by the triple standard deviation method, and the detected outliers are corrected by median substitution; finally, the numerical data such as thrust, speed and displacement are normalized, and the data are mapped to the range between 0 and 1 to reduce the impact of numerical magnitude differences on model training.

[0040] S12: annotate the state information of the pile blockage failure according to the time series of the preprocessed historical operation information to form a training data set, input the training data set into the machine learning model, train the machine learning model, and obtain an initial sagger pile blockage failure prediction model.

[0041] Specifically, the preprocessed historical operation information is sliced ​​according to the time series, and each time slice is composed of a time window of fixed length. The operation parameters in the time window include thrust, speed and displacement data, and the state information is annotated in combination with the time when the stack blockage fault occurs, wherein the state information of the stack blockage fault includes the occurrence of stack blockage (marked as 1) and the occurrence of no stack blockage (marked as 0). The length of the time series slice is set according to the actual operating conditions, for example, 1 second to 5 seconds is used as a time window, and the operation data of each time window forms an independent training sample; after the training data set is formed, the data set is divided into a training set and a validation set, wherein the training set accounts for 70%-80% of the total data volume, and the validation set accounts for 20%-30%, and then the training set is input into the machine learning model, and the training is performed using algorithms such as deep neural networks, support vector machines or random forests. The training process includes iterative optimization of model parameters (such as weights and biases), and the optimization method uses a gradient descent algorithm, wherein the loss function is a cross entropy loss function, which is used to measure the deviation between the model prediction result and the true label, and the parameters of the model are updated by minimizing the loss function, and finally an initial sagger stack blockage fault prediction model is obtained.

[0042] S13: The initial sagger pile blockage fault prediction model is verified by a cross-validation method. After successful verification, the sagger pile blockage fault prediction model is obtained.

[0043] Specifically, the initial sagger pile blockage fault prediction model is verified by cross-validation, and the K-fold cross-validation method is used to divide the verification set into K subsets, one of which is used as the verification set and the remaining K-1 subsets are used as training sets. The model is trained using K-1 subsets in each fold, and the performance indicators of the model are calculated on the remaining verification subsets. The performance indicators include precision, recall rate and F1 score. The overall performance of the model is evaluated by averaging the performance indicators of all folds. During the verification process, if the performance indicators all reach the set thresholds, such as precision greater than 90%, recall rate greater than 85%, and F1 score greater than 88%, the model verification is considered to be successful, and the verified model is used as the final sagger pile blockage fault prediction model. If the performance indicators do not reach the set thresholds, it is necessary to adjust the model structure or training parameters, such as increasing the number of neural network layers, adjusting the learning rate, or changing the optimization algorithm, and then retrain the model and verify it again until the model verification is successful.

[0044] In one embodiment, if Figure 3As shown, in step S20, the operation information of the push rod is input into the sagger pile blockage fault prediction model to obtain a pile blockage risk assessment value, including: S201: Extracting features of the operation information of the push rod to obtain dynamic operation feature parameters of the push rod.

[0045] Specifically, first, the thrust change of the push rod is analyzed. By continuously comparing the collected thrust data, the change trend of the thrust between adjacent time points is extracted, so as to obtain the instantaneous change rate of the thrust. This feature reflects the rapid fluctuation of the thrust over time. Secondly, the stability of the push rod running speed is analyzed. By selecting the speed data within a fixed time period, the fluctuation amplitude of the speed within the time period is calculated. The magnitude of the speed fluctuation amplitude is used to reflect the stability of the push rod running speed. The larger the fluctuation amplitude, the higher the instability of the running speed. Then, the change trend of the push rod displacement is extracted. By fitting the overall change direction of the displacement data within a fixed time interval, the trend of the displacement change over time is obtained. This feature is used to describe the continuity of the displacement during the operation of the push rod. Finally, the above-mentioned extracted features, including the instantaneous change rate of the thrust, the fluctuation amplitude of the running speed and the change trend of the displacement are combined to form the dynamic operation characteristic parameters of the push rod, which are used as the input of the subsequent fault prediction model.

[0046] S202: The sagger pile blockage fault prediction model performs fault prediction calculation on the dynamic operation characteristic parameters of the push rod to obtain a pile blockage risk assessment value.

[0047] Specifically, the sagger pile blockage fault prediction model receives the dynamic operation characteristic parameters of the push rod as input, including the instantaneous change rate of thrust, the fluctuation amplitude of the operating speed and the change trend of the displacement. The model first preprocesses the input characteristic data, and adjusts the numerical range of the characteristics to a consistent standard by standardizing all characteristic values ​​to reduce the impact of the magnitude differences between the characteristics on the model calculation. Then, the model performs multi-layer calculations on the standardized characteristics, and analyzes the correlation between the characteristics and the pile blockage fault layer by layer. The role of thrust change, speed fluctuation and displacement trend in the occurrence of the pile blockage fault is weightedly calculated. At the same time, the relationship between the characteristics is analyzed, such as the coupling relationship between the thrust change rate and the speed fluctuation, to generate a comprehensive risk assessment result. Finally, the pile blockage risk assessment value output by the model is a quantitative result of the possibility of failure, usually ranging from 0 to 1. The closer the median value is to 1, the higher the possibility of pile blockage failure.

[0048] In one embodiment, if Figure 4 As shown, in step S202, the sagger pile blockage fault prediction model performs fault prediction calculation on the push rod dynamic operation characteristic parameters to obtain a pile blockage risk assessment value, including: S2021: The sagger pile blockage failure prediction model calculates the pile blockage risk assessment value based on the following formula: , where R represents the risk assessment value of stack blockage, ΔF represents the instantaneous rate of change of the push rod thrust, ΔV represents the fluctuation amplitude of the push rod running speed, and ΔS represents the change trend of the push rod displacement. represents the interaction term between the thrust change rate and the speed fluctuation, W1 represents the weight coefficient of the instantaneous change rate of the thrust of the push rod, W2 represents the weight coefficient of the fluctuation amplitude of the push rod running speed, W3 represents the weight coefficient of the change trend of the push rod displacement, W4 represents the weight coefficient of the interaction term between the thrust change rate and the speed fluctuation, b represents the bias value, σ represents the nonlinear activation function, ΔF 2 It represents the influence of the square of the thrust change rate on the stack blockage failure. It represents capturing the nonlinear influence of running speed fluctuation, and log(1+|ΔS|) represents weakening the influence of displacement change on the sagger pile blockage fault prediction model.

[0049] Specifically, the process of calculating the pile blockage risk assessment value according to the push rod operation parameters collected in real time by the sagger pile blockage fault prediction model includes the following steps: First, the thrust, operation speed and displacement parameters collected in real time are preprocessed, and the instantaneous change rate of thrust ΔF is calculated by the ratio of the thrust difference at two consecutive time points to the time difference, and the calculation formula is: , where F(t) represents the thrust at the current time point, represents the thrust at the previous time point, Δt is the time interval, and the fluctuation amplitude ΔV of the running speed is calculated by the difference between the maximum and minimum speed in a certain time window. The calculation formula is: , where V represents all velocity values ​​in the time window, and the displacement change trend ΔS is calculated by fitting the change slope of the displacement data in the time window. The calculation formula is: , Si represents displacement data, ti represents the corresponding time, c and h are the mean values ​​of time and displacement respectively. Then, the interaction term between the thrust change rate and the speed fluctuation is calculated. The interaction term is obtained by multiplying the ΔF and ΔV obtained by the above calculation. Then, the above eigenvalue is substituted into the formula of the sagger pile blockage fault prediction model. The model performs weighted calculation on the eigenvalue according to the preset weight coefficients W1, W2, W3, W4 and the bias value b. After the weighted calculation, the activation function σ is used for nonlinear mapping. The activation function can use the sigmoid function. The specific formula is: The role of the activation function is to normalize the output value of the model to the range between 0 and 1 to represent the probability of the pile blockage risk. Finally, the calculated pile blockage risk assessment value R is output. If R is close to 1, it means that the pile blockage risk is high. If R is close to 0, it means that the pile blockage risk is low.

[0050] In one embodiment, if Figure 5 As shown, in step S30, the stack blocking risk assessment value is compared with a preset stack blocking risk threshold to obtain stack blocking risk status information, including: S301: The preset stack blockage risk thresholds include a low risk threshold, a high risk threshold and an intermediate risk range.

[0051] Specifically, the preset stack blockage risk threshold is determined by analyzing the historical operating data and stack blockage failure data of the push-plate kiln. The low risk threshold, high risk threshold and intermediate risk range are divided according to the distribution of the probability of stack blockage failure. The low risk threshold indicates that the operating state is at the upper limit of the safe range, and this value is determined by the maximum value of the risk assessment value when no stack blockage failure occurs in the statistical historical data; the high risk threshold indicates the lower limit of the operating state that is extremely prone to stack blockage failure, and this value is determined by the minimum risk assessment value when the stack blockage failure occurs in the statistical historical data; the intermediate risk range is defined as the interval between the low risk threshold and the high risk threshold, indicating that there is a certain possibility of stack blockage in the operating state but it does not constitute an immediate danger. The preset risk threshold is dynamically adjusted according to the probability distribution of stack blockage failure, and is stored in the equipment operation database for real-time call.

[0052] S302: Compare the stack congestion risk assessment value with the preset stack congestion risk threshold. When the stack congestion risk assessment value is less than the low risk threshold, the stack congestion risk status information is generated as low risk. If the low risk threshold is ≤ the stack congestion risk assessment value ≤ the high risk threshold, the stack congestion risk status information is generated as medium risk. If the stack congestion risk assessment value is greater than the high risk threshold, the stack congestion risk status information is generated as high risk.

[0053] Specifically, the risk level of the current push rod operation state is determined by comparing the calculated stack blockage risk assessment value with the preset low risk threshold and high risk threshold. The specific judgment process includes: first, retrieving the low risk threshold and the high risk threshold from the equipment operation database. The low risk threshold is used to indicate that the push rod operation state is within a safe range, and the high risk threshold is used to indicate that there is a great risk of stack blockage failure in the push rod operation state. Then, the stack blockage risk assessment value is compared with the low risk threshold. When the stack blockage risk assessment value is less than the low risk threshold, the generated risk state information is low risk. At this time, the push rod operation state is considered safe and no adjustment is required. If the stack blockage risk assessment value is greater than or equal to the low risk threshold and less than or equal to the high risk threshold, the generated risk state information is medium risk, indicating that the current operation state may have a potential risk of stack blockage, but does not constitute a serious risk. If the stack blockage risk assessment value is greater than the high risk threshold, the generated risk state information is high risk, indicating that there is a great possibility of stack blockage failure in the push rod operation state and adjustment measures need to be taken immediately.

[0054] In one embodiment, if Figure 6As shown, in step S302, that is, the stack blockage risk status information is medium risk, it also includes: S3021: If the stack blockage risk status information is medium risk, generate continuous observation operation status information.

[0055] Specifically, when the stack blockage risk status information is determined to be medium risk, the continuously observed operating status information is generated by analyzing the changing trends of the current push rod operating information and the stack blockage risk assessment value. The continuously observed operating status information includes a set observation time period, a sampling frequency, and the push rod operating parameters that are monitored. The observation time period is determined based on the changing cycle of the stack blockage risk under the medium risk state in the historical data, which is usually 5 to 30 seconds. The sampling frequency is set based on the dynamic operating characteristics of the push rod, which is usually 10 to 100 times per second. The push rod operating parameters that are monitored include thrust, speed, and displacement. The push rod operating parameters are continuously collected, the stack blockage risk assessment value is calculated in real time, and the risk status information is dynamically updated. The generated continuously observed operating status information is used for real-time monitoring of the push rod to ensure a rapid response to risk changes.

[0056] S3022: Based on the continuously observed operation status information, if the stack blockage risk assessment value decreases to a low risk during the continuous observation period, the original operation parameters of the push rod are restored.

[0057] Specifically, during the continuous observation period, the operating parameters of the push rod are collected in real time, and the stack blockage risk assessment value is dynamically calculated based on the collected parameters. If the calculated stack blockage risk assessment value is lower than the preset low risk threshold, it is considered that the operating state of the push rod has recovered to a safe range. At this time, a recovery operation instruction is generated to gradually restore the current adjusted operating parameters of the push rod to the original operating parameters. The specific recovery process includes gradually increasing the thrust or operating speed at fixed time intervals to get closer to the original operating parameters. During the recovery process, the operating status is monitored in real time to ensure that the recovery action does not cause new risks.

[0058] S3023: If the stack blockage risk assessment value rises to a high risk during the continuous observation period, a push rod operation parameter adjustment instruction is generated.

[0059] Specifically, during the continuous observation period, if the real-time calculated stack blockage risk assessment value exceeds the preset high-risk threshold, it is considered that there is a serious stack blockage risk in the push rod operation state. At this time, a push rod operation parameter adjustment instruction is generated. The adjustment instruction includes a target thrust value, a target speed value and an adjustment time. The target thrust value is generated by reducing the current thrust value. The target speed value is determined by dynamically adjusting the current operating speed. The adjustment time is set according to the stability requirements of the current operating state and is usually completed step by step within a few seconds to ensure the smoothness of the adjustment action. The generated adjustment instruction is sent to the push rod drive module through the control interface for real-time change of the push rod operation state.

[0060] In one embodiment, if Figure 7 As shown, in step S40, if the new stack blocking risk assessment value is less than the preset stack blocking risk threshold, the operation of the push rod is controlled according to the adjusted operation parameters, and further includes: S401: If the new stack blockage risk assessment value is greater than the preset stack blockage risk threshold, a further operating parameter optimization instruction is generated, and the operating state of the push rod is adjusted based on the further operating parameter optimization instruction to obtain re-optimized operating information, and the re-optimized operating information is input into the sagger stack blockage fault prediction model to obtain a re-adjusted stack blockage risk assessment value.

[0061] Specifically, when the new stack blockage risk assessment value exceeds the preset stack blockage risk threshold, further operating parameter optimization instructions are generated by dynamically comparing the current operating parameters of the push rod with the critical parameters of the stack blockage fault in the historical operating data. The optimization instructions include adjusting the target values ​​of thrust, speed and displacement and adjusting the execution time. The specific target value of thrust is generated by reducing the current thrust value by a certain proportion. The reduction proportion is dynamically adjusted according to the deviation of the risk assessment value. For example, the greater the amplitude of the risk value above the threshold, the higher the reduction proportion. The target value of speed is generated by reducing the current speed by a certain amplitude. The adjustment amplitude is set according to the operation smoothness requirement, usually 5% to 20%. The adjustment execution time is dynamically set according to the adjustment amplitude and the response characteristics of the equipment to ensure that the adjustment process is smooth and does not cause new abnormalities. After the optimization instruction is generated, the operating state of the push rod is adjusted in real time. The adjusted thrust, speed and displacement data are used as the re-optimized operating information. The information is input into the sagger stack blockage fault prediction model. The model recalculates the stack blockage risk assessment value based on the adjusted characteristic data. The change result of the assessment value is used for subsequent risk state judgment and further adjustment decisions.

[0062] S402: If the re-adjusted stack blockage risk assessment value is still greater than the preset stack blockage risk threshold, high-risk warning information is generated and sent to the operation terminal.

[0063] Specifically, when the pile blocking risk assessment value after re-adjustment is still higher than the preset pile blocking risk threshold, it is considered that the current push rod operation status has reached a high risk level and requires manual intervention by the operator. At this time, high-risk warning information is generated. The high-risk warning information includes the current push rod operation parameters, pile blocking risk assessment value and historical record data during the adjustment process, which is used to describe the abnormal status of the current equipment in detail; the generated warning information is sent to the operation terminal through the communication interface. After receiving the warning information, the operation terminal notifies the operator in various ways, including displaying risk prompts on the equipment control panel, sending visual signals through warning lights, and sending real-time notifications through mobile terminals, to ensure that the operator can understand the high-risk status in time and take necessary measures.

[0064] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0065] In one embodiment, a push plate kiln blockage fault prediction device is provided, and the push plate kiln blockage fault prediction device corresponds to the push plate kiln blockage fault prediction method in the above embodiment. Figure 8 As shown, the push plate kiln pile blockage fault prediction device includes a push rod operation information collection module, a pile blockage risk assessment module, a pile blockage risk state judgment module, a push rod operation parameter adjustment module, a dynamic adjustment and risk feedback module and an operation parameter maintenance module. The functional modules are described in detail as follows: A push rod operation information collection module is used to obtain the operation information of the push rod; A pile blocking risk assessment module is used to obtain a pile blocking risk assessment value by inputting the operation information of the push rod into the sagger pile blocking fault prediction model; A stack blocking risk status judgment module is used to compare the stack blocking risk assessment value with a preset stack blocking risk threshold to obtain stack blocking risk status information; A push rod operation parameter adjustment module is used to generate a push rod operation parameter adjustment instruction if the stack blocking risk status information is high risk; The dynamic adjustment and risk feedback module is used to adjust the operation state of the push rod in real time based on the push rod operation parameter adjustment instruction, obtain the adjusted operation information, input the adjusted operation information into the sagger pile blockage fault prediction model, and obtain a new pile blockage risk assessment value. If the new pile blockage risk assessment value is less than the preset pile blockage risk threshold, the operation of the push rod is controlled according to the adjusted operation parameters; The operating parameter maintaining module is used to maintain the original operating parameters of the push rod if the stack blocking risk status information is low risk.

[0066] Optionally, the stack blockage risk assessment module previously included: The historical operation information acquisition and preprocessing module is used to acquire the historical operation information of the push plate kiln, perform information preprocessing on the historical operation information of the push plate kiln, and obtain the preprocessed historical operation information; A training data set generation module is used to annotate the state information of the pile blockage failure according to the time series of the pre-processed historical operation information to form a training data set, input the training data set into the machine learning model, train the machine learning model, and obtain an initial sagger pile blockage failure prediction model; The model verification module is used to verify the initial sagger pile blockage fault prediction model through a cross-validation method. After successful verification, the sagger pile blockage fault prediction model is obtained.

[0067] Optional, stack blockage risk assessment module includes: The push rod operation feature extraction submodule is used to extract the feature of the push rod operation information and obtain the dynamic operation feature parameters of the push rod; The fault prediction calculation submodule is used for the sagger pile blockage fault prediction model to perform fault prediction calculation on the dynamic operation characteristic parameters of the push rod to obtain the pile blockage risk assessment value.

[0068] Optionally, the fault prediction calculation submodule includes: The formula application unit is used for the sagger pile blockage fault prediction model to calculate the pile blockage risk assessment value based on the following formula: , where R represents the risk assessment value of stack blockage, ΔF represents the instantaneous rate of change of the push rod thrust, ΔV represents the fluctuation amplitude of the push rod running speed, and ΔS represents the change trend of the push rod displacement. represents the interaction term between the thrust change rate and the speed fluctuation, W1 represents the weight coefficient of the instantaneous change rate of the thrust of the push rod, W2 represents the weight coefficient of the fluctuation amplitude of the push rod running speed, W3 represents the weight coefficient of the change trend of the push rod displacement, W4 represents the weight coefficient of the interaction term between the thrust change rate and the speed fluctuation, b represents the bias value, σ represents the nonlinear activation function, ΔF 2 It represents the influence of the square of the thrust change rate on the stack blockage failure. It represents capturing the nonlinear influence of running speed fluctuation, and log(1+|ΔS|) represents weakening the influence of displacement change on the sagger pile blockage fault prediction model.

[0069] Optionally, the stack blockage risk status judgment module includes: A pile blocking risk threshold setting submodule is used to preset pile blocking risk thresholds, including a low risk threshold, a high risk threshold and an intermediate risk range; The pile congestion risk status determination submodule is used to compare the pile congestion risk assessment value with the preset pile congestion risk threshold. When the pile congestion risk assessment value < low risk threshold, the pile congestion risk status information generated is low risk; if the low risk threshold ≤ pile congestion risk assessment value ≤ high risk threshold, the pile congestion risk status information generated is medium risk; if the pile congestion risk assessment value > high risk threshold, the pile congestion risk status information generated is high risk.

[0070] Optionally, the stack blockage risk state determination submodule includes: A continuous observation operation status generating unit, used for generating continuous observation operation status information if the stack blocking risk status information is medium risk; The push rod original operation parameter recovery unit is used to recover the original operation parameters of the push rod according to the continuous observation operation status information, if the stack blockage risk assessment value is reduced to a low risk during the continuous observation period; The push rod operation parameter adjustment instruction generating unit is used to generate a push rod operation parameter adjustment instruction if the stack blocking risk assessment value rises to a high risk during the continuous observation period.

[0071] Optionally, the push rod operation parameter adjustment module includes: An operating parameter optimization and re-evaluation submodule is used to generate a further operating parameter optimization instruction if the new stack blocking risk assessment value is greater than a preset stack blocking risk threshold, adjust the operating state of the push rod based on the further operating parameter optimization instruction, obtain re-optimized operating information, and input the re-optimized operating information into the sagger stack blocking fault prediction model to obtain a re-adjusted stack blocking risk assessment value; The high-risk warning information generation submodule is used to generate high-risk warning information if the re-adjusted pile blockage risk assessment value is still greater than the preset pile blockage risk threshold, and send the high-risk warning information to the operation terminal.

[0072] The specific definition of the push plate kiln blockage fault prediction device can be found in the definition of the push plate kiln blockage fault prediction method mentioned above, which will not be repeated here. Each module in the above push plate kiln blockage fault prediction device can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0073] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used for the device operation database. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for predicting a blockage fault of a push plate kiln is implemented.

[0074] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Get the operation information of the actuator; By inputting the operation information of the push rod into the sagger pile blockage fault prediction model, the pile blockage risk assessment value is obtained; Compare the stack blockage risk assessment value with a preset stack blockage risk threshold to obtain stack blockage risk status information; If the stack blocking risk status information is high risk, a push rod operation parameter adjustment instruction is generated; Based on the push rod operation parameter adjustment instruction, the operation state of the push rod is adjusted in real time to obtain the adjusted operation information, and the adjusted operation information is input into the sagger pile blockage fault prediction model to obtain a new pile blockage risk assessment value. If the new pile blockage risk assessment value is less than the preset pile blockage risk threshold, the operation of the push rod is controlled according to the adjusted operation parameters; If the stack blockage risk status information is low risk, the original operating parameters of the push rod are maintained.

[0075] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Get the operation information of the actuator; By inputting the operation information of the push rod into the sagger pile blockage fault prediction model, the pile blockage risk assessment value is obtained; Compare the stack blockage risk assessment value with a preset stack blockage risk threshold to obtain stack blockage risk status information; If the stack blocking risk status information is high risk, a push rod operation parameter adjustment instruction is generated; Based on the push rod operation parameter adjustment instruction, the operation state of the push rod is adjusted in real time to obtain the adjusted operation information, and the adjusted operation information is input into the sagger pile blockage fault prediction model to obtain a new pile blockage risk assessment value. If the new pile blockage risk assessment value is less than the preset pile blockage risk threshold, the operation of the push rod is controlled according to the adjusted operation parameters; If the stack blockage risk status information is low risk, the original operating parameters of the push rod are maintained.

[0076] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0077] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0078] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for predicting blockage failure of a push plate kiln, characterized in that: The push plate kiln blockage fault prediction method comprises: Get the operation information of the actuator; By inputting the operation information of the push rod into the sagger pile blockage fault prediction model, a pile blockage risk assessment value is obtained; Comparing the stack blockage risk assessment value with a preset stack blockage risk threshold to obtain stack blockage risk status information; If the stack blocking risk status information is high risk, generating a push rod operation parameter adjustment instruction; Based on the push rod operation parameter adjustment instruction, the operation state of the push rod is adjusted in real time to obtain adjusted operation information, and the adjusted operation information is input into the sagger pile blockage fault prediction model to obtain a new pile blockage risk assessment value, and if the new pile blockage risk assessment value is less than the preset pile blockage risk threshold, the operation of the push rod is controlled according to the adjusted operation parameters; If the stack blocking risk status information is low risk, the original operating parameters of the push rod are maintained.

2. The method for predicting blockage failure of a push plate kiln according to claim 1 is characterized in that: The sagger pile blockage fault prediction model previously includes: Acquire historical operation information of a push plate kiln, and perform information preprocessing on the historical operation information of the push plate kiln to obtain the preprocessed historical operation information; The pre-processed historical operation information is labeled with state information of the occurrence of stack blockage faults according to the time series to form a training data set, and the training data set is input into a machine learning model to train the machine learning model to obtain an initial sagger stack blockage fault prediction model; The initial sagger pile blockage fault prediction model is verified by a cross-validation method, and after successful verification, the sagger pile blockage fault prediction model is obtained.

3. The method for predicting blockage failure of a push plate kiln according to claim 1, characterized in that: The method of obtaining a pile blockage risk assessment value by inputting the operation information of the push rod into the sagger pile blockage fault prediction model comprises: Extracting features of the operation information of the push rod to obtain dynamic operation feature parameters of the push rod; The sagger blockage fault prediction model performs fault prediction calculation on the push rod dynamic operation characteristic parameters to obtain the blockage risk assessment value.

4. The method for predicting blockage failure of a push plate kiln according to claim 3 is characterized in that: The sagger pile blockage fault prediction model performs fault prediction calculation on the push rod dynamic operation characteristic parameters to obtain the pile blockage risk assessment value, including: The sagger pile blockage failure prediction model calculates the pile blockage risk assessment value based on the following formula: , wherein R represents the stack blockage risk assessment value, ΔF represents the instantaneous rate of change of the push rod thrust, ΔV represents the fluctuation amplitude of the push rod running speed, ΔS represents the change trend of the push rod displacement, and represents the interaction term between the thrust change rate and the speed fluctuation, W1 represents the weight coefficient of the instantaneous change rate of the push rod thrust, W2 represents the weight coefficient of the fluctuation amplitude of the push rod running speed, W3 represents the weight coefficient of the change trend of the push rod displacement, W4 represents the weight coefficient of the interaction term between the thrust change rate and the speed fluctuation, b represents the bias value, σ represents the nonlinear activation function, ΔF 2 represents the influence of the square of the thrust change rate on the stack blockage failure, It represents capturing the nonlinear influence of running speed fluctuation, and the log(1+|ΔS|) represents the influence on the sagger pile blockage fault prediction model when the displacement change is weakened.

5. The method for predicting blockage failure of a push plate kiln according to claim 1, characterized in that: The step of comparing the stack blockage risk assessment value with a preset stack blockage risk threshold to obtain stack blockage risk status information includes: The preset stack blockage risk threshold includes a low risk threshold, a high risk threshold and an intermediate risk range; The stack congestion risk assessment value is compared with a preset stack congestion risk threshold; when the stack congestion risk assessment value is < the low risk threshold, the stack congestion risk status information is generated as the low risk; if the low risk threshold is ≤ the stack congestion risk assessment value ≤ the high risk threshold, the stack congestion risk status information is generated as the medium risk; if the stack congestion risk assessment value is > the high risk threshold, the stack congestion risk status information is generated as the high risk.

6. The method for predicting blockage failure of a push plate kiln according to claim 5, characterized in that: The stack blockage risk status information is medium risk, and further includes: If the stack blockage risk status information is the medium risk, generating continuous observation operation status information; According to the continuously observed operation status information, if the stack blockage risk assessment value decreases to the low risk during the continuous observation period, restoring the original operation parameters of the push rod; If the stack blocking risk assessment value rises to the high risk during the continuous observation period, the push rod operation parameter adjustment instruction is generated.

7. The method for predicting blockage failure of a push plate kiln according to claim 1, characterized in that: If the new stack blocking risk assessment value is less than the preset stack blocking risk threshold, controlling the operation of the push rod according to the adjusted operation parameters, further comprising: If the new stack blocking risk assessment value is greater than the preset stack blocking risk threshold, a further operation parameter optimization instruction is generated, and the operation state of the push rod is adjusted based on the further operation parameter optimization instruction to obtain re-optimized operation information, and the re-optimized operation information is input into the sagger stack blocking fault prediction model to obtain a re-adjusted stack blocking risk assessment value; If the re-adjusted stack blockage risk assessment value is still greater than the preset stack blockage risk threshold, high-risk warning information is generated and sent to the operation terminal.

8. A device for predicting blockage failure of a push plate kiln, characterized in that: The push plate kiln blockage fault prediction device comprises: A push rod operation information collection module is used to obtain the operation information of the push rod; A pile blocking risk assessment module, used for obtaining a pile blocking risk assessment value by inputting the operation information of the push rod into a sagger pile blocking fault prediction model; A stack blocking risk state judgment module, used for comparing the stack blocking risk assessment value with a preset stack blocking risk threshold to obtain stack blocking risk state information; A push rod operation parameter adjustment module, used for generating a push rod operation parameter adjustment instruction if the stack blocking risk status information is high risk; A dynamic adjustment and risk feedback module, which is used to adjust the operation state of the push rod in real time based on the push rod operation parameter adjustment instruction, obtain the adjusted operation information, input the adjusted operation information into the sagger pile blockage fault prediction model, obtain a new pile blockage risk assessment value, and if the new pile blockage risk assessment value is less than the preset pile blockage risk threshold, control the operation of the push rod according to the adjusted operation parameters; The operating parameter maintaining module is used to maintain the original operating parameters of the push rod if the stack blocking risk status information is low risk.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the push plate kiln blockage fault prediction method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for predicting blockage failure of a push-plate kiln as claimed in any one of claims 1 to 7 are implemented.

Images