Push Plate Kiln Stacking Blockage Fault Prediction Method, Device, Computer Equipment and Medium

Abstract

The present invention relates to the technical field of fault prediction of pusher kilns. Specifically, it relates to a method, device, computer equipment and medium for predicting the blockage fault of a pusher kiln. The method includes inputting the operation information of the pusher rod into the sagger blockage fault prediction model to obtain a blockage risk assessment value, comparing the blockage risk assessment value with a preset blockage risk threshold to obtain blockage risk status information. If the blockage risk status information is high risk, a pusher rod operation parameter adjustment instruction is generated. Based on the pusher rod operation parameter adjustment instruction, the adjusted operation information is obtained, and the adjusted operation information is input into the sagger blockage fault prediction model to obtain a new blockage risk assessment value. If the new blockage risk assessment value is less than the preset blockage risk threshold, the operation of the pusher rod is controlled according to the adjusted operation parameters. If the blockage risk status information is low risk, the original operation parameters of the pusher rod are maintained. The present invention has the effect of improving the operation stability of the pusher kiln.

Description

Technical Field

[0001] The present invention relates to the technical field of fault prediction of pusher kilns, and particularly to a method, device, computer equipment and medium for predicting the stacking blockage fault of a pusher kiln. Background Art

[0002] As an important heat treatment equipment in industrial production, pusher kilns are commonly used for the sintering or high-temperature treatment of ceramics, glass and metal materials. However, during the operation of pusher kilns, the problem of stacking blockage faults of saggers often occurs. The stacking blockage fault refers to the problem that due to abnormal fluctuations in mechanical parameters (such as abnormal changes in thrust, speed or displacement) during the operation of the pusher rod, the saggers are stacked and blocked at a certain position in the kiln, which in turn leads to the accumulation of materials inside the kiln body or the interruption of equipment operation. Summary of the Invention

[0003] In order to improve the operation stability of pusher kilns, the present application provides a method, device, computer equipment and medium for predicting the stacking blockage fault of a pusher kiln.

[0004] The first invention object of the present application is achieved through the following technical solutions:

[0005] A method for predicting the stacking blockage fault of a pusher kiln, the method for predicting the stacking blockage fault of a pusher kiln includes:

[0006] Obtain the operation information of the pusher rod;

[0007] By inputting the operation information of the pusher rod into the sagger stacking blockage fault prediction model, obtain the stacking blockage risk assessment value;

[0008] Compare the stacking blockage risk assessment value with a preset stacking blockage risk threshold to obtain the stacking blockage risk status information;

[0009] If the stacking blockage risk status information is high risk, generate a pusher rod operation parameter adjustment instruction;

[0010] Based on the pusher rod operation parameter adjustment instruction, adjust the operation state of the pusher rod in real time to obtain the adjusted operation information, input the adjusted operation information into the sagger stacking blockage fault prediction model to obtain a new stacking blockage risk assessment value, if the new stacking blockage risk assessment value is less than the preset stacking blockage risk threshold, control the operation of the pusher rod according to the adjusted operation parameters;

[0011] If the stacking blockage risk status information is low risk, maintain the original operation parameters of the pusher rod.

[0012] By adopting the above technical solution, through the real-time analysis and risk assessment of the pusher operation information by the sagger stacking blockage fault prediction model, abnormal operation conditions that may lead to stacking blockage faults can be detected in advance, so as to timely take targeted adjustment measures and effectively prevent the occurrence of stacking blockage faults. When the stacking blockage risk assessment value exceeds the threshold, an operation parameter adjustment instruction is generated in a timely manner and the pusher operation state is dynamically optimized, which can quickly relieve the stacking blockage risk, avoid equipment shutdown or production line interruption caused by stacking blockage faults, and ensure the continuity of production. Stacking blockage faults often cause great mechanical impact and load pressure on the pusher and related equipment. By dynamically adjusting the pusher operation parameters to reduce the stacking blockage risk, the mechanical loss and unnecessary operation 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 pusher operates within a reasonable range, the operation fluctuations caused by the stacking blockage risk are eliminated, and the stability and reliability of the equipment operation are improved.

[0013] In a preferred example of the present application, it can be further configured that: the sagger stacking blockage fault prediction model previously includes:

[0014] Obtain the historical operation information of the pusher kiln, perform information preprocessing on the historical operation information of the pusher kiln, and obtain the preprocessed historical operation information;

[0015] Label the state information of the occurrence of stacking blockage faults for the preprocessed historical operation information according to the time series, form a training data set, input the training data set into a machine learning model, and train the machine learning model to obtain an initial sagger stacking blockage fault prediction model;

[0016] Verify the initial sagger stacking blockage fault prediction model by the cross-validation method. After successful verification, obtain the sagger stacking blockage fault prediction model.

[0017] By adopting the above technical solution, by obtaining the historical operation information of the pusher kiln and performing information preprocessing, after removing noise data and abnormal data, higher-quality training data is generated, so as to ensure the accuracy of the input data of the model and improve the accuracy of fault prediction. Using a machine learning model to train the preprocessed historical operation data, label the state information of the occurrence of stacking blockage faults according to the time series, capture the correlation between the pusher operation state and the stacking blockage fault, and the generated prediction model can automatically identify the stacking blockage risk without relying on manual experience judgment, improving the prediction efficiency. Verify the initial sagger stacking blockage fault prediction model by the 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.

[0018] In a preferred example, the present application can be further configured as follows: by inputting the operation information of the push rod into the sagger stack blockage fault prediction model, a stack blockage risk assessment value is obtained, including:

[0019] Feature extraction is performed on the operation information of the push rod to obtain dynamic operation characteristic parameters of the push rod;

[0020] The sagger stack blockage fault prediction model performs fault prediction calculations on the dynamic operation characteristic parameters of the push rod to obtain the stack blockage risk assessment value.

[0021] By adopting the above technical solution, by extracting the dynamic operation characteristics of the push rod and combining with the sagger stack blockage fault prediction model for analysis and calculation, accurate quantification and efficient prediction of the stack blockage risk can be achieved. It not only improves the early warning ability of the stack blockage fault, but also provides a scientific basis for subsequent operation adjustment and optimization, effectively ensuring the safe and stable operation of the equipment and reducing the economic losses and production risks caused by the stack blockage fault.

[0022] In a preferred example, the present application can be further configured as follows: the sagger stack blockage fault prediction model performs fault prediction calculations on the dynamic operation characteristic parameters of the push rod to obtain the stack blockage risk assessment value, including:

[0023] The sagger stack blockage fault prediction model calculates the stack blockage risk assessment value based on the following formula:

[0024] , where, R represents the stack blockage risk assessment value, ΔF represents the instantaneous change rate of the push rod thrust, ΔV represents the fluctuation amplitude of the push rod operation speed, ΔS represents the change trend of the push rod displacement, the 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 operation 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 non-linear activation function, ΔF 2 represents the influence of the square of the thrust change rate on the stack blockage fault, the represents capturing the non-linear influence of the operation speed fluctuation, and log(1 + ∣ΔS∣) represents weakening the influence on the sagger stack blockage fault prediction model when the displacement changes.

[0025] By adopting the above technical solution, the clogging risk assessment value is calculated based on a formula through the clogging fault prediction model of the sagger stack. By comprehensively considering the instantaneous change rate of the pusher thrust, the fluctuation range of the running speed, the displacement change trend and their interaction relationships, and using weighted analysis and non-linear activation functions to comprehensively quantify the influencing factors, the size of the clogging risk can be accurately evaluated, and an intuitive risk value can be provided.

[0026] In a preferred example of the present application, it can be further configured that: comparing the clogging risk assessment value with a preset clogging risk threshold to obtain clogging risk status information, including:

[0027] The preset clogging risk threshold includes a low risk threshold, a high risk threshold and an intermediate risk range;

[0028] When comparing the clogging risk assessment value with the preset clogging risk threshold, if the clogging risk assessment value < the low risk threshold, the generated clogging risk status information is the low risk. If the low risk threshold ≤ the clogging risk assessment value ≤ the high risk threshold, the generated clogging risk status information is the medium risk. If the clogging risk assessment value > the high risk threshold, the generated clogging risk status information is the high risk.

[0029] By adopting the above technical solution, by setting a low risk threshold, a high risk threshold and an intermediate risk range, and comparing the clogging risk assessment value with these thresholds, the clogging risk can be accurately classified (low risk, medium risk and high risk), so as to formulate targeted countermeasures for different risk levels, ensuring the scientificity and efficiency of processing. According to the classification of the clogging risk status information, keep the original operating parameters of the equipment in the low risk state, continuously observe the operating state in the medium risk state, and timely adjust the operating parameters or send out warning information in the high risk state, realizing the dynamic and refined management of the equipment operating state, reducing unnecessary operations, and improving the equipment operating efficiency.

[0030] In a preferred example of the present application, it can be further configured that: when the clogging risk status information is the medium risk, it further includes:

[0031] If the clogging risk status information is the medium risk, generate information for continuously observing the operating state;

[0032] According to the information for continuously observing the operating state, if the clogging risk assessment value drops to the low risk during the continuous observation period, restore the original operating parameters of the pusher;

[0033] If the clogging risk assessment value rises to the high risk during the continuous observation period, generate an instruction for adjusting the operating parameters of the pusher.

[0034] By adopting the above technical solution, generating continuous observation of the operating state information when the risk state information of the heap blockage is medium risk can monitor the operating state of the push rod in real time, dynamically grasp the change trend of the heap blockage risk assessment value, ensure accurate assessment of the risk state during dynamic changes, and provide a more reliable basis for subsequent adjustments. In the medium risk state, by continuously observing the change of the heap blockage risk assessment value, immediately taking adjustment measures is avoided, unnecessary modification of operating parameters is reduced, interference with equipment operation is lowered, and the stability and efficiency of equipment operation are ensured. If the heap blockage risk assessment value drops to low risk during continuous observation, by restoring the original operating parameters of the push rod, the equipment operation is restored to the optimal state, resource waste is avoided, and at the same time, the equipment operation efficiency and economy are improved. If the heap blockage risk assessment value rises to high risk during continuous observation, an adjustment instruction for the push rod operating parameters can be quickly generated. By dynamically optimizing the operating parameters, the high risk state can be relieved in time, the occurrence of heap blockage faults can be avoided, and equipment damage or production interruption caused by heap blockage can be reduced.

[0035] In a preferred example of the present application, it can be further configured that: if the new heap blockage risk assessment value is less than the preset heap blockage risk threshold, the operation of the push rod is controlled according to the adjusted operating parameters, and it further includes:

[0036] If the new heap blockage risk assessment value is greater than the preset heap blockage risk threshold, a further operating parameter optimization instruction is generated, the operating state of the push rod is adjusted based on the further operating parameter optimization instruction, the re-optimized operating information is obtained, and the re-optimized operating information is input into the sagger heap blockage fault prediction model to obtain the re-adjusted heap blockage risk assessment value;

[0037] If the re-adjusted heap blockage risk assessment value is still greater than the preset heap blockage risk threshold, a high risk warning information is generated and the high risk warning information is sent to the operation terminal.

[0038] By adopting the above technical solution, when the new heap blockage risk assessment value is greater than the preset heap blockage risk threshold, by generating a further operating parameter optimization instruction and adjusting the operating state of the push rod based on the optimization instruction, accurate control of the high risk state is achieved, and it is ensured that the heap blockage risk is effectively relieved in the initial stage. The adjusted operating information is input into the sagger heap blockage fault prediction model again for calculation, forming a closed-loop control process from risk assessment to adjustment and optimization to re-assessment, ensuring that the effect of each adjustment can be verified in real time. If the re-adjusted heap blockage risk assessment value is still greater than the preset heap blockage risk threshold, a high risk warning information will be automatically generated and sent to the operation terminal, which can quickly notify the operator to intervene and prevent the heap blockage risk from further escalating into a serious fault, ensuring the safety of equipment operation.

[0039] The second above-mentioned invention object of the present application is achieved by the following technical solutions:

[0040] A prediction device for the blockage fault of a pusher kiln, the prediction device for the blockage fault of the pusher kiln includes:

[0041] A pusher operation information acquisition module, configured to obtain the operation information of the pusher;

[0042] A blockage risk assessment module, configured to input the operation information of the pusher into a sagger blockage fault prediction model to obtain a blockage risk assessment value;

[0043] A blockage risk state judgment module, configured to compare the blockage risk assessment value with a preset blockage risk threshold to obtain blockage risk state information;

[0044] A pusher operation parameter adjustment module, configured to generate a pusher operation parameter adjustment instruction if the blockage risk state information is a high risk;

[0045] A dynamic adjustment and risk feedback module, configured to based on the pusher operation parameter adjustment instruction, adjust the operation state of the pusher in real time to obtain adjusted operation information, input the adjusted operation information into the sagger blockage fault prediction model to obtain a new blockage risk assessment value, and if the new blockage risk assessment value is less than the preset blockage risk threshold, control the operation of the pusher according to the adjusted operation parameters;

[0046] An operation parameter maintenance module, configured to maintain the original operation parameters of the pusher if the blockage risk state information is a low risk.

[0047] By adopting the above technical solutions, through the real-time analysis and risk assessment of the pusher operation information by the sagger blockage fault prediction model, it is possible to discover in advance the abnormal operation conditions that may lead to blockage faults, thereby timely taking targeted adjustment measures to effectively prevent the occurrence of blockage faults. When the blockage risk assessment value exceeds the threshold, a pusher operation parameter adjustment instruction is generated in a timely manner and the pusher operation state is dynamically optimized, which can quickly relieve the blockage risk, avoid equipment shutdown or production line interruption caused by blockage faults, and ensure the continuity of production. Blockage faults often cause great mechanical impact and load pressure on the pusher and related equipment. By dynamically adjusting the pusher operation parameters to reduce the blockage risk, the mechanical loss of the equipment and unnecessary operation 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, it is ensured that the pusher operates within a reasonable range, eliminating the operation fluctuations caused by the blockage risk, and improving the stability and reliability of the equipment operation.

[0048] The third above-mentioned object of the present application is achieved by the following technical solutions:

[0049] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned pusher kiln blockage fault prediction method are implemented.

[0050] The above object four of the present application is achieved through the following technical solutions:

[0051] A computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the steps of the above-mentioned pusher kiln blockage fault prediction method are implemented.

[0052] In summary, the present application includes at least one of the following beneficial technical effects:

[0053] 1. Through the real-time analysis and risk assessment of the pusher operation information by the sagger blockage fault prediction model, abnormal operation conditions that may lead to blockage faults can be detected in advance, so that targeted adjustment measures can be taken in a timely manner to effectively prevent the occurrence of blockage faults. When the blockage risk assessment value exceeds the threshold, an operation parameter adjustment instruction is generated in a timely manner and the pusher operation state is dynamically optimized, which can quickly relieve the blockage risk, avoid equipment shutdown or production line interruption caused by blockage faults, and ensure the continuity of production. Blockage faults often cause great mechanical impact and load pressure on the pusher and related equipment. By dynamically adjusting the pusher operation parameters to reduce the blockage risk, the mechanical loss and unnecessary operation 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 pusher operates within a reasonable range, the operation fluctuations caused by the blockage risk are eliminated, and the stability and reliability of the equipment operation are improved;

[0054] 2. By calculating the blockage risk assessment value based on the formula by the sagger blockage fault prediction model, comprehensively considering the instantaneous change rate of the pusher thrust, the fluctuation range of the operation speed, the displacement change trend and their interaction relationship, and using weighted analysis and non-linear activation function to comprehensively quantify the influencing factors, the size of the blockage risk can be accurately evaluated and an intuitive risk value can be provided;

[0055] 3. When the risk status information of the heap blockage is medium risk, generate continuous observation of the operating status information, which can monitor the operating status of the push rod in real time, dynamically master the change trend of the heap blockage risk assessment value, ensure accurate assessment of the risk status during dynamic changes, and provide a more reliable basis for subsequent adjustments. In the medium-risk state, by continuously observing the change of the heap blockage risk assessment value, avoid immediately taking adjustment measures, reduce unnecessary modification of operating parameters, reduce interference to the equipment operation, and ensure the stability and efficiency of the equipment operation. If the heap blockage risk assessment value drops to low risk during continuous observation, restore the original operating parameters of the push rod to make the equipment operation return to the optimal state, avoid waste of resources, and improve the equipment operation efficiency and economy at the same time. If the heap blockage risk assessment value rises to high risk during continuous observation, it can quickly generate an adjustment instruction for the push rod operating parameters, and relieve the high-risk state in time by dynamically optimizing the operating parameters, avoid the occurrence of heap blockage faults, and reduce equipment damage or production interruption caused by heap blockage. Description of the Drawings

[0056] Figure 1 is a flowchart of a method for predicting heap blockage faults in a pusher kiln according to an embodiment of the present application;

[0057] Figure 2 is a flowchart of the implementation before step S20 in the method for predicting heap blockage faults in a pusher kiln according to an embodiment of the present application;

[0058] Figure 3 is a flowchart of the implementation in step S20 in the method for predicting heap blockage faults in a pusher kiln according to an embodiment of the present application;

[0059] Figure 4 is a flowchart of the implementation in step S202 in the method for predicting heap blockage faults in a pusher kiln according to an embodiment of the present application;

[0060] Figure 5 is a flowchart of the implementation in step S30 in the method for predicting heap blockage faults in a pusher kiln according to an embodiment of the present application;

[0061] Figure 6 is a flowchart of the implementation in step S302 in the method for predicting heap blockage faults in a pusher kiln according to an embodiment of the present application;

[0062] Figure 7 is a flowchart of the implementation in step S40 in the method for predicting heap blockage faults in a pusher kiln according to an embodiment of the present application;

[0063] Figure 8 is a principle block diagram of a device for predicting heap blockage faults in a pusher kiln according to an embodiment of the present application;

[0064] Figure 9 is a schematic diagram of the equipment according to an embodiment of the present application. Detailed Embodiments

[0065] The present application will be further described in detail below with reference to the accompanying drawings.

[0066] In one embodiment, as Figure 1 shown, the present application discloses a method for predicting the stacking and blocking faults of a pusher kiln, which specifically includes the following steps:

[0067] S10: Obtain the operation information of the pusher rod.

[0068] Specifically, by installing high-precision sensors on the pusher rod, the operation information of the pusher rod is collected in real time. The sensors include a pressure sensor, a displacement sensor, and a speed sensor. The pressure sensor is used to monitor the force on the pusher rod, the displacement sensor is used to obtain the moving distance of the pusher rod, and the speed sensor obtains the running speed of the pusher rod by calculating the change of displacement per unit time. The information sampling frequency of the sensors is set to 1 millisecond to 10 milliseconds. After converting the analog signal into a digital signal, it is transmitted to the information processing module. The information processing module performs noise filtering and signal amplification processing on the collected signals, and obtains the real-time operation information of the pusher rod after removing the sampling error, including the instantaneous value of the thrust, the change trend of the running speed, and the cumulative value of the displacement, etc.

[0069] S20: By inputting the operation information of the pusher rod into the stacking and blocking fault prediction model of the sagger, obtain the stacking and blocking risk assessment value.

[0070] Specifically, the collected operation information of the pusher rod is cut into multiple time segments at fixed time intervals, and each time segment is used as an independent sample and input into the stacking and blocking fault prediction model of the sagger. The model calculates through the previously trained parameters. First, the input sample data is preprocessed, including normalizing the operation information, scaling the thrust, speed, and displacement parameters to the range between 0 and 1, ensuring that the eigenvalue of different data dimensions is in the same order of magnitude, and avoiding calculation deviation. Then, the model uses the time series analysis method to extract features from the input multiple time segments. Feature extraction includes fitting the change trend of the thrust, statistically analyzing the speed fluctuation, and calculating the increment of the cumulative displacement value. Finally, the extracted features are processed by the weight weighting and nonlinear activation of the multi-layer calculation unit of the model. The output layer of the model generates the stacking and blocking risk assessment value, and the stacking and blocking risk assessment value is a numerical value between 0 and 1, which is used to represent the size of the stacking and blocking risk.

[0071] S30: Compare the stacking and blocking risk assessment value with the preset stacking and blocking risk threshold to obtain the stacking and blocking risk status information.

[0072] Specifically, compare the calculated heap blockage risk assessment value with a preset heap blockage risk threshold. The comparison process includes loading the heap blockage risk threshold from the database. The threshold is statistically obtained based on historical operation data and the results of multiple heap blockage failure experiments and is set as a safety critical value within a fixed range. Determine the risk status by calculating the difference between the heap blockage risk assessment value and the threshold. If the difference is greater than 0, it indicates that the assessment value exceeds the safety threshold range, and high-risk status information is generated. If the difference is less than or equal to 0, it indicates that the assessment value is within the safety threshold range, and low-risk status information is generated.

[0073] S40: If the heap blockage risk status information is high risk, generate a push rod operation parameter adjustment instruction.

[0074] Specifically, after determining that the heap blockage risk status is high risk, generate a push rod operation parameter adjustment instruction based on the current operation parameters. The generation of the adjustment instruction includes calculating the adjustment range according to historical operation experience and the current parameters. Among them, 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 during heap blockage in historical data. The calculation method is to compare the current operation parameters with the parameters of similar working conditions in historical data, and extract the minimum safe operation parameters related to the occurrence of heap 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 operation parameters of the push rod, thereby reducing the heap blockage risk.

[0075] Furthermore, the generation of the push rod operation parameter adjustment instruction is based on the heap blockage risk assessment value R and the push rod operation information collected in real time. The generation of the instruction includes the following steps: First, calculate the deviation between the current operation parameters and the historical safe operation parameters according to the thrust, running speed, and displacement data collected in real time. The deviation value of the thrust is calculated by the following formula: , and the deviation value of the speed is calculated by the following formula: , where F current represents the current thrust, F safe represents the average safe thrust statistically obtained from historical failure data, V current represents the current running speed, V safe represents the average safe speed statistically obtained from historical data. Then, according to the heap blockage risk assessment value R and the deviation value, calculate the target thrust value and the target speed value. The target thrust value is determined by the following formula: , and the target speed value is calculated by the following formula: , where α represents the thrust adjustment coefficient, which is usually set according to historical data analysis and ranges from 0.5 to 0.9, and β represents the speed adjustment ratio coefficient, whose usual value range is from 0.2 to 0.6, and the adjustment range increases with the increase of the heap blockage risk assessment value R, so that the adjustment is targeted; then, calculate the adjustment execution time, and the adjustment execution time is calculated by the following formula: , where Ta djust represents the adjustment execution time, and T baseline represents the reference adjustment time, usually 3 seconds to 5 seconds, which is dynamically adjusted by 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, generate an operation parameter adjustment instruction, format the instruction into an instruction sequence, including the thrust target value, speed target value and adjustment time parameter, and send the instruction to the push rod drive module to adjust the operation state of the push rod.

[0076] S50: Based on the push rod operation parameter adjustment instruction, adjust the operation state of the push rod in real time to obtain the adjusted operation information, input the adjusted operation information into the sagger heap blockage fault prediction model to obtain a new heap blockage risk assessment value. If the new heap blockage risk assessment value is less than the preset heap blockage risk threshold, control the operation of the push rod according to the adjusted operation parameters.

[0077] Specifically, adjust the operation state of the push rod in real time according to the generated push rod operation parameter adjustment instruction. The adjusted operation state includes reducing the thrust and speed of the push rod and maintaining the continuity of the displacement. Collect the adjusted operation information in real time. The adjusted operation information includes updated thrust, speed and displacement parameters. Re-input the adjusted operation information into the sagger heap blockage fault prediction model. The model recalculates the heap blockage risk assessment value based on the adjusted information. If the new assessment value is lower than the preset risk threshold, it is considered that the adjustment is effective, maintain the adjusted parameters and continue to control the operation of the push rod in real time, record the adjusted operation parameters and heap blockage risk assessment value, and continuously monitor the push rod state to ensure the stability of the adjusted operation.

[0078] S60: If the heap blockage risk state information is low risk, maintain the original operation parameters of the push rod.

[0079] Specifically, when the risk status of heap blockage is judged to be low risk, the current operating parameters of the push rod are directly used to control the push rod without further adjustment. The operating parameters include the thrust, speed, displacement value, etc. 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 every fixed time. The operating parameters in the low-risk state are used as a reference benchmark to participate in subsequent parameter optimization and working condition analysis, maintaining the stability and continuity of operation and avoiding unnecessary adjustment actions from affecting the equipment efficiency.

[0080] In one embodiment, as Figure 2 shown, before step S20, that is, before the sagger heap blockage fault prediction model, it includes:

[0081] S11: Obtain the historical operation information of the pusher kiln, and perform information preprocessing on the historical operation information of the pusher kiln to obtain the preprocessed historical operation information.

[0082] Specifically, the obtained historical operation information includes the operating parameters of the push rod, the occurrence time of the heap blockage fault, and the operation state data before and after the heap blockage fault. The operating parameters of the push rod include thrust, operating speed, and displacement. The occurrence time of the heap blockage fault is obtained through the operation log record, and the operation state data before and after the occurrence of the heap blockage fault is determined by segment annotation of the historical operation data. When preprocessing the historical operation information, first fill in the missing values in the historical operation data. The filling method uses the interpolation method. Among them, 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 in the categorical data. Secondly, process the outliers. Detect the outliers in the operating parameters through the three-standard-deviation method, and the detected outliers are corrected by replacing them with the median. Finally, perform normalization processing on numerical data such as thrust, speed, and displacement, and map the data to the range between 0 and 1 to reduce the influence of numerical magnitude differences on model training.

[0083] S12: Mark the state information of the occurrence of the heap blockage fault in the preprocessed historical operation information according to the time series to form a training data set, and input the training data set into the machine learning model to train the machine learning model to obtain an initial sagger heap blockage fault prediction model.

[0084] Specifically, the preprocessed historical operation information is sliced according to the time series. Each time slice consists of a time window with a fixed length. The operation parameters within the time window include thrust, speed, and displacement data, and the status information is marked in combination with the time when the heap blockage fault occurs. The status information of the heap blockage fault includes heap blockage occurrence (marked as 1) and no heap blockage occurrence (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, where the training set accounts for 70%-80% of the total data volume, and the validation set accounts for 20%-30%. Then, the training set is input into the machine learning model, and algorithms such as deep neural network, support vector machine, or random forest are used for training. The training process includes iterative optimization of model parameters (such as weights and biases). The optimization method uses the gradient descent algorithm, where the loss function is the cross-entropy loss function, which is used to measure the deviation between the model prediction result and the true label. The model parameters are updated by minimizing the loss function, and finally, the initial sagger heap blockage fault prediction model is obtained.

[0085] S13: Verify the initial sagger heap blockage fault prediction model through the cross-validation method. After successful verification, the sagger heap blockage fault prediction model is obtained.

[0086] Specifically, verify the initial sagger heap blockage fault prediction model through the cross-validation method. Use the K-fold cross-validation method to divide the validation set into K subsets, where one subset is used as the validation set, and the remaining K - 1 subsets are used as the training set. The model is trained using K - 1 subsets in each fold and the performance metrics of the model are calculated on the remaining validation subset. The performance metrics include accuracy, recall rate, and F1 score. The overall performance of the model is evaluated by taking the average of the performance metrics of all folds. During the verification process, if the performance metrics all reach the set thresholds, such as the accuracy is greater than 90%, the recall rate is greater than 85%, and the F1 score is greater than 88%, then the model is considered to be successfully verified, and the verified model is used as the final sagger heap blockage fault prediction model. If the performance metrics do not reach the set thresholds, then the model structure or training parameters need to be adjusted, such as increasing the number of layers of the neural network, adjusting the learning rate, or changing the optimization algorithm, and then the model is retrained and verified again until the model is successfully verified.

[0087] In one embodiment, as Figure 3 shown, in step S20, that is, by inputting the operation information of the push rod into the sagger heap blockage fault prediction model, the heap blockage risk assessment value is obtained, including:

[0088] S201: Extract features from the operation information of the push rod to obtain the dynamic operation characteristic parameters of the push rod.

[0089] Specifically, first, analyze the change in the thrust of the push rod. By continuously comparing the collected thrust data, extract the change trend of the thrust between adjacent time points to obtain the instantaneous change rate of the thrust. This feature reflects the rapid fluctuation of the thrust over time. Second, analyze the stability of the running speed of the push rod. By selecting the speed data within a fixed time period, calculate the fluctuation amplitude of the speed within the time period. The size of the speed fluctuation amplitude is used to reflect the stability of the running speed of the push rod. The larger the fluctuation amplitude, the higher the instability of the running speed. Then, extract the change trend of the displacement of the push rod. By fitting the overall change direction of the displacement data at fixed time intervals, obtain the trend of the displacement changing with time. This feature is used to describe the continuity of the displacement during the operation of the push rod. Finally, combine the above-extracted features, including the instantaneous change rate of the thrust, the fluctuation amplitude of the running speed, and the change trend of the displacement, to form the dynamic operation characteristic parameters of the push rod for input to the subsequent fault prediction model.

[0090] S202: The sagger stacking blockage fault prediction model performs fault prediction calculations on the dynamic operation characteristic parameters of the push rod to obtain a stacking blockage risk assessment value.

[0091] Specifically, the sagger stacking blockage fault prediction model receives the dynamic operation characteristic parameters of the push rod as input, including the instantaneous change rate of the thrust, the fluctuation amplitude of the running speed, and the change trend of the displacement. First, the model preprocesses the input characteristic data. By standardizing all characteristic values, adjust the numerical range of the characteristics to a consistent standard to reduce the impact of the magnitude difference between characteristics on the model calculation. Then, the model performs multi-layer calculations on the standardized characteristics. By analyzing the correlation between the characteristics and the stacking blockage fault layer by layer, perform weighted calculations on the roles of thrust change, speed fluctuation, and displacement trend in the occurrence of the stacking blockage fault, and at the same time analyze the mutual relationship between the characteristics, such as the coupling relationship between the thrust change rate and the speed fluctuation, to generate a comprehensive risk assessment result. Finally, the stacking blockage risk assessment value output by the model is used as a quantitative result of the probability of the fault occurrence, usually in the range of 0 to 1. The closer the median is to 1, the higher the probability of the stacking blockage fault occurring.

[0092] In one embodiment, as Figure 4 shown, in step S202, that is, the sagger stacking blockage fault prediction model performs fault prediction calculations on the dynamic operation characteristic parameters of the push rod to obtain a stacking blockage risk assessment value, including:

[0093] S2021: The sagger stacking blockage fault prediction model calculates the stacking blockage risk assessment value based on the following formula:

[0094] , where R represents the stacking blockage risk assessment value, ΔF represents the instantaneous change rate 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 pusher thrust. W2 represents the weight coefficient of the fluctuation amplitude of the pusher running speed. W3 represents the weight coefficient of the change trend of the pusher 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 non-linear activation function. ΔF 2 represents the influence of the square of the thrust change rate on the blockage fault. represents capturing the non-linear influence of the running speed fluctuation. log(1 + ∣ΔS∣) represents weakening the influence on the prediction model of the sagger blockage fault when the displacement changes.

[0095] Specifically, the process of the sagger blockage fault prediction model calculating the blockage risk assessment value based on the real-time collected pusher running parameters includes the following steps: First, preprocess the real-time collected thrust, running speed, and displacement parameters. The instantaneous change rate ΔF of the thrust is calculated by the ratio of the difference in thrust between two consecutive time points to the time difference. 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. The fluctuation amplitude ΔV of the running speed is calculated by the difference between the maximum and minimum values of the speed within a certain time window. The calculation formula is: , where V represents all the speed values within the time window. The displacement change trend ΔS is calculated by fitting the change slope of the displacement data within the time window. The calculation formula is: , Si represents the displacement data, ti represents the corresponding time, c and h are the means of time and displacement respectively. Then, calculate the interaction term between the thrust change rate and the speed fluctuation. The interaction term is obtained by multiplying the above calculated ΔF and ΔV. Then, substitute the above eigenvalue into the formula of the sagger 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, perform non-linear mapping through the activation function σ. The activation function can adopt 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 size of the blockage risk. Finally, output the calculated blockage risk assessment value R. If R is close to 1, it indicates a high blockage risk. If R is close to 0, it indicates a low blockage risk.

[0096] In one embodiment, as Figure 5 shown, in step S30, that is, compare the blockage risk assessment value with the preset blockage risk threshold to obtain the blockage risk status information, including:

[0097] S301: The preset risk thresholds for blockage include a low-risk threshold, a high-risk threshold, and an intermediate risk range.

[0098] Specifically, the preset risk thresholds for blockage are determined by analyzing the historical operation data and blockage fault data of the pusher kiln. The low-risk threshold, high-risk threshold, and intermediate risk range are divided according to the distribution of the occurrence probability of blockage faults. The low-risk threshold represents the upper limit value of the safe range of the operating state, which is determined by statistically calculating the maximum value of the risk assessment values without blockage faults in the historical data; the high-risk threshold represents the lower limit value of the operating state where blockage faults are extremely likely to occur, which is determined by statistically calculating the minimum risk assessment value when blockage faults occur in the 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 blockage in the operating state but it does not pose an immediate danger. The preset risk thresholds are dynamically adjusted according to the distribution of the occurrence probability of blockage faults and stored in the equipment operation database for real-time calling.

[0099] S302: Compare the blockage risk assessment value with the preset blockage risk thresholds. When the blockage risk assessment value < the low-risk threshold, generate the blockage risk status information as low risk. If the low-risk threshold ≤ the blockage risk assessment value ≤ the high-risk threshold, generate the blockage risk status information as medium risk. If the blockage risk assessment value > the high-risk threshold, generate the blockage risk status information as high risk.

[0100] Specifically, by comparing the calculated blockage risk assessment value with the preset low-risk threshold and high-risk threshold, judge the risk level of the current pusher operation state. The specific judgment process includes: First, retrieve the low-risk threshold and high-risk threshold from the equipment operation database. The low-risk threshold is used to identify that the pusher operation state is within the safe range, and the high-risk threshold is used to identify that there is a great risk of blockage faults in the pusher operation state. Then, compare the blockage risk assessment value with the low-risk threshold. When the blockage risk assessment value is less than the low-risk threshold, generate the risk status information as low risk. At this time, it is considered that the pusher operation state is safe and no adjustment is required. If the blockage risk assessment value is greater than or equal to the low-risk threshold and less than or equal to the high-risk threshold, generate the risk status information as medium risk, indicating that there may be blockage hazards in the current operation state but it does not constitute a serious risk. If the blockage risk assessment value is greater than the high-risk threshold, generate the risk status information as high risk, indicating that there is a great possibility of blockage faults in the pusher operation state and immediate adjustment measures need to be taken.

[0101] In one embodiment, as Figure 6 shown, in step S302, that is, when the blockage risk status information is medium risk, it further includes:

[0102] S3021: If the blockage risk status information is medium risk, generate continuous observation of the operation state information.

[0103] Specifically, when the risk status information of heap blockage is determined to be medium risk, by analyzing the running information of the current push rod and the change trend of the heap blockage risk assessment value, continuous observation running status information is generated. The continuous observation running status information includes the set observation time period, sampling frequency, and the push rod running parameters to be monitored key points. The observation time period is determined according to the change cycle of the heap blockage risk in the medium risk state in historical data, usually 5 seconds to 30 seconds. The sampling frequency is set according to the running dynamic characteristics of the push rod, usually collecting 10 to 100 times per second. The push rod running parameters to be monitored key points include thrust, speed, and displacement. By continuously collecting the push rod running parameters and calculating the heap blockage risk assessment value in real time, the risk status information is dynamically updated. The generated continuous observation running status information is used for real-time monitoring of the push rod to ensure a rapid response to risk changes.

[0104] S3022: According to the continuous observation running status information, if the heap blockage risk assessment value drops to low risk during the continuous observation period, restore the original running parameters of the push rod.

[0105] Specifically, during the continuous observation period, the running parameters of the push rod are collected in real time, and the heap blockage risk assessment value is dynamically calculated according to the collected parameters. If the calculated heap blockage risk assessment value is lower than the preset low risk threshold, it is considered that the running state of the push rod has returned to the safe range. At this time, a restore running instruction is generated, and the adjusted running parameters of the current push rod are gradually restored to the original running parameters. The specific restoration process includes gradually increasing the thrust or running speed at a fixed time interval to be closer to the original running parameters. During the restoration process, the running state is monitored in real time to ensure that the restoration action will not trigger new risks.

[0106] S3023: If the heap blockage risk assessment value rises to high risk during the continuous observation period, generate a push rod running parameter adjustment instruction.

[0107] Specifically, during the continuous observation period, if the real-time calculated heap blockage risk assessment value exceeds the preset high risk threshold, it is considered that there is a serious heap blockage risk in the running state of the push rod. At this time, a push rod running parameter adjustment instruction is generated. The adjustment instruction includes the target thrust value, target speed value, and 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 running speed. The adjustment time is set according to the stability requirements of the current running state, usually gradually completed within several 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 to be used to change the running state of the push rod in real time.

[0108] In one embodiment, as Figure 7As shown, in step S40, that is, if the new clogging risk assessment value is less than the preset clogging risk threshold, the operation of the push rod is controlled according to the adjusted operation parameters, and it further includes:

[0109] S401: If the new clogging risk assessment value is greater than the preset clogging risk threshold, a further operation parameter optimization instruction is generated. Based on the further operation parameter optimization instruction, the operation state of the push rod is adjusted to obtain the re-optimized operation information, and the re-optimized operation information is input into the sagger clogging fault prediction model to obtain the re-adjusted clogging risk assessment value.

[0110] Specifically, when the new clogging risk assessment value exceeds the preset clogging risk threshold, the further operation parameter optimization instruction is generated by dynamically comparing the current operation parameters of the push rod with the clogging fault critical parameters in the historical operation data. The optimization instruction includes the target values for adjusting the thrust, speed, and displacement, as well as the adjustment execution time. Specifically, the target value for adjusting the thrust is generated by reducing the current thrust value by a certain proportion, and 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 the speed is generated by reducing the current speed by a certain amplitude, and the adjustment amplitude is set according to the requirement of operation stability, 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 a stable adjustment process without causing new abnormalities. After the optimization instruction is generated, the operation state of the push rod is adjusted in real time. The adjusted thrust, speed, and displacement data are used as the re-optimized operation information, and this information is input into the sagger clogging fault prediction model. The model recalculates the clogging risk assessment value based on the adjusted characteristic data, and the change result of the assessment value is used for subsequent risk state judgment and further adjustment decision-making.

[0111] S402: If the re-adjusted clogging risk assessment value is still greater than the preset clogging risk threshold, a high-risk warning information is generated and sent to the operation terminal.

[0112] Specifically, when the re-adjusted clogging risk assessment value is still higher than the preset clogging risk threshold, it is considered that the current operation state of the push rod has reached the high-risk level and manual intervention by the operator is required. At this time, a high-risk warning information is generated. The high-risk warning information includes the current operation parameters of the push rod, the clogging risk assessment value, and the historical record data during the adjustment process, which is used to detail the abnormal state of the current equipment. 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 a risk prompt on the equipment control panel, emitting a visual signal through a warning light, and sending a real-time notification through a mobile terminal, ensuring that the operator can timely understand the high-risk state and take necessary measures.

[0113] It should be understood that the sequence numbers of the steps in the above embodiments do not imply the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0114] In one embodiment, a push plate kiln blockage fault prediction device is provided. The push plate kiln blockage fault prediction device corresponds one-to-one to the push plate kiln blockage fault prediction method in the above embodiment. As Figure 8 shown, the push plate kiln blockage fault prediction device includes a push rod operation information acquisition module, a blockage risk assessment module, a blockage risk status judgment module, a push rod operation parameter adjustment module, a dynamic adjustment and risk feedback module, and an operation parameter maintenance module. The detailed description of each functional module is as follows:

[0115] The push rod operation information acquisition module is used to obtain the operation information of the push rod;

[0116] The blockage risk assessment module is used to input the operation information of the push rod into the sagger blockage fault prediction model to obtain a blockage risk assessment value;

[0117] The blockage risk status judgment module is used to compare the blockage risk assessment value with a preset blockage risk threshold to obtain blockage risk status information;

[0118] The push rod operation parameter adjustment module is used to generate a push rod operation parameter adjustment instruction if the blockage risk status information is high risk;

[0119] 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 to obtain the adjusted operation information, input the adjusted operation information into the sagger blockage fault prediction model to obtain a new blockage risk assessment value, and if the new blockage risk assessment value is less than the preset blockage risk threshold, control the operation of the push rod according to the adjusted operation parameters;

[0120] The operation parameter maintenance module is used to maintain the original operation parameters of the push rod if the blockage risk status information is low risk.

[0121] Optionally, before the blockage risk assessment module, there is included:

[0122] The historical operation information acquisition and preprocessing module is used to obtain the historical operation information of the push plate kiln, perform information preprocessing on the historical operation information of the push plate kiln to obtain the preprocessed historical operation information;

[0123] The training data set generation module is used to label the state information of the occurrence of blockage faults in the preprocessed historical operation information according to the time series to form a training data set, input the training data set into a machine learning model, and train the machine learning model to obtain an initial sagger blockage fault prediction model;

[0124] A model verification module, which is used to verify the initial sagger stacking blockage fault prediction model through the cross-validation method. After successful verification, the sagger stacking blockage fault prediction model is obtained.

[0125] Optionally, the stacking blockage risk assessment module includes:

[0126] A push rod operation feature extraction sub-module, which is used to extract features from the operation information of the push rod to obtain the dynamic operation feature parameters of the push rod;

[0127] A fault prediction calculation sub-module, which is used to perform fault prediction calculations on the dynamic operation feature parameters of the push rod by the sagger stacking blockage fault prediction model to obtain the stacking blockage risk assessment value.

[0128] Optionally, the fault prediction calculation sub-module includes:

[0129] A formula application unit, which is used to calculate the stacking blockage risk assessment value based on the following formula by the sagger stacking blockage fault prediction model:

[0130] , where R represents the stacking blockage risk assessment value, ΔF represents the instantaneous change rate of the push rod thrust, ΔV represents the fluctuation amplitude of the push rod operation speed, 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 push rod thrust, W2 represents the weight coefficient of the fluctuation amplitude of the push rod operation 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 non-linear activation function, ΔF 2 represents the influence of the square of the thrust change rate on the stacking blockage fault, represents capturing the non-linear influence of the operation speed fluctuation, log(1 + ∣ΔS∣) represents weakening the influence on the sagger stacking blockage fault prediction model when the displacement changes.

[0131] Optionally, the stacking blockage risk status judgment module includes:

[0132] A stacking blockage risk threshold setting sub-module, which is used to preset the stacking blockage risk thresholds, including a low risk threshold, a high risk threshold, and an intermediate risk range;

[0133] A stacking blockage risk status determination sub-module, which is used to compare the stacking blockage risk assessment value with the preset stacking blockage risk thresholds. When the stacking blockage risk assessment value < the low risk threshold, the stacking blockage risk status information is generated as low risk. If the low risk threshold ≤ the stacking blockage risk assessment value ≤ the high risk threshold, the stacking blockage risk status information is generated as medium risk. If the stacking blockage risk assessment value > the high risk threshold, the stacking blockage risk status information is generated as high risk.

[0134] Optionally, the clogging risk status determination sub-module includes:

[0135] A continuous observation of the operating state generation unit, configured to generate continuous observation of the operating state information if the clogging risk status information is medium risk;

[0136] A push rod original operating parameter restoration unit, configured to restore the original operating parameters of the push rod according to the continuous observation of the operating state information if the clogging risk assessment value drops to low risk during the continuous observation period;

[0137] A push rod operating parameter adjustment instruction generation unit, configured to generate a push rod operating parameter adjustment instruction if the clogging risk assessment value rises to high risk during the continuous observation period.

[0138] Optionally, the push rod operating parameter adjustment module includes:

[0139] An operating parameter optimization and re-evaluation sub-module, configured to generate a further operating parameter optimization instruction if the new clogging risk assessment value is greater than a preset clogging risk threshold, adjust the operating state of the push rod based on the further operating parameter optimization instruction, obtain the re-optimized operating information, and input the re-optimized operating information into the sagger clogging fault prediction model to obtain the re-adjusted clogging risk assessment value;

[0140] A high-risk warning information generation sub-module, configured to generate high-risk warning information and send the high-risk warning information to the operation terminal if the re-adjusted clogging risk assessment value is still greater than the preset clogging risk threshold.

[0141] For the specific limitations of the sagger clogging fault prediction device, reference may be made to the limitations of the sagger clogging fault prediction method in the foregoing text, which will not be elaborated here. Each module in the above sagger clogging fault prediction device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0142] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as Figure 9As shown in the figure. 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, it implements a method for predicting the blockage fault of a pusher kiln.

[0143] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented:

[0144] Obtain the operation information of the pusher rod;

[0145] By inputting the operation information of the pusher rod into the sagger blockage fault prediction model, obtain a blockage risk assessment value;

[0146] Compare the blockage risk assessment value with a preset blockage risk threshold to obtain blockage risk status information;

[0147] If the blockage risk status information is high risk, generate a pusher rod operation parameter adjustment instruction;

[0148] Based on the pusher rod operation parameter adjustment instruction, adjust the operation state of the pusher rod in real time to obtain adjusted operation information. Input the adjusted operation information into the sagger blockage fault prediction model to obtain a new blockage risk assessment value. If the new blockage risk assessment value is less than the preset blockage risk threshold, control the operation of the pusher rod according to the adjusted operation parameters;

[0149] If the blockage risk status information is low risk, maintain the original operation parameters of the pusher rod.

[0150] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the following steps are implemented:

[0151] Obtain the operation information of the pusher rod;

[0152] By inputting the operation information of the pusher rod into the sagger blockage fault prediction model, obtain a blockage risk assessment value;

[0153] Compare the blockage risk assessment value with a preset blockage risk threshold to obtain blockage risk status information;

[0154] If the risk status information of the heap blockage is high risk, an adjustment instruction for the operating parameters of the push rod is generated;

[0155] Based on the adjustment instruction for the operating parameters of the push rod, the operating state of the push rod is adjusted in real time to obtain the adjusted operating information. The adjusted operating information is input into the casket heap blockage fault prediction model to obtain a new heap blockage risk assessment value. If the new heap blockage risk assessment value is less than the preset heap blockage risk threshold, the operation of the push rod is controlled according to the adjusted operating parameters;

[0156] If the risk status information of the heap blockage is low risk, the original operating parameters of the push rod are maintained.

[0157] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. 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 methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various 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.

[0158] Those skilled in the art can clearly understand that for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above.

[0159] The foregoing embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A prediction method for the stacking and blocking failure of a pusher kiln, characterized in that, The push plate kiln blockage fault prediction method includes: Obtaining the operation information of the push rod; By inputting the operation information of the push rod into the sagger blockage fault prediction model, obtaining a blockage risk assessment value; The step of obtaining the blockage risk assessment value by inputting the operation information of the push rod into the sagger blockage fault prediction model includes: Extracting features from the operation information of the push rod to obtain dynamic operation characteristic parameters of the push rod; The sagger blockage fault prediction model performs fault prediction calculations on the dynamic operation characteristic parameters of the push rod to obtain the blockage risk assessment value; The step that the sagger blockage fault prediction model performs fault prediction calculations on the dynamic operation characteristic parameters of the push rod to obtain the blockage risk assessment value includes: The sagger blockage fault prediction model calculates the blockage risk assessment value based on the following formula: Wherein, R represents the risk assessment value of heap blockage, ΔF represents the instantaneous change rate 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, ΔF·ΔV 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 non-linear activation function, ΔF2 represents the influence of the square of the thrust change rate on the heap blockage fault, and represents capturing the non-linear influence of the running speed fluctuation, and log(1 + ∣ΔS∣) represents weakening the influence on the prediction model of the sagger heap blockage fault when the displacement changes; Comparing the blockage risk assessment value with a preset blockage risk threshold to obtain blockage risk status information; The step of comparing the blockage risk assessment value with a preset blockage risk threshold to obtain blockage risk status information includes: The preset blockage risk threshold includes a low risk threshold, a high risk threshold, and an intermediate risk range; Comparing the blockage risk assessment value with the preset blockage risk threshold. When the blockage risk assessment value < the low risk threshold, generating the blockage risk status information as low risk. If the low risk threshold ≤ the blockage risk assessment value ≤ the high risk threshold, generating the blockage risk status information as medium risk. If the blockage risk assessment value > the high risk threshold, generating the blockage risk status information as high risk; If the blockage risk status information is high risk, generating a push rod operation parameter adjustment instruction; Based on the push rod operation parameter adjustment instruction, adjusting the operation state of the push rod in real time to obtain adjusted operation information, inputting the adjusted operation information into the sagger blockage fault prediction model to obtain a new blockage risk assessment value. If the new blockage risk assessment value is less than the preset blockage risk threshold, controlling the operation of the push rod according to the adjusted operation parameters; If the blockage risk status information is low risk, maintaining the original operation parameters of the push rod.

2. The push plate kiln stacking blockage fault prediction method according to claim 1, wherein Before, the sagger blockage fault prediction model included: Obtaining the historical operation information of the push plate kiln, performing information preprocessing on the historical operation information of the push plate kiln to obtain preprocessed historical operation information; Labeling the status information of the occurrence of blockage faults for the preprocessed historical operation information according to the time series to form a training data set, inputting the training data set into a machine learning model, and training the machine learning model to obtain an initial sagger blockage fault prediction model; Verifying the initial sagger blockage fault prediction model through the cross-validation method. After successful verification, obtaining the sagger blockage fault prediction model.

3. The push plate kiln stacking blockage fault prediction method according to claim 1, characterized in that, When the blockage risk status information is medium risk, it further includes: If the blockage risk status information is medium risk, generating continuous observation operation status information; According to the continuously observed operating status information, if the risk assessment value of the heap blockage decreases to the low risk during the continuous observation, restore the original operating parameters of the push rod; If the risk assessment value of the heap blockage rises to the high risk during the continuous observation, generate an adjustment instruction for the operating parameters of the push rod.

4. The push plate kiln stacking blockage fault prediction method according to claim 1, characterized in that, If the new risk assessment value of the heap blockage is less than the preset risk threshold of the heap blockage, controlling the operation of the push rod according to the adjusted operating parameters further includes: If the new risk assessment value of the heap blockage is greater than the preset risk threshold of the heap blockage, generate a further optimization instruction for the operating parameters, adjust the operating state of the push rod based on the further optimization instruction for the operating parameters, obtain the re-optimized operating information, and input the re-optimized operating information into the sagger heap blockage fault prediction model to obtain the re-adjusted risk assessment value of the heap blockage; If the re-adjusted risk assessment value of the heap blockage is still greater than the preset risk threshold of the heap blockage, generate a high-risk warning information and send the high-risk warning information to the operation terminal.

5. A push plate kiln stacking and blocking fault prediction device, characterized in that, The sagger kiln heap blockage fault prediction device includes: A push rod operating information acquisition module for acquiring the operating information of the push rod; A heap blockage risk assessment module for obtaining a heap blockage risk assessment value by inputting the operating information of the push rod into the sagger heap blockage fault prediction model; The heap blockage risk assessment module includes: A push rod operating feature extraction sub-module for extracting features from the operating information of the push rod to obtain dynamic operating feature parameters of the push rod; A fault prediction calculation sub-module for performing fault prediction calculations on the dynamic operating feature parameters of the push rod by the sagger heap blockage fault prediction model to obtain the heap blockage risk assessment value; The fault prediction calculation sub-module includes: A formula application unit for the sagger heap blockage fault prediction model to calculate the heap blockage risk assessment value based on the following formula: Among them, R represents the risk assessment value of heap blockage, ΔF represents the instantaneous change rate 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, ΔF·ΔV 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 non-linear activation function, and ΔF 2 represents the influence of the square of the thrust change rate on the heap blockage fault, represents capturing the non-linear influence of the running speed fluctuation, and log(1 + ∣ΔS∣) represents weakening the influence on the prediction model of the sagger heap blockage fault when the displacement changes; A heap blockage risk state judgment module for comparing the heap blockage risk assessment value with a preset heap blockage risk threshold to obtain heap blockage risk state information; The heap blockage risk state judgment module includes: A heap blockage risk threshold setting sub-module, where the preset heap blockage risk threshold includes a low risk threshold, a high risk threshold, and an intermediate risk range; A heap blockage risk state determination sub-module for comparing the heap blockage risk assessment value with the preset heap blockage risk threshold. When the heap blockage risk assessment value < low risk threshold, generate the heap blockage risk state information as low risk. If the low risk threshold ≤ heap blockage risk assessment value ≤ high risk threshold, generate the heap blockage risk state information as medium risk. If the heap blockage risk assessment value > high risk threshold, generate the heap blockage risk state information as high risk; A push rod operating parameter adjustment module for generating an adjustment instruction for the push rod operating parameters if the heap blockage risk state information is the high risk; A dynamic adjustment and risk feedback module, which is used to adjust the running 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 stack blockage fault prediction model, obtain a new stack blockage risk assessment value, and if the new stack blockage risk assessment value is less than the preset stack blockage risk threshold, control the operation of the push rod according to the adjusted operation parameters; An operation parameter maintenance module, which is used to maintain the original operation parameters of the push rod if the stack blockage risk status information is the low risk.

6. 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 stack blockage fault prediction method according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the steps of the push plate kiln stack blockage fault prediction method according to any one of claims 1 to 4 are implemented.

Images