Chain transmission system fault monitoring method for scraper conveyer
By collecting chain data in real time and building a fault monitoring model using the generative adversarial network and autoencoder, the problem of efficient and accurate fault monitoring of the chain transmission system of the scraper transport aircraft is solved, real-time monitoring and fault warning of the chain transmission system is realized, and the improvement of the improvement of the chain transmission system is achieved. The reliability and safety of the equipment.
Patent Information
- Application Number
- CN202411068510.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-06
- Publication Date
- 2024-11-08
AI Technical Summary
The chain transmission system of the scraper transporter is prone to failure in heavy load and wear environments, resulting in production interruptions and safety hazards, and it is difficult for the existing technology to achieve efficient and accurate fault monitoring.
The monitoring data of chain strain value, displacement change amount and vibration frequency are collected in real time, and feature extraction and enhancement are extracted and enhanced by generating an adversarial network and autoencoder. The fault monitoring model is built based on the recurrent neural network, and the alarm is issued in real time.
Real-time status monitoring of the chain transmission system is realized, fault detection is timely detected, downtime and maintenance costs are reduced, and equipment reliability and safety is improved.
Smart Images

Figure CN118907785A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of electrical monitoring of fully mechanized working faces in underground coal mines, and in particular relates to a method for monitoring faults of a chain transmission system for a scraper conveyor. Background Art
[0002] As the key transportation equipment of the comprehensive coal mining face in underground coal mines, the scraper conveyor undertakes the important task of transporting the coal generated during the coal mining process from the working face to the ground safely and efficiently. However, due to the long-term operation of its chain transmission system under heavy load, wear and complex working conditions, the probability of chain breakage, chain jamming and other failures is relatively high. These failures will not only seriously affect the normal production progress of the coal mine and cause economic losses, but may also cause serious safety accidents due to improper fault handling, threatening the lives of miners.
[0003] In order to solve this problem, it is particularly important to develop an efficient and accurate chain drive system fault monitoring method. This monitoring method needs to be able to monitor the working status of the chain in real time, detect and warn potential faults in time, so as to avoid the occurrence of faults or deal with them in the early stage. Therefore, it is urgent to propose a chain drive system fault monitoring method for scraper conveyors. Summary of the invention
[0004] In order to solve the above technical problems, the present invention proposes a method for monitoring faults in a chain transmission system for a scraper conveyor to solve the above problems in the prior art.
[0005] To achieve the above object, the present invention provides a method for monitoring a chain transmission system fault of a scraper conveyor, comprising the following steps:
[0006] Real-time collection of chain strain values, displacement changes and vibration frequencies of the chain transmission system as monitoring data, and preprocessing of the monitoring data;
[0007] Perform time domain feature extraction and frequency domain feature extraction on the preprocessed monitoring data, perform feature enhancement and feature dimension reduction processing on the extracted feature data based on the generative adversarial network and autoencoder to generate training samples;
[0008] Fault labeling is performed on training samples, a fault monitoring model is constructed based on a recurrent neural network, and the fault monitoring model is trained based on the labeled training samples;
[0009] Based on the trained fault monitoring model, the faults of the chain drive system are monitored in real time.
[0010] Optionally, the process of collecting the chain strain value, displacement change and vibration frequency of the chain transmission system includes: installing a strain sensor, a displacement sensor and a vibration sensor on the chain transmission system to collect the chain strain value, displacement change and vibration frequency respectively;
[0011] Among them, the installation position of the strain sensor includes at least the middle of the chain, the chain link connection and the sprocket meshing area; the installation position of the displacement sensor includes at least the side of the chain guide and the sprocket axis; the installation position of the vibration sensor includes at least near the sprocket, the chain tensioning device and the chain support point.
[0012] Optionally, the process of preprocessing the chain strain value, displacement change and vibration frequency includes: filtering, denoising and data conversion operations on the chain strain value, displacement change and vibration frequency.
[0013] Optionally, the process of extracting time domain features and frequency domain features includes: extracting time domain features in the monitoring data based on envelope analysis, and extracting frequency domain features in the monitoring data based on Fourier transform.
[0014] Optionally, the process of feature enhancement based on a generative adversarial network includes: designing a generator network, inputting a low-dimensional representation of the monitoring data into the generator network, and generating virtual samples similar to the real monitoring data; designing a discriminator network, outputting the probability that the input is the real monitoring data; combining the generator network and the discriminator network for adversarial training until a preset similarity requirement is met, outputting a number of virtual samples similar to the real monitoring data, and adding them to the training samples.
[0015] Optionally, the process of real-time monitoring of the faults of the chain transmission system further includes: when the fault monitoring system detects an abnormal signal, triggering an alarm mechanism and generating a fault diagnosis report.
[0016] Optionally, the collected monitoring data and fault diagnosis report are processed by encryption technology, and then the encrypted data are transmitted to the remote monitoring center and the mobile receiving device by any one of wireless transmission technology and wired transmission technology.
[0017] The present invention also provides an electronic device, comprising: a memory and a processor; the memory is used to store a program; the processor is used to execute the program to implement each step of the fault monitoring method for the chain transmission system of a scraper conveyor.
[0018] The present invention also provides a readable storage medium on which a computer program is stored. When the computer program is executed by a processor, each step of the fault monitoring method for the chain transmission system of a scraper conveyor is implemented.
[0019] Compared with the prior art, the present invention has the following advantages and technical effects:
[0020] The present invention can continuously monitor the state of the chain transmission system by collecting the strain value, displacement change and vibration frequency of the chain in real time, detect abnormal conditions in time, and reduce potential downtime and maintenance costs.
[0021] The present invention utilizes generative adversarial networks and autoencoders to perform feature enhancement and dimensionality reduction processing, which can improve the expressiveness of features, while reducing the dimension of data and the complexity of model training; the training samples generated by the above processing provide high-quality input data for building a fault monitoring model.
[0022] The present invention utilizes the trained fault monitoring model to monitor the chain drive system in real time. Once an abnormality is detected, an alarm can be issued in time, providing maintenance personnel with an opportunity to respond quickly, thereby improving work efficiency and improving the reliability and safety of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0024] Figure 1 The present invention is a schematic flow chart of a method for monitoring a chain transmission system fault of a scraper conveyor according to an embodiment of the present invention. DETAILED DESCRIPTION
[0025] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.
[0026] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0027] Embodiment 1
[0028] like Figure 1 As shown, in this embodiment, a method for monitoring a chain transmission system fault of a scraper conveyor is provided, comprising the following steps:
[0029] Real-time collection of chain strain values, displacement changes and vibration frequencies of the chain transmission system as monitoring data, and preprocessing of the monitoring data;
[0030] Perform time domain feature extraction and frequency domain feature extraction on the preprocessed monitoring data, perform feature enhancement and feature dimension reduction processing on the extracted feature data based on the generative adversarial network and autoencoder to generate training samples;
[0031] Fault labeling is performed on training samples, a fault monitoring model is constructed based on a recurrent neural network, and the fault monitoring model is trained based on the labeled training samples;
[0032] Based on the trained fault monitoring model, the faults of the chain drive system are monitored in real time.
[0033] When the strain value of the chain is detected to exceed the preset threshold, the displacement change increases abnormally, or the vibration frequency changes significantly, the system can determine that it is a chain drive system failure and issue a warning signal. According to the fault characteristics, the fault type is further determined, such as chain breakage, chain jamming, etc., and targeted processing suggestions are provided for different types of faults.
[0034] As a specific example, on the chain drive system of a scraper conveyor, the configuration position of the sensor is crucial for accurately monitoring the operating status of the system. The following is a detailed description of the installation positions of different types of sensors on the chain drive system:
[0035] Strain Sensors:
[0036] Installation location: The strain sensor is mainly used to measure the deformation of the chain when it is stressed, so it should be installed at the stress point or high stress area of the chain. Specifically, the following locations can be selected:
[0037] Middle part of the chain: The middle part of the chain is subject to the greatest tensile force. Installing a strain sensor can directly measure the strain changes of the chain during operation and reflect the stress state of the chain.
[0038] Chain link connection: The connection between chain links is also a place where stress concentrates. Installing strain sensors can monitor the strain conditions at the chain link connection, which helps to detect the risk of chain link wear or breakage.
[0039] Sprocket meshing area: Although the sprocket is not a directly stressed component, its meshing process with the chain will produce stress transfer. Therefore, installing a strain sensor in the meshing area where the sprocket and chain contact can indirectly monitor the stress condition of the chain.
[0040] Displacement Sensor:
[0041] Installation location: The displacement sensor is used to measure the position change of the chain or sprocket during operation, and is usually installed in a position that can reflect the overall displacement of the chain drive system.
[0042] Next to the chain guide rail: Installing a displacement sensor next to the chain guide rail can measure the movement distance and speed of the chain on the guide rail, thereby reflecting the operating status of the chain drive system.
[0043] Sprocket axis: If conditions permit, a displacement sensor can be installed at the sprocket axis to indirectly monitor the chain displacement by measuring the rotation angle or axial displacement of the sprocket. However, this method may be more complicated and costly, and needs to be selected according to actual conditions.
[0044] Vibration Sensor:
[0045] Installation location: The vibration sensor is used to monitor the vibration generated by the chain drive system during operation. It is usually installed in a location where vibration is likely to occur or where the vibration transmission effect is obvious.
[0046] Near the sprocket: The sprocket will generate a certain amount of vibration during rotation, and the vibration will be transmitted along the chain. Therefore, installing a vibration sensor near the sprocket can directly measure the vibration of the sprocket and indirectly reflect the vibration state of the chain.
[0047] Chain tensioner: The chain tensioner is used to adjust the tightness of the chain, and its working state has a great influence on the vibration of the chain. Installing a vibration sensor at the chain tensioner can monitor abnormal chain vibration caused by improper adjustment or failure of the tensioner.
[0048] Key support points: Key support points in the chain drive system, such as the chain support frame, sprocket support bearing, etc., are also important nodes for vibration transmission. Installing vibration sensors at these locations can fully monitor the vibration of the chain drive system and improve the accuracy of fault identification.
[0049] The process of preprocessing the chain strain value, displacement change and vibration frequency can be implemented by filtering, denoising and data conversion of the chain strain value, displacement change and vibration frequency to improve the accuracy and reliability of the data. The filtering operation can remove high-frequency noise and interference signals in the data; the denoising operation further eliminates random errors and abnormal values in the data; and the data calibration ensures the accuracy and consistency of the data.
[0050] The process of extracting time domain features and frequency domain features can be implemented as follows: extracting time domain features in monitoring data based on envelope analysis, and extracting frequency domain features in monitoring data based on Fourier transform.
[0051] As a specific embodiment, envelope analysis is an effective signal processing method, which is particularly suitable for detecting and analyzing low-frequency envelope information in modulated signals. In chain drive systems, faults often lead to amplitude modulation of vibration signals. Envelope analysis can extract these modulation information, thereby identifying fault characteristics. Envelope analysis usually includes steps such as signal rectification and low-pass filtering to extract the envelope of the vibration signal. Frequency domain analysis is another important signal processing technology, which converts the vibration signal from the time domain to the frequency domain through Fourier transform, and then analyzes the spectral characteristics of the signal. In chain drive systems, different fault types often correspond to different spectral characteristics, such as the increase of harmonic components, frequency offset, etc. Through frequency domain analysis, these spectral characteristics can be extracted for subsequent fault diagnosis.
[0052] The feasible process of feature enhancement based on generative adversarial network includes: designing a generator network, inputting the low-dimensional representation of the monitoring data into the generator network, and generating virtual samples similar to the real monitoring data; designing a discriminator network, outputting the probability that the input is the real monitoring data; combining the generator network and the discriminator network for adversarial training until the preset similarity requirement is met, outputting several virtual samples similar to the real monitoring data, and adding them to the training samples.
[0053] Furthermore, through adversarial training, the generator gradually learns to generate virtual samples that are closer to real signals, while the discriminator continuously improves its ability to distinguish. This adversarial process enables the generator to learn more complex and sophisticated feature representations, thereby improving the robustness and generalization ability of the features.
[0054] The autoencoder is an unsupervised learning model that learns to encode input data into a low-dimensional representation and uses this representation to reconstruct the original data. In the feature extraction of the chain drive system, the autoencoder can be used for feature dimensionality reduction to simplify the model structure and improve computational efficiency. The encoder maps the high-dimensional vibration signal to a low-dimensional space and extracts a representative feature representation. This low-dimensional representation retains the main information of the original signal while reducing the redundancy and noise of the data. The decoder uses this low-dimensional representation to reconstruct the original signal. By minimizing the reconstruction error, the autoencoder can learn the optimal feature representation and achieve feature dimensionality reduction and extraction.
[0055] In this embodiment, feature extraction methods such as envelope analysis and frequency domain analysis are combined with technologies such as generative adversarial networks and autoencoders to form a complete feature extraction and enhancement process. First, the preliminary features of the vibration signal are extracted through envelope analysis and frequency domain analysis; then, feature enhancement is performed using a generative adversarial network to generate more virtual samples to enrich the training data set; finally, feature dimensionality reduction is performed using an autoencoder to extract representative low-dimensional feature representations. These feature representations will serve as input to the machine learning model for subsequent fault diagnosis and prediction. By combining a variety of signal processing technologies and deep learning algorithms, effective feature extraction and enhancement of the vibration signal of the chain drive system can be achieved, improving the generalization ability of the model and the accuracy of fault diagnosis.
[0056] The process of real-time monitoring of the faults of the chain transmission system may further include: when the fault monitoring system detects an abnormal signal, triggering an alarm mechanism and generating a fault diagnosis report.
[0057] It is also feasible to process the collected monitoring data and fault diagnosis reports using encryption technology, and then transmit the encrypted data to the remote monitoring center and the mobile receiving device using any one of wireless transmission technology and wired transmission technology.
[0058] As a specific embodiment, wireless communication technology, such as Wi-Fi, Zigbee, LoRa, etc., is usually used to transmit data packets from data collection points to wireless access points or base stations, and then transmitted to remote monitoring centers through the Internet or a dedicated network. Wireless transmission is flexible and convenient, but may be limited by signal interference and transmission distance. In some cases, in order to ensure the stability and reliability of data transmission, wired transmission methods such as Ethernet and optical fiber can also be used. Wired transmission is high-speed and stable, but the wiring cost is high and the flexibility is poor.
[0059] During data transmission, it is necessary to follow certain communication protocols, such as Modbus, TCP / IP, MQTT, etc., to ensure the correctness and integrity of the data. The communication protocol defines key parameters such as the format, rate, and verification method of data transmission. During data transmission, data security needs to be considered. Encryption technologies such as AES and RSA are used to encrypt data to prevent data from being stolen or tampered with during transmission.
[0060] As a specific embodiment, the processed data and fault identification results are stored in a database for subsequent query and analysis. The design of the database takes into account factors such as data integrity, security and scalability. A data query interface is provided to facilitate users to query the historical data and fault records of the chain drive system at any time.
[0061] Embodiment 2
[0062] The present invention provides an electronic device, comprising: a memory and a processor; the memory is used to store a program; the processor is used to execute the program to implement various steps of a method for monitoring a chain transmission system fault of a scraper conveyor.
[0063] Embodiment 3
[0064] The present invention provides a readable storage medium on which a computer program is stored. When the computer program is executed by a processor, each step of a method for monitoring a fault of a chain transmission system for a scraper conveyor is implemented.
[0065] The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A method for monitoring faults in a chain transmission system for a scraper conveyor, characterized in that: The following steps are involved: Real-time collection of chain strain values, displacement changes and vibration frequencies of the chain transmission system as monitoring data, and preprocessing of the monitoring data; Perform time domain feature extraction and frequency domain feature extraction on the preprocessed monitoring data, perform feature enhancement and feature dimension reduction processing on the extracted feature data based on the generative adversarial network and autoencoder to generate training samples; Fault labeling is performed on training samples, a fault monitoring model is constructed based on a recurrent neural network, and the fault monitoring model is trained based on the labeled training samples; Based on the trained fault monitoring model, the faults of the chain drive system are monitored in real time.
2. The method for monitoring the chain transmission system fault of a scraper conveyor according to claim 1, characterized in that: The process of collecting chain strain value, displacement change and vibration frequency of the chain transmission system includes: installing a strain sensor, a displacement sensor and a vibration sensor on the chain transmission system to collect the chain strain value, displacement change and vibration frequency respectively; Among them, the installation position of the strain sensor includes at least the middle of the chain, the chain link connection and the sprocket meshing area; the installation position of the displacement sensor includes at least the side of the chain guide and the sprocket axis; the installation position of the vibration sensor includes at least near the sprocket, the chain tensioning device and the chain support point.
3. The method for monitoring the chain transmission system fault of a scraper conveyor according to claim 1, characterized in that: The process of preprocessing the chain strain value, displacement change and vibration frequency includes: filtering, denoising and data conversion operations on the chain strain value, displacement change and vibration frequency.
4. The method for monitoring faults of a chain transmission system for a scraper conveyor according to claim 1, characterized in that: The process of extracting time domain features and frequency domain features includes: extracting time domain features in monitoring data based on envelope analysis, and extracting frequency domain features in monitoring data based on Fourier transform.
5. The method for monitoring faults of a chain transmission system for a scraper conveyor according to claim 1, characterized in that: The process of feature enhancement based on generative adversarial networks includes: designing a generator network, inputting a low-dimensional representation of the monitoring data into the generator network, and generating virtual samples similar to the real monitoring data; designing a discriminator network, and outputting the probability that the input is the real monitoring data; combining the generator network and the discriminator network for adversarial training until the preset similarity requirement is met, and outputting a number of virtual samples similar to the real monitoring data and adding them to the training samples.
6. The method for monitoring faults of a chain transmission system for a scraper conveyor according to claim 1, characterized in that: The process of real-time monitoring of the faults of the chain transmission system also includes: when the fault monitoring system detects an abnormal signal, an alarm mechanism is triggered and a fault diagnosis report is generated.
7. The method for monitoring faults of a chain transmission system for a scraper conveyor according to claim 1, characterized in that: It also includes processing the collected monitoring data and fault diagnosis reports using encryption technology, and then transmitting the encrypted data to a remote monitoring center and a mobile receiving device using any one of wireless transmission technology and wired transmission technology.
8. An electronic device, characterized in that: include: Memory and processor; The memory is used to store programs; The processor is used to execute the program to implement each step of the method for monitoring faults of a chain drive system for a scraper conveyor according to any one of claims 1 to 7.
9. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of the method for monitoring a chain drive system fault for a scraper conveyor according to any one of claims 1 to 7 is implemented.
Citation Information
Patent Citations
Wind turbine generator system driving chain health state evaluation system and method
CN106525415A
Bearing fault diagnosis method and system
CN117312924A
Training method of fault identification model of transmission chain, and fault identification method and device
CN118013386A
Large particle long-distance pipeline conveying fault diagnosis method
CN118296440A
GAN data enhanced chain transmission bearing fault diagnosis method
CN118427610A
Cited By
Bakelite guide rail fault monitoring method and system
CN120084398A
A method and system for monitoring the failure of a bakelite guide rail
CN120084398B
A method for nondestructive positioning of a roller chain wear fault based on a servo motor current signal
CN122688287A
