A device fault warning method, medium and device based on a neural network

By constructing a dynamic coupled topology link and neural network model, the problem of chain failure in IoT device failure warning method is solved, accurate prediction of fault paths and systematic risk warning are achieved, and the reliability and timeliness of early warning are improved.

CN120046087BActive Publication Date: 2025-07-22FUZHOU INSTITUE OF TECH
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202510533940.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-04-27
Publication Date
2025-07-22
Estimated Expiration
2045-04-27

AI Technical Summary

Technical Problem

Existing IoT device fault warning methods are mostly limited to the status monitoring of a single device, lack the ability to model the system-level coupled fault conduction path, and cannot predict the warning lag caused by chain failures, especially when abnormal conduction is performed through mechanically coupled links, the risk evolution of associated devices cannot be early warning.

Method used

By collecting equipment status information regularly, a dynamic coupled topology link is constructed, the first error weight and the second error weight are generated, combined with the risk level evaluation and switching detection mode, input the neural network model to predict the fault link information, and realize dual-level early warning.

Benefits of technology

It realizes accurate prediction of equipment failure paths and systematic risk warnings, improves the reliability and timeliness of early warnings, and can effectively identify the root cause of the fault and predict the failure spread sequence.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120046087B_ABST
    Figure CN120046087B_ABST
Patent Text Reader

Abstract

The present invention provides a device fault warning method, medium and device based on a neural network. After periodically collecting device status information to identify abnormal devices, the method obtains their operating parameters, structural parameters and the layout schematic diagram of the system where they are located, constructs a dynamic coupling topological link and extracts associated parameters; combines physical kinematic equations to verify and generate a first error weight, and at the same time matches historical fault data to generate a second error weight, and comprehensively generates fault status information; switches the detection mode based on risk level assessment, inputs the system dynamic coupling topological link, associated parameters, abnormal device information, and fault status information into a neural network model to output fault link information, and finally generates a first warning information and a second warning information according to the dynamic detection mode to achieve dual-level warning. This method models the fault conduction relationship between devices through a graph neural network to realize fault path prediction and systematic risk warning.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and particularly to a device fault warning method, medium and device based on a neural network. Background Art

[0002] Currently, most of the device fault warning methods for Internet of Things devices are limited to the status monitoring of a single device, lacking the ability to model the system-level coupled fault conduction path. Traditional solutions usually adopt threshold alarm or machine learning models based on isolated historical data. Although they can identify local anomalies, they cannot capture the spread of faults, and it is difficult to distinguish between accidental anomalies and potential systematic faults. The prediction of cascading faults lags behind. Especially when anomalies are conducted through mechanical coupling links, the risk evolution of associated devices cannot be predicted in advance. Summary of the Invention

[0003] In view of the above problems, the present invention provides a device fault warning method, medium and device based on a neural network, which solves the problem of late warning caused by the inability to predict cascading faults.

[0004] To achieve the above object, in the first aspect, the present application provides a device fault warning method based on a neural network, including:

[0005] Regularly obtain device status information, and determine whether the device status information is abnormal. If so, record it as an abnormal device and trigger an abnormal evaluation step, including:

[0006] Obtain abnormal device information, where the abnormal device information includes operating parameters and structural parameters;

[0007] Obtain the layout schematic diagram of the system where the abnormal device is located, construct a system dynamic coupling topology link according to the layout schematic diagram, and generate associated parameters in combination with the abnormal device information. The associated parameters are the position information of the abnormal device in the system and the device information of the other devices connected by the abnormal device;

[0008] Verify the device status information according to the physical kinematic equation based on the abnormal device information and the associated parameters, and generate a first error weight;

[0009] Match the historical working condition fault information of the abnormal device in the historical database according to the abnormal device information, calculate the fitness between the device status information and the historical working condition fault information, and generate a second error weight;

[0010] Generate the fault status information of the device according to the first error weight and the second error weight;

[0011] Evaluate the risk level of the fault status information, and generate a detection mode according to the evaluation result. The detection mode includes a high-frequency detection mode and a low-frequency detection mode;

[0012] Input the system dynamic coupling topology link, associated parameters, abnormal device information, and fault status information into the neural network model to obtain fault link information, which includes forward traceability prediction information for causing abnormal device faults, backward fault prediction information for abnormal devices, and time limit sections.

[0013] Generate a first warning message based on the fault link information, fault status information, and abnormal device information. When the detection mode is switched to the high-frequency detection mode, trigger the low-frequency detection mode for the remaining devices in the current fault link information to generate a second warning message.

[0014] In some embodiments, constructing the system dynamic coupling topology link according to the layout schematic diagram includes:

[0015] Obtain the mechanical connection relationships in the layout schematic diagram, and construct a directed graph structure with individual devices as nodes and mechanical connections as connecting lines, and perform weight initialization on the directed graph structure, including:

[0016] The node weight of each node is generated from the inherent failure rate of the individual device, and the connecting line weight of each connecting line is calculated from the material strength and design load of the nodes at both ends of the connecting line.

[0017] Monitor the vibration signals between the devices of each connecting line, generate the actual energy attenuation rate based on the vibration signals, and generate a first weight adjustment parameter based on the actual energy attenuation rate.

[0018] Monitor the cooperation parameters of the devices of each connecting line, calculate the motion cooperation coefficient between two devices based on the cooperation parameters, and generate a second weight adjustment parameter based on the motion cooperation coefficient.

[0019] Adjust the connecting line weight according to the first weight adjustment parameter and the second weight adjustment parameter.

[0020] In addition, obtain the used duration and rated duration of each device, and generate a device failure rate adjustment parameter based on the used duration and rated duration.

[0021] Adjust the node weight according to the device failure rate adjustment parameter.

[0022] In some embodiments, construct the system dynamic coupling topology link according to the layout schematic diagram, and generate associated parameters in combination with abnormal device information, including:

[0023] Mark the node of the abnormal device as an abnormal node, and conduct a conduction search along the direction of the connecting line of the abnormal node until the number of connecting lines in the first conduction path formed by the conduction search exceeds the preset tolerance value, and the preset tolerance value is generated from the product of the connecting line weights in the first conduction path and the conduction threshold.

[0024] Record the devices associated with the nodes covered by the first conduction path as affected devices;

[0025] Perform the following steps for each affected device:

[0026] Obtain the connection line weights on the second conduction path from the abnormal node to the affected device;

[0027] Calculate the geometric mean of the connection line weights on the second conduction path as the path conduction efficiency;

[0028] Obtain the node weight of the abnormal node, denoted as the abnormal node weight, and obtain the node weight of the affected device, denoted as the original node weight;

[0029] Generate a weight influence coefficient for the affected device based on the abnormal node weight, path conduction efficiency, and original node weight;

[0030] Update the original node weight according to the weight influence coefficient, denoted as the influence node weight;

[0031] Repeat the above steps until the original node weights of all affected devices are updated;

[0032] Generate the location information of the abnormal device in the system according to the first conduction path and the directed graph structure, and generate the device information of the other devices connected by the abnormal device according to the influence node weight and the affected devices, which is the associated parameter.

[0033] In some embodiments, perform a physical kinematic equation check on the device state information according to the abnormal device information and the associated parameters, and generate a first error weight including:

[0034] Generate actual installation parameters and theoretical installation parameters according to the abnormal device information and the associated parameters;

[0035] Calculate the deviation information between the actual installation parameters and the theoretical installation parameters, denoted as the installation deviation information;

[0036] Perform a physical deviation calculation according to the installation deviation information to obtain a calculation result, which is represented by formula (1), and formula (1) is as follows:

[0037] ;

[0038] In formula (1), is the position deviation, is the angle deviation, is the fit deviation, is the position sensitivity coefficient, related to the sensor type, is the actual installation position vector, is the theoretical installation position vector, is the gradient of the state information space, is the installation angle deviation value, is the high-order error term related to the angle, is the th harmonic amplitude of the vibration signal, is the fundamental wave amplitude;

[0039] According to the calculation result, it is converted into the first error weight, and the first error weight is represented by formula (2), and formula (2) is as follows:

[0040] ;

[0041] In formula (2), is the first error weight, is the original data of the uncorrected device state information, is the compensated state information, is the maximum historical amplitude of the state information under the normal operation state of the device, is the sampling time, is the number of sampling points within the sliding window, is the tightness influence factor, is the tightness index, is the position deviation amount, is the position deviation threshold, is the enhancement coefficient.

[0042] In some embodiments, the device state information includes abnormal vibration signals and abnormal spectrum characteristics generated by abnormal device operation, and the historical working condition fault information includes historical vibration signals, historical spectrum characteristics, and historical operation parameters;

[0043] Match the historical working condition fault information of the abnormal device in the historical database according to the abnormal device information, calculate the fitness of the current device state information and the historical working condition fault information, and generate the second error weight including:

[0044] Calculate the waveform similarity between the abnormal vibration signal and the historical vibration signal, and calculate the energy distribution difference value between the abnormal spectrum characteristic and the historical spectrum characteristic within the abnormal frequency band;

[0045] Correct the waveform similarity and the energy distribution difference value according to the difference information between the operation parameters in the abnormal device information and the historical operation parameters;

[0046] Fuse the corrected waveform similarity and the corrected energy distribution difference value to generate the second error weight.

[0047] In some embodiments, evaluate the risk level of the fault state information, and generate a detection mode according to the evaluation result including:

[0048] Divide the abnormal monitoring sequence in the fault status information into multiple monitoring points according to a unit time, and each monitoring point has a monitoring value;

[0049] Construct a curve graph of the abnormal monitoring sequence, where the vertical coordinate of the curve graph of the abnormal monitoring sequence is the monitoring value, and the horizontal coordinate of the curve graph of the abnormal monitoring sequence is the monitoring time;

[0050] Divide a high-risk monitoring interval, a medium-risk monitoring interval, and a low-risk monitoring interval in the curve graph of the abnormal monitoring sequence, and divide multiple monitoring values to form a high-risk set, a medium-risk set, and a low-risk set;

[0051] Calculate the proportion of the monitoring values of the high-risk set, the medium-risk set, and the low-risk set in the current abnormal monitoring sequence, and generate an evaluation result of the abnormal monitoring sequence;

[0052] If the evaluation result is high risk, monitor the abnormal device according to the high-frequency detection mode;

[0053] If the evaluation result is medium risk, monitor the abnormal device according to the low-frequency detection mode;

[0054] If the evaluation result is low risk, maintain the initial detection mode.

[0055] In some embodiments, the neural network model includes a physical decoupling model. Input the system dynamic coupling topology link, associated parameters, abnormal device information, and fault status information into the neural network model, and the obtained fault link information includes:

[0056] Extract the forward conduction path of the abnormal device in the system dynamic coupling topology link, record the devices in the forward conduction path as fault source devices, generate topological decoupling features, and extract the physical connection features between the fault source devices and the abnormal devices from the associated parameters;

[0057] Input the topological decoupling features and physical connection features into the trained physical decoupling model to obtain the forward traceability prediction information for the fault of the abnormal device, including:

[0058] Extract the fault contribution probabilities of multiple fault source devices according to the topological decoupling features and physical connection features;

[0059] Adjust the fault contribution probability of each fault source device according to the physical constraint features. The physical constraint features include energy conservation constraints and time sequence propagation constraints. Eliminate the fault source devices that do not meet the physical constraint features, and generate the corrected contribution probabilities of the remaining fault source devices;

[0060] Generate the forward traceability prediction information for the fault of the abnormal device according to the corrected contribution probabilities and their corresponding fault source devices.

[0061] In some embodiments, the neural network model includes a physical plus-coupling model. Inputting the system dynamic coupling topological link, associated parameters, abnormal device information, and fault status information into the neural network model, the obtained fault link information further includes:

[0062] Extract the backward conduction path of the abnormal device in the system dynamic coupling topological link, mark the devices in the backward conduction path as risk devices, generate topological coupling features, and extract the physical coupling features between the risk devices and the abnormal devices from the associated parameters;

[0063] Input the topological coupling features and physical coupling features into the trained physical plus-coupling model to generate backward fault prediction information of the abnormal device, including:

[0064] Calculate the inherent conduction risk value of the risk device according to the topological coupling features;

[0065] Calculate the risk correction coefficient related to the working condition according to the physical coupling features;

[0066] Fuse the risk correction coefficient and the inherent conduction risk value to obtain the conduction risk probability of each risk device;

[0067] Verify the multiple conduction risk probabilities by applying the mass conservation constraint, eliminate the risk devices that violate the mass conservation constraint, correct the conduction risk probabilities, obtain the corrected risk probabilities, and generate the time limit section corresponding to the current corrected risk probability;

[0068] Generate the backward fault prediction information and time limit section of the abnormal device according to the corrected risk probabilities and their corresponding risk devices.

[0069] In a second aspect, the present invention further provides a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method described in the first aspect is implemented.

[0070] In a third aspect, the present invention further provides an electronic device, including a memory and a processor. The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method described in the first aspect.

[0071] Different from the prior art, the above technical solution provides a device fault warning method, medium and device based on a neural network. After regularly collecting device status information to identify abnormal devices, the method obtains their operating parameters, structural parameters, and layout schematic diagrams of the systems where they are located, constructs a dynamic coupling topological link, and extracts associated parameters; combines physical kinematic equations to verify and generate a first error weight, and at the same time matches historical fault data to generate a second error weight, and comprehensively generates fault status information; switches the detection mode based on risk level assessment, inputs the system dynamic coupling topological link, associated parameters, abnormal device information, and fault status information into a neural network model, outputs fault link information, and finally generates a first warning information and a second warning information according to the dynamic detection mode to achieve dual-level warning. This method models the fault conduction relationship between devices through a graph neural network to achieve fault path prediction and systematic risk warning.

[0072] The above description of the invention content is only an overview of the technical solution of this application. In order to enable those of ordinary skill in the art to more clearly understand the technical solution of this application, and then to implement it according to the content recorded in the description and the accompanying drawings, and in order to make the above objects, other objects, features, and advantages of this application more easily understood, the following is described in conjunction with the specific embodiments of this application and the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] The drawings are only used to illustrate the principles, implementation methods, applications, features, and effects of the specific embodiments of the present invention and other related contents, and should not be considered as a limitation to this application.

[0074] In the accompanying drawings of the specification:

[0075] Figure 1 It is a method step diagram of steps S101 to S109 of the warning method described in the specific embodiment;

[0076] Figure 2 It is a method step diagram of steps S201 to S206 of the warning method described in the specific embodiment;

[0077] Figure 3 It is a method step diagram of steps S301 to S309 of the warning method described in the specific embodiment;

[0078] Figure 4 It is a method step diagram of steps S401 to S403 of the warning method described in the specific embodiment;

[0079] Figure 5 It is a structural schematic diagram of the electronic device described in the specific embodiment.

[0080] The reference numerals involved in the above respective drawings are described as follows:

[0081] 1. Electronic device;

[0082] 11. Memory;

[0083] 12. Processor. Detailed implementation manners

[0084] To describe in detail the possible application scenarios, technical principles, specific implementable solutions, achievable purposes and effects of this application, etc., the following will be described in detail with reference to the specific examples listed and in conjunction with the accompanying drawings. The embodiments described herein are only used to more clearly illustrate the technical solutions of this application, and therefore are only examples and cannot be used to limit the protection scope of this application.

[0085] Referring to "embodiment" in this article means that the specific features, structures or characteristics described in combination with the embodiment may be included in at least one embodiment of this application. The term "embodiment" that appears in various positions in the specification does not necessarily refer to the same embodiment, nor does it particularly limit its independence or relevance to other embodiments. In principle, in this application, as long as there is no technical contradiction or conflict, the technical features mentioned in each embodiment can be combined in any way to form corresponding implementable technical solutions.

[0086] Unless otherwise defined, the meanings of the technical terms used in this article are the same as those generally understood by those skilled in the technical field to which this application belongs; the use of relevant terms in this article is only for describing specific embodiments and is not intended to limit this application.

[0087] In the description of this application, the phrase "and / or" is an expression used to describe the logical relationship between objects, indicating that there can be three relationships. For example, A and / or B means: there is A, there is B, and there is both A and B at the same time. In addition, the character " / " in this article generally represents an "or" logical relationship between the associated objects before and after.

[0088] In this application, terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual quantity, primary or secondary, or order relationship between these entities or operations.

[0089] Without more limitations, in this application, the open expressions such as "including", "comprising", "having" or other similar expressions used in the statement are intended to cover non-exclusive inclusion. These expressions do not exclude that there may be other elements in the process, method or product including the said elements, so that the process, method or product including a series of elements may not only include those defined elements, but also include other elements not explicitly listed, or also include elements inherent to this process, method or product.

[0090] Similar to the understanding in the "Examination Guidelines", in this application, expressions such as "greater than", "less than", "exceeding", etc. are understood as not including the number itself; expressions such as "above", "below", "within", etc. are understood as including the number itself. In addition, in the description of the embodiments of this application, the meaning of "multiple" is two or more (including two), and similar expressions related to "many", such as "multiple groups", "multiple times", etc., are understood in this way unless otherwise specifically defined.

[0091] In the description of the embodiments of this application, the spatially related expressions used, such as "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "perpendicular", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., the indicated orientation or positional relationship is based on the orientation or positional relationship shown in the specific embodiment or the drawings, and is only for the convenience of describing the specific embodiments of this application or for the reader to understand, rather than indicating or implying that the device or component referred to must have a specific position, a specific orientation, or be constructed or operated in a specific orientation. Therefore, it should not be construed as a limitation to the embodiments of this application.

[0092] Please refer to Figure 1 , in the first aspect, this embodiment provides a method for predicting equipment failures based on a neural network, including:

[0093] S101. Regularly obtain equipment status information, and determine whether the equipment status information is abnormal. If so, record it as an abnormal device and trigger the abnormal evaluation step, including:

[0094] S102. Obtain abnormal device information, where the abnormal device information includes operating parameters and structural parameters;

[0095] S103. Obtain the layout schematic diagram of the system where the abnormal device is located, construct a system dynamic coupling topology link according to the layout schematic diagram, and generate associated parameters in combination with the abnormal device information. The associated parameters are the position information of the abnormal device in the system and the device information of the other devices connected by the abnormal device;

[0096] S104. Verify the equipment status information according to the physical kinematic equation based on the abnormal device information and the associated parameters, and generate the first error weight;

[0097] S105. Match the historical working condition fault information of the abnormal device in the historical database according to the abnormal device information, calculate the fitness between the equipment status information and the historical working condition fault information, and generate the second error weight;

[0098] S106. Generate the fault status information of the equipment according to the first error weight and the second error weight;

[0099] S107. Evaluate the risk level of the fault status information, and generate a detection mode according to the evaluation result. The detection mode includes a high-frequency detection mode and a low-frequency detection mode;

[0100] S108. Input the system dynamic coupling topology link, associated parameters, abnormal device information, and fault status information into the neural network model to obtain fault link information. The fault link information includes forward traceability prediction information that causes the abnormal device fault, backward fault prediction information of the abnormal device, and the time limit section;

[0101] S109. Generate a first warning message according to the fault link information, the fault status information, and the abnormal device information. When the detection mode is switched to the high-frequency detection mode, trigger the low-frequency detection mode of the remaining devices in the current fault link information to generate a second warning message.

[0102] In step S101, the device status information is obtained through multi-source data such as vibration signals, temperature readings, and pressure values collected by sensors in real time. The abnormality judgment of the device status information is realized through compliance verification by a physical rule engine. The physical rule engine is a rule library built based on device physical laws (such as kinetic equations and thermodynamics principles) and is used to verify in real time whether the sensor data conforms to the theoretical model. The compliance verification is performed by envelope comparison of real-time data with theoretical operating parameters (such as the safe range of bearing rotation speed and the temperature threshold of the motor). If the threshold is exceeded for a certain continuous sampling period, it is determined that the device status information is abnormal.

[0103] In step S102, the operating parameters refer to dynamic variables such as the rotation speed, load rate, and power consumption of the device during real-time operation, which characterize the current operating intensity of the device; the structural parameters include inherent attributes such as the geometric dimensions, material characteristics, and assembly clearances of the device and are used to define the physical constraint conditions of the device. The operating parameters and the structural parameters jointly constitute the complete mathematical model input of the device operating state. The structural parameters are digitally extracted from the device technical drawings, while the operating parameters are derived from the real-time monitoring data stream.

[0104] In step S103, the layout schematic diagram contains system-level information such as the transmission chain connection method and the power transmission path. Preferably, the construction of the dynamic coupling topology link is based on the analysis of the vibration transfer characteristics and energy conduction paths between nodes, and the edge weight (i.e., the weight of the connection path between two nodes) is dynamically corrected by measuring the vibration signal transmission delay between adjacent devices. The generation process of the associated parameters is completed through the calculation of the fault sensitivity of adjacent devices in the topology network and is used to quantify the fault conduction influence of abnormal devices in the system.

[0105] In step S104, theoretical fault characteristic parameters (such as characteristic frequencies, vibration modes) are calculated using physical kinematic equations. The specific content will be described in detail later. The first error weight is generated by calculating the deviation degree between the measured characteristics and the theoretical values, representing the abnormal confidence level at the physical verification level. For example, in the case of a gear tooth breakage fault, the phase difference between the actual meshing frequency and the theoretically calculated value will directly affect this weight value.

[0106] In step S105, the matching of historical operating condition fault information is realized by using the dynamic time warping algorithm. The time series characteristics of the device state information are extracted through a sliding time window, and the pattern similarity is calculated with the historical fault database. The second error weight is generated by converting the historical matching degree coefficient, reflecting the degree of coincidence between the current anomaly and the typical fault mode. Preferably, the calculation of the second error weight takes into account the time-varying influence of operating condition parameters (such as ambient temperature, lubrication state) and is corrected by the weighted Euclidean distance.

[0107] In steps S106 and S107, the fault state information can be obtained by fusing the first error weight and the second error weight through a Bayesian probability framework, which is used to quantify the probability estimate of the device being in a fault state. When the first error weight and the second error weight are positively correlated, the system will trigger a confidence acceleration accumulation mechanism. For example, when physical feature deviation and historical pattern matching occur simultaneously, the fault probability grows exponentially. Preferably, different monitoring strategies are activated according to the fault confidence score, and a fuzzy logic decision tree is used to implement the risk level assessment. When the fault confidence score crosses a preset threshold, the monitoring strategy switches from baseline sampling to high-frequency acquisition. The preset threshold is determined by the statistical distribution of historical fault data and is dynamically corrected in combination with the device fault sensitivity level and operating environment parameters.

[0108] In step S108, preferably, the neural network model includes a physical decoupling model and a physical coupling model. The generation of fault link information depends on the spatio-temporal propagation simulation of the physical coupling model. The forward traceability prediction information locates the root cause device of the fault by inversely solving the fault characteristic transfer equation, and the backward fault prediction information can use the Monte Carlo method to simulate the conduction path of the fault along the topological network, which is used to predict the fault spread sequence. The aging section characterizes the time sensitivity of the fault development, and the time window of each conduction stage is calculated through the device remaining life prediction model.

[0109] The step process for implementing equipment fault warning in this embodiment can be understood as follows: Regularly collect multi-source data such as equipment vibration, temperature, and pressure, and identify abnormal equipment through comparing the theoretical parameter envelope and continuous over-threshold judgment. Obtain the operating parameters and structural parameters of the abnormal equipment, construct a dynamic coupling topological link by combining with the system layout schematic diagram, and calculate the fault sensitivity of adjacent equipment to generate correlation parameters. Subsequently, execute the physical kinematic equation verification to generate the first error weight, and generate the second error weight by matching the historical fault mode through the dynamic time warping algorithm. Based on Bayesian probability, fuse the first error weight and the second error weight to obtain the fault state probability, and use the fuzzy logic decision tree to evaluate the risk level. When the confidence level crosses the dynamic threshold, switch the detection mode. Input the topological link, correlation parameters, and fault information into the neural network model, solve the root cause equipment of the fault through the reverse equation, predict the potential fault sequence by Monte Carlo simulation of the conduction path, and generate the aging section in combination with the remaining life model. Finally, output the first warning information, activate the low-frequency monitoring of related equipment in the high-frequency detection mode, and synchronously generate the second warning information including the maintenance window period.

[0110] In this embodiment, by integrating the physical rule engine and the neural network model, multi-dimensional verification of the abnormal state of the equipment and accurate prediction of the fault conduction link are realized, effectively improving the warning reliability. Based on the construction of the dynamic coupling topological link and the calculation of the fault sensitivity of adjacent equipment, the quantitative analysis ability of the system-level fault conduction influence is strengthened. The first error weight generated by the physical kinematic equation verification and the second error weight of the historical pattern matching significantly improve the confidence level of the fault state assessment. Through the detection mode switching strategy triggered by the dynamic threshold and the spatio-temporal propagation simulation of the neural network model, the forward fault root cause location and the backward conduction path prediction are synchronously realized. The generation of the aging section and the activation mechanism of the low-frequency monitoring of related equipment provide accurate maintenance window periods and fault spread blocking strategies for equipment maintenance, reducing the risk of equipment chain failures.

[0111] Please refer to Figure 2 , in some embodiments, constructing the system dynamic coupling topological link according to the layout schematic diagram includes:

[0112] S201. Obtain the mechanical connection relationship in the layout schematic diagram, construct a directed graph structure with a single device as a node and the mechanical connection as a connecting line, and perform weight initialization on the directed graph structure, including:

[0113] S202. The node weight of each node is generated by the inherent failure rate of a single device, and the connecting line weight of each connecting line is obtained by calculating the material strength and design load of the nodes at both ends of the connecting line;

[0114] S203. Monitor the vibration signal between the devices of each connecting line, generate the actual energy attenuation rate according to the vibration signal, and generate the first weight adjustment parameter according to the actual energy attenuation rate;

[0115] S204. Monitor the cooperation parameters of the devices on each connection line, calculate the motion cooperation coefficient between the two devices according to the cooperation parameters, and generate a second weight adjustment parameter according to the motion cooperation coefficient;

[0116] S205. Adjust the connection line weights according to the first weight adjustment parameter and the second weight adjustment parameter;

[0117] Moreover, obtain the used duration and the rated duration of each device, and generate a device failure rate adjustment parameter according to the used duration and the rated duration;

[0118] S206. Adjust the node weights according to the device failure rate adjustment parameter.

[0119] In step S201, the mechanical connection relationship is obtained by analyzing the assembly constraint information such as the transmission shaft system cooperation and the coupling interface position in the layout schematic diagram, and specifically comes from the geometric topology structure of the device CAD drawing or the physical contact relationship definition in the assembly process document. The construction of the directed graph structure follows the power transmission direction. In the weight initialization stage, basic parameters are assigned to the nodes and connection lines to provide an initial calculation benchmark for subsequent dynamic correction.

[0120] In step S202, the inherent failure rate of the node represents the basic failure probability of the device under standard working conditions, and is calculated by combining the design life parameter with the real-time health score (based on the cumulative operation duration and working conditions), reflecting the material fatigue characteristics. The calculation of the connection line weight depends on the ratio of the material strength (such as the yield limit of bearing steel) and the design load (such as the rated torque of the gear) at both ends of the node, and specifically shows the anti-overload capacity coefficient, which is used to quantify the force transmission stability of the mechanical connection under theoretical working conditions. For example, when the ratio of the material strength to the design load at both ends of the connection line reaches 1.2, the initial weight is set to 0.8 to represent a high-reliability force transmission path.

[0121] In step S203, preferably, the vibration signal is collected by acceleration sensors installed on the devices at both ends of the connection line, and the actual energy attenuation rate is generated by calculating the difference in the frequency domain integral of the vibration power spectral density at the input end and the output end, reflecting the loss characteristics of the vibration energy during the transmission process. The first weight adjustment parameter is generated according to the deviation degree between the actual energy attenuation rate and the theoretical transmission efficiency (calculated based on the material damping coefficient). For example, when the measured attenuation rate exceeds the theoretical value by 15%, the adjustment parameter reduces the connection line weight by 0.3 to mark abnormal force transmission.

[0122] In step S204, preferably, the cooperation parameters include real-time operation indexes such as the rotational speed synchronization error and load fluctuation correlation between devices, which are monitored and obtained through a high-precision encoder and a torque sensor. The motion cooperation coefficient is calculated by the mutual information entropy algorithm within a sliding time window to quantify the dynamic matching degree of the operation states between devices. The second weight adjustment parameter is generated according to the amplitude of the deviation of the cooperation coefficient from the ideal value (such as 1.0 in the case of complete synchronization). When the rotational speed deviation between devices continuously exceeds 2%, the coefficient drops to trigger the attenuation of the weight value, thereby weakening the conduction influence of this connection line in the topological link.

[0123] In step S205, the equipment failure rate adjustment parameter is generated by combining the ratio of the used duration to the rated duration (i.e., the life consumption rate) with the working condition severity coefficient (such as the high-temperature working condition acceleration aging coefficient). For example, when the life consumption rate reaches 80%, the node weight is amplified by a factor of 1.5 to increase the failure probability estimation. The adjustment of the node weight synchronously considers the conduction influence brought by the change of the connection line weight. For example, the weight increase of the adjacent nodes of the high-attenuation connection line is limited to avoid the distortion of the failure rate assessment.

[0124] In step S206, the determination of the high-risk conduction link is based on whether the cumulative weight of the path (the superposition value of the weights of each connection line) exceeds the system safety threshold, and at the same time, it is detected whether the path contains nodes with a health degree lower than the critical value (such as the life consumption rate ). The system safety threshold can be calculated and generated through a dynamic correction model based on the weight statistical distribution of the historical fault conduction paths, combined with the equipment fault sensitivity level and operation environment parameters. For example, if the cumulative weight of a certain conduction path reaches 4.2 (threshold 3.5) and contains two nodes with a health degree of 0.85, it is marked as a high-risk link and a warning is triggered. The final value of the node weight is obtained by correcting the inherent failure rate through the life consumption rate and is used for the iterative calculation of the failure probability of the conduction path.

[0125] This embodiment realizes the multi-dimensional verification of the abnormal state of the equipment and the accurate prediction of the fault conduction link by integrating the physical rule engine and the neural network model. Based on the construction of the dynamic coupling topological link and the weight dynamic adjustment mechanism, it integrally combines the mechanical connection relationship, the actual energy attenuation rate, and the equipment cooperation parameters in real time to improve the visualization analysis and quantitative evaluation ability of the fault conduction path. Through the double-parameter iterative correction of the first weight adjustment parameter of the node weight and the second weight adjustment parameter of the connection line weight, it synchronously reflects the change of the equipment inherent failure rate and the abnormality of the mechanical force transmission state, enhancing the spatio-temporal correlation of the system-level failure probability calculation. Combining the conduction path risk determination strategy triggered by the dynamic threshold, it effectively identifies the key links containing nodes with a high life consumption rate and an excessive cumulative weight, providing a decision-making basis for equipment maintenance that combines the positioning of the fault root cause and the prediction of the conduction trend, optimizing the selection of the preventive maintenance timing and suppressing the risk of the spread of cascading failures.

[0126] Please refer to Figure 3 In some embodiments, a system dynamic coupling topology link is constructed according to a layout schematic diagram, and associated parameters are generated in combination with abnormal device information, including:

[0127] S301. Denote the node of the abnormal device as an abnormal node, and starting from the abnormal node, conduct a conduction search along the connection line direction of the abnormal node until the number of connection lines in the first conduction path formed by the conduction search exceeds a preset tolerance value. The preset tolerance value is generated by multiplying the connection line weights in the first conduction path and a conduction threshold;

[0128] S302. Denote the devices associated with the nodes covered by the first conduction path as affected devices;

[0129] For each affected device, perform the following steps:

[0130] S303. Obtain the connection line weights on the second conduction path from the abnormal node to the affected device;

[0131] S304. Calculate the geometric mean of the connection line weights on the second conduction path as the path conduction efficiency;

[0132] S305. Obtain the node weight of the abnormal node, denoted as the abnormal node weight, and obtain the node weight of the affected device, denoted as the original node weight;

[0133] S306. Generate a weight influence coefficient for the affected device according to the abnormal node weight, the path conduction efficiency, and the original node weight;

[0134] S307. Update the original node weight according to the weight influence coefficient, denoted as the influence node weight;

[0135] S308. Repeat the foregoing steps until the original node weights of all affected devices are updated;

[0136] S309. Generate the position information of the abnormal device in the system according to the first conduction path and the directed graph structure, and generate the device information of the remaining devices connected by the abnormal device according to the influence node weight and the affected devices, which are the associated parameters.

[0137] In step S301, when forming the first conduction path by conduction search, the generation logic of the preset tolerance value can be understood as comparing the continuous product of the connection line weights in the first conduction path with a preset conduction threshold. When the product result is lower than the threshold, the search stops. This conduction threshold usually comes from the minimum conduction efficiency benchmark value allowed by the system and is used to prevent low-reliability paths from being included in the analysis scope. The dynamic limit mechanism of the number of connection lines in the first conduction path characterizes the system's active constraint ability on the abnormal propagation range.

[0138] In step S302, the definition of affected devices depends on the topological coverage of the first conduction path. The mapping of device association relationships is achieved by traversing all directly or indirectly connected nodes on the first conduction path.

[0139] In step S303, the weights of the connection lines on the second conduction path are obtained by backtracking the shortest conduction link from the abnormal node to the affected device and extracting the weight sequence of all connection lines on this path.

[0140] In step S304, taking the geometric mean of the weights of the connection lines on the second conduction path as the path conduction efficiency can better reflect the actual attenuation characteristics of vibration energy among series devices. When any connection line weight on the second conduction path approaches zero, the geometric mean will decrease significantly, causing the overall conduction efficiency to decay rapidly, thus automatically reflecting the substantial blocking state of the mechanical force transmission path.

[0141] In step S305, the weight of the abnormal node needs to call the real-time health assessment result of the device, which is generated by correcting the inherent failure rate of the device by the life consumption rate and reflects the severity of the abnormality at the current moment. The original node weight is the baseline failure probability estimate of the affected device before being affected by conduction.

[0142] In step S306, when generating the weight influence coefficient, the dynamic balance relationship between external abnormal input and the device's own anti-interference ability is quantified by multiplying the weight of the abnormal node by the path conduction efficiency and then dividing by the original node weight. The larger the coefficient value, the more severely the abnormal energy conduction is not effectively absorbed by the local node and the more seriously the device is affected by the abnormality.

[0143] In step S307, when updating the original node weight, a linear superposition or non-linear correction strategy of the influence coefficient and the original value can be adopted, which is specifically manifested as converting the abnormal influence on the conduction path into an incremental adjustment of the node failure probability. The acquisition of the weight affecting the node is essentially a mathematical modeling of fault risk conduction, and the quantitative expression of system-level abnormal diffusion is realized through weight iterative update.

[0144] In step S308, the repeated update mechanism ensures that the propagation process of abnormal energy in the topological network is completely mapped by traversing the second conduction paths of all affected devices, forming a globally linked weight correction result.

[0145] In step S309, the location information of the abnormal device in the system is the three-dimensional topological coordinates of the abnormal device, including the hierarchical coordinates and the intensity coordinates. The hierarchical coordinates are determined by the maximum number of hops of the conduction path, representing the longitudinal propagation depth of the abnormality in the system topology; the intensity coordinates are the highest influence coefficient among the affected devices, reflecting the lateral radiation intensity of the abnormality. The correlation parameters provide dual support of topological structure and quantization parameters for the early warning of cascading failures by establishing a dynamic coupling relationship model between the abnormal device and the rest of the system.

[0146] In this embodiment, by constructing a dynamic coupling topological link and a correlation parameter generation mechanism, accurate modeling of the abnormal conduction path of the device and system-level risk quantification assessment are realized. Based on the layout schematic diagram, a weighted directed graph structure of nodes and connection lines is established. The coverage range of the first conduction path of the abnormal node is determined through conduction search, the affected devices are identified and their second conduction paths are traced back; then the geometric mean is used to calculate the path conduction efficiency, and the weight influence coefficient is generated by combining the weight of the abnormal node and the weight of the original node, and the failure probability estimation value of each device is iteratively updated; finally, the propagation depth, radiation intensity and associated device status of the abnormal device are characterized by the location information of the abnormal device in the system and the device information of the other devices connected by the abnormal device.

[0147] This method effectively improves the visualization recognition ability and risk quantification accuracy of the cascading failure conduction path by constraining the abnormal propagation range through the conduction threshold, reflecting the path attenuation characteristics by the geometric mean, and realizing dynamic coupling analysis through weight iteration correction, provides a decision-making basis with both topological structure and dynamic parameters for abnormal root cause location and preventive maintenance strategy formulation, and enhances the active prevention and control ability of complex system failure conduction blocking.

[0148] In some embodiments, the physical kinematic equation is used to verify the device status information according to the abnormal device information and the correlation parameters, and the first error weight is generated, including:

[0149] Generate the actual installation parameters and the theoretical installation parameters according to the abnormal device information and the correlation parameters;

[0150] Calculate the deviation information between the actual installation parameters and the theoretical installation parameters, which is recorded as the installation deviation information;

[0151] Perform physical deviation calculation according to the installation deviation information to obtain the calculation result, which is represented by formula (1). Formula (1) is as follows:

[0152] ;

[0153] In formula (1), is the position deviation, is the angle deviation, is the fit deviation, is the position sensitivity coefficient, which is related to the sensor type. is the actual installation position vector. is the theoretical installation position vector. is the state information space gradient. is the installation angle deviation value. is the high-order error term related to the angle. For the th harmonic amplitude of the vibration signal. is the fundamental wave amplitude.

[0154] According to the calculation result, it is converted into the first error weight. The first error weight is represented by formula (2), and formula (2) is as follows:

[0155] ;

[0156] In formula (2), is the first error weight. is the original data of the uncorrected device state information. is the compensated state information. is the maximum historical amplitude of the state information under the normal operation state of the device. is the sampling time. is the number of sampling points within the sliding window. is the tightness influence factor. is the tightness index. is the position deviation amount. is the position deviation threshold. is the enhancement coefficient.

[0157] In this embodiment, the installation parameter deviation analysis and dynamic error weight calculation are fused through the physical kinematic equation to realize the device installation error analysis.

[0158] According to the abnormal device information and associated parameters, by parsing the sensor type identifier, historical operation data, and device association topology, the actual installation parameters and theoretical installation parameters are generated, characterizing the difference between the actual installation conditions and the design in the spatial layout and mechanical connection of the device.

[0159] According to the installation position deviation amount, calculate the sensor measurement error reference value caused thereby; combine the installation angle deviation value to correct the state information distortion caused by non-ideal installation; through analyzing the harmonic components of the vibration signal, inversely deduce the actual tightening state of the mechanical connection parts.

[0160] In formula (1), can be the calibration coefficient of the accelerometer or strain gauge. reflects the signal attenuation caused by the installation tilt. Three-dimensional positioning measurement data from the device coordinate system, Generated based on the preset coordinates of the layout schematic diagram.

[0161] In formula (2), is the calculation formula of the first error weight in the normal state (i.e., When), other states except this are abnormal states, and the calculation formula of the first error weight at this time is , where the tightness influence factor Quantify the amplification coefficient of the mechanical connection looseness on the error weight (value range 0.1 - 1.0), reflect the non-linear law of the error amplification under different looseness degrees, and be calibrated through the bolt vibration table test; the tightness index Reflect the actual tightening state of the mechanical connection (0 = completely loose, 1 = ideally tightened); the first error weight For subsequent fault state judgment; the position deviation amount Is the Euclidean distance between the actual value and the theoretical value of the installation position obtained from formula (1); the position deviation threshold Is the critical deviation value that triggers non-linear enhancement (usually take the upper limit of the design tolerance); the enhancement coefficient Is the exponential term coefficient for controlling the growth rate of the weight with the position deviation (value range 0.5 - 2.0), and is optimized through finite element simulation.

[0162] The process of generating the first error weight can be understood as: calculating the difference degree between the original state information and the state information after installation error compensation; weighting and amplifying the difference degree according to the tightness index; fusing the installation position deviation amount and the angle deviation value into the final weight according to the preset ratio; when there are installation parameters beyond the allowable range, perform non-linear enhancement on the weight value.

[0163] Compare the first error weight with the dynamic threshold, and mark it as abnormal physical verification when it exceeds the threshold. Preferably, the dynamic threshold is adaptively adjusted based on the statistical distribution of the error weight under the normal operating conditions of the device history, combined with the real-time operating environment parameters, and is used to distinguish abnormal physical verification from random fluctuations within the allowable range.

[0164] The verification process of this embodiment realizes the multi-parameter coupling analysis of the mechanical connection state, spatial positioning accuracy and signal acquisition quality through the physical modeling of the installation parameter deviation and the dynamic weight calculation, and provides a quantitative criterion for the equipment health state assessment that simultaneously considers the static installation error and the dynamic operation characteristics. The generation logic of the error weight focuses on reflecting the conduction and amplification effect of the installation defect on the state information, and enhances the detection sensitivity to the hidden installation fault through the non-linear superposition mechanism of the tightness index and the position deviation.

[0165] Please refer to Figure 4, in some embodiments, the device status information includes abnormal vibration signals and abnormal spectrum characteristics generated by abnormal device operation, and the historical working condition fault information includes historical vibration signals, historical spectrum characteristics, and historical operation parameters;

[0166] Match the historical working condition fault information of the abnormal device in the historical database according to the abnormal device information, calculate the fitness between the current device status information and the historical working condition fault information, and generate the second error weight, including:

[0167] S401. Calculate the waveform similarity between the abnormal vibration signal and the historical vibration signal, and calculate the energy distribution difference value between the abnormal spectrum characteristic and the historical spectrum characteristic within the abnormal frequency band;

[0168] S402. Correct the waveform similarity and the energy distribution difference value according to the difference information between the operation parameters in the abnormal device information and the historical operation parameters;

[0169] S403. Fuse the corrected waveform similarity and the corrected energy distribution difference value to generate the second error weight.

[0170] In this embodiment, through time-frequency domain feature matching and working condition offset compensation, a quantitative evaluation of the historical experience of the abnormal device state is realized.

[0171] In step S401, the dynamic time warping algorithm is used to calculate the waveform similarity between the abnormal vibration signal and the historical vibration signal for time-domain feature comparison, eliminate the difference in cycle length caused by rotational speed fluctuations, and obtain the similarity score by calculating the minimum cumulative path distance, which characterizes the morphological consistency of the time-domain waveform after elastic alignment on the time axis; preferably, the root mean square deviation method of the energy ratio in the frequency band is used to calculate the energy distribution difference value between the abnormal spectrum characteristic and the historical spectrum characteristic within the abnormal frequency band for frequency-domain feature comparison, extract the amplitude spectrum data within the preset abnormal frequency band, and calculate the Euclidean distance of the energy distribution at each frequency point between the current and historical spectra respectively, which is used to quantify the offset degree of high-frequency resonance or specific harmonic components.

[0172] In step S402, the waveform similarity and the energy distribution difference value are corrected by constructing a mapping function between the parameter difference rate and the feature confidence level to achieve working condition offset compensation. Specifically, the percentage difference between the operation parameters such as the load rate and the rotational speed value of the current device and the historical case is calculated to generate a parameter offset coefficient; then the S-shaped function is used to attenuate and compensate the waveform similarity and proportionally amplify the energy distribution difference value.

[0173] The process of using the S-shaped function to attenuate and compensate for waveform similarity can be understood as follows: The operation parameter difference rate is input into the S-shaped function to generate a [0, 1] attenuation coefficient. The larger the parameter difference, the smaller the output value, causing the waveform similarity to decay inversely with the degree of operating condition deviation. The process of using the S-shaped function to proportionally amplify the energy distribution difference value can be understood as follows: By adjusting the slope and offset of the S-shaped function, the parameter difference rate is mapped to interval, where is the preset maximum amplification factor, determined by the system based on engineering experience or experimental calibration. When the operation parameter difference rate reaches the maximum threshold, the output value of the S-shaped function approaches , ensuring that there is a controllable upper limit for the energy difference amplification (e.g., represents a maximum amplification of 3 times), avoiding overcorrection under extreme operating conditions. The higher the difference rate, the larger the output value, and the energy distribution difference value is multiplied by this coefficient to achieve amplification.

[0174] This step is used to eliminate the interference of operating condition fluctuations on feature matching. For example, the systematic increase in the amplitude of the vibration signal under high-load operating conditions should not affect the determination of waveform morphological similarity.

[0175] In step S403, preferably, the process of obtaining the second error weight includes a hierarchical feature fitness determination mechanism: When both the corrected waveform similarity (time-domain feature) and the energy distribution difference value (frequency-domain feature) exceed the first threshold, it indicates that the current operating condition is highly matched with the historical optimal case. At this time, the historical minimum error weight is directly used as the second error weight to inherit the verified diagnostic conclusion and avoid repeated calculations; When either the waveform similarity or the energy distribution difference value is between the first threshold and the second threshold, the sliding weighted average algorithm is used to dynamically adjust the weight ratio according to the deviation degrees of the waveform similarity and the energy distribution difference value, and correct the second error weight to ensure that partially matched cases can still contribute to the correction reference; When both the corrected waveform similarity and the corrected energy distribution difference value are lower than the second threshold, it is identified as a new abnormal mode, and the preset maximum error weight is assigned to trigger the independent analysis module.

[0176] Preferably, the first threshold is set according to the normal operating condition parameter fluctuation range, and the second threshold is determined by the historical extreme value or the system tolerance upper limit. The two are combined through statistical analysis and experimental calibration to divide the difference rate interval to balance sensitivity and stability.

[0177] This embodiment calculates the waveform similarity between the abnormal vibration signal and the historical vibration signal based on the dynamic time warping algorithm, eliminates the influence of rotational speed fluctuations on the comparison of time-domain waveform shapes, and at the same time uses the root mean square deviation method to quantify the energy distribution difference value within the abnormal frequency band to capture high-frequency resonance or harmonic shift characteristics; constructs a non-linear mapping between the operating parameter difference rate and the feature confidence level, and attenuates and corrects the waveform similarity and proportionally amplifies the energy distribution difference value through operating condition offset compensation to eliminate the interference of feature matching caused by operating condition fluctuations such as load and rotational speed; based on the dual-threshold hierarchical determination mechanism of the first threshold and the second threshold (the first threshold comes from the normal fluctuation range, and the second threshold is determined by the historical extreme value), fuses the corrected waveform similarity and the corrected energy distribution difference value, and dynamically generates the second error weight according to full match, partial match, and new abnormal scenarios.

[0178] This method effectively improves the robustness of abnormal diagnosis through time-frequency joint analysis and operating condition adaptive correction: it can inherit the historical optimal conclusion to avoid redundant calculations when highly matched, and can also retain effective correction references in partially matched scenarios through the sliding weighted algorithm, while ensuring the independent analysis and triggering of new abnormal modes, achieving a balance between the reuse of historical experience and the identification of unknown faults, and taking into account both diagnostic sensitivity and system stability.

[0179] In some embodiments, a risk level assessment is performed on the fault status information, and the detection mode is generated according to the assessment result, including:

[0180] The abnormal monitoring sequence in the fault status information is divided into multiple monitoring points according to the unit time, and each monitoring point has a monitoring value;

[0181] Construct an abnormal monitoring sequence curve graph, where the vertical coordinate of the abnormal monitoring sequence curve graph is the monitoring value, and the horizontal coordinate of the abnormal monitoring sequence curve graph is the monitoring time;

[0182] In the abnormal monitoring sequence curve graph, a high-risk monitoring interval, a medium-risk monitoring interval, and a low-risk monitoring interval are divided, and multiple monitoring values are divided to form a high-risk set, a medium-risk set, and a low-risk set;

[0183] Calculate the proportion of the monitoring values of the high-risk set, the medium-risk set, and the low-risk set in the current abnormal monitoring sequence to generate the assessment result of the abnormal monitoring sequence;

[0184] If the assessment result is high risk, monitor the abnormal device according to the high-frequency detection mode;

[0185] If the assessment result is medium risk, monitor the abnormal device according to the low-frequency detection mode;

[0186] If the assessment result is low risk, maintain the initial detection mode.

[0187] In this embodiment, through the timing feature analysis of the anomaly monitoring sequence and the dynamic division of the risk interval, the hierarchical evaluation of the equipment failure state and the adaptive adjustment of the detection mode are realized.

[0188] Dividing the anomaly monitoring sequence into multiple monitoring points per unit time can be understood as segmenting the continuously collected anomaly monitoring data at fixed time intervals (such as every minute or every hour), with each segment corresponding to a monitoring point, and its monitoring value being the statistic of the sensor data within that time period (such as the mean, peak value, or variance), which is used to quantify the anomaly degree of the equipment during that period.

[0189] When constructing the anomaly monitoring sequence curve graph, the monitoring values on the vertical axis reflect the fluctuation intensity of the equipment anomaly state, and the monitoring time on the horizontal axis marks the timing trajectory of the anomaly evolution. The anomaly mutation points or trend cumulative effects can be visually identified through the curve form.

[0190] Dividing the high-risk monitoring interval, medium-risk monitoring interval, and low-risk monitoring interval can be understood as setting vertical numerical boundaries in the curve graph based on preset thresholds or historical statistical distributions, dividing the vertical axis into numerical ranges corresponding to different risk levels. For example, the interval exceeding the upper threshold is defined as the high-risk monitoring interval, the interval between the upper and lower limits is the medium-risk monitoring interval, and the interval below the lower limit is the low-risk monitoring interval, so as to classify the monitoring values of each monitoring point into the corresponding risk sets.

[0191] By counting the number of monitoring points in the current anomaly monitoring sequence that fall into the high-risk set, medium-risk set, and low-risk set, and calculating their respective proportions in the total number of monitoring points. For example, if the proportion of the high-risk set reaches 60%, it is evaluated as high risk, which is used to characterize the persistence and severity of the anomaly state. The high-frequency detection mode means shortening the data acquisition period (such as from once every 10 minutes to once every minute) to enhance the monitoring density, which is suitable for quickly capturing the details of anomaly evolution in the high-risk state; the low-frequency detection mode extends the acquisition interval (such as from once every 10 minutes to once every 30 minutes), balancing resource consumption and monitoring requirements in the medium-risk state; the initial detection mode maintains the original acquisition frequency, which is suitable for the normal monitoring in the low-risk state.

[0192] Among them, the definition of the threshold of the risk interval can be dynamically adjusted in combination with the equipment type, historical failure data, and industry standards. For example, the numerical interval corresponding to the typical anomaly mode is divided by clustering analysis, or the threshold boundary is updated according to the recent data distribution using the sliding window statistical method. The evaluation rule of the monitoring value proportion can adopt the weighted cumulative method. For example, a higher weight is given to the high-risk set, and when the weighted score exceeds the set threshold, the corresponding risk level determination is triggered. The detection mode switching mechanism needs to be embedded with lag filtering processing to avoid frequent mode jumps caused by instantaneous fluctuations. For example, when three consecutive evaluation cycles are all high risk, the high-frequency mode is switched.

[0193] In this embodiment, through the timing feature analysis of the abnormal monitoring sequence and the dynamic division of the risk interval, the hierarchical evaluation of the device fault state and the adaptive adjustment of the detection mode are realized. The method flow includes: dividing the continuous abnormal monitoring sequence into discrete monitoring points with monitoring values per unit time, constructing an abnormal monitoring sequence curve graph with the monitoring value on the vertical axis and the monitoring time on the horizontal axis, dividing high-risk monitoring intervals, medium-risk monitoring intervals, and low-risk monitoring intervals based on preset or dynamically adjusted vertical thresholds, counting the proportion of monitoring points in each risk set to generate an evaluation result, and finally adaptively switching to high-frequency, low-frequency, or initial detection modes according to high-risk, medium-risk, or low-risk judgments.

[0194] Based on the dynamic division of the vertical threshold of the monitoring curve graph, this method combines the device type and historical data to optimize the boundary of the risk interval, and can accurately capture the abnormal fluctuation intensity and evolution trend; through the monitoring point proportion statistics and weighted evaluation rules, it takes into account the persistent characterization of the abnormal state and the response to sudden events, avoiding misjudgment by a single threshold; the detection mode switching mechanism is embedded with lag filtering processing to suppress the interference of instantaneous fluctuations and ensure the stability of mode adjustment; the dynamically adjusted high-frequency detection mode and low-frequency detection mode optimize the resource utilization rate in medium- and low-risk scenarios while ensuring the monitoring density of high-risk states, forming a closed-loop adaptive control system to achieve the balance between the fault warning sensitivity and the system operation economy.

[0195] In some embodiments, the neural network model includes a physical decoupling model. Inputting the system dynamic coupling topology link, associated parameters, abnormal device information, and fault state information into the neural network model, the obtained fault link information includes:

[0196] Extract the forward conduction path of the abnormal device from the system dynamic coupling topology link, mark the devices in the forward conduction path as fault source devices, generate topological decoupling features, and extract the physical connection features between the fault source devices and the abnormal devices from the associated parameters;

[0197] Input the topological decoupling features and physical connection features into the trained physical decoupling model to obtain the forward traceability prediction information for the faults of the abnormal devices, including:

[0198] Extract the fault contribution probabilities of multiple fault source devices according to the topological decoupling features and physical connection features;

[0199] Adjust the fault contribution probabilities of each fault source device according to the physical constraint features. The physical constraint features include energy conservation constraints and time sequence propagation constraints, eliminate the fault source devices that do not meet the physical constraint features, and generate the corrected contribution probabilities of the remaining fault source devices;

[0200] Generate forward traceability prediction information for abnormal device failures based on the corrected contribution probability and its corresponding fault source device.

[0201] In this embodiment, extracting the forward conduction path of an abnormal device from the system dynamic coupling topology link can be understood as identifying the device link that may conduct faults upstream of the abnormal device based on the real-time connection relationship and interaction strength between system nodes, and using a weighted path search algorithm (such as Dijkstra's algorithm). Mark the devices in the path that have a direct or indirect dynamic coupling relationship with the abnormal device as fault source devices for locating potential fault propagation sources.

[0202] Extract structural attributes such as node connectivity, path weight distribution, and conduction directionality from the topology link. For example, quantify the hub role of each node in fault propagation by calculating the betweenness centrality of each node, or characterize the activity level of the conduction path by the cumulative value of the path weight as a topology decoupling feature to describe the structural features of fault propagation.

[0203] Parse physical interaction parameters such as material properties, mechanical connection stiffness, or energy transfer coefficient between the fault source device and the abnormal device from the system parameter library. For example, extract the torque transfer coefficient of the coupling or the fluid resistance coefficient of the pipeline as physical connection features to quantify the fault conduction ability at the physical level.

[0204] The training of the physical decoupling model uses the verified propagation chain in historical fault cases as positive samples, generates negative samples by simulating situations that violate physical laws such as abnormal energy transfer or time series inversion. During the training process, strengthen the sensitivity of the model to physical constraints through the contrast loss function, and at the same time combine the adversarial training mechanism to improve the robustness to noise interference, so that the model embeds physical prior knowledge while retaining the advantages of data-driven, enhancing the interpretability and engineering credibility of the prediction results.

[0205] The physical decoupling model inputs topological features (such as node connectivity, conduction path weight) and physical features (such as material conduction coefficient, mechanical impedance) into a multi-layer perceptron network, establishes a topology-physical coupling relationship through a feature cross-fusion layer, and uses the attention mechanism to calculate the state correlation strength of each potential fault source device to the abnormal device, and outputs a normalized weight value as the fault contribution probability, which represents the relative influence degree of the device in the conduction path.

[0206] The energy conservation constraint means verifying whether the energy transfer efficiency from the faulty source device to the abnormal device conforms to the laws of thermodynamics or the mechanical efficiency threshold. For example, checking whether the attenuation rate of vibration energy on the conduction path is within a reasonable range; the timing propagation constraint means verifying whether the arrival timing of the fault characteristic signal in the topological link conforms to the relationship between the wave propagation speed and the path length. For example, judging the causal rationality by comparing the path distance and the signal propagation time delay. For devices that meet the constraints, retain the original probability, and for devices that violate the constraints, reduce the weight or set it to zero according to the attenuation coefficient. Finally, normalize to generate the corrected contribution probability to ensure that the result conforms to the actual physical laws and the propagation path logic.

[0207] Arrange the corrected contribution probabilities in descending order, and output the list of faulty source devices that meet the physical constraints and their associated conduction paths, which is the forward traceability prediction information, providing a priority guide for fault troubleshooting.

[0208] In this embodiment, based on the real-time topological link, extract the forward conduction path of the abnormal device and generate topological decoupling features, and quantify the conduction ability in combination with physical connection parameters; extract the initial contribution probability of the faulty source device through the physical decoupling model, and adopt the cross-fusion of topological-physical two-dimensional features and the attention mechanism to strengthen the recognition ability of the key nodes of the conduction path; then through the physical constraint feature verification mechanism, eliminate abnormal prediction results that violate the laws of thermodynamics or signal propagation logic, filter out false correlation interference, generate the corrected contribution probability, and ensure that the prediction result is consistent with the actual physical laws of the project; output the list of faulty source devices that conform to the physical laws and are sorted by the degree of influence, which is the forward traceability prediction information. This method enables the physical decoupling model to still maintain a robust discrimination ability for the real fault conduction link in a complex noise environment.

[0209] In some embodiments, the neural network model includes a physical coupling model. Input the system dynamic coupling topological link, associated parameters, abnormal device information, and fault status information into the neural network model, and the obtained fault link information also includes:

[0210] Extract the backward conduction path of the abnormal device in the system dynamic coupling topological link, mark the devices in the backward conduction path as risk devices, generate topological coupling features, and extract the physical coupling features of the risk devices and the abnormal devices from the associated parameters;

[0211] Input the topological coupling features and physical coupling features into the trained physical coupling model to generate the backward fault prediction information of the abnormal device, including:

[0212] Calculate the inherent conduction risk value of the risk device according to the topological coupling features;

[0213] Calculate the risk correction coefficient related to the working condition according to the physical coupling features;

[0214] Fuse the risk correction coefficient with the inherent conduction risk value to obtain the conduction risk probability of each risk device;

[0215] Verify multiple conduction risk probabilities by applying mass conservation constraints, eliminate risk devices that violate the mass conservation constraints, correct the conduction risk probabilities, obtain the corrected risk probabilities, and generate the time limit section corresponding to the current corrected risk probabilities;

[0216] Generate backward fault prediction information and time limit section of abnormal devices based on the corrected risk probabilities and their corresponding risk devices.

[0217] In this embodiment, extracting the backward conduction path of abnormal devices in the system's dynamic coupling topology link can be understood as being achieved through a reverse path search algorithm (such as improved breadth-first search), representing the potential path network where the faults of abnormal devices may spread to downstream devices, used to identify the secondary risk device group that may be affected by the current abnormal state. Its search direction is opposite to the actual physical flow direction of fault conduction, but the dynamic coupling strength weights between nodes are retained to reflect the conduction probability.

[0218] The generation of topological coupling characteristics includes calculating the cumulative value of the shortest path weights from each risk device to the abnormal device, used to quantify the activity of the conduction path at the topological level; at the same time, extract the nodes with high betweenness centrality in the path as key coupling points, reflecting their hub role in the fault diffusion process. For example, key nodes are screened out by counting the occurrence frequency of nodes in the conduction path, used to enhance the ability to identify conduction bottlenecks.

[0219] Preferably, the physical coupling characteristics include the dynamic interaction coefficient and the failure sensitivity. Extracting the physical coupling characteristics of risk devices and abnormal devices from the correlation parameters can be understood as follows: the dynamic interaction coefficient quantifies the physical connection strength between risk devices and abnormal devices by analyzing parameters such as the mechanical transmission efficiency, fluid resistance coefficient, or conductivity between devices in the system parameter library; the failure sensitivity calculates the performance degradation rate of risk devices in the current operating state based on real-time working condition data (such as vibration amplitude, temperature gradient) and device design thresholds, used to evaluate their vulnerability to external fault conduction.

[0220] The training of the physical coupling model adopts a curriculum learning strategy. Initially, only basic topological constraints are introduced, and complex physical rules such as mass conservation and power flow balance are gradually superimposed, enabling the model to master the mapping relationship from structural features to physical laws in stages; adversarial training generates adversarial samples with high topological coupling but violating physical constraints, forcing the model to distinguish false conduction paths. For example, a contradictory feature combination with a high topological path weight but a zero dynamic interaction coefficient is constructed to enhance the model's robustness to abnormal operating conditions. Positive samples are sourced from the verified subsequent fault device chains in historical fault logs, while negative samples are generated by randomly replacing the end devices of the conduction path or inserting physically unreachable nodes, ensuring that the samples cover both real conduction and physical violation scenarios. The design of the loss function emphasizes the punishment for physical constraint violations. For example, an additional loss term is imposed on the prediction results that violate mass conservation, and at the same time, contrastive loss is used to strengthen the difference between positive and negative samples, enabling the physical coupling model to accurately separate the conduction modes that conform to engineering practice in the feature space.

[0221] The calculation of the inherent conduction risk value fuses the path weight and key node density in the topological coupling features through a multi-layer perceptron network, and outputs the basic probability reflecting the threat of a device being affected by fault diffusion at the structural level; the risk correction coefficient is weighted and calculated through the dynamic interaction coefficient and failure sensitivity in the physical coupling features. For example, the coefficients of high transmission efficiency devices and low failure sensitivity devices are adjusted downwards to suppress their risk contributions; the fusion of the conduction risk probability adopts a gating mechanism to dynamically adjust the weight ratio of topological and physical features. For example, under high-pressure conditions, the decision weight of physical coupling features is strengthened, enabling the model to adapt to the changes in conduction characteristics under different operating environments.

[0222] The verification of the mass conservation constraint is achieved by comparing the input-output deviation of the material flow or energy flow on the fault conduction path. For example, in a hydraulic system, it is verified whether the flow loss caused by fault propagation is within the allowable range of pipeline leakage. If the deviation exceeds the threshold, it is determined that the path violates the conservation law, and the corresponding risk devices are then excluded. The time window for generating the risk probability correction is based on the time delay distribution law of similar conduction paths in historical fault cases, and combines the current system operation rate (such as the rotational speed of a rotating machine) to estimate the time window for the propagation of the fault impact. For example, the earliest and latest time intervals when the risk devices may malfunction are estimated through the ratio of the path length to the medium propagation speed.

[0223] In this embodiment, a backward fault prediction mechanism is constructed by integrating the structural characteristics of the dynamic coupling topological link of the system with the physical interaction parameters. Based on the reverse path search algorithm, the potential conduction paths of abnormal devices are extracted and the risk devices are marked to generate topological coupling features and physical coupling features. The inherent conduction risk value and the risk correction coefficient related to the working condition are calculated by the physical coupling model, and the gating mechanism is used to dynamically fuse the two to generate the conduction risk probability. The quality conservation constraint is applied to eliminate the illegal paths and correct the risk probability, and the aging section is estimated by combining the historical time delay law and the operating rate. Through the cross-validation of the topological-physical two-dimensional features and the dynamic weight adjustment mechanism, this method effectively improves the positioning accuracy of multi-source concurrent faults; the combination of the curriculum learning strategy and the adversarial training ensures the robustness of the model under complex working conditions, and the quality conservation constraint excludes false conduction paths; the aging section prediction provides a clear time window for the operation and maintenance decision-making, and the gating mechanism ensures that the model adaptively adjusts the contribution weights of the topological coupling features and the physical coupling features, enhancing the adaptability in different operating environments, and finally forming a fault conduction prediction system that conforms to the engineering physical laws and has the value of timing guidance.

[0224] In a second aspect, this embodiment also provides a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the method described in the first aspect is implemented.

[0225] The computer program involved in this embodiment can be stored in a computer-readable storage medium. The computer-readable storage medium includes, but is not limited to, magnetic disks, magnetic tapes, magnetic cards, floppy disks, flash memories, optical discs, optical cards, read-only memories (ROMs), random access memories (RAMs), erasable programmable ROMs (EPROMs), and electrically erasable programmable ROMs (EEPROMs), etc. It also includes other biological, physical, or chemical structures that can achieve the same or equivalent functions as the above-listed storage media, such as units with information storage capabilities like DNA, RNA, proteins, etc. In a specific embodiment, the storage medium involved can be one of the above medium types or a combination of the above medium types. In different embodiments, the computer program involved in the embodiment can be centrally stored in a single medium or distributedly stored in multiple media. The memory containing the computer-readable storage medium can be a non-volatile memory or a random access memory. These computer-readable storage media can be built into the device or can be connected to the device involved in the embodiment as an external device or a part of an external device. In some embodiments, the memory with the computer-readable storage medium is deployed locally; in other embodiments, a scheme of deploying the memory away from the processor can also be adopted, such as a network-attached memory accessed via an RF circuit or an external port and a communication network, where the communication network can be the Internet, one or more internal networks, local area networks (LANs), wide area wireless networks (WLANs), storage area networks (SANs), etc., or a suitable combination thereof, as long as the computer device can access the memory. In addition, the computer program involved in the embodiment can be stored in plaintext / ciphertext form or can be designed as training data and be integrally recombined and implicitly stored in the parameter states of a deep neural network or other machine learning models through model training.

[0226] Please refer to Figure 5 , in a third aspect, this embodiment also provides an electronic device 1, including a memory 11 and a processor 12. The memory 11 is used to store one or more computer program instructions, where the one or more computer program instructions are executed by the processor 12 to implement the method described in the first aspect.

[0227] The processor described in this embodiment can be implemented by hardware, firmware, software, or a combination thereof. It can use circuits, one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), central processing units (CPUs), controllers, microcontrollers, microprocessors, or at least one of the like. It also includes other physical, biological, or chemical structures that can achieve functions similar to or equivalent to those of the above-listed processors, such as biological neurons, quantum computing units, DNA computing units, etc., so that the processor can execute some steps, all steps, or any combination of the steps mentioned in the computer programs or methods involved in the various embodiments of the present application.

[0228] Different from the prior art, the above technical solution has the following beneficial effects:

[0229] The present invention realizes the system-level prediction and early warning of the equipment fault conduction path by constructing a neural network model with deep embedding of dynamic coupling topology links and physical rules. Specifically, the above technical solution abstracts the mechanical connection relationship and energy transfer characteristics between devices into a weighted topology network, combines the verification of physical kinematic equations and historical working conditions matching to generate multi-dimensional error weights, reversely locates the faulty source device through a physical decoupling model, and uses a physical coupling model to predict the backward conduction path and its time-effective section. The topology coupling feature and the physical coupling feature are dynamically fused through a gating mechanism, and the conduction paths that violate physical laws are eliminated by combining the mass conservation constraint, forming a fault propagation prediction system that conforms to engineering practice. This method breaks through the limitation of traditional single-device monitoring, integrates complex physical rules in stages through a curriculum learning strategy, and enhances the model's ability to identify topology-physical contradiction samples through adversarial training, simultaneously improving the multi-source fault location accuracy and adaptability to abnormal working conditions; calculates the time-effective section based on the path length and the medium propagation speed, and predicts the potential spread sequence by combining Monte Carlo path simulation, realizing the full-link spatio-temporal dynamic early warning from single-point anomalies to system-level risks, providing decision support for fault conduction blocking with both physical interpretability and dynamic adaptability for Internet of Things devices, and significantly improving the operation reliability of complex systems.

[0230] Finally, it should be noted that although the above embodiments have been described in the text and drawings of the specification of this application, the patent protection scope of this application cannot be limited thereby. Any technical solutions obtained by means of equivalent structure or equivalent process substitution or modification based on the substantial concept of this application and using the content recorded in the text and drawings of the specification of this application, as well as those directly or indirectly implementing the technical solutions of the above embodiments in other relevant technical fields, are all included within the patent protection scope of this application.

Claims

1. A device fault warning method based on a neural network, characterized in that The method includes: Regularly obtaining device status information, determining whether the device status information is abnormal, and if so, recording it as an abnormal device and triggering an abnormal evaluation step, including: Obtaining abnormal device information, where the abnormal device information includes operating parameters and structural parameters; Obtaining the layout schematic diagram of the system where the abnormal device is located, constructing a system dynamic coupling topology link according to the layout schematic diagram, and generating associated parameters in combination with the abnormal device information. The associated parameters are the location information of the abnormal device in the system and the device information of the other devices connected by the abnormal device; Verifying the device status information according to the abnormal device information and the associated parameters using a physical kinematic equation to generate a first error weight, including: Generating actual installation parameters and theoretical installation parameters according to the abnormal device information and the associated parameters; Calculating the deviation information between the actual installation parameters and the theoretical installation parameters, and recording it as installation deviation information; Performing physical deviation calculation according to the installation deviation information to obtain a calculation result, which is represented by formula (1). The formula (1) is as follows: ; In formula (1), is the position deviation, is the angle deviation, is the fitting deviation, is the position sensitivity coefficient, which is related to the sensor type, is the actual installation position vector, is the theoretical installation position vector, is the state information space gradient, is the installation angle deviation value, is the high-order error term related to the angle, is the th harmonic amplitude of the vibration signal, is the fundamental wave amplitude; Converting the calculation result into the first error weight. The first error weight is represented by formula (2). The formula (2) is as follows: ; In formula (2), is the first error weight, is the raw data of the uncorrected device status information, is the compensated status information, is the maximum historical amplitude of the status information under normal operation of the device, is the sampling time, is the number of sampling points within the sliding window, is the tightness influence factor, is the tightness index, is the position deviation amount, is the position deviation threshold, is the enhancement coefficient; Matching the historical working condition fault information of the abnormal device in the historical database according to the abnormal device information, calculating the fitness between the device status information and the historical working condition fault information, and generating a second error weight; Generating the fault status information of the device according to the first error weight and the second error weight; Performing a risk level assessment on the fault status information, and generating a detection mode according to the assessment result. The detection mode includes a high-frequency detection mode and a low-frequency detection mode; Inputting the system dynamic coupling topology link, the associated parameters, the abnormal device information, and the fault status information into a neural network model to obtain fault link information. The fault link information includes forward traceability prediction information for causing the abnormal device fault, backward fault prediction information for the abnormal device, and a time-effective section; Generating a first warning information according to the fault link information, the fault status information, and the abnormal device information. When the detection mode switches to the high-frequency detection mode, triggering the low-frequency detection mode for the remaining devices in the current fault link information to generate a second warning information.

2. The method for early warning of equipment faults based on a neural network according to claim 1, characterized in that, Constructing the system dynamic coupling topology link according to the layout schematic diagram includes: Obtaining the mechanical connection relationship in the layout schematic diagram, constructing a directed graph structure with individual devices as nodes and mechanical connections as connecting lines, and initializing the weights of the directed graph structure, including: The node weight of each node is generated by the inherent failure rate of a single device, and the connection line weight of each connection line is calculated from the material strength and design load of the nodes at both ends of the connection line; Monitoring the vibration signals between the devices of each connection line, generating an actual energy attenuation rate according to the vibration signals, and generating a first weight adjustment parameter according to the actual energy attenuation rate; Monitoring the cooperation parameters of the devices of each connection line, calculating the motion cooperation coefficient between two devices according to the cooperation parameters, and generating a second weight adjustment parameter according to the motion cooperation coefficient; Adjust the weight of the connection line according to the first weight adjustment parameter and the second weight adjustment parameter; Moreover, obtain the used duration and the rated duration of each device, and generate a device failure rate adjustment parameter according to the used duration and the rated duration; Adjust the node weight according to the device failure rate adjustment parameter.

3. The method for early warning of equipment faults based on a neural network according to claim 2, wherein Construct a system dynamic coupling topology link according to the layout schematic diagram, and generate associated parameters in combination with abnormal device information, including: Mark the node of the abnormal device as an abnormal node, and conduct a search along the direction of the connection line of the abnormal node until the number of connection lines in the first conduction path formed by the conduction search exceeds a preset tolerance value, and the preset tolerance value is generated by the product of the connection line weights in the first conduction path and the conduction threshold; Mark the devices associated with the nodes covered by the first conduction path as affected devices; Execute the following steps for each affected device: Obtain the connection line weight on the second conduction path from the abnormal node to the affected device; Calculate the geometric mean of the connection line weights on the second conduction path as the path conduction efficiency; Obtain the node weight of the abnormal node, denoted as the abnormal node weight, and obtain the node weight of the affected device, denoted as the original node weight; Generate a weight influence coefficient for the affected device according to the abnormal node weight, the path conduction efficiency, and the original node weight; Update the original node weight according to the weight influence coefficient, denoted as the influence node weight; Repeat the foregoing steps until the original node weights of all affected devices are updated; Generate the position information of the abnormal device in the system according to the first conduction path and the directed graph structure, and generate the device information of the other devices connected by the abnormal device according to the influence node weight and the affected device, which are the associated parameters.

4. The method for early warning of equipment failures based on a neural network according to claim 1, characterized in that, The device state information includes abnormal vibration signals and abnormal spectrum characteristics generated by the operation of the abnormal device, and the historical working condition fault information includes historical vibration signals, historical spectrum characteristics, and historical operation parameters; Match the historical working condition fault information of the abnormal device in the historical database according to the abnormal device information, calculate the fitness between the current device state information and the historical working condition fault information, and generate a second error weight, including: Calculate the waveform similarity between the abnormal vibration signal and the historical vibration signal, and calculate the energy distribution difference value between the abnormal spectrum characteristic and the historical spectrum characteristic in the abnormal frequency band; Correct the waveform similarity and the energy distribution difference value according to the difference information between the operation parameters in the abnormal device information and the historical operation parameters; Fuse the corrected waveform similarity and the corrected energy distribution difference value to generate the second error weight.

5. The method for early warning of equipment faults based on a neural network according to claim 1, characterized in that Evaluate the risk level of the fault state information, and generate a detection mode according to the evaluation result, including: Divide the abnormal monitoring sequence in the fault state information into multiple monitoring points according to the unit time, and each monitoring point has a monitoring value; Construct an abnormal monitoring sequence curve graph, where the ordinate of the abnormal monitoring sequence curve graph is the monitoring value, and the abscissa of the abnormal monitoring sequence curve graph is the monitoring time; Divide high-risk monitoring intervals, medium-risk monitoring intervals, and low-risk monitoring intervals in the abnormal monitoring sequence curve graph, and divide multiple monitoring values to form a high-risk set, a medium-risk set, and a low-risk set; Calculate the proportion of the monitoring values of the high-risk set, the medium-risk set, and the low-risk set in the current abnormal monitoring sequence, and generate an evaluation result of the abnormal monitoring sequence; If the evaluation result is high risk, monitor the abnormal device according to the high-frequency detection mode; If the evaluation result is medium risk, monitor the abnormal device according to the low-frequency detection mode; If the evaluation result is low risk, maintain the initial detection mode.

6. The method for early warning of equipment failures based on a neural network according to claim 1, characterized in that The neural network model includes a physical decoupling model. Input the system dynamic coupling topology link, associated parameters, abnormal device information, and fault status information into the neural network model, and the obtained fault link information includes: Extract the forward conduction path of the abnormal device in the system dynamic coupling topology link, mark the devices in the forward conduction path as fault source devices, generate topology decoupling features, and extract the physical connection features between the fault source devices and the abnormal devices from the associated parameters; Input the topology decoupling features and physical connection features into the trained physical decoupling model to obtain the forward traceability prediction information for the fault of the abnormal device, including: Extract the fault contribution probabilities of multiple fault source devices according to the topology decoupling features and physical connection features; Adjust the fault contribution probability of each fault source device according to the physical constraint features. The physical constraint features include energy conservation constraints and timing propagation constraints. Eliminate the fault source devices that do not meet the physical constraint features, and generate the corrected contribution probabilities of the remaining fault source devices; Generate the forward traceability prediction information for the fault of the abnormal device according to the corrected contribution probabilities and their corresponding fault source devices.

7. The method for early warning of equipment faults based on a neural network according to claim 6, characterized in that The neural network model includes a physical coupling model. Input the system dynamic coupling topology link, associated parameters, abnormal device information, and fault status information into the neural network model, and the obtained fault link information further includes: Extract the backward conduction path of the abnormal device in the system dynamic coupling topology link, mark the devices in the backward conduction path as risk devices, generate topology coupling features, and extract the physical coupling features between the risk devices and the abnormal devices from the associated parameters; Input the topology coupling features and physical coupling features into the trained physical coupling model to generate the backward fault prediction information of the abnormal device, including: Calculate the inherent conduction risk value of the risk device according to the topology coupling features; Calculate the risk correction coefficient related to the working condition according to the physical coupling features; Fuse the risk correction coefficient and the inherent conduction risk value to obtain the conduction risk probability of each risk device; Verify the multiple conduction risk probabilities by applying the mass conservation constraint, eliminate the risk devices that violate the mass conservation constraint, correct the conduction risk probabilities, obtain the corrected risk probabilities, and generate the time period corresponding to the current corrected risk probability; Generate the backward fault prediction information and time period of the abnormal device according to the corrected risk probabilities and their corresponding risk devices.

8. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, The computer program instructions, when executed by a processor, implement the method according to any one of claims 1 to 7.

9. An electronic device, comprising a memory and a processor, characterized in that, The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method according to any one of claims 1 to 7.

Citation Information

Patent Citations

  • Communication network operation and maintenance fault positioning and tracking method and system

    CN119420639A

  • Fault event positioning method based on topological model tracking analysis

    CN119847116A