Operation and maintenance processing method and system applied to intelligent solid beverage production control platform

Abstract

The invention relates to an operation and maintenance processing method and system applied to a solid beverage intelligent production control platform, and belongs to the technical field of equipment operation and maintenance processing. Comprising the steps of obtaining sensor monitoring data and control platform state data; the edge detection module checks the collected system data, diagnoses the operation states of the sensor and the control platform, and gives an alarm when the network performance data is abnormal; integrating the authenticated data into a data packet based on the device code, encrypting the data packet, and uploading the encrypted data packet to a cloud computing center; the cloud computing center predicts the equipment fault state through the received system data; and according to the prediction result of the equipment fault state, generating an operation state score of each piece of processing equipment. According to the invention, through cloud-side cooperation, system data is uploaded after the state of the control platform is detected, and fault prediction of the processing equipment is carried out, so that predictive operation and maintenance of the equipment are realized, and the system stability and the production efficiency are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of equipment operation and maintenance processing, and specifically relates to an operation and maintenance processing method and system applied to a solid beverage intelligent production control platform. Background Art

[0002] Solid beverages, also known as solid drinks, refer to solid products made from food raw materials, additives, etc. in powder, granular or block form for mixing or brewing. Solid beverages are convenient, easy to carry, easy to store, delicate in taste, and rich in nutrition, and are loved by many consumers. The production process of solid beverages usually includes multiple steps such as raw material pretreatment, mixing, drying, and packaging. These links require high-precision monitoring and control to ensure product quality and production efficiency. At present, most solid beverage production lines still rely on manual intervention and experience management. This method has problems such as low efficiency, insufficient data utilization, and delayed fault handling. At the same time, there are a large number of designed equipment on the automated production line, which has the characteristics of large data volume and high real-time processing requirements. In addition, the existing technology only focuses on the operating status of the equipment itself for fault detection, but usually lacks a comprehensive analysis of equipment status data and control process data, resulting in low prediction accuracy.

[0003] Therefore, it is urgent to propose an operation and maintenance processing method and system applied to the solid beverage intelligent production control platform, so as to realize the efficiency and intelligence of modern production of solid beverages through cloud-edge collaboration. Summary of the invention

[0004] In order to solve the above-mentioned problems existing in the prior art, the present invention provides an operation and maintenance processing method and system applied to a solid beverage intelligent production control platform. Through cloud-edge collaboration, the control platform status is detected and then the system data is uploaded to predict the faults of the processing equipment, thereby realizing predictive operation and maintenance of the equipment and improving system stability and production efficiency.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A first aspect of the present disclosure provides an operation and maintenance processing method applied to a solid beverage intelligent production control platform, comprising the following steps:

[0007] Collect system data: obtain sensor monitoring data and control platform status data;

[0008] System data authentication: The edge detection module checks the collected system data, diagnoses the operating status of the sensor and control platform, completes the authentication of the system data, and issues an alarm when abnormal network performance data occurs;

[0009] Authentication data upload: The authenticated data is integrated into a data package based on the device code and uploaded to the cloud computing center after encryption;

[0010] Fault status assessment: The cloud computing center predicts the equipment fault status based on the received system data;

[0011] Generate operation and maintenance reports: Generate an operation status score for each processing equipment based on the predicted results of equipment failure status, and use trend charts and heat maps to show the time and space distribution of potential problems.

[0012] Furthermore, the sensor monitoring data includes temperature, humidity, pressure, flow, vibration and electric energy data; the control platform status data includes network performance data and control log data.

[0013] Furthermore, the system data authentication comprises the following steps:

[0014] Data preprocessing: Clean and organize system data, remove noise and outliers, and perform data standardization or normalization;

[0015] Establish control logic model: classify system data, determine state variables, use system identification method to estimate system matrix parameters, and build control logic model for detection or prediction;

[0016] Logical consistency analysis: Use the set rules in the control logic to build a logical judgment framework and use Boolean logic expressions to define the rule base;

[0017] Build a series of rule-based judgment logic, monitor the system output in real time, check whether it complies with the predetermined rules, and mark the logic anomaly if the output deviates from the rules.

[0018] Furthermore, the control logic model is expressed as:

[0019] x′(t)=Ax(t)+Bu(t);

[0020] y(t)=Cx(t)+Du(t);

[0021] Where x(t) is the state vector, x′(t) is the time derivative of the state vector, u(t) is the input vector, y(t) is the output vector, A, B, C, and D are the system matrix, input matrix, output matrix, and direct transfer matrix, respectively.

[0022] Furthermore, the system data authentication further includes the following steps:

[0023] Fault feature extraction: Extract the features of system data based on abnormal logic, use wavelet transform to decompose the signal into different frequency components, identify the sudden changes, periodic changes and frequency characteristics in the signal, identify the fault features and classify them;

[0024] Fault prediction and classification: LSTM neural network is used to make predictions based on the historical data of time series signals. The signal sequence is input into the LSTM model. The units in the hidden layer are used to capture the temporal relationship between signals. The output layer predicts the fault probability and category based on the classification task.

[0025] Fault alarm and response: Use a dynamic threshold alarm system to dynamically set the alarm threshold based on the statistical characteristics of the control system during normal operation. When the monitoring signal exceeds the preset range, an alarm is triggered, and a normal signal is authenticated.

[0026] Furthermore, the fault status assessment comprises the following steps:

[0027] Data integration: Define the equipment status through power data to establish status labels, assign corresponding status labels to vibration data to complete data annotation, and establish a prediction data set;

[0028] Signal decomposition: The vibration signal is decomposed using the improved adaptive noise complete empirical mode decomposition method;

[0029] Feature extraction: Calculate the correlation coefficient between each IMF component and the original vibration signal, and select the IMF component for reconstruction to form a reconstructed signal based on the results of the correlation analysis;

[0030] Determine the parameters for fuzzy entropy calculation, including embedding dimension and tolerance, and construct fuzzy sets based on the selected IMF components;

[0031] The calculated fuzzy entropy value is combined with the mean, variance and kurtosis of the IMF component to form a feature vector set.

[0032] Furthermore, the fault status assessment comprises the following steps:

[0033] Model training: Take the extracted feature vector set as input data and match it with the corresponding state label data. Select the bidirectional long short-term memory network for training. Use historical data and corresponding state labels for supervised learning. Minimize the prediction error by optimizing the model parameters.

[0034] State prediction: Use the trained Bi-LSTM model to predict the collected vibration signal and output the health status of the equipment; the model uses the extracted feature vectors through the forward propagation process to perform real-time health status assessment.

[0035] Furthermore, the signal decomposition specifically comprises the following steps:

[0036] De-noising the original vibration signal to remove background noise and interference, and normalize it at the same time;

[0037] Set the parameters of the ICEEMDAN algorithm, including the number of decomposition levels and noise amplitude, and add an appropriate amount of white noise to the original vibration signal;

[0038] The empirical mode decomposition method is used to decompose the noisy signal and extract multiple IMFs; noise is repeatedly added to each IMF component and EMD decomposition is performed until the preset decomposition level or convergence condition is reached.

[0039] A second aspect of the present disclosure provides an operation and maintenance processing system applied to a solid beverage intelligent production control platform, which is used to execute an operation and maintenance processing method applied to a solid beverage intelligent production control platform as described above, including an edge monitoring module and a cloud computing center, wherein the edge monitoring module establishes a communication connection with the cloud computing center in a wired or wireless manner;

[0040] The edge monitoring module is used to collect system data of the control platform and perform data authentication and fault warning, and upload the authenticated data to the cloud computing center.

[0041] As a preferred technical solution of the present invention, the edge monitoring module is used to monitor the status of the running equipment in the area at the equipment node, control the compliance of the input and output status detection execution logic of the platform, and perform timely system status monitoring. When an abnormality is detected, real-time alarm processing is performed. When there is no abnormality, the system data is sent to the cloud computing center according to the data upload stage;

[0042] The cloud computing center is used to predict the equipment failure status of the solid beverage production line through sensor data and generate an equipment operation and maintenance report.

[0043] The beneficial effects of the present invention are:

[0044] The present invention first collects two parts of data from the control platform, including the equipment status data used by the control platform to automatically control the operating parameters of the equipment and the process data generated by the control platform control; by providing an edge monitoring module to monitor the communication status and control logic of the control platform, real-time alarm for the control platform is realized, and the validity of the input data used for early warning of full equipment failures is guaranteed through logical detection, thereby improving the accuracy and reliability of fault prediction in the cloud computing center, realizing the predictive operation and maintenance of production equipment and the automated control rule operation and maintenance of the control platform; at the same time, through cloud-edge collaboration, the efficiency of operation and maintenance data processing and the real-time processing capability of the system are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0046] Figure 1 A schematic flow chart of an operation and maintenance processing method applied to a solid beverage intelligent production control platform provided by an embodiment of the present invention;

[0047] Figure 2 A schematic diagram of the structure of an operation and maintenance processing system applied to a solid beverage intelligent production control platform provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0049] The solid beverage smart production control platform controls thousands of rotating and moving equipment or parts on the production line. Once a failure occurs, the entire production will stop, resulting in huge economic losses or production safety accidents. Therefore, it is necessary to perform predictive operation and maintenance on the equipment, and through real-time monitoring of equipment and parts, to perceive equipment failures in advance, prevent equipment failures in advance, and efficiently solve equipment failures to meet the needs of full life cycle management of important equipment and parts.

[0050] This embodiment provides an operation and maintenance processing method applied to a solid beverage intelligent production control platform, such as Figure 1 As shown, the following steps are included:

[0051] S1. Collect system data: obtain sensor monitoring data and control platform status data, where sensor monitoring data includes temperature, humidity, pressure, flow, vibration and power data; control platform status data includes network performance data and control log data.

[0052] It is understandable that the sensor monitoring data includes, on the one hand, the index data of the material itself during the production and processing of solid beverages, such as temperature, humidity, pressure and flow, among which the flow data refers to the flow rate during the material processing process, which is used to correspond to the running speed of the equipment or the processing effect. On the other hand, it includes the operating status data of the processing equipment, such as equipment vibration data and power data, so as to feedback the operating status of the equipment.

[0053] It should be noted that the control platform status data is used to detect the communication connection status between the production control platform and the equipment-side control module and the control logic of the production control platform to ensure the normal operation of the control platform, thereby verifying the accuracy of the sensor data and automatically adjusting the operating parameters of the processing equipment based on the sensor equipment. The control log data records the execution process of the control program, including logical judgment, control instructions, state changes, etc., in order to analyze whether the program has logical errors or abnormal behavior.

[0054] S2. System data authentication: The edge detection module checks the collected system data, diagnoses the operating status of the sensor and control platform, completes the authentication of the system data, and issues an alarm when the network performance data is abnormal. The specific steps include:

[0055] S21. Data preprocessing: Clean and organize system data, remove noise and outliers, and standardize or normalize the data.

[0056] S22. Establish a control logic model: classify the system data, determine the state variables (such as input signals, output signals, and feedback signals), use the system identification method to estimate the system matrix parameters, and build a control logic model for detection or prediction.

[0057] Among them, the control logic model is expressed as:

[0058] x′(t)=Ax(t)+Bu(t);

[0059] y(t)=Cx(t)+Du(t);

[0060] Where x(t) is the state vector, x′(t) is the time derivative of the state vector, u(t) is the input vector, y(t) is the output vector, A, B, C, and D are the system matrix, input matrix, output matrix, and direct transfer matrix, respectively.

[0061] It is understandable that after the model is established and the system matrix parameters are estimated through system identification methods, the model fitting effect needs to be verified and the accuracy is evaluated through residual analysis or mean square error (MSE). The system identification, such as through the least squares method, minimizes the error between the actual output and the model output.

[0062] S23, logical consistency analysis: Use the set rules in the control logic (such as "IF-THEN" conditions) to build a logical judgment framework and use Boolean logic expressions to define the rule base;

[0063] Build a series of rule-based decision logic (for example, using SQL rules or custom logic language), monitor system output in real time, check whether it complies with the predetermined rules, and mark the logic anomaly if the output deviates from the rules.

[0064] S24, fault feature extraction: extract the features of system data according to abnormal logic, use wavelet transform to decompose the signal into different frequency components, identify the sudden change, periodic change and frequency characteristics in the signal, identify the fault features and classify them;

[0065] S25. Fault prediction and classification: LSTM neural network is used to make predictions based on the historical data of time series signals. Signal sequences (such as control instructions and feedback signals) are input into the LSTM model. The units in the hidden layer are used to capture the temporal relationship between signals. The output layer predicts the fault probability and category based on the classification task.

[0066] LSTM neural network (Long Short-Term Memory) is a special recurrent neural network (RNN) structure that is used to solve the gradient vanishing and gradient exploding problems of traditional RNN in long sequence data training. LSTM effectively captures long-term dependencies by introducing three gating mechanisms, including input gate, forget gate, and output gate, to control the flow of information.

[0067] It should be noted that the prediction results of the LSTM model are based on the signal features extracted previously, and the weights obtained through training are used to judge the future signal state.

[0068] S26, Fault alarm and response: Use a dynamic threshold alarm system to dynamically set the alarm threshold based on the statistical characteristics of the control system during normal operation (such as mean, standard deviation, etc.). When the monitoring signal exceeds the preset range, an alarm is triggered, and a normal signal is authenticated.

[0069] It should be noted that the edge detection module predicts the faults of the control logic through the collected system data. After preprocessing the collected signal data, it lays the foundation for the establishment of the logic model. By constructing a state space model, the system signal and the logical relationship are quantified. Then, the rule engine method is used to detect the logical consistency of the model to locate potential problems. Then, the abnormal signal features are extracted through wavelet transform to further clarify the fault characteristics. The LSTM model is used to predict the fault trend to classify and judge the type of problem. Finally, based on the dynamic threshold setting, real-time alarms are triggered and response measures are provided. Each step is closely connected to ensure the integrity and effectiveness of the system from data analysis to fault prediction. By predicting the control logic faults of the control platform, the accuracy of the system's automatic control of equipment parameters is guaranteed, so that the equipment can make correct adjustments according to actual needs, which also ensures the validity of the data feedback from the sensor and prevents the error cycle of control.

[0070] S3, Authentication data upload: The authenticated data is integrated into a data packet based on the device code and uploaded to the cloud computing center after encryption.

[0071] S4. Fault status assessment: The cloud computing center predicts the equipment fault status based on the received system data, including the following steps:

[0072] S41, data integration: define the equipment status through the power data to establish the status label, assign the corresponding status label to the vibration data to complete the data labeling, and establish the prediction data set;

[0073] S42, signal decomposition: using the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) method to decompose the vibration signal, specifically including the following steps:

[0074] S421, performing denoising processing on the original vibration signal to remove background noise and interference, and performing normalization processing at the same time;

[0075] S422, setting parameters of the ICEEMDAN algorithm, including the number of decomposition layers and noise amplitude, etc., and adding an appropriate amount of white noise to the original vibration signal to improve the stability and accuracy of the decomposition;

[0076] The Empirical Mode Decomposition (EMD) method is used to decompose the noisy signal and extract multiple Intrinsic Mode Functions (IMFs);

[0077] Repeat adding noise and performing EMD decomposition for each IMF component until the preset number of decomposition levels or convergence conditions are reached.

[0078] S43, feature extraction: calculating the correlation coefficient between each IMF component and the original vibration signal, and selecting the IMF component for reconstruction to form a reconstructed signal according to the result of the correlation analysis;

[0079] Determine the parameters for fuzzy entropy calculation, including embedding dimension and tolerance, and construct fuzzy sets based on the selected IMF components;

[0080] The calculated fuzzy entropy value is combined with the mean, variance and kurtosis of the IMF component to form a feature vector set.

[0081] It is understandable that the fuzzy entropy value of each IMF component under given parameters is calculated. The calculation of fuzzy entropy usually includes the following steps: generating an embedding vector of the time series; calculating the distance between the embedding vectors and performing fuzzification according to the tolerance; statistically calculating the complexity of the fuzzy set, and finally obtaining the fuzzy entropy value.

[0082] S44, model training: Take the extracted feature vector set as input data and match it with the corresponding state label data, select the bidirectional long short-term memory network (Bidirectional Long Short-Term Memory, Bi-LSTM) for training, use historical data and corresponding state labels for supervised learning, and minimize the prediction error by optimizing the model parameters.

[0083] It is understandable that the bidirectional long short-term memory network prediction method takes into account the before and after rules of data information at the prediction moment, which greatly improves the prediction accuracy, and the temporal nature of its data is stronger than that of a single LSTM network.

[0084] S45, state prediction: Use the trained Bi-LSTM model to predict the collected vibration signal and output the health status of the equipment; the model uses the extracted feature vectors through the forward propagation process to perform real-time health status assessment.

[0085] This embodiment uses the above method to predict the state of processing equipment, which can effectively extract key features from complex time series signals, thereby capturing long-term dependencies in equipment operation. This method not only improves the accuracy and reliability of predictions, but also can timely identify potential failure risks, support preventive maintenance and failure warnings of equipment, and ultimately help reduce maintenance costs, extend equipment life, and improve overall production efficiency. Through real-time monitoring and prediction, enterprises can better plan maintenance strategies and reduce unexpected downtime.

[0086] S5. Generate operation and maintenance report: Generate an operation status score for each processing equipment based on the prediction results of the equipment failure status, and use trend charts and heat maps to show the time and space distribution of potential problems.

[0087] This embodiment also provides an operation and maintenance processing system applied to the solid beverage intelligent production control platform, such as Figure 2 As shown, it includes multiple edge monitoring modules and a cloud computing center, and the edge monitoring module establishes a communication connection with the cloud computing center through a wired or wireless method;

[0088] The edge monitoring module is used to collect system data of the control platform and perform data authentication and fault warning, and upload the authenticated data to the cloud computing center.

[0089] It can be understood that the edge monitoring module is used to perform status monitoring on the running equipment in the area at the device node, so as to control the compliance of the input and output status detection execution logic of the platform, conduct timely system status monitoring, and perform real-time alarm processing when an abnormality is detected. When there is no abnormality, the system data will be sent to the cloud computing center according to the data upload stage.

[0090] It should be noted that multiple edge monitoring modules can be set up according to the device node area division to reduce the pressure of computing power and improve processing efficiency.

[0091] The cloud computing center is used to predict the equipment failure status of the solid beverage production line through sensor data and generate an equipment operation and maintenance report.

[0092] It should be noted that the cloud computing center mainly predicts faults of all processing equipment in the solid beverage production line through uploaded system data, and generates operation and maintenance reports for display to achieve predictive operation and maintenance.

[0093] The present invention first collects two parts of data from the control platform, including the equipment status data used by the control platform to automatically control the operating parameters of the equipment and the process data generated by the control platform control; by providing an edge monitoring module to monitor the communication status and control logic of the control platform, real-time alarm for the control platform is realized, and the validity of the input data used for early warning of full equipment failures is guaranteed through logical detection, thereby improving the accuracy and reliability of fault prediction in the cloud computing center, realizing the predictive operation and maintenance of production equipment and the automated control rule operation and maintenance of the control platform; at the same time, through cloud-edge collaboration, the efficiency of operation and maintenance data processing and the real-time processing capability of the system are improved.

[0094] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. An operation and maintenance processing method applied to a solid beverage intelligent production control platform, characterized in that: The following steps are involved: Collect system data: obtain sensor monitoring data and control platform status data; System data authentication: The edge detection module checks the collected system data, diagnoses the operating status of the sensor and control platform, completes the authentication of the system data, and issues an alarm when abnormal network performance data occurs; Authentication data upload: The authenticated data is integrated into a data package based on the device code and uploaded to the cloud computing center after encryption; Fault status assessment: The cloud computing center predicts the equipment fault status based on the received system data; Generate operation and maintenance reports: Generate an operation status score for each processing equipment based on the predicted results of equipment failure status, and use trend charts and heat maps to show the time and space distribution of potential problems.

2. The operation and maintenance processing method applied to the solid beverage intelligent production control platform according to claim 1 is characterized in that: The sensor monitoring data includes temperature, humidity, pressure, flow, vibration and electric energy data; the control platform status data includes network performance data and control log data.

3. The operation and maintenance processing method applied to the solid beverage intelligent production control platform according to claim 1 is characterized in that: The system data authentication comprises the following steps: Data preprocessing: Clean and organize system data, remove noise and outliers, and perform data standardization or normalization; Establish control logic model: classify system data, determine state variables, use system identification method to estimate system matrix parameters, and build control logic model for detection or prediction; Logical consistency analysis: Use the set rules in the control logic to build a logical judgment framework and use Boolean logic expressions to define the rule base; Build a series of rule-based judgment logic, monitor the system output in real time, check whether it complies with the predetermined rules, and mark the logic anomaly if the output deviates from the rules.

4. The operation and maintenance processing method applied to the solid beverage intelligent production control platform according to claim 3 is characterized in that: The control logic model is expressed as: x′(t)=Ax(t)+Bu(t); y(t)=Cx(t)+Du(t); Where x(t) is the state vector, x′(t) is the time derivative of the state vector, u(t) is the input vector, y(t) is the output vector, A, B, C, and D are the system matrix, input matrix, output matrix, and direct transfer matrix, respectively.

5. The operation and maintenance processing method applied to the solid beverage intelligent production control platform according to claim 4, characterized in that: The system data authentication also The following steps are involved: Fault feature extraction: Extract the features of system data based on abnormal logic, use wavelet transform to decompose the signal into different frequency components, identify the sudden changes, periodic changes and frequency characteristics in the signal, identify the fault features and classify them; Fault prediction and classification: LSTM neural network is used to make predictions based on the historical data of time series signals. The signal sequence is input into the LSTM model. The units in the hidden layer are used to capture the temporal relationship between signals. The output layer predicts the fault probability and category based on the classification task. Fault alarm and response: Use a dynamic threshold alarm system to dynamically set the alarm threshold based on the statistical characteristics of the control system during normal operation. When the monitoring signal exceeds the preset range, an alarm is triggered, and a normal signal is authenticated.

6. The operation and maintenance processing method applied to the solid beverage intelligent production control platform according to claim 1, characterized in that: The fault status assessment comprises the following steps: Data integration: Define the equipment status through power data to establish status labels, assign corresponding status labels to vibration data to complete data annotation, and establish a prediction data set; Signal decomposition: The vibration signal is decomposed using the improved adaptive noise complete empirical mode decomposition method; Feature extraction: Calculate the correlation coefficient between each IMF component and the original vibration signal, and select the IMF component for reconstruction to form a reconstructed signal based on the results of the correlation analysis; Determine the parameters for fuzzy entropy calculation, including embedding dimension and tolerance, and construct fuzzy sets based on the selected IMF components; The calculated fuzzy entropy value is combined with the mean, variance and kurtosis of the IMF component to form a feature vector set.

7. The operation and maintenance processing method applied to the solid beverage intelligent production control platform according to claim 6 is characterized by: The fault status assessment comprises the following steps: Model training: Take the extracted feature vector set as input data and match it with the corresponding state label data. Select the bidirectional long short-term memory network for training. Use historical data and corresponding state labels for supervised learning. Minimize the prediction error by optimizing the model parameters. State prediction: Use the trained Bi-LSTM model to predict the collected vibration signal and output the health status of the equipment; the model uses the extracted feature vectors through the forward propagation process to perform real-time health status assessment.

8. The operation and maintenance processing method applied to the solid beverage intelligent production control platform according to claim 7 is characterized in that: The signal decomposition specifically comprises the following steps: De-noising the original vibration signal to remove background noise and interference, and normalize it at the same time; Set the parameters of the ICEEMDAN algorithm, including the number of decomposition levels and noise amplitude, and add an appropriate amount of white noise to the original vibration signal; The empirical mode decomposition method is used to decompose the noisy signal and extract multiple IMFs; noise is repeatedly added to each IMF component and EMD decomposition is performed until the preset decomposition level or convergence condition is reached.

9. An operation and maintenance processing system applied to a solid beverage intelligent production control platform, used to execute an operation and maintenance processing method applied to a solid beverage intelligent production control platform as claimed in any one of claims 1 to 8, characterized in that: It includes multiple edge monitoring modules and a cloud computing center, wherein the edge monitoring modules establish a communication connection with the cloud computing center via wired or wireless means; The edge monitoring module is used to collect system data of the control platform and perform data authentication and fault warning, and upload the authenticated data to the cloud computing center.

10. The operation and maintenance processing system applied to the solid beverage intelligent production control platform according to claim 9, characterized in that: The edge monitoring module is used to monitor the status of the running equipment in the area at the equipment node, control the compliance of the input and output status detection execution logic of the platform, and conduct timely system status monitoring. When an abnormality is detected, real-time alarm processing is performed. When there is no abnormality, the system data is sent to the cloud computing center according to the data upload stage; The cloud computing center is used to predict the equipment failure status of the solid beverage production line through sensor data and generate an equipment operation and maintenance report.

Images