Equipment fault monitoring method and monitoring system based on bearing monitoring

Abstract

This application provides a method and system for monitoring equipment faults based on bearing monitoring, relating to the technical field of fault diagnosis. The method includes the following steps: data acquisition, signal decoupling, first model construction, fault prediction, second model construction, fault propagation, and equipment fault prediction. The system includes a data acquisition module, a signal decoupling module, a first model construction module, a fault prediction module, a second model construction module, a fault propagation module, and an equipment fault prediction module. This application can monitor the health status of multiple bearings in real time, predict the propagation of faults between different bearings, and identify potential equipment faults in advance, thus achieving accurate fault monitoring and prediction for multi-bearing equipment.

Description

Technical Field

[0001] The present application relates to the technical field of fault diagnosis, and in particular to an equipment fault monitoring method and monitoring system based on bearing monitoring. Background Art

[0002] With the continuous improvement of industrialization and automation, the operating efficiency and reliability of mechanical equipment play a vital role in modern manufacturing. As one of the core components of mechanical equipment, bearings are subjected to multiple pressures such as rotation, load, and friction. Their health directly affects the performance and service life of the equipment.

[0003] The Chinese invention patent, with an application publication date of July 12, 2024 and publication number CN118329450A, provides a bearing fault diagnosis method, system, device, and storage medium. The patent obtains original bearing vibration data to construct a bearing vibration sample set; constructs a bearing fault diagnosis model, and uses the unlabeled data and labeled data in the bearing vibration sample set to perform unsupervised pre-training and supervised fine-tuning training on the bearing fault diagnosis model; obtains bearing vibration data to be classified, and uses the supervised fine-tuned bearing fault diagnosis model to perform end-to-end bearing fault diagnosis on the bearing vibration data to be classified to obtain a bearing fault classification result. The present invention uses time series modeling technology and masked autoencoding technology to perform unsupervised pre-training and supervised fine-tuning training on unlabeled data and labeled data, so that the trained bearing fault diagnosis model can perform end-to-end high-precision bearing fault classification on bearing vibration data.

[0004] The above-mentioned technical solutions focus on fault diagnosis of a single bearing, ignoring the mutual influence and fault propagation between multiple bearings. When a bearing of a multi-bearing device fails, the fault signals are easily intertwined and superimposed, making it difficult to accurately identify the source of the fault from the signal collected from a single sensor. Moreover, the fault diagnosis of a single bearing may ignore the evolution of the entire equipment fault and cannot accurately predict the overall health status of the equipment. Summary of the Invention

[0005] In order to improve the accuracy of bearing fault monitoring in a multi-bearing system, the present application provides an equipment fault monitoring method and a monitoring system based on bearing monitoring.

[0006] In a first aspect, the present application provides a method for monitoring equipment faults based on bearing monitoring, which adopts the following technical solutions:

[0007] A method for monitoring equipment failure based on bearing monitoring, comprising the following steps:

[0008] Data collection: Collect the test data of the equipment's bearing group; the test data includes vibration signals, temperature, lubricating oil metal powder, speed and load;

[0009] Signal decoupling: Use blind source separation technology to perform signal decoupling on the collected detection data to obtain the detection data of each bearing in the bearing group;

[0010] First model construction: build a fault prediction model based on deep learning algorithm;

[0011] Fault prediction: predict the fault type label of each bearing based on the detection data of each bearing;

[0012] Second model construction: construct the fault propagation model of the bearing group;

[0013] Fault propagation: Based on the fault type label of each bearing, the faulty bearings are screened out and the number of faulty bearings is determined to see whether it exceeds the preset threshold.

[0014] If so, the device is judged to be faulty and the current time is output as the device fault time;

[0015] If not, the detection data of the selected bearings are input into the fault propagation model, the fault evolution results are output, and the equipment fault prediction step is executed;

[0016] Equipment failure prediction: Predict the remaining life of the equipment based on the failure evolution results.

[0017] By employing this technical solution, blind source separation technology is used to decouple the collected test data, ensuring independent and accurate fault detection data for each bearing. This improves the accuracy of bearing fault detection in multi-bearing systems. Furthermore, by establishing a fault propagation model for bearing groups, the health status of multiple bearings can be monitored in real time, the propagation of faults between different bearings can be predicted, and potential equipment failures can be identified in advance, achieving precise fault monitoring and prediction for multi-bearing equipment.

[0018] Optionally, before executing the step of data collection, the method further includes:

[0019] Sensor type selection: According to the type of bearing detection data that needs to be collected, set the sensor that collects the corresponding data type, and regard a group of sensors corresponding to the detection data type as a sensor group;

[0020] Define the optimization goal: minimize the number of sensor groups and maximize the fault detection coverage, and construct the objective function;

[0021] Define constraints: Use the operating characteristics, failure modes, and interference between sensors of each bearing in the equipment's bearing group as constraints for the objective function.

[0022] Sensor location optimization: Based on the objective function and constraints, an optimization algorithm is used to obtain the number of sensor groups and the corresponding installation locations.

[0023] By adopting the above technical solution, the number, position and arrangement of sensors are optimized to ensure maximum fault detection coverage of the equipment's bearing groups. At the same time, the operating characteristics and failure modes of the bearings are taken into account. While reducing costs, it is not only possible to effectively monitor the status of each bearing, but also to effectively reduce signal distortion caused by sensor interference, thereby improving the quality of detection data, reducing noise and redundant information, and helping to improve the accuracy of fault diagnosis and the reliability of the equipment.

[0024] Optionally, after performing the step of data acquisition and before performing the step of signal decoupling, the method further includes:

[0025] Time domain analysis: The time domain analysis method is used to extract the time domain features from the inspection data of the bearing group, and the extracted time domain features and the inspection data of the bearing group are used as new inspection data of the bearing group.

[0026] By employing this technical solution, redundant information and noise in the raw data are compressed into feature data, reducing interference signals during the decoupling process and improving the accuracy of signal decoupling. Furthermore, features extracted through time-domain analysis enhance the discernibility of each bearing signal, helping to separate individual bearing signals from the mixed overall signal during the signal decoupling process. This improves decoupling efficiency, accuracy, and data quality.

[0027] Optionally, after performing the signal decoupling step and before performing the first model building step, the method further includes:

[0028] Data fusion: performing time series matching on the detection data of each bearing in the bearing group and the same data type belonging to the same bearing, and recording the matched data as the first data;

[0029] Feature extraction: The detection data of each bearing belonging to the same sensor group is taken as a group of sensor group data. Feature extraction is performed on the sensor group data of each bearing to obtain several sensor data features of each bearing.

[0030] Feature fusion: The sensor data features of each bearing are fused to obtain the fused features of each bearing, which are recorded as the first feature;

[0031] Data splicing: Splice the first data with the first feature, and use the spliced ​​data as the new detection data for each bearing.

[0032] By adopting the above technical solution, time series matching is used to align the detection data of the same data type for each bearing, avoiding analysis errors caused by asynchronous or incomplete data, thereby ensuring the accuracy of subsequent bearing fault analysis. In addition, ensuring that all data is synchronized on the time axis helps to further strengthen the model's capture of bearing state changes and avoid diagnostic problems caused by time misalignment or omissions. In addition, through feature extraction and feature fusion of detection data, complex raw data is converted into efficient features that are easy to analyze, which helps to extract more comprehensive and accurate fault information from multi-sensor data, enhance the multi-dimensional capabilities of bearing fault detection, improve the learning effect of the fault diagnosis model, and enhance the accuracy of bearing fault diagnosis.

[0033] Optionally, after executing the step of building the first model and before executing the step of fault prediction, the method further includes:

[0034] Constructing a first sample training set: obtaining historical test data and corresponding fault type labels for each bearing in a bearing group of the equipment, and constructing a first sample training set based on the obtained historical test data and corresponding fault type labels; the fault type labels include fault type and fault severity;

[0035] First model training: The first sample training set is input into the fault prediction model. The shared layer of the fault prediction model extracts the features of the historical detection data and the fault type labels corresponding to the historical detection data, which are recorded as shared features. Task-specific branches are created according to the fault type labels. The task-specific branches include fault type classification tasks and fault severity classification tasks. The fault prediction loss function is defined, and the shared features are input into the task-specific branch. The task is processed, and the fault prediction model is iteratively optimized by minimizing the fault prediction loss function. The optimized fault prediction model is used as the new fault prediction model.

[0036] By adopting the above technical solution, not only the fault type is classified, but also the severity of the fault is considered. The dual-task structure is designed so that the bearing fault prediction model can not only identify the specific type of equipment fault, but also evaluate its severity, thereby improving the accuracy of bearing fault identification.

[0037] Optionally, after performing the step of fault prediction and before performing the step of building the second model, the method further includes:

[0038] Define node features: take each bearing as a node, the inspection data of each bearing as the initial feature of the node, and the fault type label of each bearing as the target feature of the node;

[0039] Define edge features: Each bearing is connected by an edge, and define the propagation probability and propagation strength as edge features for each edge;

[0040] Constructing an adjacency matrix: Based on the structure and working principle of the equipment, the connection relationship between each bearing in the bearing group is obtained, and the adjacency matrix is ​​constructed based on the connection relationship between each bearing.

[0041] By adopting the above technical solution, each bearing is treated as a node, its detection data is used as the initial node features, and the fault type label is used as the target feature. This enables each node to carry rich state information, better capturing the operating status of the bearing and possible fault types, thereby improving sensitivity to changes in the state of each node (bearing). In addition, by defining the propagation probability and propagation strength for each pair of bearings, the propagation process of faults between bearings can be simulated. By defining node features, edge features, and constructing an adjacency matrix, the state of each bearing within the equipment and the fault propagation process between them can be effectively modeled. This accurately captures the structural characteristics of the equipment and the interactions between bearings, improving the accuracy of fault prediction.

[0042] Optionally, after executing the step of building the second model and before executing the step of fault propagation, the method further includes:

[0043] Constructing a second sample training set: Obtaining historical inspection data, corresponding fault type labels, and corresponding historical fault propagation records of each bearing in the bearing group of the equipment to construct a second sample training set;

[0044] Define loss function: Define fault propagation loss function;

[0045] Constructing a second sample training set: Obtaining historical inspection data, corresponding fault type labels, and corresponding historical fault propagation records of each bearing in the bearing group of the equipment to construct a second sample training set;

[0046] Second model training: The second sample training set is input into the fault propagation model to perform model inference. The output of the fault propagation model is calculated through forward propagation. The difference between the predicted results and the actual results is compared, the model loss is calculated, and the fault propagation model parameters are updated using backward calculation. The fault propagation model is iteratively optimized by minimizing the fault propagation loss function, and the optimized fault propagation model is used as the new fault propagation model.

[0047] By adopting the above technical solution, an accurate fault propagation model is established, which can identify and simulate the propagation process of faults from one bearing to other mutually coupled bearings. It can not only predict the failure of a single bearing, but also analyze the mutual influence and fault path between different components, helping the system design more robust fault-tolerant strategies.

[0048] Optionally, after executing the step of fault propagation and before executing the step of device fault prediction, the method further includes:

[0049] First fault identification: Based on the obtained fault evolution results, the predicted failure time of each bearing in the bearing group is obtained. From the current moment, each bearing is sorted in ascending order of predicted failure time, and the number of bearing failures is accumulated in order. When the accumulated number of bearing failures exceeds the preset number threshold, the predicted failure time of the last accumulated bearing is recorded as the first time, the predicted failure time of the main bearing is obtained and recorded as the second time, and it is determined whether the first time is greater than the second time:

[0050] If so, the second time is used as the equipment failure time, and the equipment failure prediction step is performed;

[0051] If not, the first time is taken as the equipment failure time, and the equipment failure prediction step is performed.

[0052] By employing this technical solution, the predicted failure time of the main bearing is prioritized as a reference, preventing inaccurate predictions of equipment failure times due to non-main bearing failures. Furthermore, by ranking the predicted failure times of all bearings and accumulating the number of failures, this method effectively identifies the bearing failure that will have the most severe impact on the equipment. This is particularly true when multiple bearings are failing, allowing for a more accurate reflection of the overall equipment failure trend.

[0053] In a second aspect, the present invention provides an equipment fault monitoring system based on bearing monitoring, which adopts the following technical solution:

[0054] An equipment fault monitoring system based on bearing monitoring, comprising:

[0055] The data acquisition module is used to collect the test data of the bearing group of the equipment; the test data includes vibration signal, temperature, lubricating oil metal powder, speed and load;

[0056] A signal decoupling module is used to perform signal decoupling on the collected detection data using blind source separation technology to obtain detection data of each bearing in the bearing group;

[0057] A first model building module is used to build a fault prediction model based on a deep learning algorithm;

[0058] A fault prediction module is used to predict the fault type label of each bearing based on the detection data of each bearing;

[0059] a second model building module for building a fault propagation model of the bearing group;

[0060] The fault propagation module is used to filter out faulty bearings based on the fault type label of each bearing and determine whether the number of faulty bearings exceeds a preset threshold:

[0061] If the number of faulty bearings exceeds the preset threshold, the device is judged to be faulty and the current time is output as the device fault time;

[0062] If the number of faulty bearings does not exceed the preset threshold, the detection data of the selected bearings is input into the fault propagation model, the fault evolution results are output, and the equipment fault prediction module is triggered;

[0063] The equipment failure prediction module is used to predict the remaining life of the equipment based on the failure evolution results.

[0064] By adopting this technical solution, the signal decoupling module uses blind source separation technology to decouple the collected detection data, ensuring independent and accurate fault detection data for each bearing, thereby improving the accuracy of bearing fault detection in multi-bearing systems. Furthermore, a second model building module establishes a fault propagation model for the bearing group, enabling real-time monitoring of the health status of multiple bearings, predicting the propagation of faults between different bearings, and identifying potential equipment failures in advance, thus achieving precise fault monitoring and prediction for multi-bearing equipment.

[0065] In summary, this application includes at least one of the following beneficial technical effects:

[0066] 1. Using blind source separation technology to decouple the collected test data, the system ensures independent and accurate fault detection data for each bearing, improving the accuracy of bearing fault detection in multi-bearing systems. Furthermore, by establishing a fault propagation model for bearing groups, the system can monitor the health of multiple bearings in real time, predict the propagation of faults between different bearings, and identify potential equipment failures in advance, achieving precise fault monitoring and prediction for multi-bearing systems.

[0067] 2. Optimize the number, location, and layout of sensors to ensure maximum fault detection coverage of the equipment's bearing groups. At the same time, consider the operating characteristics and failure modes of the bearings. While reducing costs, this not only effectively monitors the status of each bearing, but also effectively reduces signal distortion caused by sensor interference, thereby improving the quality of detection data, reducing noise and redundant information, and helping to improve the accuracy of fault diagnosis and equipment reliability.

[0068] 3. Utilize time series matching to align the detection data of the same data type for each bearing, avoiding analysis errors caused by asynchronous or incomplete data, thereby ensuring the accuracy of subsequent bearing fault analysis. In addition, ensuring that all data is synchronized on the time axis helps further strengthen the model's capture of bearing state changes and avoid diagnostic problems caused by time misalignment or omissions. In addition, through feature extraction and feature fusion of detection data, complex raw data is converted into efficient features that are easy to analyze, which helps to extract more comprehensive and accurate fault information from multi-sensor data, enhance the multi-dimensional capabilities of bearing fault detection, improve the learning effect of the fault diagnosis model, and enhance the accuracy of bearing fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 is a flow chart of Example 1 of the present application;

[0070] Figure 2 is a flow chart of the S1 sensor layout of Example 1 of the present application;

[0071] Figure 3 This is a flowchart of the first data processing in S41 of Example 1 of the present application;

[0072] Figure 4 This is a flowchart of the first model construction in S5 of Example 1 of the present application;

[0073] Figure 5 This is a flowchart of the construction of the second model of S7 in Example 1 of the present application. DETAILED DESCRIPTION

[0074] The following combination Figures 1 to 5 This application is described in further detail.

[0075] Example 1: This example discloses a device fault monitoring method based on bearing monitoring, such as Figure 1 As shown, the monitoring method includes: collecting detection data of the bearing group of the equipment, using blind source separation technology to perform signal decoupling on the collected detection data to obtain detection data of each bearing in the bearing group, building a fault prediction model, predicting the fault type label of each bearing based on the detection data of each bearing, building a fault propagation model of the bearing group, screening out faulty bearings based on the fault type label of each bearing, and determining whether the number of faulty bearings exceeds a preset number threshold: if so, determining that the equipment is faulty and outputting the current time as the equipment fault time; if not, inputting the detection data of the screened bearings into the fault propagation model, outputting the fault evolution result, and predicting the remaining life of the equipment based on the fault evolution result. This embodiment includes the following steps:

[0076] S1 sensor layout: including S11 sensor type selection, S12 optimization goal definition, S13 constraint definition and S14 sensor position optimization, such as Figure 2 shown.

[0077] S11 sensor type selection: According to the type of bearing detection data to be collected, set the vibration sensor, temperature sensor, magnetic sensor, speed sensor and piezoelectric sensor. A group of vibration sensors, temperature sensors, magnetic sensors, speed sensors and piezoelectric sensors is regarded as a sensor group.

[0078] Among them, the vibration sensor is used to collect bearing vibration signals, the temperature sensor is used to collect bearing temperature, the magnetic sensor is used to collect bearing lubricating oil metal powder data, the speed sensor is used to collect bearing speed, and the piezoelectric sensor is used to collect bearing load.

[0079] S12 defines the optimization goal: to minimize the number of sensors and maximize the fault detection coverage, and construct the objective function.

[0080] S13 defines the constraints: the operating characteristics, failure modes, and interference between sensors of each bearing in the bearing group of the equipment are used as the constraints of the objective function.

[0081] Operating characteristic constraints: At least one sensor group should be installed at the main bearing of a bearing group; at least one sensor group should be installed at a high-load bearing; at least one sensor group should be installed at a bearing that is closely coupled with other bearings; and at least one sensor group should be installed at a bearing in a vulnerable area. The sensor installation locations should be determined based on the operating conditions of each sensor in the sensor group. For example, vibration sensors should be placed at key locations such as the bearing contact surface, outer ring, inner ring, and rolling elements, and temperature sensors should be placed at the outer ring or nearby heat sources.

[0082] Fault mode constraints: The sensors in the sensor group must be able to cover the data variation range of different bearing failure modes.

[0083] Interference constraint between sensors: The sum of interferences between the selected sensors must be less than a preset interference threshold.

[0084] S14 Sensor Position Optimization: Based on the objective function and constraints, a genetic algorithm is used to optimize the number of sensor groups and their corresponding installation locations. This includes S141 initializing the population, S142 defining the fitness function, S143 selecting operations, S144 crossover operations, S145 mutation operations, S146 updating the population, and S147 outputting the optimal solution.

[0085] S141 Initialize population: Generate the initial population. Each individual can be represented by a binary string or integer sequence, where each gene bit represents the installation position or selection of a sensor.

[0086] S142 defines the fitness function: The fitness function is defined as:

[0087] .

[0088] in, Indicates the The number of sensors for each solution, Indicates the The failure mode coverage of each solution, Indicates the The sensor interference of each solution is express The weight of express The weight of express The weight of .

[0089] S143 selection operation: calculate the fitness of each individual according to the fitness function, allocate the selection probability according to the proportion of the fitness of all individuals, perform roulette wheel selection based on the selection probability, and select the parent individual.

[0090] S144 crossover operation: Randomly select two parent individuals from the selected parent individuals, randomly select a crossover point, exchange the genes of parent 1 and parent 2 at the crossover point, generate two offspring, and place the newly generated offspring individuals into the next generation population.

[0091] S145 mutation operation: randomly select an individual, and according to the set mutation probability, randomly select a gene in the individual to mutate (for example, change the position of a sensor, or switch the type of sensor), re-evaluate the fitness of the mutated individual, and put it into the next generation population.

[0092] S146 Update population: After selection, crossover, and mutation, a new generation population is generated. The fitness value of each individual in the new generation population is calculated, the individuals of the parent and child generations are merged, the individual with the best fitness is retained, and the individuals in the updated population are used as the new generation population.

[0093] S147 outputs the optimal solution: iterative updates are performed continuously until the maximum number of iterations is reached or the fitness function converges, the algorithm terminates, and the optimal solution is output, that is, the number of sensor groups and the corresponding installation positions are obtained.

[0094] S2 Data Collection: Collects test data of the equipment's bearing group; the test data includes vibration signals, temperature, lubricating oil metal powder, speed and load.

[0095] According to the S1 sensor layout, the number of sensor groups and the corresponding installation positions are obtained to install sensors. The vibration signals, temperature, lubricating oil metal powder, speed and load of the bearing group of the equipment are collected based on the installed sensors.

[0096] In this embodiment, when collecting test data from a bearing group of a device, the bearing group's vibration signal, temperature, lubricating oil metal powder, rotational speed, and load collected at the same time are considered a set of bearing group data. Because multiple sensor groups are provided to collect test data from the bearing group, the test data collected at the same time includes data from multiple sensor groups.

[0097] In this embodiment, after the detection data of the bearing group is collected, the collected detection data needs to be preprocessed. The data preprocessing steps include data cleaning, data normalization and feature extraction.

[0098] Data cleaning: De-noising, processing missing values, and removing outliers are performed on the collected test data.

[0099] Denoising involves applying smoothing filters (such as sliding averages) to temperature, speed, and load data to eliminate small fluctuations. Wavelet transforms are used to decompose vibration signals, remove noise components, and then reconstruct the data. Smoothing filters are used to remove measurement fluctuations in lubricating oil and metal dust data. Missing value handling involves directly deleting data containing missing values. Outlier removal involves detecting outliers in the data using the 3-sigma rule or boxplots and deleting any detected outliers.

[0100] Data normalization: Normalize the collected test data.

[0101] S3 Time Domain Analysis: The time domain analysis method is used to extract the time domain features of the bearing group test data. The time domain features of each test data are extracted as follows:

[0102] Time domain characteristics of vibration signals: mean, RMS value, maximum value, peak-to-peak value, variance, skewness, and kurtosis.

[0103] Time domain characteristics of temperature signals: mean, maximum, standard deviation, and rate of change.

[0104] Time domain characteristics of lubricating oil metal dust: mean, maximum and variance.

[0105] Time domain characteristics of the speed signal: mean, standard deviation and maximum value.

[0106] Time domain characteristics of the load signal: mean, maximum value and standard deviation.

[0107] The extracted time domain features of each detection data and the detection data of the bearing group are used as new detection data of the bearing group.

[0108] S4 signal decoupling: Use blind source separation technology to perform signal decoupling on the collected detection data to obtain the detection data of each bearing in the bearing group.

[0109] In the collected test data, each sensor has a corresponding signal value at a certain moment. A data matrix consisting of M sensors and L time points is constructed, referred to as the mixed signal matrix. The mixed signal matrix is ​​demeaned to remove the DC component of the signal. The signal is then whitened to ensure unit variance and uncorrelated signals in all directions. Independent component analysis is then used to extract independent components, yielding the test data for each bearing.

[0110] In this embodiment, after executing S4 signal decoupling and before executing S5 first model building, it includes S41 first data processing: including S411 data fusion, S412 feature extraction, S413 feature fusion and S414 data splicing, such as Figure 3 shown.

[0111] S411 data fusion: perform time sequence matching on the detection data of each bearing in the bearing group that belong to the same data type of the same bearing, and record the matched data as the first data.

[0112] S412 Feature extraction: The detection data of each bearing that belongs to the same sensor group is taken as a group of sensor group data, and feature extraction is performed on the sensor group data of each bearing to obtain a number of sensor data features of each bearing.

[0113] S413 Feature Fusion: Perform feature fusion on the sensor data features of each bearing to obtain a fused feature for each bearing, recorded as the first feature. For example, the bearing detection data includes the detection data of sensor group 1 of bearing 1, the detection data of sensor group 1 of bearing 2, the detection data of sensor group 1 of bearing 3, and the detection data of sensor group 2 of bearing 1. The detection data of sensor group 1 of bearing 1 and the detection data of sensor group 2 of bearing 1 are used as the sensor group data of bearing 1. Feature extraction is performed on all the detection data of sensor group 1 of bearing 1 and all the detection data of sensor group 2 of bearing 1 to obtain the data features of sensor group 1 and the data features of sensor group 2 of bearing 1. The data features of sensor group 1 and sensor group 2 are then feature-fused to obtain the first feature of bearing 1.

[0114] S414 Data splicing: Splicing the first data with the first feature, and using the spliced ​​data as new detection data for each bearing.

[0115] S5 First Model Construction: Build a fault prediction model based on deep learning algorithm. This includes S51 model construction, S52 first sample training set construction, and S53 first model training. Figure 4 shown.

[0116] S51 Model Construction: The Transformer model is selected as the base model of the fault prediction model. Therefore, some Transformer encoder layers are used as shared layers of the fault prediction model, and the remaining Transformer encoder layers and the fully connected layers that perform specific tasks in the Transformer model are used as task-specific layers of the fault prediction model.

[0117] S52 constructs a first sample training set: historical detection data and corresponding fault type labels of each bearing in the bearing group of the equipment are obtained, and the first sample training set is constructed based on the obtained historical detection data and corresponding fault type labels. The fault type labels include fault type and fault severity.

[0118] S53 First model training: The first sample training set is input into the fault prediction model. The shared layer of the fault prediction model extracts the features of the historical detection data and the fault type labels corresponding to the historical detection data, which are recorded as shared features. Task-specific branches are created according to the fault type labels. The task-specific branches include fault type classification tasks and fault severity classification tasks. The fault prediction loss function is defined, the shared features are input into the task-specific branch, the task is processed, and the fault prediction model is iteratively optimized by minimizing the fault prediction loss function. The optimized fault prediction model is used as the new fault prediction model.

[0119] The fault prediction loss function is: in, represents the fault prediction loss function, is the cross entropy loss for the fault type classification task, is the cross entropy loss for the fault severity classification task, and are weight coefficients, .

[0120] S6 Fault Prediction: Predict the fault type label of each bearing based on the detection data of each bearing.

[0121] S7 Second Model Construction: Construct the fault propagation model of the bearing group. This includes S71 defining node features, S72 defining edge features, S73 constructing the adjacency matrix, S74 constructing the fault propagation model, S75 constructing the second sample training set, S76 defining the loss function, and S77 second model training, such as Figure 5 shown.

[0122] S71 defines node features: each bearing is regarded as a node, the detection data of each bearing is regarded as the node initial feature, the fault type label of each bearing is regarded as the node target feature, and the node feature matrix is ​​obtained based on the node initial features and node target features of all nodes.

[0123] S72 defines edge features: each bearing is connected by an edge, and the propagation probability and propagation strength are defined for each edge as edge features.

[0124] Considering the coupling relationship between bearings, bearing workload and the influence of bearing fault types, a propagation probability formula is constructed.

[0125] The propagation probability formula is:

[0126] .

[0127] in, Indicates bearings With bearings The probability of transmission between Indicates bearings With bearings The coupling weight between Indicates bearings With bearings The load weight between Indicates bearings With bearings The fault weight.

[0128] Based on historical equipment failure data, the fault propagation between different bearing couplings is statistically analyzed to determine the coupling weight coefficients between bearings. Using historical bearing load and failure data, regression analysis is performed to determine the impact of bearing load on fault propagation and to determine the load weight coefficients between bearings. Experts use historical equipment usage or experimental data to empirically assess the propagation speed and impact of different types of faults and assign bearing fault weights.

[0129] S73 builds the adjacency matrix: According to the structure and working principle of the equipment, the connection relationship between each bearing in the bearing group is obtained, and the adjacency matrix is ​​built based on the connection relationship and propagation probability between each bearing. With node , then in the corresponding position of the adjacency matrix Assign value to 1, otherwise it is 0. Since each bearing is regarded as a node, the bearing It's the node , bearings It's the node .

[0130] S74 fault propagation model construction: Based on the node feature matrix and adjacency matrix, a graph convolutional network is used to define an initial faulty node and build a fault propagation model.

[0131] In the fault propagation model, the graph convolution layer of each layer aggregates the node features with the neighbor node features through the graph convolution operation:

[0132] .

[0133] in, Indicates the The node feature matrix of the graph convolutional layer, ReLU activation function is used in this embodiment. represents the normalized adjacency matrix, Indicates the The node feature matrix of the graph convolutional layer, Indicates the Model weight matrix for graph convolutional layers.

[0134] S75 constructs a second sample training set: obtains historical detection data of each bearing in the bearing group of the equipment, a corresponding fault type label, and a corresponding historical fault propagation record, and constructs a second sample training set.

[0135] S76 defines loss function: defines the fault propagation loss function as the cross entropy loss function.

[0136] The fault propagation loss function is:

[0137] .

[0138] in, represents the fault propagation loss function, represents the number of samples in the second sample training set, Indicates the The actual fault label of each bearing, No. The predicted failure probability of each bearing.

[0139] S77 Second model training: Input the second sample training set into the fault propagation model, perform model inference, calculate the output of the fault propagation model through forward propagation, compare the difference between the predicted results and the actual results, calculate the model loss, use backward calculation to update the fault propagation model parameters, iteratively optimize the fault propagation model by minimizing the fault propagation loss function, and use the optimized fault propagation model as the new fault propagation model.

[0140] S8 fault propagation: Filter out faulty bearings based on the fault type label of each bearing and determine whether the number of faulty bearings exceeds the preset threshold.

[0141] If so, the device is judged to be faulty and the current time is output as the device fault time.

[0142] If not, the detected data of the selected bearings are input into the fault propagation model, the fault evolution result is output, and the first fault determination in S81 is executed.

[0143] S81 First fault judgment: Based on the obtained fault evolution results, obtain the predicted fault time of each bearing in the bearing group. From the current moment, sort the bearings in ascending order of predicted fault time to obtain a first sorting table. Accumulate the number of bearing faults in the order of the first sorting table. When the accumulated number of bearing faults exceeds the preset number threshold, record the predicted fault time of the last accumulated bearing as the first time, obtain the predicted fault time of the main bearing, record it as the second time, and determine whether the first time is greater than the second time.

[0144] If yes, the second time is used as the equipment failure time, and the first equipment life prediction in S94 is executed.

[0145] If not, the first time is used as the equipment failure time, and S95 second equipment life prediction is executed.

[0146] S9 Equipment Failure Prediction: Predicts the remaining life of equipment based on fault evolution results. This includes S91: Building a remaining life prediction model, S92: Building a third sample training set, S93: Training the third model, and S94: Predicting equipment life.

[0147] S91: Constructing a remaining life prediction model: A recurrent neural network is used to construct a remaining life prediction model. In this embodiment, an LSTM (Long Short-Term Memory Network) is used as the basic model to construct the remaining life prediction model.

[0148] S92 constructs a third sample training set: Acquire the fault data of each bearing in the bearing group and the corresponding equipment status data to construct a third sample training set. The equipment status data includes the equipment operating time and the physical status of the equipment.

[0149] S93 Third model training: Input the third sample training set into the remaining life prediction model for model inference, define the remaining life loss function, iteratively optimize the remaining life prediction model by minimizing the remaining life loss function, and use the optimized remaining life prediction model as the new remaining life prediction model.

[0150] The remaining life loss function is:

[0151] .

[0152] in, represents the remaining life loss function, represents the number of samples in the third sample training set, Indicates the The actual lifespan of the samples, No. The predicted life span of the samples.

[0153] S94 First Equipment Life Prediction: According to the first ranking table, the bearing detection data before the main bearing and the main bearing detection data are input into the remaining life prediction model to obtain the remaining life of the equipment.

[0154] S95 Second Equipment Life Prediction: The bearing detection data accumulated in the first fault judgment of S81 is input into the remaining life prediction model to obtain the remaining life of the equipment.

[0155] In this embodiment, blind source separation technology is used to decouple the collected detection data, ensuring independent and accurate fault detection data for each bearing. This improves the accuracy of bearing fault detection in multi-bearing systems. Furthermore, by establishing a fault propagation model for bearing groups, the health status of multiple bearings can be monitored in real time, the propagation of faults between different bearings can be predicted, and potential equipment failures can be identified in advance, achieving precise fault monitoring and prediction for multi-bearing systems.

[0156] Example 1: There are four interrelated bearings in an automobile transmission, including the main bearing A1, the auxiliary bearing A2, the auxiliary bearing A3 and the small bearing A4. Bearing A1 is a rolling bearing located at both ends of the transmission main shaft; the auxiliary bearing A2 is a deep groove ball bearing near the input shaft or output shaft of the transmission; the auxiliary bearing A3 is a needle roller bearing installed on the auxiliary drive shaft of the transmission; and the small bearing A4 is a sliding bearing installed in the gearbox in the transmission.

[0157] The fault detection of the above four bearings is as follows:

[0158] 1. Sensor Layout

[0159] 1. Select a vibration sensor, a temperature sensor, a magnetic sensor, a speed sensor, and a piezoelectric sensor as a sensor group.

[0160] Determine the working characteristics of each bearing: main bearing A1, heavy load, prone to wear and fatigue failure; secondary bearing A2, medium load, prone to overheating; auxiliary bearing A3, light load; small bearing A4, light load, easily affected by the environment.

[0161] Therefore, a sensor group is provided on the main bearing A1, a vibration sensor and a temperature sensor are provided on the secondary bearing A2, a vibration sensor is provided on the auxiliary bearing A3, and a vibration sensor and a temperature sensor are provided on the small bearing A4.

[0162] 2. Use genetic algorithm to optimize and obtain the sensor installation position.

[0163] In the initial stage, multiple candidate sensor placement schemes are generated, and each scheme can be represented by a binary string, for example, whether each sensor is installed at a different location or not.

[0164] Considering the minimum number of sensors, all failure modes of each bearing are adequately covered and the interference between sensors is below the threshold.

[0165] The fitness of each individual is calculated according to the fitness function formula, the selection probability is allocated according to the proportion of the fitness of all individuals, and the roulette wheel selection is performed based on the selection probability to select the parent individual.

[0166] Two parent individuals are randomly selected and crossover is performed to swap their gene positions to generate a new offspring. For example, some sensor positions of parent 1 are swapped with other sensor positions of parent 2 to form a new sensor layout.

[0167] Randomly select individuals from the newly generated offspring and change the value of a gene (that is, change the position or type of a sensor).

[0168] Update the population, retain the individuals with the best fitness, and generate a new generation of population.

[0169] After multiple rounds of iterations, the optimal sensor group layout solution is output, that is, the final number, location and type of sensors.

[0170] The sensor layout is as follows:

[0171] The vibration sensor of bearing A1 is installed on the inner ring, the temperature sensor is installed on the outer ring, the piezoelectric sensor is installed on the outer ring, the speed sensor is installed near the transmission main shaft, and the magnetic sensor is installed on the bearing seat of bearing A1.

[0172] The vibration sensor of bearing A2 is installed on the outer ring, the temperature sensor is installed on the outer ring, and the speed sensor is installed near the transmission output shaft.

[0173] The vibration sensor of bearing A3 is installed on the outer ring.

[0174] The vibration sensor of bearing A4 is installed on the outer ring, and the temperature sensor is installed on the outer ring.

[0175] 3. Collect data based on the set sensors and perform signal decoupling on the collected data.

[0176]

[0177] Build a file containing The data matrix of sensors and L time points is recorded as a mixed signal matrix. , the number of time points 3. Build a signal matrix.

[0178] The signal matrix is ​​whitened and the whitened signal matrix is ​​used as an independent component analysis algorithm to decouple the whitened signal into independent bearing detection data.

[0179] The detection data of bearings A1, A2, A3 and A4 are subjected to the steps of data fusion, feature extraction, feature fusion and data splicing to obtain the detection data of each bearing.

[0180] 4. Build a fault prediction model to predict whether the bearing is faulty based on the collected bearing inspection data.

[0181] The historical detection data of bearings A1, A2, A3, and A4 and the corresponding fault type labels are collected as sample data for training a fault prediction model to obtain a trained fault prediction model.

[0182] The inspection data of bearings A1, A2, A3, and A4 are input into the trained fault prediction model, and the fault type labels of bearings A1, A2, A3, and A4 are output. Among them, bearing A1 has a mild wear fault, bearing A2 has a moderate wear fault, and bearings A3 and A4 have no fault.

[0183] 5. Screen out the faulty bearings and determine whether the car's transmission is faulty;

[0184] Filter out the faulty bearings and determine whether the number of faulty bearings exceeds 3.

[0185] At this time, the faulty bearings are A1 and A2, and the number of bearing faults is less than 2. Therefore, a fault propagation model is constructed. The collected historical detection data of bearings A1, A2, A3, and A4, the corresponding fault type labels, and the corresponding historical fault propagation records are used as sample data to train the fault propagation model. The screened detection data of bearings A1 and A2, as well as the fault labels of bearing A1's mild wear fault and bearing A2's moderate wear fault are input into the fault propagation model, and the fault evolution results are output. Bearing A1 is expected to stop working on February 15, 2025, bearing A2 is expected to stop working on March 1, 2025, bearing A3 is expected to stop working on May 10, 2025, and bearing A4 is expected to stop working on June 20, 2025.

[0186] 6. Sort the prediction results, obtain the corresponding sorting table, and determine the failure time of the automobile transmission.

[0187] Bearings A1, A2, A3, and A4 ceased functioning in the following order: bearing A1, A2, A3, and A4. Main bearing A1 ceased functioning less frequently than the other bearings, so the transmission failure time is calculated as the time main bearing A1 ceased functioning. If main bearing A1 is not promptly repaired, the transmission will fail on February 15, 2025.

[0188] Example 2: This example discloses an equipment fault monitoring system based on bearing monitoring, the monitoring system comprising:

[0189] The sensor layout module includes a sensor type selection unit and a sensor position determination unit.

[0190] The sensor type selection unit is used to determine the required sensor according to the input detection data type that needs to be collected by the bearing.

[0191] The sensor position determination unit is used to output the installation position of each sensor according to the working characteristics and failure modes of the bearing that need to be collected as input and the required sensors.

[0192] The data acquisition module is in communication with the sensor layout module and includes a vibration sensor, a temperature sensor, a magnetic sensor, a speed sensor and a piezoelectric sensor, and is used to collect detection data of the bearing group of the equipment; the detection data includes vibration signals, temperature, lubricating oil metal powder, speed and load.

[0193] The signal decoupling module is used to perform signal decoupling on the collected detection data using blind source separation technology to obtain detection data of each bearing in the bearing group.

[0194] The first model building module is used to build a fault prediction model based on a deep learning algorithm.

[0195] The fault prediction module is used to predict the fault type label of each bearing based on the detection data of each bearing.

[0196] The second model building module is used to build a fault propagation model of the bearing group.

[0197] The fault propagation module is used to filter out faulty bearings based on the fault type label of each bearing and determine whether the number of faulty bearings exceeds a preset threshold.

[0198] If the number of faulty bearings exceeds a preset threshold, the device is judged to be faulty and the current time is output as the device fault time.

[0199] If the number of faulty bearings does not exceed the preset threshold, the detection data of the screened bearings will be input into the fault propagation model, the fault evolution results will be output, and the equipment fault prediction module will be triggered.

[0200] The equipment failure prediction module is used to predict the remaining life of the equipment based on the failure evolution results.

[0201] In this embodiment, the signal decoupling module uses blind source separation technology to decouple the collected detection data, ensuring independent and accurate fault detection data for each bearing, thereby improving the accuracy of bearing fault detection in multi-bearing systems. Furthermore, the second model building module establishes a fault propagation model for the bearing group, enabling real-time monitoring of the health status of multiple bearings, predicting the propagation of faults between different bearings, and proactively identifying potential equipment failures, thus achieving precise fault monitoring and prediction for multi-bearing systems.

[0202] The above are all preferred embodiments of the present application, and are not intended to limit the scope of protection of the present application. Therefore, any equivalent changes made based on the structure, shape, and principle of the present application should be included in the scope of protection of the present application.

Claims

1. A method for monitoring equipment failure based on bearing monitoring, characterized in that: include: Data collection: Collect the test data of the equipment's bearing group; the test data includes vibration signals, temperature, lubricating oil metal powder, speed and load; Signal decoupling: Collect the test data of the bearing group of the equipment and obtain the test data of each bearing in the bearing group; First model construction: build a fault prediction model based on deep learning algorithm; Fault prediction: predict the fault type label of each bearing based on the detection data of each bearing; Second model construction: Construct a fault propagation model for the bearing group, including: Define node features: Take each bearing as a node, the detection data of each bearing as the node initial feature, and the fault type label of each bearing as the node target feature. Obtain the node feature matrix based on the node initial features and node target features of all nodes. Define edge features: Each bearing is connected by an edge, and define the propagation probability and propagation strength as edge features for each edge; Constructing an adjacency matrix: Based on the structure and working principle of the equipment, the connection relationship between each bearing in the bearing group is obtained, and the adjacency matrix is ​​constructed based on the connection relationship between each bearing; Fault propagation model construction: Based on the node feature matrix and adjacency matrix, a graph convolutional network is used to define an initial faulty node and build a fault propagation model. Fault propagation: Based on the fault type label of each bearing, the faulty bearings are screened out and the number of faulty bearings is determined to see whether it exceeds the preset threshold. If so, the device is judged to be faulty and the current time is output as the time of the device failure; If not, the detection data of the selected bearings are input into the fault propagation model, the fault evolution results are output, and the equipment fault prediction step is executed; Equipment failure prediction: Predict the remaining life of the equipment based on the failure evolution results.

2. The equipment fault monitoring method based on bearing monitoring according to claim 1 is characterized in that: Before executing the data acquisition step, it also includes: Sensor type selection: According to the type of bearing detection data that needs to be collected, set the sensor that collects the corresponding data type, and regard a group of sensors corresponding to the detection data type as a sensor group; Define the optimization goal: minimize the number of sensor groups and maximize the fault detection coverage, and construct the objective function; Define constraints: Use the operating characteristics, failure modes, and interference between sensors of each bearing in the equipment's bearing group as constraints for the objective function. Sensor location optimization: Based on the objective function and constraints, an optimization algorithm is used to obtain the number of sensor groups and the corresponding installation locations.

3. The equipment fault monitoring method based on bearing monitoring according to claim 1 is characterized in that: After the step of performing data acquisition and before the step of performing signal decoupling, the method further includes: Time domain analysis: The time domain analysis method is used to extract the time domain features from the inspection data of the bearing group, and the extracted time domain features and the inspection data of the bearing group are used as new inspection data of the bearing group.

4. The equipment fault monitoring method based on bearing monitoring according to claim 2 is characterized in that: After performing the signal decoupling step and before performing the first model building step, the method further includes: Data fusion: performing time series matching on the detection data of each bearing in the bearing group and the same data type belonging to the same bearing, and recording the matched data as the first data; Feature extraction: The detection data of each bearing belonging to the same sensor group is taken as a group of sensor group data. Feature extraction is performed on the sensor group data of each bearing to obtain several sensor data features of each bearing. Feature fusion: The sensor data features of each bearing are fused to obtain the fused features of each bearing, which are recorded as the first feature; Data splicing: Splice the first data with the first feature, and use the spliced ​​data as the new detection data for each bearing.

5. The equipment fault monitoring method based on bearing monitoring according to claim 1 is characterized in that: After executing the step of building the first model and before executing the step of fault prediction, the method further includes: Constructing a first sample training set: obtaining historical test data and corresponding fault type labels for each bearing in a bearing group of the equipment, and constructing a first sample training set based on the obtained historical test data and corresponding fault type labels; the fault type labels include fault type and fault severity; First model training: The first sample training set is input into the fault prediction model. The shared layer of the fault prediction model extracts the features of the historical detection data and the fault type labels corresponding to the historical detection data, which are recorded as shared features. Task-specific branches are created according to the fault type labels. The task-specific branches include fault type classification tasks and fault severity classification tasks. The fault prediction loss function is defined, and the shared features are input into the task-specific branch. The task is processed, and the fault prediction model is iteratively optimized by minimizing the fault prediction loss function. The optimized fault prediction model is used as the new fault prediction model.

6. The equipment fault monitoring method based on bearing monitoring according to claim 1 is characterized in that: After executing the step of building the second model and before executing the step of fault propagation, the method further includes: Constructing a second sample training set: Obtaining historical inspection data, corresponding fault type labels, and corresponding historical fault propagation records of each bearing in the bearing group of the equipment to construct a second sample training set; Define loss function: Define fault propagation loss function; Second model training: The second sample training set is input into the fault propagation model to perform model inference. The output of the fault propagation model is calculated through forward propagation. The difference between the predicted results and the actual results is compared, the model loss is calculated, and the fault propagation model parameters are updated using backward calculation. The fault propagation model is iteratively optimized by minimizing the fault propagation loss function, and the optimized fault propagation model is used as the new fault propagation model.

7. The equipment fault monitoring method based on bearing monitoring according to claim 1 is characterized in that: After executing the step of fault propagation and before executing the step of equipment fault prediction, the method further includes: First fault identification: Based on the obtained fault evolution results, the predicted failure time of each bearing in the bearing group is obtained. From the current moment, each bearing is sorted in ascending order of predicted failure time, and the number of bearing failures is accumulated in order. When the accumulated number of bearing failures exceeds the preset number threshold, the predicted failure time of the last accumulated bearing is recorded as the first time, the predicted failure time of the main bearing is obtained and recorded as the second time, and it is determined whether the first time is greater than the second time: If so, the second time is used as the equipment failure time, and the equipment failure prediction step is performed; If not, the first time is taken as the equipment failure time, and the equipment failure prediction step is performed.

8. An equipment fault monitoring system based on bearing monitoring, the system being applicable to the method according to any one of claims 1 to 7, characterized in that: include: The data acquisition module is used to collect the test data of the bearing group of the equipment; the test data includes vibration signal, temperature, lubricating oil metal powder, speed and load; A signal decoupling module is used to perform signal decoupling on the collected detection data using blind source separation technology to obtain detection data of each bearing in the bearing group; A first model building module is used to build a fault prediction model based on a deep learning algorithm; A fault prediction module is used to predict the fault type label of each bearing based on the detection data of each bearing; a second model building module for building a fault propagation model of the bearing group; The fault propagation module is used to filter out faulty bearings based on the fault type label of each bearing and determine whether the number of faulty bearings exceeds a preset threshold: If the number of faulty bearings exceeds the preset threshold, the device is judged to be faulty and the current time is output as the device fault time. If the number of faulty bearings does not exceed the preset threshold, the detection data of the selected bearings is input into the fault propagation model, the fault evolution results are output, and the equipment fault prediction module is triggered; The equipment failure prediction module is used to predict the remaining life of the equipment based on the failure evolution results.

Images