Parameter correlation fault diagnosis method and system based on neural network

Abstract

The invention relates to the technical field of fault diagnosis, discloses a parameter correlation fault diagnosis method and system based on a neural network, and aims to solve the problem that a traditional diagnosis method depends on a single threshold value and is difficult to capture hidden composite faults. According to the method, through multi-source sensing data space-time alignment and graph neural network modeling, a dynamic parameter association graph is constructed, a comparison learning training encoder is utilized to extract node embedding, through topology difference, an abnormal propagation path is identified, a fault source is positioned, and in combination with a fault template library, an output type, a position and confidence coefficient are matched. The system comprises a sensing acquisition module, an edge preprocessing module, a graph construction module, a graph coding module, a difference measurement module, a fault positioning module, a mode matching module and a decision output module, and supports multi-fault concurrent diagnosis, self-calibration updating and sensor fault-tolerant compensation. According to the method, early hidden fault accurate identification is realized, the marking dependence is reduced, the diagnosis robustness and the maintenance decision efficiency are improved, and the method adapts to equipment aging and complex working condition evolution.

Description

Technical Field

[0001] This invention relates to the field of fault diagnosis technology, and specifically to a parameter correlation fault diagnosis method and system based on neural networks. Background Technology

[0002] With the continuous improvement of the intelligence and automation of industrial equipment, the importance of fault diagnosis technology in ensuring stable system operation and reducing maintenance costs is becoming increasingly prominent. Traditional fault diagnosis methods mostly rely on expert experience or statistical models, judging the operating status of equipment through preset thresholds and fixed logic. Their core principle is based on the induction of static patterns of historical faults. However, modern complex systems exhibit highly nonlinear, strongly coupled, and dynamically correlated parameters during operation: there are implicit interactions between the parameters of various sensors inside the equipment, and external operating condition disturbances and load fluctuations can trigger real-time evolution of the parameter correlation structure. Static models, unable to capture the dynamic coupling mechanism between parameters, often lead to false alarms, missed alarms, or diagnostic lags, exacerbating the accumulation of hidden damage to equipment, control strategy mismatch, and other risks, significantly weakening system reliability. In addition, users have increasingly stringent requirements for diagnostic accuracy, response speed, and cross-scenario generalization capabilities (such as sudden fault early warning and multi-condition adaptive diagnosis). The rigid criterion system of traditional methods is difficult to meet the needs of high-dimensional parameter correlation modeling and real-time inference in complex industrial scenarios. Summary of the Invention

[0003] This invention provides a parameter correlation fault diagnosis method and system based on neural networks. It constructs a spatiotemporal alignment framework for multi-source heterogeneous sensor data to achieve high-density synchronous acquisition and structured characterization of key physical parameters during equipment operation. Based on this, a graph neural network modeling mechanism for nonlinear dynamic coupling relationships between parameters is established. Using historical data under normal operating conditions as training samples, the system learns the correlation strength distribution and propagation path of each parameter node under steady-state operating conditions. When real-time operating data is input, the system calculates the topological difference between the current parameter correlation graph and the baseline correlation graph to identify abnormal propagation paths and deviating nodes, thereby locating potential fault sources. Simultaneously, a fault mode matching engine is introduced to compare the identified abnormal correlation patterns with a pre-built fault feature library, outputting the fault type, location, and confidence score, ultimately forming a closed-loop diagnostic decision output.

[0004] As one embodiment of the present invention, the method includes: a multimodal sensor array deployed at key measuring points of industrial equipment, used to synchronously collect five types of physical parameters during equipment operation: vibration, temperature, pressure, current, and rotational speed. The sampling frequency is uniformly set to 1000 Hz, and the timestamp accuracy is not less than 1 microsecond. The collected raw data undergoes preprocessing operations via edge computing nodes. The preprocessing operations include zero-point drift correction, outlier removal, sliding window mean filtering, and normalization mapping to form standardized time-series data blocks. Each data block contains 500 consecutive sampling points, constituting a basic input unit for a diagnostic cycle. The standardized time-series data blocks are then fed into a parameter correlation graph construction module. Each physical parameter is used as a graph node, and the mutual information value between any two nodes within a sliding time window is used as the edge weight to construct a dynamically weighted undirected graph. The graph structure is updated in real time as the time window slides, with an update step size of 50 sampling points. The dynamically weighted undirected graph is input to a graph neural network encoder, which adopts a three-layer graph convolutional layer stacked structure. Each layer includes adjacency matrix normalization, linear transformation of node features, and nonlinear activation function operation, finally outputting the hidden layer embedding vector of each node, with a dimension of 128. The hidden layer embedding vector is sent to the association difference measurement module, which calculates the cosine distance matrix between the current graph structure and the reference graph structure in the node embedding space. For nodes in the matrix that exceed a preset threshold, the module performs a cosine distance measurement. Edges corresponding to elements with a value of 0.3 are marked to form an abnormal associated edge set. This abnormal associated edge set is input to the fault source localization module. This module calculates the fault contribution of each node based on the positional relationship of the nodes connected by the abnormal edges in the physical topology of the equipment, combined with the direction and magnitude of edge weight changes, using a weighted centrality algorithm. The node with the highest contribution is identified as a candidate fault source. The candidate fault source and its associated abnormal patterns are sent to the fault pattern matching engine. This engine has a pre-stored feature template library covering five typical faults: bearing wear, gear tooth breakage, shaft misalignment, lubrication failure, and motor inter-turn short circuit. Each template consists of a typical topological structure and edge weights of the parameter association graph under the corresponding fault state. The distribution range and node embedding vector cluster centers constitute the system. The matching process uses the structure-preserving embedding distance metric to calculate the similarity score between the current abnormal pattern and each template. The fault type corresponding to the highest score is the diagnosis result, and the confidence level of the result is also output. The confidence level is defined as the ratio of the embedding space distance between the current pattern and the best matching template to the distance of the second best template. When the ratio is less than 0.5, it is judged as a high-confidence diagnosis. The diagnosis result is output through the human-computer interaction interface, including the fault type name, the location coordinates, the confidence level value, and the suggested handling measures. At the same time, the equipment maintenance work order generation module is triggered to automatically create a maintenance task record including the diagnosis time, equipment number, fault description, and priority identifier.

[0005] In one embodiment of the present invention, the system includes: a multimodal sensing data acquisition unit, which consists of a vibration sensor, an infrared temperature sensor, a piezoresistive pressure sensor, a Hall current sensor, and a photoelectric encoder. Each sensor is connected to an edge computing node via an industrial Ethernet bus. The data acquisition cycle is uniformly triggered by a hardware timer to ensure that the data from each channel is strictly aligned on the time axis; an edge preprocessing unit, which is embedded in the firmware layer of the edge computing node, performs data cleaning and format conversion operations, and outputs standardized data blocks that conform to the neural network input specifications; a parameter correlation graph construction unit, which runs on an embedded graphics processor, uses a sliding window mechanism to dynamically calculate the mutual information between parameters, and constructs a weighted graph structure that is updated in real time; and a graph neural network encoding unit, which is deployed on the edge computing node. The system includes a field-programmable gate array (FPGA) accelerator card that enables parallel processing of graph convolution operations, capable of encoding 20 graph structures per second; an association difference measurement unit, implemented on a general-purpose CPU core, that performs batch calculations of the cosine distance matrix and threshold filtering; a fault source localization unit that uses an improved betweenness centrality algorithm, combined with prior knowledge of the equipment's mechanical structure, to perform spatial weighted aggregation of the abnormal edge set and output the fault source coordinates; a fault mode matching unit that runs on a cloud server, utilizing a distributed vector database to store fault feature templates and supporting millisecond-level similarity retrieval; and a diagnostic decision output unit that is integrated into the human-machine interface of the equipment monitoring terminal, presenting diagnostic results as a visual topology graph overlaid with anomaly markers, and supporting the automatic generation and export of diagnostic reports.

[0006] As one embodiment of the present invention, the training process of the graph neural network encoder includes: collecting historical data of the device running continuously for 30 days in a fault-free state, dividing the training samples according to the diagnostic cycle, each sample containing a complete parameter association graph and its corresponding node embedding label; the node embedding label is generated through a self-supervised contrastive learning strategy, specifically by performing data augmentation on the normal graph structure of the same device under different time windows, the augmentation methods including random edge discarding, node feature perturbation and time axis resampling, to construct positive sample pairs; negative sample pairs are composed of abnormal graph structures collected from different devices or the same device in fault injection experiments; the loss function adopts a contrastive loss function, the objective of which is to maximize the similarity of positive sample pairs in the embedding space while minimizing the similarity of negative sample pairs; the training process adopts the batch gradient descent method, the batch size is set to 32, the initial learning rate is 0.001, and it decays to one-tenth of the original value every ten training rounds, with a total of 500 training rounds; after training, the encoder parameters are solidified and burned into the non-volatile storage area of ​​the field-programmable gate array chip to ensure the real-time performance and stability of the inference process.

[0007] As one embodiment of the present invention, the method for constructing the fault feature template library includes: applying five preset fault modes to the target equipment in a laboratory environment, repeating each fault mode ten times, and continuously collecting complete sensor data for ten minutes before and after each fault occurrence; performing the same preprocessing and graph construction process as normal data on each fault experiment data to extract the parameter association graph sequence under the fault state; calculating the average graph structure of each fault sequence during the entire fault evolution process as the baseline template for that fault type; simultaneously recording the dynamic evolution trajectory of the graph structure within five diagnostic cycles before and after the fault occurrence time to form a fault evolution sub-template set; storing all templates according to fault type and attaching metadata tags, the metadata including fault severity level, typical triggering conditions, and historical maintenance record index; the template library supports an online update mechanism, and when the on-site diagnostic results are manually verified and confirmed, the corresponding abnormal mode is automatically archived and included in the template library for rapid matching of similar faults in the future.

[0008] As one embodiment of the present invention, the process of generating the abnormal associated edge set further includes: after calculating the cosine distance matrix, performing dual threshold screening on the matrix elements, the first threshold being 0.3 for initially marking deviation edges; the second threshold being 0.5 for identifying strong abnormal edges; the nodes connected to the strong abnormal edges are assigned higher fault weights; at the same time, a time continuity constraint is introduced, if an edge is marked as abnormal in three consecutive diagnostic cycles, its fault confidence is increased by 20%; if the abnormal edge set contains more than three edges connecting the same node, then that node is forcibly promoted to a fault source candidate point, regardless of whether its individual contribution is the highest.

[0009] As one embodiment of the present invention, the human-computer interaction interface is further configured with a diagnostic result traceability function. Users can click on any fault node in the diagnostic report, and the system will automatically trace back the correlation strength change curve, embedded vector trajectory, and mutual information evolution heat map of the node in the 20 diagnostic cycles before the fault occurred. At the same time, it supports historical comparison of fault modes. Users can select any historical fault record, and the system will automatically calculate the structural similarity between the current abnormal mode and the selected historical mode, and highlight the difference area to assist maintenance personnel in judging the fault evolution trend.

[0010] As one embodiment of the present invention, the maintenance work order generation module further includes: automatically assigning maintenance priorities according to the fault type and confidence level, with priorities divided into four levels: emergency, high, medium, and low; emergency priority corresponds to a confidence level higher than 0.8 and a fault type of short circuit between motor turns or broken gear teeth, in which the system automatically sends an SMS notification to the maintenance supervisor and locks the equipment control authority; high priority corresponds to a confidence level between 0.6 and 0.8 or a fault type of bearing wear, in which the system pops up an alert window on the monitoring screen and generates a work order for response within two hours; medium priority corresponds to a confidence level between 0.4 and 0.6, in which the system generates an inspection work order within twenty-four hours; low priority corresponds to a confidence level lower than 0.4 but the abnormality persists, in which the system records it as an event to be observed and generates a summary report weekly.

[0011] As one embodiment of the present invention, the system further includes a model self-calibration unit, which periodically collects the operating data of the equipment under known health conditions, recalculates the baseline correlation graph, and performs a structural consistency check with the currently used baseline graph; if the consistency metric is lower than a preset safety threshold of 0.9, the model retraining process is triggered, the graph neural network encoder parameters are updated using the latest health data, and the normal state reference template in the fault feature template library is refreshed simultaneously to ensure that the diagnostic benchmark dynamically adapts with the aging process of the equipment.

[0012] As one embodiment of the present invention, the multimodal sensing data acquisition unit further includes a sensor health self-check module, which performs zero-point verification and range verification on the output of each sensor before the start of each diagnostic cycle; if the output of a sensor deviates from the factory calibration value by more than 5%, the sensor data is marked as unreliable, and its corresponding node is blocked during the graph construction stage, while triggering a sensor replacement warning; the blocked node does not participate in the association calculation in subsequent diagnoses, and its missing data is compensated by the data of adjacent physical location sensors through spatial interpolation. The interpolation method adopts the inverse distance weighting method, and the weighting coefficient is inversely proportional to the sensor spacing.

[0013] As one embodiment of the present invention, the fault mode matching engine further supports concurrent diagnosis of multiple faults. When the set of abnormal associated edges covers multiple unconnected subgraph structures, the system performs independent template matching on each subgraph and outputs multiple fault diagnosis results. Each result is accompanied by an independent confidence score and spatial positioning coordinates. The system simultaneously calculates the spatiotemporal correlation between each fault result. If the time interval between two faults is less than five diagnosis cycles and the spatial distance is less than 10% of the total length of the equipment, they are marked as associated fault events, and a joint handling plan is suggested in the output report.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0015] This invention overcomes the limitations of traditional fault diagnosis methods that rely on single threshold alarms or fixed rule matching by constructing a dynamic neural network representation system based on parameter correlation graphs, achieving early detection and precise location of latent equipment faults. Its graph structure modeling of nonlinear coupling relationships between parameters effectively identifies complex fault modes caused by multi-parameter collaborative anomalies, solving the problem of missed diagnoses due to isolated parameter analysis in existing technologies. By introducing a self-supervised comparative learning mechanism to train the graph encoder, the dependence on labeled fault data is significantly reduced, enabling the system to maintain strong generalization capabilities even in scenarios lacking historical fault samples. The online update mechanism of the fault feature template library ensures continuous accumulation and iterative optimization of diagnostic knowledge, adapting to pattern drift caused by equipment aging and changing operating conditions. The confidence score and automatic maintenance priority allocation functions attached to the diagnostic results significantly improve the scientific nature and response efficiency of maintenance decisions. Sensor health self-checking and data compensation mechanisms ensure the robust operation of the system when some sensor units fail. The multi-fault concurrent diagnosis and correlation analysis functions provide system-level insights for the health management of complex industrial systems, effectively avoiding the problem of ignoring system-level cascading risks due to isolated handling of single faults. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the overall technical architecture of a parameter correlation fault diagnosis method and system based on neural networks proposed in this invention. Figure 2 This is a schematic diagram of the core principle framework of the graph neural network modeling mechanism for nonlinear dynamic coupling relationships between parameters in this invention; Figure 3 This is a flowchart illustrating the main stages of the process from multi-source sensor data acquisition to fault diagnosis decision output in this invention. Detailed Implementation

[0017] This invention provides a parameter correlation fault diagnosis method and system based on neural networks. Its core lies in constructing a spatiotemporal alignment framework for multi-source heterogeneous sensor data to achieve high-density synchronous acquisition and structured characterization of key physical parameters during equipment operation. Based on this, a graph neural network modeling mechanism for nonlinear dynamic coupling relationships between parameters is established. Using historical data under normal operating conditions as training samples, the system learns the correlation strength distribution and propagation path of each parameter node under steady-state operating conditions. When real-time operating data is input, the system calculates the topological difference between the current parameter correlation graph and the baseline correlation graph to identify abnormal propagation paths and deviating nodes, thereby locating potential fault sources. Simultaneously, a fault mode matching engine is introduced to compare the identified abnormal correlation patterns with a pre-built fault feature library, outputting the fault type, location, and confidence score, ultimately forming a closed-loop diagnostic decision output.

[0018] As one embodiment of the present invention, the method includes: a multimodal sensor array deployed at key measuring points of industrial equipment, used to synchronously collect five types of physical parameters during equipment operation: vibration, temperature, pressure, current, and rotational speed. The sampling frequency is uniformly set to 1000 Hz, and the timestamp accuracy is not less than 1 microsecond. The collected raw data undergoes preprocessing operations via edge computing nodes. The preprocessing operations include zero-point drift correction, outlier removal, sliding window mean filtering, and normalization mapping to form standardized time-series data blocks. Each data block contains 500 consecutive sampling points, constituting a basic input unit for a diagnostic cycle. The standardized time-series data blocks are then fed into a parameter correlation graph construction module. Each physical parameter is used as a graph node, and the mutual information value between any two nodes within a sliding time window is used as the edge weight to construct a dynamically weighted undirected graph. The graph structure is updated in real time as the time window slides, with an update step size of 50 sampling points. The dynamically weighted undirected graph is input to a graph neural network encoder, which adopts a three-layer graph convolutional layer stacked structure. Each layer includes adjacency matrix normalization, linear transformation of node features, and nonlinear activation function operation, finally outputting the hidden layer embedding vector of each node, with a dimension of 128. The hidden layer embedding vector is sent to the association difference measurement module, which calculates the cosine distance matrix between the current graph structure and the reference graph structure in the node embedding space. For nodes in the matrix that exceed a preset threshold, the module performs a cosine distance measurement. Edges corresponding to elements with a value of 0.3 are marked to form an abnormal associated edge set. This abnormal associated edge set is input to the fault source localization module. This module calculates the fault contribution of each node based on the positional relationship of the nodes connected by the abnormal edges in the physical topology of the equipment, combined with the direction and magnitude of edge weight changes, using a weighted centrality algorithm. The node with the highest contribution is identified as a candidate fault source. The candidate fault source and its associated abnormal patterns are sent to the fault pattern matching engine. This engine has a pre-stored feature template library covering five typical faults: bearing wear, gear tooth breakage, shaft misalignment, lubrication failure, and motor inter-turn short circuit. Each template consists of a typical topological structure and edge weights of the parameter association graph under the corresponding fault state. The distribution range and node embedding vector cluster centers constitute the system. The matching process uses the structure-preserving embedding distance metric to calculate the similarity score between the current abnormal pattern and each template. The fault type corresponding to the highest score is the diagnosis result, and the confidence level of the result is also output. The confidence level is defined as the ratio of the embedding space distance between the current pattern and the best matching template to the distance of the second best template. When the ratio is less than 0.5, it is judged as a high-confidence diagnosis. The diagnosis result is output through the human-computer interaction interface, including the fault type name, the location coordinates, the confidence level value, and the suggested handling measures. At the same time, the equipment maintenance work order generation module is triggered to automatically create a maintenance task record including the diagnosis time, equipment number, fault description, and priority identifier.

[0019] In the above method, a multimodal sensor array deployed at key measurement points of industrial equipment is used to synchronously collect five types of physical parameters during equipment operation: vibration, temperature, pressure, current, and rotational speed. The sampling frequency is uniformly set to 1000 Hz, and the timestamp accuracy is no less than 1 microsecond. This sensor array consists of vibration sensors, infrared temperature sensors, piezoresistive pressure sensors, Hall current sensors, and photoelectric encoders. Each sensor is connected to an edge computing node via an industrial Ethernet bus. The data acquisition cycle is uniformly triggered by a hardware timer to ensure that the data from each channel is strictly aligned on the time axis. Vibration sensors are mounted on the surface of bearing housings or gearbox housings to capture high-frequency vibration signals of the equipment's mechanical structure. Their sensitivity is no less than 10 millivolts per meter per second squared, and their frequency response range covers 0 to 5000 Hz. Infrared temperature sensors are non-contactly mounted on motor housings or bearing end caps to measure surface temperature changes. The temperature measurement range is -40 degrees Celsius to +200 degrees Celsius, with a resolution of 0.1 degrees Celsius. Piezoresistive pressure sensors are integrated into hydraulic or pneumatic pipelines to monitor system pressure fluctuations in real time. The range is set according to the equipment's rated working pressure, with a typical value of 0 to 10 MPa and an accuracy class of 0.5. Hall effect current sensors are connected in series in the motor's main power supply circuit to measure the effective value and instantaneous waveform of the three-phase current. The bandwidth is no less than 20 kHz, and the linearity error is less than 1%. Photoelectric encoders are coaxially mounted on the rotating shaft end. The output pulse signal is converted into a speed value by a counter, with a resolution of no less than 1000 pulses per revolution and a response time of less than 1 millisecond. Before the start of each diagnostic cycle, all sensors undergo zero-point calibration and range verification. If the output of a sensor deviates from the factory calibration value by more than 5%, the sensor data is marked as unreliable, and its corresponding node is blocked during the graph construction phase, while triggering a sensor replacement warning. Blocked nodes do not participate in correlation calculations in subsequent diagnostics, and their missing data is compensated by spatial interpolation from data of adjacent physical location sensors. The interpolation method adopts the inverse distance weighting method, and the weighting coefficient is inversely proportional to the sensor spacing.

[0020] In the above method, the acquired raw data undergoes preprocessing operations via edge computing nodes. These preprocessing operations include zero-point drift correction, outlier removal, sliding window mean filtering, and normalization mapping, forming standardized time-series data blocks. Each data block contains 500 consecutive sampling points, constituting the basic input unit for one diagnostic cycle. Zero-point drift correction is achieved by calculating the static output mean of each channel under no-load conditions and subtracting this mean from subsequent sampled data. Outlier removal uses the three-sigma criterion, discarding data points exceeding the mean plus or minus three standard deviations and replacing them with linear interpolation of adjacent points. The sliding window mean filtering window length is set to 20 sampling points to smooth high-frequency noise. Normalization mapping uses the minimum-maximum scaling method to linearly map each channel's data to the 0-1 interval. The mapping formula is: Here, xmin and xmax represent the global minimum and maximum values ​​of each channel in the device's historical operating data. These values ​​are derived from 30 days of fault-free operating data and stored during system initialization. The preprocessed data is arranged chronologically, with every 500 consecutive sampling points encapsulated into a data block. Overlapping data blocks is allowed, with an overlap length of 450 sampling points to ensure data continuity during sliding window updates. Each data block is sent as an independent input unit to the subsequent processing module. Its internal structure is a 5*500 two-dimensional matrix, with rows corresponding to five types of physical parameters and columns corresponding to time-series sampling points.

[0021] In the above method, the standardized time-series data block is fed into a parameter correlation graph construction module. This module uses each physical parameter as a graph node and the mutual information value between any two nodes within a sliding time window as the edge weight to construct a dynamically weighted undirected graph. The graph structure is updated in real time as the time window slides, with an update step size of 50 sampling points. The mutual information is calculated using the kernel density estimation method. For any two parameter sequences X and Y, their mutual information I(X;Y) is defined as:

[0022] Where p(x,y) is the joint probability density, and p(x) and p(y) are the marginal probability densities. The probability density function is estimated using a Gaussian kernel function, and the bandwidth parameter is automatically determined by the Silverman rule. The calculated mutual information values ​​are exponentially normalized and compressed to the interval between 0 and 1, serving as the weights of the corresponding edges in the graph. The initial graph structure is constructed when the first data block is input, containing five nodes and ten undirected edges. Subsequently, for each new data block received, the sliding window advances 50 sampling points, recalculates the mutual information matrix of the data within the window, and updates the graph edge weights. The number of graph nodes is fixed at five, and the node identifiers are bound one-to-one with the physical parameter types, remaining unchanged over time. The graph structure is stored in the form of an adjacency matrix, where the matrix element Aij represents the edge weight between node i and node j, and the diagonal elements are always zero.

[0023] In the above method, the dynamically weighted undirected graph is input to a graph neural network encoder, which employs a three-layer stacked graph convolutional layer structure. Each layer includes adjacency matrix normalization, linear transformation of node features, and nonlinear activation function operations, ultimately outputting the hidden layer embedding vector of each node, with a dimension of 128. The graph convolutional layer operations follow the following formula: , in For the first Layer node feature matrix, For learnable weight matrix, To add a self-loop adjacency matrix, for The degree matrix, To correct the activation function of the linear unit, the first layer input features are statistical feature vectors of the original parameter sequences of the nodes, with a dimension of ten, including mean, variance, skewness, kurtosis, maximum value, minimum value, zero-crossing rate, energy, spectral centroid, and spectral entropy; the second layer output has a dimension of 64; and the third layer output has a dimension of 128. Batch normalization is performed after each layer operation to accelerate convergence. The encoder parameters are optimized during the training phase using a self-supervised contrastive learning strategy. The training samples are derived from 30 consecutive days of historical data under fault-free conditions. Each sample contains a complete parameter correlation graph and its corresponding node embedding label. Positive sample pairs are constructed through data augmentation, including a random edge drop probability of 0.1, a node feature perturbation standard deviation of 0.05, and a time axis resampling scaling factor of 0.9 to 1.1. Negative sample pairs are composed of experimental data injected from different devices or faults. The contrastive loss function is used, aiming to maximize the similarity of positive sample pairs and minimize the similarity of negative sample pairs. Training employs batch gradient descent with a batch size of 32, an initial learning rate of 0.001, and a decay to one-tenth of the original value every ten rounds, for a total of 500 training rounds. After training, the parameters are permanently burned into the non-volatile memory area of ​​the field-programmable gate array chip.

[0024] In the above method, the hidden layer embedding vector is fed into the association difference measurement module. This module calculates the cosine distance matrix between the current graph structure and the reference graph structure in the node embedding space. Edges corresponding to elements in the matrix that exceed a preset threshold of 0.3 are marked, forming a set of abnormal association edges. The cosine distance calculation formula is:

[0025] Where u and v are the embedding vectors of the same node in the current graph and the baseline graph, respectively. The baseline graph structure consists of the set of embedding vectors of each node obtained during the device's most recent health status calibration, and is stored in non-volatile memory. The calculated distance matrix is ​​a 5x5 symmetric matrix, with diagonal elements ignored; a dual threshold screening is performed on off-diagonal elements, with a first threshold of 0.3 used for initial marking of deviation edges and a second threshold of 0.5 used for identifying strong abnormal edges; nodes connected by strong abnormal edges are assigned higher fault weights; at the same time, a time continuity constraint is introduced: if an edge is marked as abnormal in three consecutive diagnostic cycles, its fault confidence is increased by 20%; if the set of abnormal edges contains more than three edges connecting the same node, then that node is forcibly promoted to a candidate fault source point, regardless of whether its individual contribution is the highest.

[0026] In the above method, the set of abnormal associated edges is input to the fault source localization module. This module calculates the fault contribution of each node using a weighted centrality algorithm, based on the positional relationship of the nodes connected by the abnormal edges in the device's physical topology, combined with the direction and magnitude of edge weight changes. The node with the highest contribution is identified as a candidate fault source. The weighted centrality algorithm defines the fault contribution Ci of node i as: , Where N(i) is the set of neighboring nodes connected to node i, Wij is the current edge weight, ΔWij is the absolute difference between the current weight and the baseline weight, and dij is the Euclidean distance between nodes i and j in the physical space of the device, which is pre-determined by the sensor installation location coordinates. The contribution calculation result is normalized to the interval between 0 and 1, and the one with the largest value is selected as the candidate point for the fault source. If there are multiple candidate points with a contribution difference of less than 0.1, all candidate points are retained and enter the subsequent matching stage.

[0027] In the above method, the candidate fault sources and their associated anomaly patterns are fed into a fault mode matching engine. This engine pre-stores a feature template library covering five typical faults: bearing wear, gear tooth breakage, shaft misalignment, lubrication failure, and inter-turn short circuit in motors. Each template consists of a typical topological structure of the parameter association graph under the corresponding fault state, the distribution range of edge weights, and the cluster center of the node embedding vector. The matching process uses a structure-preserving embedding distance metric to calculate the similarity score between the current anomaly pattern and each template. The fault type corresponding to the highest score is the diagnosis result, and the confidence level of this result is output. The confidence level is defined as the ratio of the embedding space distance between the current pattern and the best matching template to the distance of the second-best template. A ratio less than 0.5 is considered a high-confidence diagnosis. The structure-preserving embedding distance metric aligns the current graph structure with the template graph structure in the embedding space and then calculates the Frobenius norm distance. The alignment process uses Protodyakonov analysis to eliminate translation, rotation, and scaling differences. The template library construction method includes: applying five preset fault modes to the target equipment in a laboratory environment, with each fault mode repeated ten times, and continuously collecting complete sensor data for ten minutes before and after each fault occurrence; performing the same preprocessing and graph construction process as normal data on each fault experiment data to extract parameter association graph sequences under fault conditions; calculating the average graph structure of each fault sequence throughout the entire fault evolution process as the baseline template for that fault type; simultaneously recording the dynamic evolution trajectory of the graph structure within five diagnostic cycles before and after the fault occurrence time to form a fault evolution sub-template set; storing all templates according to fault type and attaching metadata tags, with the metadata including fault severity level, typical triggering conditions, and historical maintenance record index; the template library supports an online update mechanism, and when the on-site diagnostic results are manually reviewed and confirmed, the corresponding abnormal mode is automatically archived and included in the template library.

[0028] In the above method, the diagnostic results are output via a human-machine interface, including the fault type name, location coordinates, confidence level, and suggested remedial measures. Simultaneously, it triggers the equipment maintenance work order generation module, automatically creating a maintenance task record containing the diagnostic time, equipment number, fault description, and priority identifier. The human-machine interface is further configured with a diagnostic result traceability function. Users can click on any fault node in the diagnostic report, and the system automatically traces back the correlation strength change curve, embedded vector trajectory, and mutual information evolution heatmap of that node in the 20 diagnostic cycles prior to the fault occurrence. It also supports historical comparison of fault modes; users can select any historical fault record, and the system automatically calculates the structural similarity between the current abnormal mode and the selected historical mode, highlighting the areas of difference. The maintenance work order generation module automatically assigns maintenance priorities based on fault type and confidence level. Priorities are divided into four levels: emergency, high, medium, and low. Emergency priority corresponds to situations with a confidence level higher than 0.8 and fault types such as inter-turn short circuit in motors or broken gear teeth. The system automatically sends an SMS notification to the maintenance supervisor and locks equipment control permissions. High priority corresponds to situations with a confidence level between 0.6 and 0.8 or fault types such as bearing wear. The system displays an alert window on the monitoring screen and generates a work order for response within two hours. Medium priority corresponds to situations with a confidence level between 0.4 and 0.6. The system generates an inspection work order within 24 hours. Low priority corresponds to situations with a confidence level lower than 0.4 but where the abnormality persists. The system records these as events to be observed and generates a summary report weekly.

[0029] In the above method, the system further includes a model self-calibration unit, which periodically collects operational data of the equipment under known health conditions, recalculates the baseline correlation graph, and performs a structural consistency check with the currently used baseline graph. If the consistency metric is lower than a preset safety threshold of 0.9, the model retraining process is triggered. The graph neural network encoder parameters are updated using the latest health data, and the normal state reference templates in the fault feature template library are simultaneously refreshed to ensure that the diagnostic baseline dynamically adapts as the equipment ages. The consistency metric uses the Kendall rank correlation coefficient to calculate the consistency between the current baseline graph and the newly calculated baseline graph in terms of edge weight ranking; a coefficient lower than 0.9 is considered a significant drift. The retraining process reuses the original training framework but only uses the latest health data, reducing the number of training rounds to one hundred to accelerate convergence.

[0030] In the above method, the fault mode matching engine further supports concurrent diagnosis of multiple faults. When the set of abnormal associated edges covers multiple unconnected subgraph structures, the system performs independent template matching on each subgraph and outputs multiple fault diagnosis results. Each result is accompanied by an independent confidence score and spatial location coordinates. The system simultaneously calculates the spatiotemporal correlation between each fault result. If two faults are less than five diagnostic cycles apart in time and less than 10% of the total length of the equipment in space, they are marked as associated fault events, and a joint handling plan is suggested in the output report. The spatiotemporal correlation calculation is based on the time difference of the fault occurrence and the spatial Euclidean distance between the fault source coordinates. The joint handling plan is generated by matching a preset rule base, which contains the handling priority and resource allocation strategy for typical fault combinations.

[0031] This invention overcomes the limitations of traditional fault diagnosis methods that rely on single threshold alarms or fixed rule matching by constructing a dynamic neural network representation system based on parameter correlation graphs, achieving early detection and precise location of latent equipment faults. Its graph structure modeling of nonlinear coupling relationships between parameters effectively identifies complex fault modes caused by multi-parameter collaborative anomalies, solving the problem of missed diagnoses due to isolated parameter analysis in existing technologies. By introducing a self-supervised comparative learning mechanism to train the graph encoder, the dependence on labeled fault data is significantly reduced, enabling the system to maintain strong generalization capabilities even in scenarios lacking historical fault samples. The online update mechanism of the fault feature template library ensures continuous accumulation and iterative optimization of diagnostic knowledge, adapting to pattern drift caused by equipment aging and changing operating conditions. The confidence score and automatic maintenance priority allocation functions attached to the diagnostic results significantly improve the scientific nature and response efficiency of maintenance decisions. Sensor health self-checking and data compensation mechanisms ensure the robust operation of the system when some sensor units fail. The multi-fault concurrent diagnosis and correlation analysis functions provide system-level insights for the health management of complex industrial systems, effectively avoiding the problem of ignoring system-level cascading risks due to isolated handling of single faults.

[0032] The above content is only a preferred embodiment of the present invention. For those skilled in the art, many changes can be made in the specific implementation and application scope based on the ideas of the present invention. As long as these changes do not depart from the concept of the present invention, they all fall within the protection scope of this patent.

Claims

1. A neural network-based parameter correlation fault diagnosis method, characterized by, The application relates to a method for diagnosing faults of industrial equipment, comprising the following steps: Synchronously collecting five types of physical parameters, including vibration, temperature, pressure, current and rotating speed, through a multi-modal sensor array deployed at key measuring points of the industrial equipment, the sampling frequency is uniformly set to 1000 Hz, and the timestamp accuracy is not less than 1 microsecond; Performing zero drift correction, wild value elimination, sliding window mean filtering and normalization mapping on the collected original data to form standardized time series data blocks, each data block containing 500 continuous sampling points; Taking each physical parameter as a graph node and taking the mutual information value between any two nodes within a sliding time window as an edge weight, a dynamic weighted undirected graph is constructed, the graph structure is updated in real time with a time window sliding, and the update step is 50 sampling points; Inputting the dynamic weighted undirected graph into a graph neural network encoder, the graph neural network encoder adopts a three-layer graph convolution layer stacking structure, each layer contains an adjacent matrix normalization operation, a node feature linear transformation and a nonlinear activation function operation, and outputs a 128-dimensional hidden layer embedding vector of each node; Calculating the cosine distance between the embedding vectors of the nodes of the current time graph structure and the embedding vectors of the corresponding nodes of the reference graph structure in the node embedding space to form a cosine distance matrix, marking the edges corresponding to the elements in the matrix that exceed a preset threshold value 0.3 to form an abnormal association edge set; According to the positional relationship of the nodes connected by the abnormal edges in the physical topology of the equipment, combining the change direction and amplitude of the edge weight, the fault contribution degree of each node is calculated by using a weighted centrality algorithm, and the node with the highest contribution degree is determined as a fault source candidate point; Inputting the fault source candidate point and the associated abnormal mode into a fault mode matching engine, the fault mode matching engine has a pre-stored feature template library covering five types of typical faults, including bearing wear, gear tooth breakage, shaft misalignment, lubrication failure and motor inter-turn short circuit, each template is composed of a typical topological structure of a parameter association graph in a corresponding fault state, a range of edge weight distribution and a node embedding vector clustering center; The similarity scores between the current abnormal mode and each template are calculated by using a structure-preserving embedding distance measurement method, and the fault type corresponding to the highest score is the diagnosis result, and the confidence of the result is output, the confidence is defined as the ratio of the embedding space distance between the current mode and the optimal matching template to the suboptimal template distance; The diagnosis result is output through a man-machine interaction interface, including the fault type name, the occurrence position coordinates, the confidence value and the recommended treatment measures, and a device maintenance work order generation module is triggered to automatically create a maintenance task record containing the diagnosis time, the device number, the fault description and the priority identification. 2.The neural network-based parameter association fault diagnosis method according to claim 1, characterized in that, The application also relates to a method for processing time series data, comprising the following steps: Calculating the static output mean of each channel in the no-load state, and subtracting the mean from the subsequent sampling data to complete zero drift correction; Eliminating the data points exceeding the mean plus or minus three times the standard deviation by using a three-sigma criterion and replacing them with linear interpolation of adjacent points; Performing sliding window mean filtering with a window length of 20 sampling points to smooth high-frequency noise; The minimum-maximum scaling method is used to linearly map each channel data to the interval of 0 to 1, and the mapping formula is: xmin and xmax are the global minimum and maximum values of each channel in the historical operation data of the device.

3. The neural network-based parameter correlation fault diagnosis method according to claim 2, characterized in that, A dynamic weighted undirected graph is constructed, including: The mutual information I(X;Y) between any two parameter sequences X and Y is calculated using the kernel density estimation method, and the formula is: ， The probability density function is estimated by the Gaussian kernel function, and the bandwidth parameter is automatically determined by the Silverman rule; The calculated mutual information value is exponentially normalized to the interval of 0 to 1 as the weight of the corresponding edge in the graph; The initial graph structure contains 5 nodes and 10 undirected edges, and then the sliding window is pushed forward by 50 sampling points for each new data block received, the mutual information matrix of the data in the window is recalculated, and the edge weight of the graph is updated.

4. The neural network-based parameter correlation fault diagnosis method according to claim 3, characterized in that, The dynamic weighted undirected graph is input into the graph neural network encoder, including: The input feature of the first layer is a 10-dimensional statistical feature vector of the original parameter sequence of the node, including mean, variance, skewness, kurtosis, maximum value, minimum value, zero-crossing rate, energy, spectral centroid and spectral entropy; The output dimension of the second layer is 64, and the output dimension of the third layer is 128; Batch normalization is performed after each layer operation; The graph convolution layer operation follows the formula: ， wherein is the first layer node feature matrix, is the learnable weight matrix, is the adjacency matrix with added self-loops, is the degree matrix of is the rectified linear unit activation function.

5. The neural network-based parameter correlation fault diagnosis method according to claim 4, characterized in that, The cosine distance matrix between the current graph structure and the reference graph structure in the node embedding space is calculated, including: The cosine distance calculation formula is: where u and v are the embedding vectors of the same node in the current graph and the reference graph, respectively; Double threshold screening is performed on the non-diagonal elements, the first threshold 0.3 is used to preliminarily mark the deviation edges, and the second threshold 0.5 is used to identify strong abnormal edges; If a certain edge is marked as abnormal in three consecutive diagnosis cycles, the fault confidence is increased by 20%; If the abnormal edge set contains more than three edges connected to the same node, the node is forced to be promoted as a fault source candidate point.

6. The neural network-based parameter association fault diagnosis method according to claim 5, characterized in that, The fault contribution degree of each node is calculated using the weighted centrality algorithm, including: The fault contribution degree Ci of node i is defined as: ， Where N(i) is the set of neighbor nodes connected to node i, Wij is the current edge weight, ΔWij is the absolute difference between the current weight and the reference weight, and dij is the Euclidean distance between nodes i and j in the physical space of the device. The contribution degree calculation result is normalized to the interval of 0 to 1, and the maximum value is taken as the fault source candidate point. If there are multiple candidate points with a contribution degree difference less than 0.1, all candidate points are retained for the subsequent matching stage.

7. The neural network-based parameter association fault diagnosis method according to claim 6, characterized in that, The similarity score between the current abnormal pattern and each template is calculated using the structure-preserving embedding distance measurement method, including: The Frobenius norm distance is calculated after aligning the current graph structure and the template graph structure in the embedding space, and the alignment process eliminates the differences in translation, rotation and scaling through Procrustes analysis. The template library construction method includes: five types of preset fault patterns are applied to the target device in the laboratory environment, each type of fault is repeated 10 times, and each time lasts for 10 minutes of complete sensing data before and after the fault occurs. The same preprocessing and graph construction process as the normal data is performed on the fault experiment data of each time to extract the parameter correlation graph sequence in the fault state. The average graph structure of each fault sequence in the entire fault evolution process is calculated as the reference template of this fault type. The dynamic evolution trajectory of the graph structure in each of the five diagnosis cycles before and after the fault occurs is recorded to form a fault evolution sub-template set. All templates are stored by fault type and attached with metadata labels containing fault severity level, typical trigger conditions and historical maintenance record index; The template library supports online update mechanism, when the on-site diagnosis result is confirmed by manual review, the corresponding abnormal pattern is automatically archived and included in the template library.

8. The neural network-based parameter association fault diagnosis method according to claim 7, characterized in that, The trigger device maintenance work order generation module includes: According to the fault type and confidence, the maintenance priority is automatically assigned, which is divided into four grades: emergency, high, medium and low; The emergency priority corresponds to the situation that the confidence is higher than 0.8 and the fault type is motor inter-turn short circuit or gear tooth breakage, the system automatically sends a short message to inform the maintenance supervisor and locks the device control authority; The high priority corresponds to the situation that the confidence is between 0.6 and 0.8 or the fault type is bearing wear, the system pops up a warning window on the monitoring screen and generates a work order that needs to be responded within two hours; The medium priority corresponds to the situation that the confidence is between 0.4 and 0.6, the system generates a patrol work order within 24 hours; The low priority corresponds to the situation that the confidence is lower than 0.4 but the anomaly persists, the system records it as an observation event and generates a weekly summary report.

9. A neural network-based parameter correlation fault diagnosis system characterized by, It includes: A multi-modal sensor data acquisition unit is used to synchronously acquire five types of physical parameters, including vibration, temperature, pressure, current and speed, during the operation of the industrial equipment through a multi-modal sensor array deployed at key measurement points of the equipment, the sampling frequency is uniformly set to 1000 Hz, and the timestamp accuracy is not less than 1 microsecond; An edge preprocessing unit is used to perform zero drift correction, outlier rejection, sliding window mean filtering and normalization mapping on the raw data obtained by acquisition, forming standardized time series data blocks, each data block containing 500 consecutive sampling points; A parameter correlation graph construction unit is used to construct a dynamic weighted undirected graph, taking each physical parameter as a graph node and the mutual information value between any two nodes within a sliding time window as the edge weight, the graph structure is updated in real time with a time window sliding, and the update step is 50 sampling points; A graph neural network encoding unit is used to input the dynamic weighted undirected graph into a graph neural network encoder, the graph neural network encoder adopts a three-layer graph convolution layer stacking structure, each layer contains adjacency matrix normalization operation, node feature linear transformation and nonlinear activation function operation, and outputs a 128-dimensional hidden layer embedding vector for each node; An association difference measurement unit is used to calculate the cosine distance matrix of the current time graph structure and the reference graph structure in the node embedding space, and mark the edges corresponding to the elements in the matrix that exceed the preset threshold value 0.3 to form an abnormal association edge set; A fault source positioning unit is used to calculate the fault contribution degree of each node by using a weighted centrality algorithm according to the positional relationship of the nodes connected by the abnormal edges in the device physical topology, combined with the change direction and amplitude of the edge weight, and the node with the highest contribution degree is determined as the fault source candidate point; A fault mode matching unit is configured to input the fault source candidate point and its associated abnormal mode into a fault mode matching engine, which has a pre-stored characteristic template library covering five typical faults of bearing wear, gear tooth breakage, shaft misalignment, lubrication failure, and motor inter-turn short circuit. Each template is composed of a typical topology structure of a parameter correlation graph under a corresponding fault state, an edge weight distribution range, and a node embedding vector clustering center; A diagnostic decision output unit is configured to calculate similarity scores between the current abnormal mode and each template using a structure-preserving embedding distance measurement method. The fault type corresponding to the highest score is the diagnostic result, and the confidence of the result is also output. The confidence is defined as the ratio of the embedding space distance between the current mode and the optimal matching template to the distance between the current mode and the suboptimal template. The diagnostic result is output via a human-machine interaction interface, including the fault type name, occurrence location coordinates, confidence value, and recommended treatment measures. Meanwhile, a device maintenance work order generation module is triggered to automatically create a maintenance task record including the diagnostic time, device number, fault description, and priority identification.

10. The neural network-based parameter association fault diagnosis system according to claim 9, characterized in that, The edge preprocessing unit is configured to: Calculate the static output mean of each channel in the no-load state and subtract the mean from the subsequent sampling data to complete zero-point drift correction; Remove data points exceeding the mean plus or minus three times the standard deviation using a three-sigma criterion and replace them with linear interpolation of adjacent points; Perform sliding window mean filtering with a window length of 20 sampling points to smooth high-frequency noise; The minimum-maximum scaling method is used to linearly map each channel data to the interval of 0 to 1, and the mapping formula is: where xmin and xmax are the global minimum and maximum values of each channel in the historical operation data of the device.

Images