Intelligent Monitoring and Maintenance System and Method for Dynamic Equipment Based on Vibration Signal Fusion of Multi-Source Information

Abstract

The present invention discloses an intelligent monitoring and maintenance system and method for moving equipment based on vibration signal fusion of multi-source information, which relates to the technical field of multi-dimensional monitoring of moving equipment. The method includes the following steps: S1. Using a non-invasive signal acquisition scheme, parameters of normal moving equipment and faulty moving equipment during operation are collected, including vibration signals, external magnetic field signals, temperature signals, and sound signals; key features are extracted from the collected vibration, external magnetic field, sound, and temperature signals of the current faulty moving equipment, and feature indicators with the highest correlation with different fault states of the moving equipment are screened through an algorithm, and feature vectors are constructed; based on the feature vectors under different fault states of the moving equipment, a moving equipment fault determination model is constructed based on the collected operating parameter characteristics of the current moving equipment. The present invention effectively improves the accuracy of equipment fault diagnosis by simultaneously collecting and analyzing the vibration, sound, temperature, and external magnetic field signals of the moving equipment, thereby making up for the shortcomings of a single signal source.

Description

Technical Field

[0001] The present invention relates to the technical field of multi-dimensional monitoring of moving equipment, and in particular to a system and method for intelligent monitoring and maintenance of moving equipment based on vibration signal fusion of multi-source information. Background Art

[0002] Dynamic equipment is widely used in industry, but the complex working conditions and changing external environment of the equipment often lead to various types of equipment failures, such as cavitation, impeller damage, mechanical seal failure, etc. These failures may affect the normal operation and efficiency of the equipment, and even cause safety hazards.

[0003] Traditional monitoring methods are mostly based on a single vibration signal or pressure pulsation signal. However, due to the diverse types of faults in moving equipment and their often associated different failure modes, rotating machinery failures are mainly manifested in abnormal vibration and electromagnetic field changes. Traditional single-signal source monitoring methods are difficult to fully reflect the operating status and failure modes of the equipment, and have problems with practicality and functionality. Therefore, a monitoring system that can integrate multi-source information is urgently needed to improve the comprehensiveness and accuracy of monitoring during the operation of moving equipment.

[0004] Currently, no effective solutions have been proposed for the problems in related technologies. Summary of the Invention

[0005] In response to the problems in the related art, the present invention proposes an intelligent monitoring and maintenance system and method for moving equipment based on vibration signal fusion of multi-source information to overcome the above-mentioned technical problems existing in the existing related art.

[0006] To this end, the specific technical solutions adopted in the present invention are as follows:

[0007] The method for intelligent monitoring and maintenance of moving equipment based on vibration signal fusion of multi-source information includes the following steps:

[0008] S1. Use a non-invasive signal acquisition solution to collect parameters during the operation of normal and faulty moving equipment, including vibration signals, external magnetic field signals, temperature signals, and sound signals;

[0009] S2. Extract key features from the collected vibration, external magnetic field, sound, and temperature signals of the currently faulty moving equipment. Use an algorithm to select the characteristic indicators with the highest correlation with different fault states of the moving equipment and construct a feature vector.

[0010] S3. Based on the characteristic vectors of the dynamic equipment under different fault states, a dynamic equipment fault judgment model is constructed. Based on the collected operating parameter characteristics of the current dynamic equipment and combined with the dynamic equipment fault judgment model, multi-dimensional judgments are made on potential faults that have not occurred during the operation of the dynamic equipment, and faults that have occurred are diagnosed.

[0011] As a preferred embodiment, the S1 includes the following sub-steps:

[0012] S11. Place high-sensitivity vibration sensors at key locations of the moving equipment, including bearings, rotors, mechanical seals, and impellers, to collect vibration characteristics of the moving equipment under different conditions, including vibration frequency, amplitude, vibration phase, and spectral characteristics;

[0013] S12. Based on the principle of electromagnetic induction, the induction coil installed outside the motor of the moving device is used to collect the external magnetic field signals of the moving device under different states, including characteristic frequency and amplitude;

[0014] S13, monitoring the external temperature distribution of different moving devices through non-contact infrared temperature sensors, and combining the data collected by internal temperature sensors to obtain the temperature changes of the moving devices under different states;

[0015] S14. A directional microphone is arranged outside the moving device in different states to collect the operating sound signal of the moving device in a non-contact manner.

[0016] As a preferred embodiment, the S2 comprises the following steps:

[0017] S21. Extracting key features of the vibration signal, external magnetic field signal, temperature signal, and sound signal of the moving device under normal conditions as reference state parameter features of the moving device, respectively.

[0018] S22. For the vibration signals, external magnetic field signals, temperature signals and sound signals of the moving equipment under different fault states, the key features of the vibration signals, external magnetic field signals, temperature signals and sound signals are extracted respectively. Based on the Mahalanobis distance and the characteristics of the benchmark state parameters of the moving equipment, the correlation characteristic indicators under different fault states are screened to construct different fault feature vectors.

[0019] As a preferred embodiment, the S21 includes the following steps:

[0020] S211. Extracting time domain features and frequency domain features from the vibration signal of the moving equipment under normal conditions, wherein the time domain features include mean, standard deviation, peak value, and kurtosis, and the frequency domain features include main frequency, spectrum, and frequency center;

[0021] S212. Extract characteristic parameters from the external magnetic field signal of the moving device under normal conditions, including peak value, maximum intensity change rate, main frequency change, harmonic characteristics, offset, and fluctuation amplitude.

[0022] S213. Extract trend features and dynamic features from the collected temperature signals of the moving equipment in a normal state, wherein the trend features include the temperature mean, temperature change rate, maximum temperature, and minimum temperature; and the dynamic features include the temperature fluctuation amplitude, temperature rise rate, and temperature gradient;

[0023] S214, extracting characteristic parameters of the sound signal collected in a normal state, including short-time energy, signal zero-crossing rate, spectrum center frequency, bandwidth, and Mel frequency cepstrum coefficient;

[0024] S215、Extraction of normal moving equipment The vibration signal characteristics, external magnetic field signal characteristics, temperature signal characteristics and sound signal characteristic parameter values are averaged and the averaged characteristic values are used as the reference state parameter characteristic vector of the dynamic equipment:

[0025] ;

[0026] in, Represents the characteristic vector of the reference state parameters of the dynamic equipment, They represent the key features after mean processing of vibration signal, external magnetic field signal, temperature signal and sound signal respectively.

[0027] As a preferred embodiment, the S22 includes the following steps:

[0028] S221, analyze the vibration signal, external magnetic field signal, temperature signal and sound signal of the moving equipment under different fault conditions Group collection, and group based on fault type, through Establish different fault type files respectively, and collect data of the equipment under the same fault type. The group parameters are averaged, and the characteristic parameter values after averaging are recorded in the corresponding fault type file to construct the fault state feature vector:

[0029] ;

[0030] in, Representative The fault state feature vector under the fault type file, Representing the The key features of the vibration signal, external magnetic field signal, temperature signal and sound signal after mean processing under each fault type file;

[0031] S222. Based on the Mahalanobis distance algorithm and the baseline state parameter characteristics of the dynamic equipment, the Mahalanobis distance between the dynamic equipment acquisition parameters and the baseline state parameter characteristics under different fault type files is calculated respectively. The algorithm formula is:

[0032] ;

[0033] in, represents the covariance matrix of the baseline state parameter eigenvector, Representative The Mahalanobis distance between each feature and the reference state parameter feature under each fault type file;

[0034] S223, based on Mahalanobis distance threshold , screen the characteristic indicators that are highly correlated with each fault state. The specific steps are:

[0035] Statistics all > These characteristics are the high-correlation characteristic indicators under different fault states. Based on the selected correlation characteristic indicators, the correlation characteristic vectors under different fault states are constructed:

[0036] ;

[0037] in, That is the The associated feature vector under each fault type file, Representing the The vibration, magnetic field, temperature and sound characteristics that are highly correlated with the fault status under each fault type file.

[0038] As a preferred embodiment, the S3 includes the following sub-steps:

[0039] S31. Based on the characteristic vectors of the dynamic equipment under different fault conditions, a dynamic equipment fault determination model is constructed. The specific steps are as follows:

[0040] The eigenvectors of normal state and different fault states are labeled, where the label of normal state is 0 and the label of fault state is 1 to N. Based on the associated eigenvectors, the characteristic parameters related to the fault are selected to construct the input feature matrix :

[0041] ;

[0042] The equipment fault judgment model is constructed based on the neural network. The output of the input layer is the input feature vector. , the output of each hidden layer is transformed nonlinearly through the activation function. The number of neurons in the output layer is equal to the number of categories, which is N+1 categories, including normal state and N fault states. At the same time, the output of the output layer is transformed through The activation function performs probability distribution conversion and the marked feature matrix The neural model is trained with the label input under the fault state to obtain the dynamic equipment fault judgment model;

[0043] S32. Collect vibration signals, external magnetic field signals, sound signals, and temperature signals during the current operation of the dynamic equipment, extract characteristic parameters, construct the current characteristic vector, and based on the obtained dynamic equipment fault judgment model, make multi-dimensional predictions on potential faults that have not occurred during the operation of the dynamic equipment, and diagnose faults that have already occurred.

[0044] As a preferred embodiment, the S32 includes the following steps:

[0045] S321. Collect vibration signals, external magnetic field signals, sound signals, and temperature signals during the operation of the current moving equipment, extract characteristic parameters, and construct a real-time feature vector:

[0046] ;

[0047] in, They respectively represent the key features of the vibration signal, external magnetic field signal, temperature signal and sound signal collected during the operation of the current dynamic equipment;

[0048] S322. Input the real-time feature vector into the dynamic equipment fault determination model to detect whether there is a potential fault in the dynamic equipment:

[0049] The output layer usually uses The activation function converts the real-time feature vector input and output into the probability distribution of each category and selects the category with the highest probability as the final prediction result:

[0050] When the output result is 0, the current device is in normal state;

[0051] When the prediction result is 1 to N, it means that there is a potential fault in the dynamic equipment;

[0052] S323. For the dynamic equipment with potential faults, extract abnormal characteristic parameters to obtain abnormal characteristic vectors:

[0053] ;

[0054] in, Respectively represent the abnormal characteristics of the current moving equipment in vibration signal, external magnetic field signal, temperature signal and sound signal, and calculate The cosine similarity of the associated feature vectors under each fault type file is sorted in descending order, and the fault type file with the first position is selected as the diagnostic output fault of the current abnormal fault of the dynamic equipment.

[0055] The intelligent monitoring and maintenance system for moving equipment based on vibration signal fusion of multi-source information includes data acquisition module, feature extraction module, model building module, and output judgment module:

[0056] The data acquisition module collects parameters of normal and faulty moving equipment during operation, including vibration signals, external magnetic field signals, temperature signals, and sound signals, through a non-invasive signal acquisition solution;

[0057] The feature extraction module extracts key features from the vibration, external magnetic field, sound and temperature signals of the currently faulty moving equipment collected by the data acquisition module, selects the feature indicators with the highest correlation with different fault states of the moving equipment through an algorithm, and constructs a feature vector;

[0058] The model building module builds a dynamic equipment fault judgment model through a neural network based on the characteristic vectors under different fault states of the dynamic equipment, and outputs the model to the output judgment module;

[0059] The output determination module, in combination with the operating parameter characteristics of the current dynamic equipment collected by the data acquisition module, uses the dynamic equipment fault determination model to perform multi-dimensional determination on potential faults that have not occurred during the operation of the dynamic equipment, and diagnose faults that have occurred.

[0060] The beneficial effects of the present invention are:

[0061] 1. The present invention collects vibration signals, external magnetic field signals, temperature signals, and sound signals from moving equipment in a faulty state, and analyzes, compares, and calculates the characteristic parameters of the signals under different faulty states in combination with the characteristic parameters of the signals under normal states to obtain characteristic parameter vectors under different faulty states. By collecting multiple types of signals, a more comprehensive understanding of the operating status of the equipment is achieved, thereby improving the accuracy of moving equipment fault diagnosis.

[0062] 2. The present invention constructs a feature vector by comparing the signal characteristic parameters of the fault state and the normal state, which helps to highlight the fault characteristics and improve the diagnosis accuracy. At the same time, the characteristics of vibration, external magnetic field, temperature and sound signals can be used to more accurately locate different fault types to assist in the fault diagnosis of mobile equipment.

[0063] 3. The present invention establishes a dynamic equipment fault determination model that can analyze multiple signal features collected during the operation of the dynamic equipment in real time, promptly identify abnormal signals to predict faults, and help to carry out maintenance work in advance. By diagnosing abnormal signals, the most likely fault type of the current dynamic equipment can be determined, thereby assisting maintenance personnel in repairing the dynamic equipment, enhancing practicality and functionality.

[0064] 4. The present invention can comprehensively improve the accuracy of dynamic equipment fault diagnosis and the monitoring efficiency under complex working conditions through multi-source information fusion analysis of vibration, external magnetic field, sound and temperature signals, and realize automatic dynamic equipment fault identification and classification by using the constructed judgment model. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0066] Figure 1 is a flow chart of a method for intelligent monitoring and maintenance of moving equipment based on vibration signal fusion of multi-source information according to an embodiment of the present invention;

[0067] Figure 2 This is a block diagram of a system for intelligent monitoring and maintenance of moving equipment based on vibration signal fusion of multi-source information according to an embodiment of the present invention. DETAILED DESCRIPTION

[0068] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention. They are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. By referring to these contents, ordinary technicians in this field should be able to understand other possible implementation methods and advantages of the present invention. The components in the figures are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0069] According to an embodiment of the present invention, a system and method for intelligent monitoring and maintenance of moving equipment based on vibration signal fusion of multi-source information are provided.

[0070] The present invention will now be further described with reference to the accompanying drawings and specific embodiments:

[0071] Example 1: Figure 1 As shown, according to an embodiment of the present invention, a method for intelligent monitoring and maintenance of moving equipment based on vibration signal fusion of multi-source information includes the following steps:

[0072] S1. Use a non-invasive signal acquisition solution to collect parameters during the operation of normal and faulty moving equipment, including vibration signals, external magnetic field signals, temperature signals, and sound signals;

[0073] S11. Place high-sensitivity vibration sensors at key locations of the moving equipment, including bearings, rotors, mechanical seals, and impellers, to collect vibration characteristics of the moving equipment under different conditions, including vibration frequency, amplitude, vibration phase, and spectral characteristics;

[0074] It should be noted that when different abnormalities occur in the moving equipment, the rotor imbalance fault manifests as radial vibration, the frequency of which is mainly concentrated on the fundamental frequency. Mechanical seal damage failure usually causes abnormal high-frequency vibration, and impeller damage failure causes specific vibration spectrum characteristic changes.

[0075] S12. Based on the principle of electromagnetic induction, the induction coil installed outside the motor of the moving device is used to collect the external magnetic field signals of the moving device under different states, including characteristic frequency and amplitude;

[0076] It should be noted that the induction coil reflects the load change by capturing the change in the stator magnetic field of the moving equipment. When the working conditions or load of the moving equipment changes, the characteristic frequency and amplitude of the external magnetic field signal will also change accordingly.

[0077] S13, monitoring the external temperature distribution of different moving devices through non-contact infrared temperature sensors, and combining the data collected by internal temperature sensors to obtain the temperature changes of the moving devices under different states;

[0078] It should be noted that when the load of the moving equipment increases or a key component fails, the temperature signal will show an abnormal upward trend. By collecting the current temperature change of the moving equipment, the moving equipment failure can be determined;

[0079] S14. A directional microphone is arranged outside the moving device in different states to collect the operating sound signal of the moving device in a non-contact manner.

[0080] It should be noted that different fault types will cause changes in sound characteristics. For example, impeller damage will cause a pulse-type sound characteristic, and mechanical friction faults will increase high-frequency noise. By collecting the sound signals of the moving equipment and further extracting the characteristics of the sound signals, the sound signal characteristics can be obtained.

[0081] S2. Extract key features from the collected vibration, external magnetic field, sound, and temperature signals of the currently faulty moving equipment. Use an algorithm to select the characteristic indicators with the highest correlation with different fault states of the moving equipment and construct a feature vector.

[0082] S21. Extracting key features of the vibration signal, external magnetic field signal, temperature signal, and sound signal of the moving device under normal conditions as reference state parameter features of the moving device, respectively.

[0083] S211. Extracting time domain features and frequency domain features from the vibration signal of the moving equipment under normal conditions, wherein the time domain features include mean, standard deviation, peak value, and kurtosis, and the frequency domain features include main frequency, spectrum, and frequency center;

[0084] It should be noted that in the vibration signal, the mean is the average value of the vibration signal, which reflects the overall level of vibration amplitude. The peak is the maximum amplitude of the vibration signal, which indicates the intensity of abnormal vibration. The kurtosis is a measure of the sharpness of the vibration signal, which will increase significantly when a fault occurs in the moving equipment. The main frequency is the main vibration frequency of the signal, which is used to identify specific fault types, such as rotor imbalance. The spectrum is the energy distribution in the frequency domain, which is used to analyze fault signals in a specific frequency band.

[0085] S212. Extract characteristic parameters from the external magnetic field signal of the moving device under normal conditions, including peak value, maximum intensity change rate, main frequency change, harmonic characteristics, offset, and fluctuation amplitude.

[0086] It should be noted that in the external magnetic field signal, the peak value reflects the degree of change in the motor load, the maximum intensity change rate reflects the speed of intensity change when the load changes rapidly, the main frequency change can indicate the characteristic frequency fluctuation of the magnetic field caused by the load change, the harmonic characteristics are the high-order harmonic components generated when the load fluctuates or the torque fluctuates, the offset is the average value deviation of the magnetic field intensity, indicating the overall load trend, and the fluctuation amplitude is the range of change of the magnetic field intensity in a short period of time.

[0087] S213. Extract trend features and dynamic features from the collected temperature signals of the moving equipment in a normal state, wherein the trend features include the temperature mean, temperature change rate, maximum temperature, and minimum temperature; and the dynamic features include the temperature fluctuation amplitude, temperature rise rate, and temperature gradient;

[0088] It should be noted that in the temperature signal, the temperature mean and rate of change are used to identify the thermal equilibrium state and heating or cooling trend. The maximum and minimum temperature values reflect the thermal load and cooling capacity of the equipment. The temperature fluctuation amplitude indicates the stability of the temperature signal, which may cause increased fluctuations when the moving equipment fails. The temperature rise rate represents the speed of temperature rise and is used to diagnose equipment overload or insufficient heat dissipation. The temperature gradient is used to identify local overheating when the moving equipment fails.

[0089] S214, extracting characteristic parameters of the sound signal collected in a normal state, including short-time energy, signal zero-crossing rate, spectrum center frequency, bandwidth, and Mel frequency cepstrum coefficient;

[0090] It should be noted that in sound signals, short-time energy is the local energy of the sound signal, which is used to reflect the intensity of noise or impact signals. The signal zero-crossing rate can reflect the high-frequency components and noise level of the sound signal. The spectrum center frequency is the main frequency of the sound signal and is used to identify the source of the dynamic equipment failure. The bandwidth is the width of the sound signal energy distribution and indicates the complexity of the signal. The Mel-frequency cepstral coefficient is used to describe the frequency distribution of the sound signal.

[0091] S215, extraction of normal moving equipment The vibration signal characteristics, external magnetic field signal characteristics, temperature signal characteristics and sound signal characteristic parameter values are averaged and the averaged characteristic values are used as the reference state parameter characteristic vector of the dynamic equipment:

[0092] ;

[0093] in, Represents the characteristic vector of the reference state parameters of the dynamic equipment, They represent the key features after mean processing of vibration signal, external magnetic field signal, temperature signal and sound signal respectively.

[0094] It should be noted that, by Collecting group parameters and calculating the mean can reduce the error of collected data. The value is generally set to 5, and can also be adjusted according to actual conditions;

[0095] S22. Extract key features of the vibration signals, external magnetic field signals, temperature signals, and sound signals of the moving equipment under different fault states, respectively. Based on the Mahalanobis distance and the characteristics of the moving equipment's baseline state parameters, select correlation characteristic indicators under different fault states and construct different fault feature vectors.

[0096] S221, analyze the vibration signal, external magnetic field signal, temperature signal and sound signal of the moving equipment under different fault conditions Group collection, and group based on fault type, through Establish different fault type files respectively, and collect data of the equipment under the same fault type. The group parameters are averaged, and the characteristic parameter values after averaging are recorded in the corresponding fault type file to construct the fault state feature vector:

[0097] ;

[0098] in, Representative The fault state feature vector under the fault type file, Representing the The key features of the vibration signal, external magnetic field signal, temperature signal and sound signal after mean processing under each fault type file;

[0099] It should be noted that Collecting group parameters and calculating the mean can reduce the error of collected data. The value remains the same as that in S215.

[0100] S222. Based on the Mahalanobis distance algorithm and the baseline state parameter characteristics of the dynamic equipment, the Mahalanobis distance between the dynamic equipment acquisition parameters and the baseline state parameter characteristics under different fault type files is calculated respectively. The algorithm formula is:

[0101] ;

[0102] in, represents the covariance matrix of the baseline state parameter eigenvector, Representative The Mahalanobis distance between each feature and the reference state parameter feature under each fault type file;

[0103] S223, based on Mahalanobis distance threshold , screen the characteristic indicators that are highly correlated with each fault state. The specific steps are:

[0104] Statistics all > These characteristics are the high-correlation characteristic indicators under different fault states. Based on the selected correlation characteristic indicators, the correlation characteristic vectors under different fault states are constructed:

[0105] ;

[0106] in, That is the The associated feature vector under each fault type file, Representing the The vibration, magnetic field, temperature and sound characteristics that are highly correlated with the fault status under each fault type file.

[0107] It should be noted that based on the Mahalanobis distance combined with the characteristics of the benchmark state parameters of the dynamic equipment, the correlation characteristic indicators under different fault states are screened out, and different fault feature vectors are constructed, so as to achieve effective identification and diagnosis of the fault state of the dynamic equipment. According to the Mahalanobis distance, the distribution of samples in the feature space can be judged, and the feature parameters that contribute most to the classification can be selected. The Mahalanobis distance threshold It is necessary to calculate the covariance matrix of the baseline state eigenvector to calculate the Mahalanobis distance under normal conditions and draw its distribution. According to the chi-square distribution table, select the appropriate confidence level to obtain the corresponding Mahalanobis distance threshold.

[0108] Example 2: S3, based on the characteristic vectors of the dynamic equipment under different fault states, a dynamic equipment fault determination model is constructed. Based on the collected operating parameter characteristics of the current dynamic equipment and combined with the dynamic equipment fault determination model, a multi-dimensional determination is made on potential faults that have not occurred during the operation of the dynamic equipment, and faults that have already occurred are diagnosed;

[0109] S31. Based on the characteristic vectors of the dynamic equipment under different fault conditions, a dynamic equipment fault determination model is constructed. The specific steps are as follows:

[0110] The eigenvectors of normal state and different fault states are labeled, where the label of normal state is 0 and the label of fault state is 1 to N. Based on the associated eigenvectors, the characteristic parameters related to the fault are selected to construct the input feature matrix :

[0111] ;

[0112] The equipment fault judgment model is constructed based on the neural network. The output of the input layer is the input feature vector. , the output of each hidden layer is transformed nonlinearly through the activation function. The number of neurons in the output layer is equal to the number of categories, which is N+1 categories, including normal state and N fault states. At the same time, the output of the output layer is transformed through The activation function performs probability distribution conversion and the marked feature matrix The neural model is trained with the label input under the fault state to obtain the dynamic equipment fault judgment model;

[0113] It should be noted that in the process of building a neural network model, forward propagation, loss function, and back propagation are required to ultimately train the model. The specific steps of forward propagation are as follows:

[0114] ;

[0115] ;

[0116] in, is the weight matrix from the input layer to the hidden layer, is the bias vector, is the ReLU activation function.

[0117] S32. Collect vibration signals, external magnetic field signals, sound signals, and temperature signals during the current operation of the dynamic equipment, extract characteristic parameters, construct a current characteristic vector, and perform multi-dimensional prediction of potential faults that have not yet occurred during the operation of the dynamic equipment based on the obtained dynamic equipment fault determination model, and diagnose faults that have already occurred;

[0118] S321. Collect vibration signals, external magnetic field signals, sound signals, and temperature signals during the operation of the current moving equipment, extract characteristic parameters, and construct a real-time feature vector:

[0119] ;

[0120] in, They respectively represent the key features of the vibration signal, external magnetic field signal, temperature signal and sound signal collected during the operation of the current dynamic equipment;

[0121] S322. Input the real-time feature vector into the dynamic equipment fault determination model to detect whether there is a potential fault in the dynamic equipment:

[0122] The output layer usually uses The activation function converts the real-time feature vector input and output into the probability distribution of each category and selects the category with the highest probability as the final prediction result:

[0123] When the output result is 0, the current device is in normal state;

[0124] When the prediction result is 1 to N, it means that there is a potential fault in the dynamic equipment;

[0125] S323. For the dynamic equipment with potential faults, extract abnormal characteristic parameters to obtain abnormal characteristic vectors:

[0126] ;

[0127] in, Respectively represent the abnormal characteristics of the current moving equipment in vibration signal, external magnetic field signal, temperature signal and sound signal, and calculate The cosine similarity of the associated feature vectors under each fault type file is sorted in descending order, and the fault type file with the first position is selected as the diagnostic output fault of the current abnormal fault of the dynamic equipment.

[0128] It should be noted that the greater the cosine similarity, the more similar the two feature vectors are, that is, the more similar the current abnormal feature of the dynamic equipment is to the associated feature vector in the fault file, the higher the similarity between the current abnormality and the fault is. Outputting the fault through diagnostic output can assist operators in timely maintenance and early repair of the abnormality of the dynamic equipment.

[0129] Example 3: Figure 2 As shown in the figure, the intelligent monitoring and maintenance system for dynamic equipment based on vibration signal fusion of multi-source information includes a data acquisition module, a feature extraction module, a model building module, and an output judgment module:

[0130] The data acquisition module collects parameters of normal and faulty moving equipment during operation through a non-invasive signal acquisition solution, including vibration signals, external magnetic field signals, temperature signals, and sound signals;

[0131] The feature extraction module extracts key features from the vibration, external magnetic field, sound, and temperature signals of the currently faulty moving equipment collected by the data acquisition module. It uses an algorithm to select the feature indicators with the highest correlation with different fault states of the moving equipment and construct a feature vector.

[0132] The model building module builds a dynamic equipment fault judgment model through a neural network based on the characteristic vectors under different fault states of the dynamic equipment, and outputs the model to the output judgment module;

[0133] The output judgment module, combined with the operating parameter characteristics of the current dynamic equipment collected by the data acquisition module, uses the dynamic equipment fault judgment model to make multi-dimensional judgments on potential faults that have not occurred during the operation process of the dynamic equipment, and diagnose faults that have already occurred.

[0134] In summary, the present invention collects vibration signals, external magnetic field signals, temperature signals, and sound signals from moving equipment in a faulty state, and analyzes, compares, and calculates the characteristic parameters of the signals under different faulty states in combination with the characteristic parameters of the signals under a normal state to obtain characteristic parameter vectors under different faulty states. By collecting multiple types of signals, a more comprehensive understanding of the operating status of the equipment is achieved, thereby improving the accuracy of moving equipment fault diagnosis.

[0135] By building a dynamic equipment fault judgment model, it is possible to analyze the various signal characteristics collected during the operation of the dynamic equipment in real time, and promptly judge abnormal signals to predict faults, which helps to carry out maintenance work in advance. By diagnosing abnormal signals, the most likely fault type of the current dynamic equipment can be determined, thereby assisting maintenance personnel in repairing the dynamic equipment and enhancing practicality and functionality.

[0136] 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 spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for intelligent monitoring and maintenance of moving equipment based on vibration signal fusion of multi-source information, characterized in that: The method comprises the following steps: S1. Use a non-invasive signal acquisition solution to collect parameters during the operation of normal and faulty moving equipment, including vibration signals, external magnetic field signals, temperature signals, and sound signals; S2. Extract key features from the collected vibration, external magnetic field, sound, and temperature signals of the currently faulty moving equipment. Use an algorithm to select the characteristic indicators with the highest correlation with different fault states of the moving equipment and construct a feature vector. S21. Extracting key features of the vibration signal, external magnetic field signal, temperature signal, and sound signal of the moving device under normal conditions as reference state parameter features of the moving device, respectively. S22. Extract key features of the vibration signals, external magnetic field signals, temperature signals, and sound signals of the moving equipment under different fault states, respectively. Based on the Mahalanobis distance and the characteristics of the moving equipment's baseline state parameters, select correlation characteristic indicators under different fault states and construct different fault feature vectors. S221. Collect n groups of vibration signals, external magnetic field signals, temperature signals, and sound signals of the moving equipment under different fault states, group them based on the fault type, create different fault type files through MySQL, perform mean processing on the n groups of parameters collected from the moving equipment under the same fault type, and record the characteristic parameter values after mean processing in the corresponding fault type file to construct the fault state feature vector: F i =[f Ai ,f Bi ,f Ci ,f Di ]; Among them, F i represents the fault state feature vector under the i-th fault type file, f Ai 、f Bi 、f Ci 、f Di They represent the key features of the vibration signal, external magnetic field signal, temperature signal and sound signal after mean value processing under the i-th fault type file; S222. Based on the Mahalanobis distance algorithm and the baseline state parameter characteristics of the dynamic equipment, the Mahalanobis distance between the dynamic equipment acquisition parameters and the baseline state parameter characteristics under different fault type files is calculated respectively. The algorithm formula is: Among them, C represents the covariance matrix of the baseline state parameter eigenvector, D M (F 基准 ,F i ) represents the Mahalanobis distance between each feature and the baseline state parameter feature under the i-th fault type file; S223, based on Mahalanobis distance threshold D θ , screen the characteristic indicators that are highly correlated with each fault state. The specific steps are: Count all D M (F 基准 ,F i )>D θ These characteristics are the high-correlation characteristic indicators under different fault states. Based on the selected correlation characteristic indicators, the correlation characteristic vectors under different fault states are constructed: F i ’=[f ai ,f bi ,f ci ,f di ]; Among them, F i ' is the associated feature vector under the i-th fault type file, f ai 、f bi 、f ci 、f di They represent the vibration, magnetic field, temperature and sound characteristics that are highly correlated with the fault state under the i-th fault type file; S3. Based on the characteristic vectors of the dynamic equipment under different fault states, a dynamic equipment fault judgment model is constructed. Based on the collected operating parameter characteristics of the current dynamic equipment and combined with the dynamic equipment fault judgment model, multi-dimensional judgments are made on potential faults that have not occurred during the operation of the dynamic equipment, and faults that have occurred are diagnosed.

2. The method for intelligent monitoring and maintenance of moving equipment based on vibration signal fusion of multi-source information according to claim 1 is characterized in that: The S1 includes the following sub-steps: S11. Place high-sensitivity vibration sensors at key locations of the moving equipment, including bearings, rotors, mechanical seals, and impellers, to collect vibration characteristics of the moving equipment under different conditions, including vibration frequency, amplitude, vibration phase, and spectral characteristics; S12. Based on the principle of electromagnetic induction, the induction coil installed outside the motor of the moving device is used to collect the external magnetic field signals of the moving device under different states, including characteristic frequency and amplitude; S13, monitoring the external temperature distribution of different moving devices through non-contact infrared temperature sensors, and combining the data collected by internal temperature sensors to obtain the temperature changes of the moving devices under different states; S14. A directional microphone is arranged outside the moving device in different states to collect the operating sound signal of the moving device in a non-contact manner.

3. The method for intelligent monitoring and maintenance of moving equipment based on vibration signal fusion of multi-source information according to claim 1 is characterized in that: The S21 includes the following steps: S211. Extracting time domain features and frequency domain features from the vibration signal of the moving equipment under normal conditions, wherein the time domain features include mean, standard deviation, peak value, and kurtosis, and the frequency domain features include main frequency, spectrum, and frequency center; S212. Extract characteristic parameters from the external magnetic field signal of the moving device under normal conditions, including peak value, maximum intensity change rate, main frequency change, harmonic characteristics, offset, and fluctuation amplitude. S213. Extract trend features and dynamic features from the collected temperature signals of the moving equipment in a normal state, wherein the trend features include the temperature mean, temperature change rate, maximum temperature, and minimum temperature; and the dynamic features include the temperature fluctuation amplitude, temperature rise rate, and temperature gradient; S214, extracting characteristic parameters of the sound signal collected in a normal state, including short-time energy, signal zero-crossing rate, spectrum center frequency, bandwidth, and Mel frequency cepstrum coefficient; S215. Perform mean processing on the n groups of vibration signal features, external magnetic field signal features, temperature signal features, and sound signal feature parameter values extracted from the normal moving equipment, and use the feature values after the mean as the moving equipment reference state parameter feature vector: F 基准 =[f A ,f B ,f C ,f D ]; Among them, F 基准 Represents the characteristic vector of the reference state parameters of the dynamic equipment, f A 、f B 、f C 、f D They represent the key features after mean processing of vibration signal, external magnetic field signal, temperature signal and sound signal respectively.

4. The method for intelligent monitoring and maintenance of moving equipment based on vibration signal fusion of multi-source information according to claim 1 is characterized in that: The S3 includes the following sub-steps: S31. Based on the characteristic vectors of the dynamic equipment under different fault conditions, a dynamic equipment fault determination model is constructed. The specific steps are as follows: The eigenvectors of the normal state and different fault states are labeled, where the label of the normal state is 0 and the label of the fault state is 1 to N. Based on the associated eigenvectors, the characteristic parameters related to the fault are selected to construct the input feature matrix X: X=[F 基准 ,F’1,F’2,F’3,...,F’ N ]; A dynamic equipment fault determination model is constructed based on a neural network. The output of the input layer is the input feature vector X. The output of each hidden layer is nonlinearly transformed using an activation function. The number of neurons in the output layer is equal to the number of categories, which is N+1 categories, including normal state and N fault states. At the same time, the output of the output layer is converted to a probability distribution using a Softmax activation function. The labeled feature matrix X and the labels under the fault state are input into the neural model for training to obtain a dynamic equipment fault determination model. S32. Collect vibration signals, external magnetic field signals, sound signals, and temperature signals during the current operation of the dynamic equipment, extract characteristic parameters, construct the current characteristic vector, and based on the obtained dynamic equipment fault judgment model, make multi-dimensional predictions on potential faults that have not occurred during the operation of the dynamic equipment, and diagnose faults that have already occurred.

5. The method for intelligent monitoring and maintenance of moving equipment based on vibration signal fusion of multi-source information according to claim 4 is characterized in that: The S32 includes the following steps: S321. Collect vibration signals, external magnetic field signals, sound signals, and temperature signals during the operation of the current moving equipment, extract characteristic parameters, and construct a real-time feature vector: F 实时 =[f 振动 ,f 外磁场 ,f 温度 ,f 声音 ]; Among them, f 振动 、f 外磁场 、f 温度 、f 声音 They respectively represent the key features of the vibration signal, external magnetic field signal, temperature signal and sound signal collected during the operation of the current dynamic equipment; S322. Input the real-time feature vector into the dynamic equipment fault determination model to detect whether there is a potential fault in the dynamic equipment: The output layer usually uses the Softmax activation function to convert the real-time feature vector input and output into the probability distribution of each category, and selects the category with the highest probability as the final prediction result: When the output result is 0, the current device is in normal state; When the prediction result is 1 to N, it means that there is a potential fault in the dynamic equipment; S323. For the dynamic equipment with potential faults, extract abnormal characteristic parameters to obtain abnormal characteristic vectors: F 异常 =[j A ,j B ,j C ,j D ]; Among them, j A 、j B 、j C 、j D They represent the abnormal characteristics of the vibration signal, external magnetic field signal, temperature signal and sound signal of the current moving equipment, and calculate F respectively. 异常 The cosine similarity of the associated feature vectors under each fault type file is sorted in descending order, and the fault type file with the first position is selected as the diagnostic output fault of the current abnormal fault of the dynamic equipment.

6. Intelligent monitoring and maintenance system for moving equipment based on vibration signal fusion of multi-source information, characterized by: The system adopts the method for intelligent monitoring and maintenance of moving equipment based on vibration signal fusion of multi-source information as described in any one of claims 1 to 5, including a data acquisition module, a feature extraction module, a model construction module, and an output judgment module: The data acquisition module collects parameters of normal and faulty moving equipment during operation, including vibration signals, external magnetic field signals, temperature signals, and sound signals, through a non-invasive signal acquisition solution; The feature extraction module extracts key features from the vibration, external magnetic field, sound and temperature signals of the currently faulty moving equipment collected by the data acquisition module, selects the feature indicators with the highest correlation with different fault states of the moving equipment through an algorithm, and constructs a feature vector; The model building module builds a dynamic equipment fault judgment model through a neural network based on the characteristic vectors under different fault states of the dynamic equipment, and outputs the model to the output judgment module; The output determination module, in combination with the operating parameter characteristics of the current dynamic equipment collected by the data acquisition module, uses the dynamic equipment fault determination model to perform multi-dimensional determination on potential faults that have not occurred during the operation of the dynamic equipment, and diagnose faults that have occurred.

Images