Intelligent predictive dust removal equipment maintenance system and method thereof

Abstract

The invention relates to the technical field of dust removal equipment maintenance systems, in particular to an intelligent predictive dust removal equipment maintenance system and method, and the system comprises a data collection end which is used for collecting the operation data of dust removal equipment; the data storage end is used for storing and preprocessing the operation data; the data processing platform is used for analyzing the operation data and carrying out fault detection and prediction; and the user side is used for displaying the analysis result. Wherein the data acquisition end, the data storage end, the data processing platform and the user end are interconnected through a network to form an integrated data processing system, and the data acquisition end monitors the running state of the dust removal equipment in an omnibearing manner through various types of sensors, so that the comprehensiveness and the accuracy of data are ensured. And the data storage end adopts a distributed storage technology, so that the data processing capability is greatly improved, and the security and reliability of the data are ensured. The data processing platform integrates big data analysis and machine learning technologies, and realizes accurate analysis and prediction of the equipment state.

Description

Technical Field

[0001] The present invention relates to the technical field of dust removal equipment maintenance systems, and in particular to an intelligent predictive dust removal equipment maintenance system and method thereof. Background Art

[0002] With the continuous development of industrial production and increasingly stringent environmental protection requirements, dust removal equipment plays an increasingly important role in industrial production. Traditional dust removal equipment maintenance methods mainly rely on regular inspections and passive responses, which have many shortcomings. First, regular inspections often fail to detect potential problems with equipment in a timely manner, resulting in repairs only when failures occur, causing production line downtime and economic losses. Secondly, passive response maintenance cannot predict the life cycle of equipment, making it difficult to formulate a reasonable maintenance plan, which increases maintenance costs. In addition, traditional methods lack in-depth analysis of equipment operation data, cannot extract valuable information from massive data, and miss the opportunity to optimize equipment performance.

[0003] In recent years, with the development of the Internet of Things and big data technologies, some companies have begun to try to apply these new technologies to the maintenance of dust removal equipment. However, there are still some problems with the existing intelligent maintenance system. First, the comprehensiveness and real-time nature of data collection are insufficient, making it difficult to fully reflect the operating status of the equipment. Secondly, the data storage and processing capabilities are limited and cannot cope with the massive data generated in industrial production. Furthermore, the analysis model of the existing system is relatively simple, and the prediction accuracy is not high, which makes it difficult to meet the high requirements of industrial production for equipment reliability. Finally, the system's scalability and versatility are insufficient, making it difficult to adapt to different types of dust removal equipment and production environments. Summary of the invention

[0004] The present invention aims to solve the above technical problems and proposes an intelligent predictive dust removal equipment maintenance system and method. The system integrates advanced Internet of Things technology, big data processing technology and artificial intelligence algorithms to achieve comprehensive monitoring, intelligent analysis and accurate prediction of dust removal equipment.

[0005] The present invention proposes an intelligent predictive dust removal equipment maintenance system, comprising:

[0006] Data collection terminal, used to collect the operation data of dust removal equipment;

[0007] A data storage terminal, used for storing and preprocessing the operation data;

[0008] A data processing platform for analyzing the operating data and performing fault detection and prediction; and

[0009] The user end is used to display the analysis results;

[0010] The data collection end, data storage end, data processing platform and user end are interconnected through a network to form an integrated data processing system.

[0011] Preferably, the data acquisition terminal includes:

[0012] Multiple sensors are fixed on different dust removal equipment to collect multi-dimensional operation data; and

[0013] The collector is connected to the sensor and is used to collect and preliminarily process the operation data and transmit the processed data to the data storage terminal.

[0014] Preferably, the sensor comprises:

[0015] Pressure sensor, used to collect pressure data in the air outlet duct of the dust removal fan;

[0016] Temperature sensor, used to collect temperature data of the dust removal fan outlet pipe;

[0017] An angle sensor, used to collect the rotation angle of the hopper vibration motor; and

[0018] Current sensor, used to collect voltage, current, power electrical parameters of hopper vibration and electrical parameters of transformer; and

[0019] Emission sensors are used to collect emission data from dust removal equipment.

[0020] Preferably, the data storage end comprises:

[0021] Cloud storage devices are used to store large amounts of historical data;

[0022] HDFS cluster for distributed storage and processing of real-time data streams; and

[0023] Database cluster, used to store structured data and model parameters;

[0024] The HDFS cluster performs preliminary data processing through Storm real-time stream processing technology, and interacts with the Spark big data computing cluster through MapReduce.

[0025] Preferably, the HDFS cluster includes:

[0026] The metadata service module is used to manage the entire HDFS cluster, including the name node and resource manager; and

[0027] Multiple data nodes, distributed in different computer nodes, are used to store actual data;

[0028] The metadata service module stores the data in the form of files in the multiple data nodes, each file corresponds to a data block, and the name node and resource manager record the mapping relationship between the file name and the block number.

[0029] Preferably, the database cluster includes:

[0030] Hive database, used to store and query large-scale structured data;

[0031] MongoDB database, for storing unstructured and semi-structured data; and

[0032] Redis database, used to cache hot data and improve system response speed;

[0033] The Hive database and the MongoDB database are used to store user information, user relationship information and system messages, and the Redis database is used to cache frequently accessed data.

[0034] Preferably, the data processing platform includes:

[0035] Data cleaning module, used to filter and preprocess the raw data;

[0036] Feature extraction module, used to extract key features from the cleaned data;

[0037] A model training module for training a prediction model based on historical data; and

[0038] The predictive analysis module is used to use the trained model to perform fault detection and predictive analysis on the current data, and the predictive analysis includes dust removal emission prediction and transformer operation power consumption adjustment prediction.

[0039] Preferably, the user terminal includes:

[0040] Data visualization interface, used to display analysis results in the form of charts, tables, etc.;

[0041] an alarm module for sounding an alarm when a potential fault is detected; and

[0042] The interaction module is used to receive user input and respond to user requests.

[0043] The data processing method based on the intelligent predictive dust removal equipment maintenance system comprises the following steps:

[0044] Data collection step: collecting the operation data of the dust removal equipment in real time through the sensor of the data collection end, and transmitting the data to the data storage end through the collector;

[0045] Data storage step: storing the received data in the HDFS cluster and performing real-time stream processing through Storm technology;

[0046] Data preprocessing step: Use MapReduce technology to clean and extract features from the data stored in the HDFS cluster;

[0047] Data analysis step: Use Spark big data computing cluster to conduct in-depth analysis of preprocessed data, including fault detection and predictive analysis;

[0048] Result storage step: storing the analysis results in the database cluster, including storing structured data in a Hive database, storing unstructured data in a MongoDB database, and using a Redis database to cache hot data;

[0049] Visualization step: The analysis results are presented to the user in an intuitive manner through the data visualization interface of the user terminal.

[0050] Preferably, the data analysis step further comprises:

[0051] Model training sub-step: Use historical data to train the machine learning model;

[0052] Real-time prediction sub-step: Use the trained model to analyze and predict real-time data;

[0053] Threshold judgment sub-step: compare the prediction result with the preset threshold to determine whether there is a potential fault;

[0054] Warning generation sub-step: when a potential fault is detected, a warning message is generated and an alarm is issued through the alarm module of the user end.

[0055] The beneficial effects of the present invention are mainly reflected in the following aspects:

[0056] From a macro perspective, the system realizes the intelligent and automated maintenance of dust removal equipment, greatly improving the reliability and production efficiency of the equipment while reducing maintenance costs and environmental risks.

[0057] First of all, the system architecture of the present invention realizes the seamless integration of data collection, storage, processing and display. The data collection end monitors the operating status of the dust removal equipment in an all-round way through various types of sensors, ensuring the comprehensiveness and accuracy of the data. The data storage end adopts distributed storage technology, which not only greatly improves the data processing capability, but also ensures the security and reliability of the data. The data processing platform integrates big data analysis and machine learning technology to achieve accurate analysis and prediction of equipment status. The intuitive visual interface of the user end makes complex data analysis results easy to understand and operate. This comprehensive system integration greatly improves the efficiency and accuracy of dust removal equipment maintenance.

[0058] Secondly, the data processing method of the present invention embodies the advanced concept of "prevention is better than cure". Through in-depth analysis of massive historical data and real-time operation data, the system can detect potential equipment problems early and give accurate warnings. This predictive maintenance method not only greatly reduces the incidence of equipment failures, but also optimizes maintenance plans, reducing unnecessary downtime and maintenance costs.

[0059] Furthermore, the system of the present invention has strong scalability and versatility. The modular design allows the system to easily adapt to different types of dust removal equipment and production environments. At the same time, the open architecture of the system also facilitates future technology upgrades and functional expansions, ensuring the long-term value of the system.

[0060] From a microscopic perspective, the present invention has innovations and breakthroughs in many technical details. For example, in terms of data collection, the collaborative work of multiple types of sensors enables all-round monitoring of equipment status. In terms of data storage, the combination of HDFS clusters and multiple types of databases not only ensures the efficient storage of massive data, but also meets the storage requirements of different types of data. In terms of data analysis, the combination of Storm real-time stream processing technology and Spark big data computing platform enables real-time processing and in-depth analysis of data. In terms of fault prediction, the use of advanced machine learning algorithms, such as long short-term memory networks (LSTM), significantly improves the accuracy of predictions.

[0061] It is worth noting that the present invention performs well in resolving technical contradictions. For example, the system needs to process massive data while ensuring real-time response. This seemingly contradictory requirement is well resolved through distributed storage and computing technology. Another example is that the system needs to strike a balance between improving prediction accuracy and controlling computational complexity, which is achieved through carefully designed feature extraction and model selection.

[0062] In general, the intelligent predictive dust removal equipment maintenance system and method of the present invention realizes the intelligent and efficient maintenance of dust removal equipment through technological innovation and system integration. It not only improves the reliability and production efficiency of the equipment and reduces the maintenance cost, but also makes a positive contribution to energy conservation and emission reduction in industrial production. This innovative solution has opened up a new path for the intelligent maintenance of industrial equipment, and has broad application prospects and important economic and social value. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 It is the overall logic block diagram of the system of the present invention.

[0064] Figure 2 It is a logic block diagram of the data acquisition terminal of the present invention.

[0065] Figure 3 It is a logic block diagram of the data storage end of the present invention.

[0066] Figure 4 It is a logical block diagram of the data processing platform of the present invention.

[0067] Figure 5 It is a logic block diagram of the user end of the present invention.

[0068] Figure 6 It is the overall logic block diagram of the data processing method of the present invention.

[0069] Figure 7 It is a detailed logic block diagram of the data analysis step of the present invention. DETAILED DESCRIPTION

[0070] 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 thereof are described in detail below in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0071] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0072] Example 1

[0073] See also Figure 1-7 The present invention relates to an intelligent predictive dust removal equipment maintenance system and method thereof, and in particular to a dust removal equipment maintenance prediction system based on big data and artificial intelligence technology.

[0074] First, the present invention proposes an intelligent predictive dust removal equipment maintenance system, which includes a data acquisition terminal 1, a data storage terminal 2, a data processing platform 3 and a user terminal 4. These four core components are interconnected through a network to form an integrated data processing system. The data acquisition terminal 1 is responsible for collecting the operating data of the dust removal equipment, the data storage terminal 2 is used to store and preprocess the operating data, the data processing platform 3 is responsible for analyzing the operating data and performing fault detection and prediction, and finally, the user terminal 4 is used to display the analysis results. The design of this system architecture makes the entire dust removal equipment maintenance process automated and intelligent, greatly improving the maintenance efficiency and accuracy.

[0075] Secondly, the present invention describes in depth the specific structure of the data acquisition terminal 1. The data acquisition terminal 1 includes multiple sensors 11 and collectors 12. Multiple sensors 11 are fixed on different dust removal equipment to collect multi-dimensional operation data. The collector 12 is connected to these sensors 11 to collect and preliminarily process the operation data and transmit the processed data to the data storage terminal 2. This design ensures the comprehensiveness and real-time nature of data collection and provides a reliable data basis for subsequent analysis.

[0076] Again, the present invention describes in detail the types and functions of the sensor 11. The sensor 11 includes a pressure sensor 111, a temperature sensor 112, an angle sensor 113, a current sensor 114 and an emission sensor. The pressure sensor 111 is used to collect pressure data in the dust removal fan outlet duct, the temperature sensor 112 is used to collect temperature data of the dust removal fan outlet duct, the angle sensor 113 is used to collect the rotation angle of the ash hopper vibration motor, and the current sensor 114 is used to collect the voltage, current, power and other electrical parameters of the ash hopper vibration and the electrical parameters of the transformer; the emission sensor is used to collect the emission data of the dust removal equipment. This multi-dimensional data collection method ensures comprehensive monitoring of the operating status of the dust removal equipment.

[0077] In one embodiment of the present invention, the measuring range of the pressure sensor 111 is 0-10 kPa, with an accuracy of ±0.5%, the measuring range of the temperature sensor 112 is -50°C to 150°C, with an accuracy of ±0.1°C, the measuring range of the angle sensor 113 is 0-360°, with an accuracy of ±0.1°, and the measuring range of the current sensor 114 is 0-100A, with an accuracy of ±0.5%. The selection of these parameters is based on the operating characteristics of typical dust removal equipment and can meet the needs of most industrial application scenarios.

[0078] The collector 12 is connected to these sensors 11, and is used to collect and preliminarily process the operating data, and transmit the processed data to the data storage terminal 2. This multi-dimensional data collection method not only ensures comprehensive monitoring of the operating status of the dust removal equipment, but also provides comprehensive data support for transformer status monitoring.

[0079] Next, the present invention describes in detail the structure of the data storage terminal 2. The data storage terminal 2 includes a cloud storage device 21, an HDFS cluster 22, and a database cluster 23. The cloud storage device 21 is used to store large-capacity historical data, the HDFS cluster 22 is used for distributed storage and processing of real-time data streams, and the database cluster 23 is used to store structured data and model parameters. It is worth noting that the HDFS cluster 22 performs preliminary processing of data through Storm real-time stream processing technology, and interacts with the Spark big data computing cluster through MapReduce. This design makes full use of the advantages of big data technology and realizes efficient processing and analysis of massive data.

[0080] Preferably, the specific structure of the HDFS cluster 22 includes a metadata service module 221 and multiple data nodes 222. The metadata service module 221 is used to manage the entire HDFS cluster 22, including a name node 2211 and a resource manager 2212. Multiple data nodes 222 are distributed in different computer nodes and are used to store actual data. The metadata service module 221 stores data in multiple data nodes 222 in the form of files, each file corresponds to a data block, and the name node 2211 and the resource manager 2212 record the mapping relationship between the file name and the block number. This distributed storage method greatly improves the data access speed and system reliability.

[0081] Furthermore, the present invention describes in detail the composition of the database cluster 23. The database cluster 23 includes a Hive database 231, a MongoDB database 232, and a Redis database 233. The Hive database 231 is used to store and query large-scale structured data, the MongoDB database 232 is used to store unstructured and semi-structured data, and the Redis database 233 is used to cache hot data to improve the system response speed. Specifically, the Hive database 231 and the MongoDB database 232 are used to store user information, user relationship information, and system messages, and the Redis database 233 is used to cache frequently accessed data. This combination of multiple types of databases enables the system to efficiently process various types of data and meet different data storage and query requirements.

[0082] A key innovation of the present invention lies in the design of the data processing platform 3. The data processing platform 3 includes a data cleaning module 31, a feature extraction module 32, a model training module 33 and a prediction analysis module 34. The data cleaning module 31 is used to filter and preprocess the original data to remove noise and outliers. The feature extraction module 32 extracts key features from the cleaned data, such as equipment vibration frequency, temperature change rate, etc. The model training module 33 trains a prediction model based on historical data, such as a support vector machine (SVM) or a deep neural network (DNN). The prediction analysis module 34 uses the trained model to perform fault detection and prediction analysis on the current data. In addition to the original dust removal equipment fault prediction, the system can also perform dust removal emission prediction and transformer operating power consumption adjustment prediction. This multi-dimensional prediction and analysis capability greatly improves the practicality and scope of application of the system.

[0083] In one embodiment of the present invention, the model training module 33 uses a long short-term memory network (LSTM) for time series prediction. The input of the LSTM model includes the equipment operation data of the past 24 hours, one data point per hour, and features including pressure, temperature, vibration frequency, etc. The output of the model is the probability of equipment failure within the next 12 hours. The model is trained using the Adam optimizer, with a learning rate set to 0.001, a batch size of 64, and a training round number of 100. This setting shows good prediction results in practical applications and can warn of potential equipment failures several hours in advance.

[0084] Finally, the present invention describes in detail the structure and function of the user terminal 4. The user terminal 4 includes a data visualization interface 41, an alarm module 42 and an interaction module 43. The data visualization interface 41 is used to display the analysis results in the form of charts, tables, etc., so that the complex data analysis results become intuitive and easy to understand. The alarm module 42 issues an alarm when a potential fault is detected to ensure that maintenance personnel can respond in time. The interaction module 43 is used to receive user input and respond to user requests, providing a good human-computer interaction experience.

[0085] Next, the present invention proposes a data processing method based on the above-mentioned intelligent predictive dust removal equipment maintenance system. The method comprises the following steps:

[0086] The first step is data collection, where the sensor 11 of the data collection terminal 1 collects the operating data of the dust removal equipment in real time, and transmits the data to the data storage terminal 2 through the collector 12. This step ensures that the system can obtain the latest and most comprehensive equipment operation data.

[0087] Then comes the data storage step, where the received data is stored in the HDFS cluster 22 and processed in real time using Storm technology. This step enables efficient storage and preliminary processing of massive data.

[0088] Next is the data preprocessing step, which uses MapReduce technology to clean and extract features from the data stored in the HDFS cluster 22. This step removes noise and outliers in the original data and extracts the most valuable features for fault prediction.

[0089] The next step is data analysis. The Spark big data computing cluster is used to conduct in-depth analysis of the pre-processed data, including fault detection and predictive analysis. In addition to conventional fault detection, the system can also predict dust removal emissions and transformer power consumption adjustment. These prediction results provide an important basis for the optimized operation and timely maintenance of equipment.

[0090] The next step is the result storage step, which stores the analysis results in the database cluster 23, including storing structured data in the Hive database 231, storing unstructured data in the MongoDB database 232, and using the Redis database 233 to cache hot data. This step ensures persistent storage and fast access to the analysis results.

[0091] The last step is visualization, which presents the analysis results to the user in an intuitive manner through the data visualization interface 41 of the user terminal 4. This step makes the complex analysis results easy to understand and operate.

[0092] An important feature of the present invention is the detailed design of the data analysis step, which includes a model training sub-step, a real-time prediction sub-step, a threshold judgment sub-step and an early warning generation sub-step.

[0093] The model training substep uses historical data to train the machine learning model. In a specific embodiment, we use the random forest algorithm for model training. The number of trees in the random forest is set to 100 and the maximum depth is 10. These parameters are obtained through cross-validation and can achieve a good balance between model complexity and generalization ability.

[0094] The real-time prediction sub-step uses the trained model to analyze and predict real-time data. For example, the model predicts the latest equipment operation data every 5 minutes and outputs the probability of equipment failure in the next 24 hours.

[0095] The threshold judgment sub-step compares the prediction result with the preset threshold to determine whether there is a potential fault. In one embodiment of the present invention, we set the fault probability threshold to 0.7. When the predicted fault probability exceeds 0.7, the system considers that there is a potential fault risk. The selection of this threshold is based on the analysis of historical data, and a good balance is achieved between reducing the false alarm rate and improving the detection rate.

[0096] When a potential fault is detected, the early warning generation substep generates early warning information and issues an alarm through the alarm module 42 of the user terminal 4. The early warning information includes key information such as fault type, probability of occurrence, and estimated time of occurrence, which helps maintenance personnel quickly locate and solve problems.

[0097] In general, the intelligent predictive dust removal equipment maintenance system and method proposed in the present invention realizes intelligent maintenance of dust removal equipment by integrating the Internet of Things, big data and artificial intelligence technologies. The system can not only monitor the operating status of the equipment in real time, but also predict potential failures, greatly improving maintenance efficiency and reducing maintenance costs. In addition, the modular design and distributed architecture of the system also provide convenience for future expansion and upgrading. It is believed that this system will open up a new path for the intelligent maintenance of industrial equipment and make important contributions to improving industrial production efficiency and environmental protection.

[0098] It should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. Intelligent predictive dust removal equipment maintenance system, characterized in that: include: Data collection terminal, used to collect the operation data of dust removal equipment; A data storage terminal, used for storing and preprocessing the operation data; A data processing platform for analyzing the operating data and performing fault detection and prediction; as well as The user end is used to display the analysis results; The data collection end, data storage end, data processing platform and user end are interconnected through a network to form an integrated data processing system.

2. The intelligent predictive dust removal equipment maintenance system according to claim 1, characterized in that: The data collection end comprises: Multiple sensors are fixed on different dust removal equipment to collect multi-dimensional operation data; and The collector is connected to the sensor and is used to collect and preliminarily process the operation data and transmit the processed data to the data storage terminal.

3. The intelligent predictive dust removal equipment maintenance system according to claim 2, characterized in that: The sensor comprises: Pressure sensor, used to collect pressure data in the air outlet duct of the dust removal fan; Temperature sensor, used to collect temperature data of the dust removal fan outlet duct and transformer temperature data; Angle sensor, used to collect the rotation angle of the hopper vibration motor; Current sensor, used to collect voltage, current, power electrical parameters of hopper vibration and electrical parameters of transformer; and Emission sensors are used to collect emission data from dust removal equipment.

4. The intelligent predictive dust removal equipment maintenance system according to claim 1, characterized in that: The data storage end comprises: Cloud storage devices are used to store large amounts of historical data; HDFS cluster for distributed storage and processing of real-time data streams; and Database cluster, used to store structured data and model parameters; The HDFS cluster performs preliminary data processing through Storm real-time stream processing technology, and interacts with the Spark big data computing cluster through MapReduce.

5. The intelligent predictive dust removal equipment maintenance system according to claim 4, characterized in that: The HDFS cluster includes: The metadata service module is used to manage the entire HDFS cluster, including the name node and resource manager; and Multiple data nodes, distributed in different computer nodes, are used to store actual data; The metadata service module stores the data in the form of files in the multiple data nodes, each file corresponds to a data block, and the name node and resource manager record the mapping relationship between the file name and the block number.

6. The intelligent predictive dust removal equipment maintenance system according to claim 4, characterized in that: The database cluster includes: Hive database, used to store and query large-scale structured data; MongoDB database, for storing unstructured and semi-structured data; and Redis database, used to cache hot data and improve system response speed; The Hive database and the MongoDB database are used to store user information, user relationship information and system messages, and the Redis database is used to cache frequently accessed data.

7. The intelligent predictive dust removal equipment maintenance system according to claim 1, characterized in that: The data processing platform comprises: Data cleaning module, used to filter and preprocess the raw data; Feature extraction module, used to extract key features from the cleaned data; A model training module for training a prediction model based on historical data; and The predictive analysis module is used to use the trained model to perform fault detection and predictive analysis on the current data, and the predictive analysis includes dust removal emission prediction and transformer operation power consumption adjustment prediction.

8. The intelligent predictive dust removal equipment maintenance system according to claim 1, characterized in that: The user terminal comprises: Data visualization interface, used to display analysis results in the form of charts, tables, etc.; an alarm module for sounding an alarm when a potential fault is detected; and The interaction module is used to receive user input and respond to user requests.

9. A data processing method for the intelligent predictive dust removal equipment maintenance system according to any one of claims 1 to 8, characterized in that: The following steps are involved: Data collection step: collecting the operating data of the dust removal equipment in real time through the sensor of the data collection end, and transmitting the data to the data storage end through the collector; Data storage step: storing the received data in the HDFS cluster and performing real-time stream processing through Storm technology; Data preprocessing step: Use MapReduce technology to clean and extract features from the data stored in the HDFS cluster; Data analysis step: Use Spark big data computing cluster to conduct in-depth analysis on the preprocessed data, including fault detection and predictive analysis, and the predictive analysis includes dust removal emission prediction; Result storage step: storing the analysis results in the database cluster, including storing structured data in a Hive database, storing unstructured data in a MongoDB database, and using a Redis database to cache hot data; Visualization step: The analysis results are presented to the user in an intuitive manner through the data visualization interface of the user terminal.

10. The data processing method according to claim 9, characterized in that: The data analysis step also includes: a model training sub-step: training a machine learning model using historical data; Real-time prediction sub-step: Use the trained model to analyze and predict real-time data; Threshold judgment sub-step: compare the prediction result with the preset threshold to determine whether there is a potential fault; Warning generation sub-step: when a potential fault is detected, a warning message is generated and an alarm is issued through the alarm module of the user end.

Images