Intelligent control method and system for production equipment based on real-time feedback

Abstract

The embodiment of the application provides a production equipment intelligent regulation and control method and system based on real-time feedback, first, a real-time monitoring data set in the running process of production equipment is collected, containing equipment running parameters and environment associated parameters, then dynamic feature extraction processing is performed on the real-time monitoring data set, equipment running feature set and environment associated feature set are obtained; then real-time running state information of the production equipment is identified according to the correlation relationship between the two, a dynamic regulation and control strategy set containing equipment parameter adjustment instructions and environment adaptation instructions is generated based on the real-time running state information, finally, the dynamic regulation and control strategy set is used for dynamically adjusting the running parameters of the production equipment, and the real-time monitoring data set is updated, so that intelligent and accurate regulation and control of the production equipment can be realized, and production efficiency and product quality are improved.

Description

Technical Field

[0001] This invention relates to the field of smart factory technology, and more specifically, to a method and system for intelligent control of production equipment based on real-time feedback. Background Technology

[0002] In modern industrial production, the stable operation and efficient output of production equipment are crucial to a company's economic benefits and competitiveness. As industrial automation continues to increase, production equipment becomes increasingly complex, and its operation is affected by a variety of factors, including the equipment's own operating parameters and the related parameters of the surrounding environment.

[0003] Currently, traditional methods of controlling production equipment mainly rely on human experience or pre-set fixed procedures. Human experience-based control suffers from high subjectivity and difficulty in coping with complex and changing production environments, while fixed-procedure control lacks flexibility and cannot adjust in a timely manner according to real-time equipment operating status and environmental changes. This leads to problems such as low efficiency, excessive energy consumption, and unstable product quality during production equipment operation, failing to meet the requirements of modern industrial production for high efficiency, energy saving, and high quality. Therefore, a method is needed that can intelligently control production equipment based on real-time sensing of operating status and environmental changes to improve operating efficiency and product quality. Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide a method and system for intelligent control of production equipment based on real-time feedback.

[0005] According to one aspect of the present invention, a method for intelligent control of production equipment based on real-time feedback is provided, the method comprising:

[0006] The system collects a set of real-time monitoring data during the operation of production equipment, including equipment operating parameters and environmental parameters.

[0007] Dynamic feature extraction processing is performed on the real-time monitoring data set to obtain a set of equipment operation features and a set of environmental related features;

[0008] Based on the correlation between the set of equipment operation features and the set of environmental associated features, the real-time operating status information of the production equipment is identified;

[0009] Based on the real-time operating status information, a set of dynamic control strategies for the production equipment is generated. The set of dynamic control strategies includes equipment parameter adjustment instructions and environment adaptation instructions.

[0010] The operating parameters of the production equipment are dynamically adjusted according to the set of dynamic control strategies, and the real-time monitoring data set is updated based on the adjusted operating parameters.

[0011] According to another aspect of the present invention, a production equipment intelligent control system based on real-time feedback is provided, comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; the memory is used to store a computer program; and the processor is used to execute the computer program to implement the steps of the production equipment intelligent control method based on real-time feedback as described above.

[0012] According to another aspect of the present invention, a readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, can perform the steps of the above-described intelligent control method for production equipment based on real-time feedback.

[0013] Through any of the above aspects, embodiments of the present invention, by collecting real-time monitoring data sets during the operation of production equipment and performing dynamic feature extraction processing on these data sets, can accurately extract equipment operation feature sets and environmental correlation feature sets. Furthermore, by deeply analyzing the correlation between the two, the real-time operating status information of the production equipment can be accurately identified. The dynamic control strategy set generated based on this real-time operating status information includes both equipment parameter adjustment instructions and environmental adaptation instructions, achieving coordinated control of production equipment operating parameters and environmental factors. Dynamically adjusting the production equipment operating parameters according to the dynamic control strategy set and updating the real-time monitoring data set based on the adjusted operating parameters can significantly improve the operating efficiency of the production equipment, reduce energy consumption, improve product quality, and enhance the stability and reliability of the production process.

[0014] To make the above-mentioned objects, features and advantages of the embodiments of the present invention more apparent and understandable, a detailed description will be given below in conjunction with the embodiments and the accompanying drawings. Attached Figure Description

[0015] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A schematic diagram of the components of the intelligent control system for production equipment based on real-time feedback provided in an embodiment of the present invention is shown.

[0017] Figure 2 The diagram shows a flowchart of the intelligent control method for production equipment based on real-time feedback provided in an embodiment of the present invention. Detailed Implementation

[0018] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] The terms “first,” “second,” “third,” etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0020] Figure 1A schematic diagram of exemplary components of a real-time feedback-based intelligent control system 100 for production equipment is shown. The real-time feedback-based intelligent control system 100 may include one or more processors 104, such as one or more central processing units (CPUs), each of which may implement one or more hardware threads. The real-time feedback-based intelligent control system 100 may also include any storage medium 106 for storing any kind of information such as code, settings, data, etc. Non-limitingly, for example, storage medium 106 may include any type of RAM, any type of ROM, flash memory device, hard disk, optical disk, etc. More generally, any storage medium can use any technology to store information. Furthermore, any storage medium may provide volatile or non-volatile retention of information. Furthermore, any storage medium may represent a fixed or removable component of the real-time feedback-based intelligent control system 100. In one case, when processor 104 executes dependent instructions stored in any storage medium or combination of storage media, the real-time feedback-based intelligent control system 100 may perform any operation of the associated instructions. The intelligent control system 100 for production equipment based on real-time feedback also includes one or more drive units 108 for interacting with any storage medium, such as hard disk drive units, optical disk drive units, etc.

[0021] The intelligent control system 100 for production equipment based on real-time feedback also includes input / output (I / O) 110 for receiving various inputs (via input unit 112) and providing various outputs (via output unit 114). A specific output mechanism may include a presentation device 116 and a dependent graphical user interface (GUI) 118. The intelligent control system 100 for production equipment based on real-time feedback may also include one or more network interfaces 120 for exchanging data with other devices via one or more communication units 122. One or more communication buses 124 couple the components described above together.

[0022] The communication unit 122 can be implemented in any way, such as via a local area network, a wide area network (e.g., the Internet), a point-to-point connection, or any combination thereof. The communication unit 122 may include any combination of hardwired links, wireless links, routers, gateway functions, or names such as the production equipment intelligent control system 100 based on real-time feedback, governed by any protocol or combination of protocols.

[0023] Figure 2 This diagram illustrates a flow chart of a production equipment intelligent control method and system based on real-time feedback provided in an embodiment of the present invention. The production equipment intelligent control method and system based on real-time feedback can be derived from… Figure 1The production equipment intelligent control system 100 based on real-time feedback shown in the figure is executed. The detailed steps of the production equipment intelligent control method based on real-time feedback are described below.

[0024] Step S110: Collect a set of real-time monitoring data of the production equipment during operation. The set of real-time monitoring data includes equipment operating parameters and environmental related parameters.

[0025] In waste paper recycling production scenarios, to achieve intelligent control of production equipment, it is necessary to comprehensively and accurately collect a set of real-time monitoring data during equipment operation. This set of real-time monitoring data covers equipment operating parameters and environmentally related parameters, which is crucial for understanding the operating status of the equipment and its environmental impact. Taking a waste paper recycling production line as an example, the production equipment includes pulpers, screening machines, dewatering machines, etc. These machines generate various parameters during operation, and the environment in which they are located also affects their operation; therefore, it is necessary to collect the corresponding data.

[0026] Step S111: Configure multiple sensor nodes connected to the production equipment, the sensor nodes including equipment parameter sensors and environmental parameter sensors.

[0027] Next, to accurately collect the required data, multiple sensor nodes need to be configured and connected to the production equipment. These sensor nodes are divided into two categories: equipment parameter sensors and environmental parameter sensors. For equipment on the waste paper recycling production line, equipment parameter sensors can be installed at the motor of the pulper to monitor the motor's operating status; sensors can be installed at the screen of the screening machine to obtain the screen's working condition. Environmental parameter sensors are arranged in different locations in the production workshop, such as near windows and around equipment, to collect environmental data.

[0028] Step S112: Collect the operating parameters of the production equipment through the equipment parameter sensor. The operating parameters include temperature parameters, pressure parameters and energy consumption parameters.

[0029] Then, the operating parameters of the production equipment are collected using equipment parameter sensors. Taking a pulper as an example, during the pulping process, the motor generates heat, causing the temperature to rise. The equipment parameter sensors collect the motor's temperature parameter in real time, denoted as T. Inside the pulper, when crushing and agitating waste paper, a certain pressure is generated; the sensor collects this pressure parameter, denoted as P. Simultaneously, the motor consumes electrical energy during operation, and the sensor records the energy consumption parameter, denoted as E. These parameters reflect the operating status and performance of the pulper.

[0030] Step S113: Collect environmental parameters of the environment in which the production equipment is located through the environmental parameter sensor. The environmental parameters include humidity parameters, vibration parameters and air quality parameters.

[0031] Subsequently, environmental parameter sensors begin collecting environmental parameters related to the environment in which the production equipment is located. In the waste paper recycling workshop, air humidity affects the waste paper processing efficiency and equipment lifespan; the environmental parameter sensors collect humidity parameters, denoted as H. The operation of other equipment and material conveying within the workshop may generate vibrations; the sensors collect vibration parameters, denoted as V. Furthermore, air quality within the workshop, such as dust content, also affects equipment and operators; the sensors collect air quality parameters, denoted as A.

[0032] Step S114: Perform data standardization processing on the operating parameters and the environmental related parameters to generate a real-time monitoring data set with unified dimensions.

[0033] Because the collected operating parameters and environmental parameters have different dimensions, these parameters need to be standardized to ensure the accuracy and consistency of subsequent processing.

[0034] Step S1141: Normalize the temperature parameter, pressure parameter and energy consumption parameter in the operating parameters to obtain standardized temperature parameter, standardized pressure parameter and standardized energy consumption parameter.

[0035] For the temperature parameter T, assuming its original value range is between T_min and T_max, it is normalized to the range [0, 1] to obtain the standardized temperature parameter T_norm. The normalization calculation logic is as follows: first calculate the ratio of the temperature parameter to its value range, i.e., (T-T_min) / (T_max-T_min), and the result is the standardized temperature parameter T_norm.

[0036] For the pressure parameter P, it is also assumed that its original value range is between P_min and P_max. Following the same normalization method as the temperature parameter, (P-P_min) / (P_max-P_min) is calculated to obtain the standardized pressure parameter P_norm.

[0037] For the energy consumption parameter E, assuming its original value range is between E_min and E_max, the standardized energy consumption parameter E_norm is obtained by calculating (E-E_min) / (E_max-E_min).

[0038] Step S1142: Normalize the humidity parameter, vibration parameter and air quality parameter in the environmental correlation parameters to obtain standardized humidity parameter, standardized vibration parameter and standardized air quality parameter.

[0039] For the humidity parameter H, assuming its original value range is between H_min and H_max, the standardized humidity parameter H_norm is obtained by calculating (H-H_min) / (H_max-H_min).

[0040] For the vibration parameter V, assuming its original value range is between V_min and V_max, the standardized vibration parameter V_norm is obtained by calculating (V-V_min) / (V_max-V_min).

[0041] For air quality parameter A, assuming its original value range is between A_min and A_max, the standardized air quality parameter A_norm is obtained by calculating (A-A_min) / (A_max-A_min).

[0042] Step S1143: Align the standardized temperature parameter, the standardized pressure parameter, the standardized energy consumption parameter, the standardized humidity parameter, the standardized vibration parameter, and the standardized air quality parameter according to the timestamp to generate the real-time monitoring data set with unified dimensions.

[0043] Finally, the obtained standardized temperature parameter T_norm, standardized pressure parameter P_norm, standardized energy consumption parameter E_norm, standardized humidity parameter H_norm, standardized vibration parameter V_norm, and standardized air quality parameter A_norm are aligned according to the acquisition timestamps. For example, these standardized parameters acquired at the same time t are combined to form a multi-dimensional data vector. Combining these data vectors from different times generates a real-time monitoring data set with unified dimensions.

[0044] Step S120: Perform dynamic feature extraction processing on the real-time monitoring data set to obtain the equipment operation feature set and the environment-related feature set.

[0045] After obtaining a set of real-time monitoring data with unified dimensions, dynamic feature extraction processing is required to extract useful information from the data, resulting in a set of equipment operation features and a set of environmental correlation features. In the waste paper recycling production scenario, this helps to gain a deeper understanding of the equipment's operating characteristics and the impact of the environment on the equipment.

[0046] Step S121: Perform time-series segmentation processing on the equipment operation parameters in the real-time monitoring data set to obtain a set of equipment operation sub-parameters corresponding to multiple consecutive time windows.

[0047] First, the equipment operating parameters in the real-time monitoring dataset are processed by time-series segmentation. Taking the operating parameters of a pulper as an example, the temperature parameter T_norm, pressure parameter P_norm, and energy consumption parameter E_norm collected over a period of time are divided into continuous time windows. Assuming the length of the time window is Δt, starting from the initial time t_0, the first time window is [t_0, t_0+Δt]. The temperature parameter, pressure parameter, and energy consumption parameter within this time window constitute a set of equipment operating sub-parameters D_1. The second time window is [t_0+Δt, t_0+2Δt], and the corresponding set of equipment operating sub-parameters is D_2, and so on, to obtain multiple sets of equipment operating sub-parameters D_1, D_2, ..., D_n corresponding to consecutive time windows.

[0048] Step S122: Perform multi-dimensional feature extraction processing on each set of device operation sub-parameters to obtain a set of device operation features corresponding to each time window. The multi-dimensional feature extraction processing includes parameter fluctuation feature extraction, trend correlation feature extraction, and anomaly accumulation feature extraction.

[0049] Next, multi-dimensional feature extraction processing is performed on the set of sub-parameters for each device operation.

[0050] For parameter fluctuation feature extraction, taking temperature as an example, the temperature parameter T_norm may fluctuate within a certain time window [t_i, t_i+Δt]. The standard deviation σ_T of the temperature parameter within this time window can be calculated to represent the degree of temperature fluctuation; the larger the standard deviation, the more severe the temperature fluctuation. The same method is used for the pressure parameter P_norm and the energy consumption parameter E_norm, respectively, to calculate their standard deviations σ_P and σ_E. These standard deviations are combined to form the parameter fluctuation feature vector F_1=[σ_T, σ_P, σ_E] for this time window.

[0051] For trend correlation feature extraction, the changing trends of temperature, pressure, and energy consumption parameters within a time window and the correlations between them are analyzed. For example, the difference in temperature parameter ΔT, pressure parameter ΔP, and energy consumption parameter ΔE between adjacent time points can be calculated, and then the correlation between these differences can be analyzed. If ΔT and ΔE show a positive correlation, it indicates that an increase in temperature may be accompanied by an increase in energy consumption. These trend correlation features are combined to form a trend correlation feature vector F_2.

[0052] For anomaly cumulative feature extraction, a normal value range is defined for each parameter. Within a time window, if a parameter exceeds the normal range, it is considered an anomaly. The number of times each parameter exhibits an anomaly within the time window is counted; for example, the number of anomalies for the temperature parameter is N_T, for the pressure parameter is N_P, and for the energy consumption parameter is N_E. These anomaly cumulative counts are combined to form the anomaly cumulative feature vector F_3 = [N_T, N_P, N_E].

[0053] Finally, the parameter fluctuation feature vector F_1, the trend correlation feature vector F_2, and the anomaly accumulation feature vector F_3 are concatenated to obtain the device operation feature subset C_i corresponding to each time window.

[0054] Step S123: Perform spatial partitioning on the environmental correlation parameters in the real-time monitoring data set to obtain a set of environmental correlation sub-parameters corresponding to each time window.

[0055] Then, the environmental parameters in the real-time monitoring dataset are spatially partitioned. In a waste paper recycling workshop, environmental parameters may vary at different locations. The workshop is divided into multiple spatial regions, for example, m regions based on its layout. For each time window, the humidity parameter H_norm, vibration parameter V_norm, and air quality parameter A_norm collected from each region within that time window are combined to form a set of environmentally related sub-parameters. For example, within the time window [t_j, t_j+Δt], the set of environmentally related sub-parameters for the k-th region is E_kj=[H_norm_kj, V_norm_kj, A_norm_kj], where k=1, 2, ..., m.

[0056] Step S124: Perform environmental response feature extraction processing on each set of environmental associated sub-parameters to obtain the environmental associated feature subset corresponding to each time window.

[0057] Subsequently, environmental response features are extracted for each set of environmentally related sub-parameters. Taking humidity as an example, the potential impact of its changes in different regions and time windows on equipment operation is analyzed. The average value μ_H and variance σ_H of humidity parameters in different regions can be calculated. The average value reflects the average humidity level of the region, and the variance reflects the humidity fluctuation. The same method is used for vibration parameters and air quality parameters, calculating their average values ​​μ_V and μ_A and their variances σ_V and σ_A, respectively. These average values ​​and variances are combined to form the environmental response feature vector R_kj=[μ_H_kj, σ_H_kj, μ_V_kj, σ_V_kj, μ_A_kj, σ_A_kj] for the region within the time window. Combining the environmental response feature vectors of each region yields the environmentally related feature subset E_j corresponding to each time window.

[0058] Step S125: Aggregate the device operation feature subset and the environment-related feature subset for each time window to generate the device operation feature set and the environment-related feature set.

[0059] Finally, the device operation feature subsets C_1, C_2, ..., C_n of each time window are aggregated to form the device operation feature set C. A simple concatenation method can be used to sequentially concatenate the device operation feature subsets of each time window to obtain the device operation feature set C. Similarly, the environment association feature subsets E_1, E_2, ..., E_n of each time window are aggregated to form the environment association feature set E.

[0060] Step S130: Identify the real-time operating status information of the production equipment based on the correlation between the equipment operation feature set and the environment association feature set.

[0061] After obtaining the set of equipment operating characteristics and the set of environmental correlation characteristics, it is necessary to analyze the correlation between them in order to identify the real-time operating status information of the production equipment. In the waste paper recycling production scenario, the operating status of the equipment is affected by environmental factors, so analyzing this correlation is crucial for accurately judging the equipment status.

[0062] Step S131: Obtain the device operation feature subset for each time window in the device operation feature set, and the environment association feature subset for the corresponding time window in the environment association feature set.

[0063] First, extract the device operation feature subset C_i for each time window from the device operation feature set C, and simultaneously extract the environment-related feature subset E_i for the corresponding time window from the environment-related feature set E. For example, within the time window [t_i, t_i+Δt], obtain the device operation feature subset C_i and the environment-related feature subset E_i.

[0064] Step S132: Perform joint encoding processing on the device operation feature subset and the environment-related feature subset to generate a joint state feature vector for each time window.

[0065] Next, the equipment operation feature subset C_i and the environment-related feature subset E_i are jointly encoded. An encoder network from deep learning can be used, taking C_i and E_i as input, and performing feature transformation and fusion through a multi-layer neural network. The input layer of the encoder network receives the feature vectors of C_i and E_i, which undergo nonlinear transformation in the hidden layers, ultimately outputting a joint state feature vector S_i. This joint state feature vector integrates equipment operation features and environment-related features, providing a more comprehensive reflection of the production equipment's state within that time window.

[0066] Step S133: Perform state recognition processing on the joint state feature vector according to the preset state classification model to obtain the preliminary state classification result for each time window.

[0067] Then, a pre-defined state classification model is used to perform state recognition processing on the joint state feature vector S_i. The state classification model can be a trained neural network classifier, such as a multilayer perceptron (MLP). The joint state feature vector S_i is input into the MLP. The input layer of the MLP receives the feature vector of S_i, and the feature vector is processed and classified through the intermediate hidden layers. Finally, the output layer outputs the preliminary state classification result. The state classification result can be divided into normal operating state, mild abnormal state, severe abnormal state, etc.

[0068] Step S134: Perform state transition analysis on the preliminary state classification results of the continuous time window to generate real-time operating status information of the production equipment in the continuous operating cycle. The real-time operating status information includes the equipment performance degradation trend and environmental coupling anomaly mode.

[0069] Finally, state transition analysis is performed on the preliminary state classification results of the continuous time windows. A state transition matrix can be constructed to record the transition probability from the state of one time window to the state of the next time window. For example, the probability of transitioning from a normal operating state to a slightly abnormal state, and the probability of transitioning from a slightly abnormal state to a severely abnormal state. By analyzing the state transition matrix and the state changes within the continuous time windows, real-time operating status information of the production equipment within a continuous operating cycle can be generated. The trend of equipment performance degradation can be judged by observing the gradual change of state from normal to abnormal within the continuous time window, and the environmental coupling anomaly pattern can be determined by analyzing the relationship between environmental correlation characteristics and equipment state changes.

[0070] Step S140: Based on the real-time operating status information, generate a set of dynamic control strategies for the production equipment. The set of dynamic control strategies includes equipment parameter adjustment instructions and environment adaptation instructions.

[0071] After identifying the real-time operating status information of the production equipment, a set of dynamic control strategies needs to be generated based on this information. In the waste paper recycling production scenario, the set of dynamic control strategies includes equipment parameter adjustment instructions and environmental adaptation instructions to ensure that the equipment can operate stably and efficiently under different operating conditions.

[0072] Step S141: Divide the device performance degradation trend in the real-time operating status information into degradation stages to obtain the performance degradation characteristics corresponding to different degradation stages.

[0073] First, the degradation trend of equipment performance in real-time operating status information is divided into degradation stages. Based on the change in equipment performance from normal to abnormal, the degradation process can be divided into multiple stages, such as early degradation, mid-term degradation, and late degradation. For each degradation stage, the performance degradation characteristics of the equipment are analyzed. Taking a pulper as an example, in the early degradation stage, energy consumption may increase slightly and temperature fluctuations may increase slightly; in the mid-term degradation stage, pressure parameters may become unstable and the equipment's processing efficiency may decrease; in the late degradation stage, the equipment may frequently experience abnormalities, and its processing capacity may decrease significantly. The performance degradation characteristics of each degradation stage are recorded to form a set of performance degradation characteristics corresponding to different degradation stages.

[0074] Step S142: Based on the performance degradation characteristics, match the preset control rule library to filter and obtain candidate device parameter adjustment instructions corresponding to the current degradation stage.

[0075] Next, a pre-defined control rule library is used to match the performance degradation characteristics. This rule library stores equipment parameter adjustment instructions corresponding to different performance degradation characteristics. For example, if the performance degradation characteristic manifests as increased energy consumption, the control rule library might contain equipment parameter adjustment instructions such as reducing motor speed or optimizing operating modes. Based on the performance degradation characteristics of the current degradation stage, candidate equipment parameter adjustment instructions that match are selected from the control rule library.

[0076] Step S143: Perform an anomaly impact assessment on the environmental coupling anomaly mode in the real-time operating status information to obtain the environmental anomaly impact level.

[0077] Then, the environmental coupling anomaly patterns in the real-time operating status information are assessed for their impact. The degree of impact of environmental anomalies on equipment operation is analyzed. For example, abnormal humidity may cause equipment to rust and affect the waste paper processing effect; abnormal vibration may cause equipment parts to loosen and affect the stability of the equipment. Based on the severity of the environmental anomalies and the magnitude of their impact on equipment operation, the impact levels of environmental anomalies are divided into mild, moderate, and severe.

[0078] Step S144: Based on the environmental anomaly impact level, select candidate environment adaptation instructions corresponding to the current environmental anomaly mode from the control rule base.

[0079] Subsequently, candidate environmental adaptation instructions corresponding to the current environmental anomaly mode are selected from the control rule base based on the level of environmental anomaly impact. The control rule base stores environmental adaptation instructions corresponding to different levels of environmental anomaly impact. For example, if the level of environmental anomaly impact is mild, possible environmental adaptation instructions include strengthening ventilation and adjusting the parameters of humidity control equipment; if the level of environmental anomaly impact is severe, more radical measures may be required, such as suspending production or carrying out comprehensive environmental remediation.

[0080] Step S145: Perform strategy priority sorting on the candidate device parameter adjustment instructions and the candidate environment adaptation instructions to generate the dynamic control strategy set.

[0081] Finally, the candidate device parameter adjustment instructions and candidate environment adaptation instructions are prioritized according to policy. Considering the importance and urgency of different instructions to device operation and environmental improvement, each instruction is assigned a priority. For example, instructions that seriously affect the safe operation of the device are given higher priority; instructions that have some impact on device performance but are not urgent are given lower priority. The prioritized candidate device parameter adjustment instructions and candidate environment adaptation instructions are then combined to generate a dynamic control policy set.

[0082] Step S150: Dynamically adjust the operating parameters of the production equipment according to the set of dynamic control strategies, and update the real-time monitoring data set based on the adjusted operating parameters.

[0083] After generating a set of dynamic control strategies, the operating parameters of the production equipment need to be dynamically adjusted based on this set, and the real-time monitoring data set needs to be updated based on the adjusted operating parameters. In the waste paper recycling production scenario, this step ensures that the equipment is optimized and adjusted according to the real-time operating status, thereby improving production efficiency and quality.

[0084] Step S151: Parse the equipment parameter adjustment instructions in the set of dynamic control strategies to determine the target equipment parameters to be adjusted and the adjustment range.

[0085] In waste paper recycling production scenarios, parsing the equipment parameter adjustment instructions in the dynamic control strategy set is a crucial first step. For example, if the dynamic control strategy set includes equipment parameter adjustment instructions for the pulper, the instructions may explicitly state that parameters such as the pulper's motor speed and pulping time should be adjusted. For the target equipment parameter, motor speed, the specific adjustment range needs to be determined. Assuming the current motor speed is a parameter R1 (represented by a letter), and the adjustment instruction requires adjusting it to a new speed R2, then the adjustment range is the difference between R2 and R1, i.e., R2 - R1. Similarly, for the pulping time parameter, assuming the current pulping time is T1 and the adjusted pulping time is T2, the adjustment range is T2 - T1. Through this parsing process, the target equipment parameter to be adjusted and its corresponding adjustment range can be accurately determined, providing a clear basis for subsequent parameter adjustment operations.

[0086] Step S152: Match the corresponding device control interface according to the type of the target device parameters, and send parameter adjustment instructions to the actuator of the production equipment through the device control interface.

[0087] Next, the corresponding equipment control interface is matched based on the type of the determined target equipment parameter. On a waste paper recycling production line, different equipment parameters correspond to different control interfaces. Taking a pulper as an example, if the target equipment parameter is motor speed, the corresponding equipment control interface might be the motor speed controller. Through this speed controller, the parameter adjustment command for adjusting the motor speed can be sent to the motor actuator of the pulper. Similarly, if the target equipment parameter is pulping time, the corresponding equipment control interface might be the pulper's time control module, through which the command for adjusting the pulping time is sent to the corresponding actuator of the pulper. During the command sending process, it is necessary to ensure the accuracy and completeness of the command to guarantee that the actuator can correctly execute the adjustment operation.

[0088] Step S153: Monitor the response data of the actuator to the parameter adjustment command in real time, and calculate the parameter adjustment error rate based on the response data.

[0089] After the parameter adjustment command is sent to the actuator, the actuator's response data needs to be monitored in real time. For adjusting the motor speed of the pulper, the actual speed R_actual of the motor is monitored in real time. The actual speed R_actual is compared with the target speed R2 to calculate the speed adjustment error rate. The calculation logic of the error rate is as follows: first, calculate the absolute value of the difference between the actual speed and the target speed, i.e., |R_actual-R2|, and then divide this difference by the target speed R2 to obtain the speed adjustment error rate E_R. For adjusting the pulping time, the actual pulping time T_actual of the pulper is monitored in real time. Similarly, the absolute value of the difference between the actual pulping time and the target pulping time T2 is calculated, i.e., |T_actual-T2|, and then divided by the target pulping time T2 to obtain the pulping time adjustment error rate E_T. By monitoring and calculating the parameter adjustment error rate in real time, the execution status of the actuator to the parameter adjustment command can be understood in a timely manner.

[0090] Step S154: If the parameter adjustment error rate exceeds a preset threshold, the process of regenerating the dynamic control strategy set is triggered, and the parameter adjustment instruction is updated based on the regenerated dynamic control strategy set.

[0091] If the calculated parameter adjustment error rate exceeds a preset threshold, it indicates that the current parameter adjustment has not achieved the expected effect, and the process of regenerating the dynamic control strategy set needs to be triggered. Taking the adjustment of the pulper motor speed as an example, if the speed adjustment error rate E_R exceeds the preset speed error threshold E_R_threshold, the real-time operating status of the production equipment needs to be reassessed. This includes re-collecting equipment operating parameters and environmental related parameters, performing dynamic feature extraction processing again, identifying the real-time operating status information of the equipment, and then regenerating the dynamic control strategy set based on the new real-time operating status information. The regenerated dynamic control strategy set will contain new equipment parameter adjustment instructions. These new instructions will update the previous parameter adjustment instructions and be sent to the actuator again for adjustment, hoping to achieve a better adjustment effect.

[0092] Step S160: According to claim 8, after dynamically adjusting the operating parameters of the production equipment according to the set of dynamic control strategies, the method further includes obtaining a set of equipment response data corresponding to the adjusted operating parameters, wherein the set of equipment response data includes equipment operating status indicators and environmental status indicators after parameter adjustment.

[0093] After dynamically adjusting the operating parameters of the production equipment, it is necessary to obtain the equipment response data set corresponding to the adjusted operating parameters. In the waste paper recycling production scenario, for a pulper, equipment operating status indicators may include adjusted motor speed, pulping efficiency, energy consumption, and other parameters, while environmental status indicators may include humidity and air quality in the workshop. For example, after adjusting the pulper motor speed, the actual motor speed is collected in real time by corresponding sensors and used as one of the equipment operating status indicators. At the same time, humidity sensor data and air quality sensor data in the workshop are collected as environmental status indicators. These data constitute the equipment response data set, which can reflect the actual operating status of the equipment and the changes in the environment after parameter adjustment.

[0094] Step S161: Perform a difference analysis on the equipment operating status indicators and the expected adjustment target to generate an evaluation result of the parameter adjustment effect.

[0095] Next, a difference analysis was performed on the equipment operating status indicators and the expected adjustment targets. Taking the motor speed of the pulper as an example, the expected adjustment target speed was R2, while the actual adjusted motor speed was R_actual. The difference between the two, |R_actual-R2|, was calculated, and the parameter adjustment effect was evaluated based on the magnitude of this difference and the preset evaluation criteria. If the difference was small, it indicated a good adjustment effect, and the parameter adjustment effect evaluation result might be "good"; if the difference was large, it indicated a poor adjustment effect, and the evaluation result might be "poor". A similar method was used to analyze the difference for other equipment operating status indicators such as pulping efficiency. The evaluation results of each equipment operating status indicator were combined to generate the final parameter adjustment effect evaluation result.

[0096] Step S162: Perform a difference analysis on the environmental status indicators and the expected environmental adaptation target to generate an environmental adaptation effect evaluation result.

[0097] For environmental status indicators, a difference analysis is also required between the actual environmental status indicators and the expected environmental adaptation target. Taking humidity in the workshop as an example, the expected environmental adaptation target humidity is H2, and the actual collected adjusted humidity is H_actual. The difference between the two, |H_actual-H2|, is calculated, and the environmental adaptation effect is evaluated based on the magnitude of the difference and the preset evaluation criteria. If the difference is within an acceptable range, it indicates that the environmental adaptation effect is good, and the environmental adaptation effect evaluation result may be "meets the standard"; if the difference exceeds the range, it indicates that the environmental adaptation effect is not ideal, and the evaluation result may be "does not meet the standard". Similar analysis is performed for other environmental status indicators such as air quality, and the evaluation results of various environmental status indicators are combined to generate the environmental adaptation effect evaluation result.

[0098] Step S163: If the parameter adjustment effect evaluation result indicates that the equipment operating status index has not reached the expected adjustment target, then the priority of the control strategy associated with the current equipment parameter adjustment command is increased.

[0099] If the evaluation results of parameter adjustment effects show that the equipment operating status indicators have not reached the expected adjustment targets, it indicates that the current equipment parameter adjustment commands may need to be executed and optimized with higher priority. For example, if the motor speed of the pulper does not reach the expected target after adjustment, then the control strategy associated with the motor speed adjustment command needs to be prioritized. This means that in subsequent control processes, further adjustments to the motor speed will be given higher priority, possibly with larger adjustment magnitudes or more refined adjustment strategies, in order to bring the equipment operating status indicators to the expected targets as quickly as possible.

[0100] Step S164: If the environmental adaptation effect evaluation result indicates that the environmental status index has not reached the expected environmental adaptation target, then the priority of the control strategy associated with the current environmental adaptation command is increased.

[0101] Similarly, if the environmental adaptation effect assessment results indicate that the environmental status indicators have not reached the expected environmental adaptation goals, the priority of the control strategies associated with the current environmental adaptation commands needs to be increased. For example, if the humidity in the workshop has not reached the expected adaptation goal, the priority of the control strategies for environmental adaptation commands related to humidity adjustment will be increased. This might involve increasing the operating power of humidity control equipment or adjusting the parameters of the ventilation system to accelerate the process of the environmental status indicators reaching the expected goals.

[0102] Step S165: If the parameter adjustment effect evaluation result and the environmental adaptation effect evaluation result both meet the expected goals, then reduce the priority of the executed control strategy and activate the next candidate control strategy.

[0103] When both the parameter adjustment effect evaluation results and the environmental adaptation effect evaluation results meet the expected goals, it indicates that the currently implemented control strategy has achieved good results. At this point, reducing the priority of the executed control strategies means that these successfully executed strategies will no longer be given priority in subsequent control processes. Simultaneously, the next candidate control strategy is activated to continue optimizing and adjusting the operating parameters of the production equipment and the environment to further improve production efficiency and quality. For example, if the motor speed of the pulper and the humidity in the workshop both meet the expected goals, then the priority of control strategies related to motor speed and humidity adjustments is reduced, and the next candidate control strategy targeting equipment energy consumption or waste paper processing quality is activated.

[0104] After updating the real-time monitoring dataset based on the adjusted operating parameters, the process also includes:

[0105] Step S170: Perform anomaly detection processing on the updated real-time monitoring data set to identify abnormal data fragments generated during the data acquisition process.

[0106] After updating the real-time monitoring dataset, anomaly detection processing is required to identify any abnormal data segments that may have occurred during data acquisition. In the waste paper recycling production scenario, abnormal data may arise due to sensor malfunctions, communication interference, or other reasons. For pulper operating parameters, such as temperature and pressure, anomaly detection is performed by setting normal value ranges. Assuming the normal value range for temperature parameters is between T_min and T_max, if the collected temperature data exceeds this normal range, it is marked as abnormal data. The same method is used for anomaly detection for other operating parameters such as pressure and energy consumption, as well as environmentally related parameters such as humidity and vibration. By traversing the updated real-time monitoring dataset, all data segments that exceed the normal value range are identified and designated as abnormal data segments.

[0107] Step S171: Perform data repair processing on the abnormal data fragments to generate a repaired subset of real-time monitoring data.

[0108] After identifying abnormal data segments, data repair is required. A common repair method is interpolation. Taking the temperature data of a pulper as an example, if the temperature data collected at a certain moment is an abnormal value T_abnormal, and the normal temperature data before and after that moment are T_before and T_after, respectively, the abnormal value can be repaired using linear interpolation. The calculation logic of linear interpolation is to calculate the estimated temperature value T_estimate at that moment based on the time interval and numerical relationship of the normal data before and after. Assuming the time interval between the normal data before and after is Δt, and the time interval between the abnormal value moment and the previous normal data moment is Δt1, then T_estimate = T_before + (T_after - T_before) * (Δt1 / Δt). A similar interpolation method is used to repair abnormal data for other parameters. All the repaired data are combined to generate a repaired subset of real-time monitoring data.

[0109] Step S172: Merge the repaired real-time monitoring data subset with the normal data fragments to generate an updated real-time monitoring data set.

[0110] The repaired subset of real-time monitoring data is merged with previously unidentified normal data segments. The merging process involves arranging the data chronologically and inserting the repaired data into its corresponding time slots. For example, in a time series, the repaired temperature, pressure, and energy consumption data are sorted with their corresponding normal data by timestamp, forming a complete and updated real-time monitoring dataset. This dataset includes both repaired abnormal and normal data, providing a more accurate reflection of the operating status of production equipment and environmental conditions.

[0111] Step S173: Re-execute the dynamic feature extraction process and subsequent steps based on the updated real-time monitoring data set to achieve closed-loop control of the production equipment.

[0112] Finally, the dynamic feature extraction process and subsequent steps are re-executed based on the updated real-time monitoring data set. The updated real-time monitoring data set is again subjected to temporal and spatial segmentation processing to extract equipment operation feature sets and environmental correlation feature sets. Based on these feature sets, the real-time operating status information of the production equipment is identified, a dynamic control strategy set is generated, the operating parameters of the production equipment are dynamically adjusted, and the real-time monitoring data set is updated. By continuously cyclically executing these steps, closed-loop control of the production equipment is achieved, ensuring that the production equipment always operates in optimal condition, thereby improving the efficiency and quality of waste paper recycling production.

[0113] Regarding the construction and training of state classification models:

[0114] Step S210: Construct a state classification model, which adopts a multilayer perceptron (MLP) and includes an input layer, a hidden layer and an output layer.

[0115] When constructing the state classification model, a Multilayer Perceptron (MLP) is chosen as the model structure. The number of neurons in the input layer is determined by the dimension of the joint state feature vector. Assuming the dimension of the joint state feature vector is n, then the input layer has n neurons to receive the various feature values ​​of the joint state feature vector. Multiple hidden layers can be set, each containing a certain number of neurons. These neurons transform the input data and extract features through a non-linear activation function. The number of neurons in the output layer is determined by the number of state classification categories. For example, if the state classification results are divided into three types: normal operating state, mildly abnormal state, and severely abnormal state, then the output layer has 3 neurons.

[0116] Step S220: Prepare training data, which includes joint state feature vector samples and corresponding state classification labels.

[0117] When preparing training data, a large number of joint state feature vector samples and corresponding state classification labels are collected. The joint state feature vector samples are obtained by jointly encoding historical equipment operation feature sets and environmental correlation feature sets. State classification labels are assigned based on expert experience or actual equipment operation conditions. For example, a normally operating equipment state is labeled "normal operating state"; a state with minor faults that do not affect normal production is labeled "minor abnormal state"; and a state that seriously affects production or may even damage the equipment is labeled "serious abnormal state". These joint state feature vector samples and corresponding state classification labels are combined to form the training dataset.

[0118] Step S230: Initialize model parameters, including the weight matrix from the input layer to the hidden layer, the weight matrix from the hidden layer to the output layer, and the bias vector of each layer.

[0119] Before training begins, the model parameters need to be initialized. The dimension of the weight matrix W1 from the input layer to the hidden layer is the number of neurons in the hidden layer multiplied by the number of neurons in the input layer, and the dimension of the weight matrix W2 from the hidden layer to the output layer is the number of neurons in the output layer multiplied by the number of neurons in the hidden layer. The dimensions of the bias vectors b1 and b2 for each layer are the same as the number of neurons in the hidden layer and the output layer, respectively. The initial values ​​of these weight matrices and bias vectors can be generated using random initialization methods, such as using a uniform distribution or a Gaussian distribution to generate random values.

[0120] Step S240: Perform model training, using the backpropagation algorithm and optimizer to update the model parameters.

[0121] During model training, backpropagation and an optimizer are used to update the model parameters. First, the joint state feature vector samples from the training dataset are input into the MLP. After computation through the input layer, hidden layer, and output layer, the model's output is obtained. The model's output is compared with the corresponding state classification label, and the loss function value is calculated. The loss function can be the cross-entropy loss function, which measures the difference between the model's output and the true label. Then, the gradient of the loss function with respect to the model parameters is calculated using the backpropagation algorithm. Based on the gradient information, an optimizer (such as stochastic gradient descent, Adam optimizer, etc.) is used to update the model parameters. This process is repeated until the model's loss function value converges or the preset number of training epochs is reached.

[0122] Step S250: Evaluate model performance by testing the trained model using a test dataset and calculating metrics such as accuracy and recall.

[0123] After model training is complete, the performance of the model is evaluated using a test dataset. The test dataset is prepared similarly to the training dataset, containing joint state feature vector samples and corresponding state classification labels. Samples from the test dataset are input into the trained model to obtain the model's prediction results. The prediction results are compared with the true labels to calculate metrics such as accuracy and recall. Accuracy represents the proportion of correctly predicted samples out of the total number of samples, while recall represents the proportion of correctly predicted samples of a particular class out of the total number of true samples of that class. These metrics are used to evaluate the model's performance. If the performance is unsatisfactory, the model's structure or training parameters can be adjusted, and retraining can be performed.

[0124] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0125] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, it is intended that all variations falling within the meaning and scope of equivalents of the claims be included within the present invention.

Claims

1. A method for intelligent control of production equipment based on real-time feedback, characterized in that, The method includes: The system collects a set of real-time monitoring data during the operation of production equipment, including equipment operating parameters and environmental parameters. Dynamic feature extraction processing is performed on the real-time monitoring data set to obtain a set of equipment operation features and a set of environmental related features; Based on the correlation between the set of equipment operation features and the set of environmental associated features, the real-time operating status information of the production equipment is identified; Based on the real-time operating status information, a set of dynamic control strategies for the production equipment is generated. The set of dynamic control strategies includes equipment parameter adjustment instructions and environment adaptation instructions. The operating parameters of the production equipment are dynamically adjusted according to the set of dynamic control strategies, and the real-time monitoring data set is updated based on the adjusted operating parameters. The step of identifying the real-time operating status information of the production equipment based on the correlation between the equipment operating feature set and the environmental associated feature set includes: Obtain the device operation feature subset for each time window in the device operation feature set, and the environment association feature subset for the corresponding time window in the environment association feature set; The device operation feature subset and the environment-related feature subset are jointly encoded to generate a joint state feature vector for each time window; The joint state feature vector is processed for state identification according to the preset state classification model to obtain the preliminary state classification result for each time window; The preliminary state classification results of the continuous time window are processed by state transition analysis to generate real-time operating status information of the production equipment in the continuous operating cycle. The real-time operating status information includes the equipment performance degradation trend and environmental coupling anomaly mode.

2. The intelligent control method for production equipment based on real-time feedback according to claim 1, characterized in that, The dynamic feature extraction process performed on the real-time monitoring data set yields a set of equipment operation features and a set of environmental correlation features, including: The device operating parameters in the real-time monitoring data set are processed by time-series segmentation to obtain a set of device operating sub-parameters corresponding to multiple consecutive time windows; Multi-dimensional feature extraction processing is performed on each set of equipment operation sub-parameters to obtain a set of equipment operation features corresponding to each time window. The multi-dimensional feature extraction processing includes parameter fluctuation feature extraction, trend correlation feature extraction, and anomaly accumulation feature extraction. The environmental parameters in the real-time monitoring data set are spatially partitioned to obtain a set of environmental sub-parameters corresponding to each time window; Environmental response feature extraction processing is performed on each set of environmental associated sub-parameters to obtain the environmental associated feature subset corresponding to each time window; The device operation feature subset and the environment-related feature subset of each time window are aggregated to generate the device operation feature set and the environment-related feature set.

3. The intelligent control method for production equipment based on real-time feedback according to claim 1, characterized in that, The step of generating a set of dynamic control strategies for the production equipment based on the real-time operating status information includes: The device performance degradation trend in the real-time operating status information is divided into degradation stages to obtain the performance degradation characteristics corresponding to different degradation stages; Based on the performance degradation characteristics, a preset control rule library is matched to filter and obtain candidate device parameter adjustment instructions corresponding to the current degradation stage; An anomaly impact degree assessment is performed on the environmental coupling anomaly patterns in the real-time operating status information to obtain the environmental anomaly impact level. Based on the environmental anomaly impact level, candidate environmental adaptation instructions corresponding to the current environmental anomaly mode are selected from the control rule base. The candidate device parameter adjustment instructions and the candidate environment adaptation instructions are sorted by strategy priority to generate the dynamic control strategy set.

4. The intelligent control method for production equipment based on real-time feedback according to claim 1, characterized in that, The step of dynamically adjusting the operating parameters of the production equipment according to the set of dynamic control strategies includes: Analyze the equipment parameter adjustment instructions in the dynamic control strategy set to determine the target equipment parameters to be adjusted and the adjustment range; Match the corresponding equipment control interface according to the type of the target equipment parameters, and send parameter adjustment instructions to the actuator of the production equipment through the equipment control interface; The system monitors the response data of the actuator to the parameter adjustment command in real time and calculates the parameter adjustment error rate based on the response data. If the parameter adjustment error rate exceeds a preset threshold, a process for regenerating the dynamic control strategy set is triggered, and the parameter adjustment instruction is updated based on the regenerated dynamic control strategy set.

5. The intelligent control method for production equipment based on real-time feedback according to claim 1, characterized in that, The collection of real-time monitoring data from the production equipment during operation includes: Configure multiple sensor nodes connected to the production equipment, the sensor nodes including equipment parameter sensors and environmental parameter sensors; The operating parameters of the production equipment are collected by the equipment parameter sensors, including temperature parameters, pressure parameters, and energy consumption parameters. The environmental parameter sensor collects environmental parameters related to the environment in which the production equipment is located. These environmental parameters include humidity parameters, vibration parameters, and air quality parameters. The operating parameters and the environmental parameters are standardized to generate a set of real-time monitoring data with unified dimensions.

6. The intelligent control method for production equipment based on real-time feedback according to claim 5, characterized in that, The step of standardizing the operating parameters and the environmental parameters to generate a real-time monitoring data set with unified dimensions includes: The temperature, pressure, and energy consumption parameters in the operating parameters are normalized to obtain standardized temperature, pressure, and energy consumption parameters, respectively. The humidity parameter, vibration parameter, and air quality parameter in the environmental correlation parameters are normalized to obtain standardized humidity parameter, standardized vibration parameter, and standardized air quality parameter; The standardized temperature parameter, standardized pressure parameter, standardized energy consumption parameter, standardized humidity parameter, standardized vibration parameter, and standardized air quality parameter are aligned according to timestamps to generate the unified dimension real-time monitoring data set.

7. The intelligent control method for production equipment based on real-time feedback according to claim 1, characterized in that, After dynamically adjusting the operating parameters of the production equipment according to the set of dynamic control strategies, the method further includes: Obtain the set of device response data corresponding to the adjusted operating parameters, wherein the set of device response data includes the device operating status indicators and environmental status indicators after parameter adjustment; The difference between the equipment operating status indicators and the expected adjustment targets is analyzed to generate an evaluation result of the parameter adjustment effect. The environmental status indicators are analyzed to determine the difference between the environmental status indicators and the expected environmental adaptation targets, and the environmental adaptation effect evaluation results are generated. If the evaluation result of the parameter adjustment effect indicates that the equipment operating status indicators have not reached the expected adjustment target, then the priority of the control strategy associated with the current equipment parameter adjustment command will be increased; If the environmental adaptation effect assessment result indicates that the environmental status indicators have not reached the expected environmental adaptation target, then the priority of the control strategy associated with the current environmental adaptation command will be increased. If both the parameter adjustment effect evaluation result and the environmental adaptation effect evaluation result meet the expected goals, the priority of the implemented control strategy will be reduced, and the next candidate control strategy will be activated.

8. The intelligent control method for production equipment based on real-time feedback according to claim 1, characterized in that, After updating the real-time monitoring data set based on the adjusted operating parameters, the process further includes: Anomaly detection processing is performed on the updated real-time monitoring dataset to identify abnormal data fragments generated during the data acquisition process; The abnormal data fragments are repaired to generate a repaired subset of real-time monitoring data. The repaired real-time monitoring data subset is merged with the normal data fragments to generate an updated real-time monitoring data subset; Based on the updated real-time monitoring data set, the dynamic feature extraction process and subsequent steps are re-executed to achieve closed-loop control of the production equipment.

9. A production equipment intelligent control system based on real-time feedback, characterized in that, include: The processor, communication interface, memory, and communication bus are provided, wherein the processor, communication interface, and memory communicate with each other via the communication bus. The memory is used to store computer programs; the processor is used to execute the computer programs to implement the steps of the intelligent control method for production equipment based on real-time feedback as described in any one of claims 1-8.

Images