Remote fault diagnosis system and method for coal slime treatment equipment

Abstract

The invention relates to the technical field of coal processing equipment, in particular to a remote fault diagnosis system and method for coal slime processing equipment, and the system collects the operation data of the equipment in real time through a sensor installed on the coal slime processing equipment, and transmits the collected operation data to a remote server through a wireless communication network. The remote server preprocesses the received operation data, including data cleaning, de-noising and standardization processing, extracts fault features by using a signal processing technology based on the preprocessed data, inputs the fault features into a pre-trained fault diagnosis model, diagnoses the operation state and the fault type of the equipment, and sends the equipment fault to the remote server when the equipment fault is diagnosed. And the remote server sends fault alarm information to equipment maintenance personnel in a short message, mail or APP push mode, and provides corresponding fault processing suggestions. According to the method, the accuracy and efficiency of fault diagnosis are improved, stable operation of equipment is guaranteed, and the method has wide application prospects and remarkable economic benefits.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of coal processing equipment, and particularly relates to a remote fault diagnosis system and method for coal slime processing equipment. BACKGROUND

[0002] With the development of the coal industry, coal slime processing equipment plays a crucial role in the coal washing process. The normal operation of coal slime processing equipment is of great significance to improve the quality of coal, reduce production costs and reduce environmental pollution. However, coal slime processing equipment is easily affected by factors such as vibration, temperature, pressure and flow during operation, which can cause equipment failure and affect production efficiency and equipment life. Therefore, it is particularly important to effectively diagnose and maintain coal slime processing equipment. Traditional fault diagnosis methods mainly rely on periodic manual inspection and experience-based judgment, which has problems such as delayed detection, low accuracy and high maintenance costs, and cannot meet the needs of modern coal slime processing equipment for efficient, accurate and intelligent fault diagnosis.

[0003] In the prior art, although some coal slime processing equipment has begun to use sensor networks and data acquisition equipment to monitor the running state of the equipment, there are still technical problems in data processing and fault diagnosis. First, the data collection is not comprehensive, especially in complex operating environments, traditional sensors cannot obtain comprehensive and accurate operating data. Second, there are security risks in the data transmission process, which is easily disturbed and attacked, affecting the integrity and reliability of the data. Third, the existing data preprocessing and analysis methods are inefficient and cannot effectively remove noise and outliers, resulting in inaccurate fault diagnosis results. In addition, the establishment and training of the fault diagnosis model are complex, lack efficient intelligent analysis and fault prediction capabilities, and cannot provide timely and accurate fault alarms and maintenance recommendations. SUMMARY

[0004] Based on the above purpose, the present application provides a remote fault diagnosis system and method for coal slime processing equipment.

[0005] A remote fault diagnosis system and method for coal slime processing equipment, comprising the following steps: S1, data acquisition: real-time acquisition of operating data of the equipment through sensors installed on the coal slime processing equipment, including vibration signals, temperature signals, pressure signals and flow signals; S2. Data transmission: transmitting the collected operating data to a remote server through a wireless communication network; S3, data preprocessing: the remote server pre-processes the received operating data, including data cleaning, denoising and standardization processing; S4, fault feature extraction: based on the pre-processed data, the signal processing technology is used to extract the fault features; S5, fault diagnosis: input the fault features into the pre-trained fault diagnosis model to diagnose the running state and fault type of the equipment; S6, fault alarm and processing: when the equipment fault is diagnosed, the remote server sends the fault alarm information to the equipment maintenance personnel through SMS, email or APP push, and provides corresponding fault processing suggestions.

[0006] Optionally, the data collection step includes: vibration sensor: used to collect the vibration signal of the equipment; temperature sensor: installed on the bearing, motor and other parts of the equipment, used to monitor the temperature change of the equipment; pressure sensor: installed on the pipeline and container of the equipment, used to measure the internal pressure of the equipment; flow sensor: installed on the inlet and outlet pipeline of the equipment, used to monitor the coal slime flow.

[0007] Optionally, the data transmission step includes: data transmission module: install data transmission module on the equipment, transmit the collected data to the remote server in real time through 4G / 5G network or Wi-Fi; data encryption: use AES (Advanced Encryption Standard) algorithm to encrypt the data during data transmission, to ensure the security and integrity of data transmission.

[0008] Optionally, the data preprocessing step includes: data cleaning: use median filter and wavelet denoising method to smooth the original data, remove noise and outliers; data denoising: use wavelet transform and fast Fourier transform (FFT) method to remove high-frequency noise in the collected data; data standardization: use Z-score standardization method to standardize the data to meet the input requirements of the fault diagnosis model.

[0009] Optionally, the fault feature extraction step includes: spectrum analysis: perform fast Fourier transform (FFT) on the vibration signal to extract the frequency spectrum feature; time domain analysis: extract time domain features from temperature, pressure and flow signals; wavelet transform: decompose the collected signals using wavelet transform to extract fault features at different scales.

[0010] Optionally, the fault diagnosis model is trained and established using machine learning algorithm, specifically including: Dataset preparation: Collect historical operating data and fault records of coal slime processing equipment to construct training and test datasets. The datasets contain data in both normal operating and fault states. Model selection: Use support vector machine algorithm to establish fault diagnosis model; Model training: Use the training data set to train the fault diagnosis model, optimize the model parameters, and improve the model's diagnostic accuracy; Model validation: Use the test dataset to validate the trained model and evaluate the model's performance and generalization ability.

[0011] Optionally, a cross-validation method is used during the model training process, specifically including: K-fold cross validation: Divide the training dataset into K subsets and perform K training and validation. Each time, select one subset as the validation set and the remaining subsets as the training set. The specific steps include: Data partitioning: randomly divide the training dataset into K subsets, ensuring that the data distribution of each subset is the same; Cross-validation: Select each subset as the validation set in turn, and the remaining subsets as the training set, and perform K training and validation; Result calculation: Calculate the accuracy and error of each verification, and take the average of K verification results as the final evaluation indicator of the model.

[0012] Optionally, the fault alarm and processing steps include: Fault alarm: When a device fault is diagnosed, the remote server sends a fault alarm message to the device maintenance personnel via SMS, email, and mobile app push; Troubleshooting suggestions: Based on the fault type and diagnosis results, detailed troubleshooting suggestions are provided, including possible fault causes, troubleshooting steps, and required tools; The troubleshooting suggestions are generated based on the expert system and include: Troubleshooting knowledge base: Collect the experience and suggestions of equipment maintenance experts to build a troubleshooting knowledge base; Fault handling reasoning engine: Based on the knowledge base and fault diagnosis results, the reasoning engine is used to generate corresponding fault handling suggestions.

[0013] Optionally, it also includes a device health status assessment step, including: Health Index Calculation: Based on pre-processed operating data and fault characteristics, the health index of the device is calculated to evaluate the operating status of the device. Specifically, it includes: Health Index Formula: The device health index is calculated by weighting multiple key parameters using the following formula: ,in, is the health index, the weight of the first parameter, the standardized value of the first parameter, the weight of the first parameter, the standardized value of the first parameter, the number of parameters; Health status assessment: According to the trend of health index, predict the potential failure and maintenance demand of the equipment, and provide preventive maintenance suggestions.

[0014] A remote fault diagnosis system of coal slime treatment equipment is used to realize the remote fault diagnosis method of the coal slime treatment equipment, comprising the following modules: Data acquisition module: through the vibration sensor, temperature sensor, pressure sensor and flow sensor installed on the coal slime treatment equipment, the running data of the equipment is collected in real time, including vibration signal, temperature signal, pressure signal and flow signal; Data transmission module: the collected running data is transmitted to the remote server through the wireless communication network, and the AES-256 encryption algorithm is used in the data transmission process to ensure the security and integrity of the data; Data preprocessing module: the received running data is subjected to data cleaning, denoising and standardization processing, and the median filtering, wavelet denoising and Z-score standardization method are used to ensure the accuracy and consistency of the data; Fault feature extraction module: based on the preprocessed data, the fault features are extracted by using frequency spectrum analysis, time domain analysis and wavelet transform and other signal processing technologies; Fault diagnosis module: the fault features are input into the pre-trained fault diagnosis model, and the model adopts the support vector machine machine learning algorithm to diagnose the running state and fault type of the equipment; Fault alarm and processing module: when the equipment fault is diagnosed, the remote server sends the fault alarm information to the equipment maintenance personnel through SMS, email and mobile application push, and provides fault processing suggestions based on the expert system; Health status assessment module: based on the preprocessed running data and fault features, the health index of the equipment is calculated, and the running state of the equipment is evaluated.

[0015] The beneficial effects of the present application are: The present application can comprehensively and real-timely collect the running data of the equipment through the vibration sensor, temperature sensor, pressure sensor and flow sensor installed on the coal slime treatment equipment, ensure the comprehensive monitoring of the running state of the equipment, and the collected data is transmitted to the remote server in real time through the wireless communication network (such as 4G / 5G network or Wi-Fi), and the data is encrypted by using the AES-256 encryption algorithm, which ensures the security and integrity of the data in the data transmission process, prevents data leakage and tampering, and ensures the reliability of the system and the safety of the data.

[0016] The application, the data preprocessing module carries out data cleaning, denoising and standardization processing to the received operation data, uses the median filtering, wavelet denoising and Z-score standardization method, effectively removes the noise and abnormal value, ensures the accuracy and consistency of the data, provides a reliable data basis for fault feature extraction and fault diagnosis, the fault feature extraction module extracts the key fault feature parameter from the preprocessed data by using the signal processing technology such as spectrum analysis, time domain analysis and wavelet transform. The fault diagnosis module adopts the support vector machine machine learning algorithm, establishes an efficient and accurate fault diagnosis model, can accurately diagnose the running state and fault type of the equipment through the analysis and identification of the fault feature, and significantly improves the accuracy and efficiency of fault diagnosis.

[0017] When diagnosing the equipment fault, the fault alarm and processing module sends the fault alarm information to the equipment maintenance personnel in time through the ways such as short message, electronic mail and mobile application push, and provides detailed fault processing suggestions based on the expert system, including fault reason analysis, processing step guidance and required tool list, ensures that the maintenance personnel can quickly and effectively handle the fault, reduces the equipment downtime, the health state evaluation module calculates the health index of the equipment based on the preprocessed operation data and fault feature, evaluates the running state of the equipment, and predicts the potential fault and maintenance demand of the equipment by analyzing the change trend of the health index, provides preventive maintenance suggestions such as periodic inspection, replacement of vulnerable parts and adjustment of operation parameters, helps the maintenance personnel to prevent potential problems in advance, prolongs the service life of the equipment, and improves the operation efficiency and reliability of the equipment. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the present application or prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0019] Figure 1 The method steps of the embodiments of the present application are shown in the following. Figure 2 The system flowchart of the embodiments of the present application is shown in the following. DETAILED DESCRIPTION

[0020] The present application will be described in detail below in combination with the drawings and specific embodiments. It should be noted here that in order to make the embodiments more detailed, the following embodiments are the best, preferred embodiments, and other alternative ways can also be used by those skilled in the art to implement some known technologies; and the drawings are only used to describe the embodiments more specifically, and are not intended to limit the present application specifically.

[0021] It should be noted that the terms "one embodiment", "an embodiment", "exemplary embodiment", "some embodiments" and the like, in the specification, indicate that the embodiment described can include a particular feature, structure, or characteristic, but every embodiment can not necessarily include the particular feature, structure, or characteristic. Moreover, the descriptions of the various embodiments can be presented with reference to the accompanying drawings, in which the same reference numerals are used throughout the drawings to refer to the same or similar features, structures, or characteristics. Additionally, the descriptions of the various embodiments can be presented with reference to the accompanying drawings, in which the same reference numerals are used throughout the drawings to refer to the same or similar features, structures, or characteristics.

[0022] Generally, the terminology can be understood at least in part from a context of a use of the terminology. For example, the term "one or more" as used herein, depending at least in part upon a context of a use of the term, can be used to describe any feature, structure, or characteristic in a singular sense or can be used to describe combinations of features, structures, or characteristics in a plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but instead can allow for existence of other factors not necessarily expressly described, again, at least in part, depending at least in part on a context in which the term is used.

[0023] As shown in Figure 1 A remote fault diagnosis method of a slime treatment equipment, comprising the following steps: S1, data acquisition: real-time acquisition of operation data of the equipment through sensors installed on the slime treatment equipment, including vibration signals, temperature signals, pressure signals and flow signals; S2. Data transmission: transmit the collected operation data to a remote server through a wireless communication network; S3, data preprocessing: the remote server pre-processes the received operation data, including data cleaning, denoising and standardization processing; S4, fault feature extraction: based on the pre-processed data, the fault features are extracted using signal processing technology; S5, fault diagnosis: input the fault features into a pre-trained fault diagnosis model to diagnose the running state and fault type of the equipment; S6, fault alarm and processing: when the equipment fault is diagnosed, the remote server sends the fault alarm information to the equipment maintenance personnel through the ways of SMS, email or APP push, and provides corresponding fault processing suggestions.

[0024] The data acquisition step includes: Vibration sensor: used to collect vibration signals of the equipment; Temperature sensor: installed on the bearings, motors and other parts of the equipment, used to monitor the temperature change of the equipment; Pressure sensor: installed on the pipelines and containers of the equipment, used to measure the pressure inside the equipment; Flow sensor: installed on the inlet and outlet pipes of the device to monitor the flow of coal slime.

[0025] Data transmission steps include: Data transmission module: install a data transmission module on the device, transmit the collected data to the remote server in real time through 4G / 5G network or Wi-Fi; Data encryption: use AES (Advanced Encryption Standard) algorithm to encrypt data during data transmission to ensure data transmission security and integrity, including: Data encryption: encrypt the collected data on the device side to generate encrypted data packets; Data transmission: transmit encrypted data packets through wireless communication network; Data decryption: decrypt the received data on the remote server side to restore the original data.

[0026] Data preprocessing steps include: Data cleaning: use median filtering and wavelet denoising methods to smooth the original data, remove noise and outliers, including: Median filtering: use a window size of 3 to perform median filtering on each data point to remove short impulse noise; Wavelet denoising: use Daubechies wavelet for multi-scale decomposition to remove high-frequency noise and retain the main features of the signal; Data denoising: use wavelet transform and fast Fourier transform (FFT) methods to remove high-frequency noise in the collected data, including: Wavelet transform: wavelet decomposition of the signal to remove high-frequency noise and retain low-frequency signals; FFT denoising: Fourier transform of the signal to filter out high-frequency noise components and retain low-frequency effective signals; Data standardization: use Z-score standardization method to standardize the data to meet the input requirements of the fault diagnosis model, the formula is: where, is the standardized data, is the original data, is the data mean, is the data standard deviation.

[0027] Fault feature extraction steps include: Spectrum analysis: perform fast Fourier transform (FFT) on the vibration signal to extract spectral features, including: Spectral features: calculate the main frequency, harmonic components and bandwidth of the vibration signal, the formula is: where, is the frequency domain signal, is the time domain signal, is the signal length; Time domain analysis: Extract time domain features from temperature, pressure and flow signals, including: Time domain features: Calculate the mean, standard deviation, peak value and skewness of the signal, the formula is: ; Standard deviation: ; Peak value: ; Skewness: ; Wavelet transform: Perform wavelet decomposition on the collected signals to extract fault features at different scales, including: Wavelet decomposition: Use Daubechies wavelet for multi-scale decomposition to obtain detail signals and approximation signals at different scales; Feature extraction: Calculate energy, entropy and singularity parameters at each scale.

[0028] The fault diagnosis model is trained and established using machine learning algorithms, including: Data set preparation: Collect historical operation data and fault records of coal slime treatment equipment, build training data set and test data set, the data set contains normal operation state and fault state data; Model selection: Use support vector machine algorithm to establish fault diagnosis model; Model training: Use training data set to train fault diagnosis model, optimize model parameters, improve model diagnosis accuracy, including: Data normalization: Normalize the input data to meet the model input requirements; Model training: Use gradient descent (GD) or Adam optimization algorithm to minimize loss function and optimize model parameters; Model verification: Use test data set to verify the trained model, evaluate the performance and generalization ability of the model, including: Cross-validation: Divide the test data set into K subsets, perform K times training and verification, take the average value as the model performance index; Performance evaluation: Calculate the accuracy, recall and F1 score of the model to evaluate the diagnosis effect of the model.

[0029] Cross-validation method is used in model training process, including: K-fold cross-validation: divide the training dataset into K subsets, perform K times of training and validation, each time select one subset as the validation set, the rest as the training set, the specific steps include: Data division: randomly divide the training dataset into K subsets, ensure that the data distribution of each subset is the same; Cross-validation: select each subset as the validation set in turn, the rest as the training set, perform K times of training and validation; Result calculation: calculate the accuracy and error of each validation, take the average value of K validation results as the final evaluation index of the model.

[0030] Fault alarm and processing steps include: Fault alarm: when diagnosing device failure, the remote server sends fault alarm information to device maintenance personnel through SMS, email and mobile application push, including: SMS alarm: send fault information to the maintenance personnel's mobile phone through the SMS gateway; Email alarm: send fault information to the maintenance personnel's mailbox through the email server; Mobile application push: push fault information to the maintenance personnel's mobile application through the mobile application; Fault handling suggestion: according to the fault type and diagnosis result, provide detailed fault handling suggestions, including possible fault causes, processing steps and required tools, including: Fault cause analysis: based on fault characteristics and diagnosis model, analyze possible fault causes; Processing step guidance: provide detailed fault handling steps, including disassembly, inspection, replacement and reinstallation, etc; Required tool list: list the tools and spare parts required in the fault handling process to ensure that the maintenance personnel are fully prepared; Fault handling suggestions are generated based on expert system, including: Fault handling knowledge base: collect the experience and suggestions of equipment maintenance experts, build a fault handling knowledge base, including: Knowledge base construction: convert the experience and suggestions of experts into rules and cases and store them in the knowledge base; Knowledge base maintenance: regularly update and expand the knowledge base to ensure its accuracy and comprehensiveness; Fault handling reasoning engine: based on the knowledge base and fault diagnosis results, use the reasoning engine to generate corresponding fault handling suggestions, including: Rule reasoning: infer the fault handling scheme according to the rules in the knowledge base; Case reasoning: find similar historical cases according to the cases in the knowledge base, and provide corresponding processing suggestions.

[0031] Further comprising a device health state evaluation step, specifically including: Health index calculation: based on the pre-processed operation data and fault features, the health index of the device is calculated to evaluate the operation state of the device, specifically including: Health index formula: the health index of the device is calculated by weighting multiple key parameters, and the formula is: , wherein, is the health index, is the weight of the th parameter, is the normalized value of the th parameter, is the number of parameters; Parameter selection: select key parameters that affect the health state of the device, including vibration, temperature, pressure and flow, etc. Weight determination: determine the weight of each parameter according to the influence degree of each parameter on the health state of the device; Health state evaluation: according to the change trend of the health index, predict the potential failure and maintenance requirement of the device, and provide preventive maintenance suggestions, specifically including: Trend analysis: identify the abnormality of the device operation state by analyzing the change trend of the health index; Failure prediction: predict the potential failure of the device according to the change of the health index; Maintenance suggestion: provide preventive maintenance suggestions, including regular inspection, replacement of vulnerable parts and adjustment of operation parameters, etc.

[0032] As shown in Figure 2 , a remote fault diagnosis system for coal slime treatment equipment is used to implement the above-mentioned remote fault diagnosis method for coal slime treatment equipment, which includes the following modules: Data acquisition module: through the vibration sensor, temperature sensor, pressure sensor and flow sensor installed on the coal slime treatment equipment, real-time acquisition of the operation data of the device, including vibration signal, temperature signal, pressure signal and flow signal; Data transmission module: transmit the collected operation data to the remote server through the wireless communication network, and use AES-256 encryption algorithm to ensure the security and integrity of the data during data transmission; Data preprocessing module: data cleaning, denoising and standardization processing are performed on the received operation data, using median filtering, wavelet denoising and Z-score standardization method to ensure the accuracy and consistency of the data; Fault feature extraction module: based on the pre-processed data, use signal processing techniques such as frequency spectrum analysis, time domain analysis and wavelet transform to extract fault features; Fault diagnosis module: input the fault feature into the pre-trained fault diagnosis model, the model adopts support vector machine machine learning algorithm, and the running state and fault type of the equipment are diagnosed; Fault alarm and processing module: when the equipment fault is diagnosed, the remote server sends the fault alarm information to the equipment maintenance personnel through short message, email and mobile application push, and provides fault processing suggestions based on the expert system; Health status evaluation module: based on the preprocessed running data and fault feature, the health index of the equipment is calculated, and the running state of the equipment is evaluated.

[0033] The present application covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present application. In order to make the public have a thorough understanding of the present application, specific details are described in the following preferred embodiments of the present application, and the present application can also be fully understood without the description of these details for those skilled in the art. In addition, in order not to cause unnecessary confusion to the essence of the present application, well-known methods, processes, procedures, elements and circuits are not described in detail.

[0034] The above is only the preferred embodiment of the present application, and it should be pointed out that for those skilled in the art, without departing from the principle of the present application, a number of improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present application.

Claims

1. A remote failure diagnosis method for a coal slime treatment plant, characterized by, The method comprises the following steps: S1, data collection: real-time collection of operation data of the coal slime treatment equipment through sensors installed on the equipment, including vibration signals, temperature signals, pressure signals and flow signals; S2. Data transmission: transmitting the collected operation data to a remote server through a wireless communication network; S3, data preprocessing: preprocessing the received operation data by the remote server, including data cleaning, denoising and standardization processing; S4, fault feature extraction: based on the preprocessed data, using signal processing technology to extract fault features; S5, fault diagnosis: inputting the fault features into the pre-trained fault diagnosis model to diagnose the operation state and fault type of the equipment; S6, fault alarm and processing: when diagnosing the equipment fault, the remote server sends fault alarm information to the equipment maintenance personnel through SMS, email or APP push, and provides corresponding fault processing suggestions.

2. The remote fault diagnosis method of a coal slime treatment device according to claim 1, characterized in that, The data collection step includes: Vibration sensor: used to collect the vibration signals of the equipment; Temperature sensor: used to monitor the temperature change of the equipment; Pressure sensor: used to measure the pressure inside the equipment; Flow sensor: used to monitor the coal slime flow.

3. The remote fault diagnosis method of a coal slime treatment device according to claim 2, characterized in that, The data transmission step includes: S21, data transmission module: installing a data transmission module on the equipment, and transmitting the collected data to the remote server in real time through 4G / 5G network or Wi-Fi; S22, data encryption: using AES (Advanced Encryption Standard) algorithm to encrypt the data during data transmission, to ensure the security and integrity of data transmission.

4. The remote fault diagnosis method of a coal slime treatment device according to claim 3, characterized in that, The data preprocessing step includes: S31, data cleaning: using median filter and wavelet denoising method to smooth the original data, to remove noise and outliers; S32, data denoising: using wavelet transform and fast Fourier transform (FFT) method to remove high-frequency noise in the collected data; S33, data standardization: using Z-score standardization method to standardize the data, to meet the input requirements of the fault diagnosis model.

5. The remote fault diagnosis method of a coal slime treatment device according to claim 4, characterized in that, The fault feature extraction step includes: S41, spectral analysis: performing fast Fourier transform (FFT) on the vibration signal to extract spectral features; S42, time domain analysis: performing time domain feature extraction on temperature, pressure and flow signals; S43, wavelet transform: performing wavelet decomposition on the collected signals to extract fault features at different scales.

6. The remote fault diagnosis method of a coal slime treatment device according to claim 5, characterized in that, The fault diagnosis model is trained and established using machine learning algorithm, specifically including: S51, data set preparation: collecting historical operation data and fault records of the coal slime treatment equipment, constructing training data set and test data set, and the data set contains data of normal operation state and fault state; S52, model selection: using support vector machine algorithm to establish the fault diagnosis model; S53, model training: using the training data set to train the fault diagnosis model, optimizing the model parameters, and improving the diagnosis accuracy of the model; S54, model verification: using the test data set to verify the trained model, to evaluate the performance and generalization ability of the model.

7. The remote fault diagnosis method of a coal slime treatment device according to claim 6, characterized in that, Cross-validation method is used in the model training process, specifically including: S531, K-fold cross-validation: divide the training dataset into K subsets, perform K times of training and validation, each time select one subset as the validation set and the remaining subsets as the training set, the specific steps include: S532, data division: randomly divide the training dataset into K subsets, ensure that the data distribution of each subset is the same; S534, cross-validation: select each subset as the validation set in turn, and the remaining subsets as the training set, perform K times of training and validation; S535, result calculation: calculate the accuracy and error of each validation, take the average value of K validation results as the final evaluation index of the model.

8. The remote fault diagnosis method of a coal slime treatment device according to claim 1, characterized in that, The fault alarm and processing steps include: S61, fault alarm: when diagnosing equipment failure, the remote server sends fault alarm information to equipment maintenance personnel through SMS, email and mobile application push; S62, fault handling suggestion: according to the fault type and diagnosis result, provide fault handling suggestion, including fault reason, processing steps and required tools; S63, the fault handling suggestion is generated based on expert system, specifically including: S631, fault handling knowledge base: collect the experience and suggestions of equipment maintenance experts, and build a fault handling knowledge base; S632, fault handling reasoning engine: based on the knowledge base and fault diagnosis result, use reasoning engine to generate corresponding fault handling suggestion.

9. The remote fault diagnosis method of a coal slime treatment plant according to claim 1, characterized in that, Also includes equipment health status evaluation steps, specifically including: Health index calculation: based on the preprocessed running data and fault features, calculate the health index of the equipment, evaluate the running state of the equipment, specifically including: Health index formula: the health index of the equipment is calculated by weighting a plurality of key parameters, and the formula is: wherein, is a health index, is a weight for the th parameter, is a normalized value for the th parameter, is a number of parameters; Health status evaluation: according to the change trend of health index, predict the potential failure and maintenance demand of the equipment, and provide preventive maintenance suggestion.

10. A remote fault diagnosis system of a coal slime treatment plant for implementing the remote fault diagnosis method of the coal slime treatment plant according to any one of claims 1-9, characterized in that, Including the following modules: Data acquisition module: through the vibration sensor, temperature sensor, pressure sensor and flow sensor installed on the coal slime treatment equipment, real-time acquisition of the running data of the equipment, including vibration signal, temperature signal, pressure signal and flow signal; Data transmission module: transmit the collected running data to the remote server through the wireless communication network, and use AES-256 encryption algorithm to ensure the security and integrity of the data during data transmission; Data preprocessing module: data cleaning, denoising and standardization processing are performed on the received running data, median filtering, wavelet denoising and Z-score standardization method are used to ensure the accuracy and consistency of the data; Fault feature extraction module: based on the preprocessed data, use signal processing techniques such as frequency spectrum analysis, time domain analysis and wavelet transform to extract fault features; Fault diagnosis module: input the fault features into the pre-trained fault diagnosis model, the model uses support vector machine machine learning algorithm to diagnose the running state and fault type of the equipment; Fault alarm and processing module: when diagnosing equipment failure, the remote server sends fault alarm information to equipment maintenance personnel through SMS, email and mobile application push, and provides fault handling suggestion based on expert system; Health state evaluation module: based on the pre-processed operation data and fault features, the health index of the equipment is calculated, and the operation state of the equipment is evaluated.

Images