Intelligent fault diagnosis method for quick gate

Abstract

The application belongs to the technical field of fault diagnosis, and specifically discloses a quick gate intelligent fault diagnosis method, which comprises the following steps: collecting operation characteristic parameters of three subsystems; sequentially performing first-level threshold comparison diagnosis, which comprises comparing the operation characteristic parameters with a preset threshold range, and determining that an obvious fault exists if the operation characteristic parameters exceed the range; second-level characteristic value matching diagnosis, which comprises extracting fluctuation characteristic values from operation characteristic parameters that do not trigger threshold abnormalities but have parameter fluctuations, constructing a fault characteristic map, and performing similarity matching with a preset implicit fault characteristic sample, and determining that an implicit fault exists when a preset matching threshold is reached; and third-level coupling logic tracing diagnosis, which comprises constructing a fault cause-effect logic chain when operation characteristic parameters of at least two subsystems simultaneously appear abnormal, and locating a root node of a coupling fault through reverse reasoning and joint probability calculation; obtaining a diagnosis result, and generating a fault disposal strategy.

Description

Technical Field

[0001] This application belongs to the field of fault diagnosis technology, and more specifically, relates to a method for intelligent fault diagnosis of fast gates. Background Technology

[0002] High-speed gates are crucial safety protection equipment in water conservancy and hydropower projects. Their core function is to quickly close and stop water flow in the event of sudden conditions such as unit failure, pipeline rupture, or load shedding, preventing unit runaway, backflow, and flooding of the powerhouse, thus ensuring the safety of hydraulic structures and electromechanical equipment. The reliable operation of high-speed gates depends on the coordinated operation of three major subsystems: the gate's mechanical structure, the hydraulic opening and closing actuator, and the electrical control system. Failure in any subsystem may cause the entire gate to fail to open or close, or even lose its core function of emergency flow interruption.

[0003] Current fault diagnosis for high-speed gates primarily relies on manual, experience-based inspections and single-parameter monitoring. This approach depends heavily on the on-site experience of maintenance personnel, resulting in low diagnostic efficiency, high subjectivity, and poor fault identification accuracy. Existing technologies only monitor single parameters such as hydraulic system oil pressure or electrical system current, failing to provide early warnings and lacking the ability to simultaneously collect and analyze all parameters across multiple dimensions. This can easily lead to missed opportunities for optimal intervention and increase the risk of safety accidents. Most importantly, the fault tracing capability is insufficient. For coupled faults, only the symptoms can be detected, without accurately pinpointing the root cause, leading to incomplete fault handling and recurring problems. While some existing gate fault monitoring devices exist, they are all single-function monitoring modules lacking systematic diagnostic logic and tracing algorithms, thus failing to address the aforementioned technical issues.

[0004] In summary, existing fault diagnosis methods for fast gates have low diagnostic accuracy. Summary of the Invention

[0005] To address the shortcomings of existing technologies, the purpose of this application is to provide an intelligent fault diagnosis method for fast gates, which aims to solve the problem that existing fault diagnosis methods for fast gates rely on human experience and only monitor a single parameter, resulting in low diagnostic accuracy.

[0006] To achieve the above objectives, in a first aspect, this application provides a method for intelligent fault diagnosis of fast gates, comprising: The operational characteristic parameters of three subsystems are collected. The three subsystems include the mechanical structure of the fast gate body, the hydraulic opening and closing actuator, and the electrical control system. Based on the aforementioned operational characteristic parameters, the first-level threshold comparison diagnosis, the second-level feature value matching diagnosis, and the third-level coupling logic tracing diagnosis are executed sequentially to obtain the diagnostic results. The first-level threshold comparison diagnosis includes: comparing the operating characteristic parameters with the preset parameter safety threshold range; if the parameters exceed the safety threshold range, it is determined to be an obvious fault, and the fault type and fault location are output. The secondary feature value matching diagnosis includes: extracting fluctuation feature values ​​for operating feature parameters that have not triggered threshold abnormalities but have parameter fluctuations, constructing a fault feature map, matching the fault feature map with the latent fault feature samples in the preset fault feature database, and determining the latent fault when the similarity reaches the preset matching threshold, and completing the fault level classification based on the matching degree. The three-level coupled logic source tracing diagnosis includes: when at least two subsystems are detected to have abnormal operating characteristic parameters at the same time, and the abnormality is not eliminated after handling a single fault, a fault causal logic chain is constructed based on the linkage operation mechanism of the three subsystems, and the root cause node of the coupled fault is located through reverse reasoning and joint probability calculation. Based on the diagnostic results, a corresponding fault handling strategy is generated.

[0007] This application constructs a three-level progressive intelligent diagnostic model encompassing explicit, implicit, and coupled faults: "threshold triggering – feature matching – mechanism tracing." This changes the traditional diagnostic mode based on a single threshold judgment. The first-level threshold comparison diagnosis can quickly identify explicit faults with parameters exceeding limits, directly outputting the fault type and location with a fast response speed. The second-level feature matching diagnosis performs feature map matching on parameters that have not triggered the threshold but exhibit fluctuation trends, enabling the identification and classification of implicit faults before they occur, achieving early warning before faults occur and solving the problem of missed detection of implicit faults in existing technologies. The third-level coupled logic tracing diagnosis constructs a fault causal logic chain for the three subsystems, combining reverse reasoning and joint probability calculation, to accurately locate the root cause node of coupled faults in multiple systems, solving the fundamental deficiency in existing technologies that can only detect phenomena but cannot trace the source of coupled faults. At the same time, fault handling strategies are automatically generated based on the diagnostic results, forming an automated response closed loop from "fault identification" to "fault handling". This achieves an intelligent leap from "alarm after fault occurs" to "early warning before fault occurs and source tracing after fault occurs", improving the fault diagnosis accuracy of the fast gate and thus enhancing the operational reliability and emergency response capability of the fast gate.

[0008] According to the intelligent fault diagnosis method for fast gates provided in this application, the acquisition of operational characteristic parameters of three subsystems includes: The system collects the following data: door leaf vibration amplitude and frequency, frictional resistance between guide rail and slider, leakage of water-stopping device, door leaf verticality deviation, door groove silt thickness, rotational torque of lifting lug shaft, hydraulic system oil pressure, cylinder inlet and outlet pressure difference, hydraulic oil temperature, hydraulic oil cleanliness, accumulator nitrogen pressure, oil pump motor speed and current, hydraulic pipeline flow rate, PLC input and output signal amplitude, stroke sensor feedback, limit switch on / off status, inverter operating current and voltage, uninterruptible power supply (UPS) backup power voltage, and electromagnetic interference intensity.

[0009] This application specifies a list of operational characteristic parameters collected from three subsystems, covering 19 key parameters across three dimensions: mechanical, hydraulic, and electrical. This parameter list covers core operational indicators at high-incidence points of rapid gate failures: mechanical parameters include gate leaf vibration, guide rail friction resistance, and water leakage, reflecting structural health; hydraulic parameters include oil pressure, cylinder inlet / outlet pressure difference, and accumulator nitrogen pressure, reflecting the hydraulic system's operating status; and electrical parameters include PLC signals, stroke feedback, and inverter operating status, reflecting the control system's working status. These parameters are all key characteristic parameters directly related to rapid gate failures, collected without redundancy. This ensures the comprehensiveness and accuracy of the data required for diagnosis while reducing data processing pressure. It enables the three-level progressive diagnostic model to perform fault identification, prediction, and tracing based on sufficient and accurate multi-dimensional data, thereby effectively improving the accuracy of fault identification and reducing the missed and false positive rates.

[0010] According to the intelligent fault diagnosis method for fast gates provided in this application, the method further includes: The operational characteristic parameters are subjected to filtering and noise reduction, outlier removal, and normalization.

[0011] This application includes preprocessing steps for filtering and denoising, outlier removal, and normalization of operational characteristic parameters. The operating environment of high-speed gates is harsh, and the raw parameters collected are inevitably affected by external factors such as water flow impact, electromagnetic interference, and silt erosion, containing a large amount of invalid noise and abnormal data. Filtering and denoising effectively remove high-frequency spike signals caused by water flow turbulence; outlier removal filters obviously erroneous values ​​based on the physical limits of the sensors; and normalization maps parameter values ​​of different dimensions, such as pressure, flow rate, and current, to the same numerical range, eliminating the impact of dimensional differences on subsequent feature matching and probability calculations. This preprocessing step effectively improves the quality of parameter data input to the diagnostic model, ensuring the accuracy and reliability of subsequent three-level diagnoses, and making the diagnostic results more accurate and reliable.

[0012] According to the intelligent fault diagnosis method for fast gates provided in this application, the fault causal logic chain is constructed based on the linkage operation mechanism of three subsystems, and the root cause node of the coupled fault is located through reverse reasoning and joint probability calculation, including: Based on the operating mechanism of the fast gate, a causal relationship model integrating Bayesian network and fault tree is constructed. The causal relationship model is used to characterize the linkage relationship of the three subsystems. Based on the causal relationship model, by reverse reasoning and joint probability calculation, the fault point corresponding to the first abnormal parameter is traced, which is the root node of the coupled fault.

[0013] This application constructs a causal relationship model fused with Bayesian networks and fault trees based on the operating mechanism of high-speed gates. This model can systematically characterize the linkage fault propagation relationship between the three subsystems of the high-speed gate: mechanical failure of the gate body leads to increased load on the hydraulic mechanism, causing abnormal hydraulic parameters; failure of the hydraulic mechanism leads to distortion of feedback signals from the electrical control system, causing abnormal electrical parameters; failure of the electrical control system leads to malfunction of the hydraulic mechanism, exacerbating wear on the mechanical structure. Based on this causal relationship model, reverse reasoning and joint probability calculation can trace the first abnormal parameter node from the complex appearance of simultaneous anomalies in multiple systems and locate it as the root cause of the coupled fault. Compared with existing technologies, this method transforms the source tracing process of coupled faults from subjective judgment relying on human experience to quantitative analysis based on probabilistic reasoning, significantly improving the accuracy and reliability of root cause location of coupled faults, making fault handling more thorough, and effectively preventing the recurrence of faults.

[0014] According to the intelligent fault diagnosis method for fast gates provided in this application, the fault levels include minor faults, moderate faults, and severe faults, wherein: Minor faults are hidden minor faults that do not affect the normal opening and closing of the gate, and only a warning is issued; A moderate fault is a fault that affects the gate's opening and closing efficiency but does not lose its core function. An audible and visual warning will be issued and handling suggestions will be pushed out. A severe fault is a fault or coupled fault that causes the gate to fail to open or close or lose its emergency flow interruption function. An emergency audible and visual warning is issued, and the emergency protection action of the linkage execution unit is triggered simultaneously. The emergency protection action includes: hydraulic system depressurization, oil pump shutdown, electrical control system power failure protection, and emergency gate closing or position holding.

[0015] This application classifies faults into three levels: minor, moderate, and severe, and matches different intensities of warning signals and handling actions to each level: minor faults only send warning prompts, without affecting normal operation and avoiding overreaction; moderate faults trigger audible and visual warnings and send handling suggestions to guide maintenance personnel to intervene in a timely manner; severe faults and coupled faults trigger emergency audible and visual warnings and simultaneously execute emergency protection actions such as hydraulic system depressurization, oil pump shutdown, electrical power failure protection, and emergency gate closing or position holding, achieving automatic safety protection for the equipment. This graded handling mechanism realizes differentiated management and control throughout the entire process of "minor fault prompts, moderate fault handling, and major fault emergency protection," which not only prevents minor faults from escalating into major accidents due to lack of warnings, but also prevents major faults from causing serious safety accidents such as gate opening and closing failures, unit runaway, and flooding of the plant due to untimely response. At the same time, the emergency protection actions are coordinated and linked with the original protection system of the fast gate, without conflict or interference, ensuring high safety.

[0016] According to the intelligent fault diagnosis method for fast gates provided in this application, the method further includes: After the diagnosis is completed, the diagnosed fault parameters, fault type, and handling results are stored in the preset fault feature database.

[0017] This application stores fault parameters, fault types, and handling results into a pre-defined fault feature database after each diagnosis. This allows the fault feature database to continuously accumulate new fault case data over time, expanding the coverage of the fault feature sample library and enriching the feature sample dimensions of latent and coupled faults. The continuous accumulation of database samples provides richer matching reference benchmarks for subsequent secondary feature value matching diagnosis. It also provides more validation and optimization data for the causal model in the tertiary coupled fault source tracing diagnosis, enabling the identification accuracy and source tracing accuracy of the diagnostic model to continuously improve with the accumulation of running data. It possesses adaptive and iterative evolution capabilities, becoming more accurate with use.

[0018] Secondly, this application provides a fast gate intelligent fault diagnosis device, comprising: The acquisition module is used to collect the operating characteristic parameters of three subsystems, which include the mechanical structure of the fast gate body, the hydraulic opening and closing actuator, and the electrical control system. The diagnostic module is used to perform first-level threshold comparison diagnosis, second-level feature value matching diagnosis, and third-level coupling logic tracing diagnosis sequentially based on the aforementioned operational feature parameters to obtain diagnostic results. The first-level threshold comparison diagnosis includes: comparing the operating characteristic parameters with the preset parameter safety threshold range; if the parameters exceed the safety threshold range, it is determined to be an obvious fault, and the fault type and fault location are output. The secondary feature value matching diagnosis includes: extracting fluctuation feature values ​​for operating feature parameters that have not triggered threshold abnormalities but have parameter fluctuations, constructing a fault feature map, matching the fault feature map with the latent fault feature samples in the preset fault feature database, and determining the latent fault when the similarity reaches the preset matching threshold, and completing the fault level classification based on the matching degree. The three-level coupled logic source tracing diagnosis includes: when at least two subsystems are detected to have abnormal operating characteristic parameters at the same time, and the abnormality is not eliminated after handling a single fault, a fault causal logic chain is constructed based on the linkage operation mechanism of the three subsystems, and the root cause node of the coupled fault is located through reverse reasoning and joint probability calculation. The generation module is used to generate corresponding fault handling strategies based on the diagnostic results.

[0019] Thirdly, this application provides an electronic device, comprising: at least one memory for storing a program; and at least one processor for executing the program stored in the memory, wherein when the program stored in the memory is executed, the processor is configured to execute the fast gate intelligent fault diagnosis method described in the first aspect or any possible implementation thereof.

[0020] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when run on a processor, causes the processor to execute the fast gate intelligent fault diagnosis method described in the first aspect or any possible implementation of the first aspect.

[0021] Fifthly, this application provides a computer program product that, when run on a processor, causes the processor to execute the fast gate intelligent fault diagnosis method described in the first aspect or any possible implementation of the first aspect.

[0022] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here.

[0023] Overall, the technical solutions conceived in this application have the following beneficial effects compared with the prior art: This application constructs a three-level progressive intelligent diagnostic model encompassing explicit, implicit, and coupled faults: "threshold triggering – feature matching – mechanism tracing." This changes the traditional diagnostic mode based on a single threshold judgment. The first-level threshold comparison diagnosis can quickly identify explicit faults with parameters exceeding limits, directly outputting the fault type and location with a fast response speed. The second-level feature matching diagnosis performs feature map matching on parameters that have not triggered the threshold but exhibit fluctuation trends, enabling the identification and classification of implicit faults before they occur, achieving early warning before faults occur and solving the problem of missed detection of implicit faults in existing technologies. The third-level coupled logic tracing diagnosis constructs a fault causal logic chain for the three subsystems, combining reverse reasoning and joint probability calculation, to accurately locate the root cause node of coupled faults in multiple systems, solving the fundamental deficiency in existing technologies that can only detect phenomena but cannot trace the source of coupled faults. At the same time, fault handling strategies are automatically generated based on the diagnostic results, forming an automated response closed loop from "fault identification" to "fault handling". This achieves an intelligent leap from "alarm after fault occurs" to "early warning before fault occurs and source tracing after fault occurs", improving the fault diagnosis accuracy of the fast gate and thus enhancing the operational reliability and emergency response capability of the fast gate. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart illustrating the intelligent fault diagnosis method for fast gates provided in the embodiments of this application; Figure 2 This is a schematic diagram of the structure of the intelligent fault diagnosis system for fast gates provided in the embodiments of this application; Figure 3 This is a schematic diagram of the structure of the intelligent fault diagnosis device for fast gates provided in the embodiments of this application; Figure 4 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0027] In this article, the term "and / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The symbol " / " in this article indicates that the related objects are in an "or" relationship; for example, A / B means A or B.

[0028] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0029] In the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more, for example, multiple processing units means two or more processing units, multiple elements means two or more elements, etc.

[0030] Next, combined Figures 1-2 The intelligent fault diagnosis method for fast gates provided in the embodiments of this application is introduced.

[0031] Figure 1 This is a flowchart illustrating the intelligent fault diagnosis method for fast-acting gates provided in this application embodiment, as shown below. Figure 1 As shown, the method includes the following steps: Step S1: Collect the operating characteristic parameters of the three subsystems, which include the mechanical structure of the fast gate body, the hydraulic opening and closing actuator, and the electrical control system. Optionally, sensor acquisition components can be deployed at high-fault characteristic points of the three major subsystems of the fast gate body: mechanical structure, hydraulic opening and closing actuator, and electrical control system, to simultaneously collect full-dimensional operational characteristic parameters.

[0032] Optionally, the operating characteristic parameters may include: mechanical characteristic parameters of the gate body, operating parameters of the hydraulic opening and closing mechanism, and operating parameters of the electrical control system.

[0033] Optionally, the multi-dimensional sensing acquisition unit synchronously acquires characteristic parameters of the three subsystems at a preset frequency. The acquired parameters are the core characteristic parameters of the fast gate operation, all of which are key parameters directly related to the fault. There is no redundant acquisition, which ensures diagnostic accuracy while reducing data processing pressure.

[0034] Optionally, all sensors are industrial-grade, waterproof, electromagnetic interference resistant, and resistant to mud and sand erosion, making them suitable for the harsh operating environment of high-speed gates. Step S2: Based on the running feature parameters, perform first-level threshold comparison diagnosis, second-level feature value matching diagnosis, and third-level coupling logic tracing diagnosis in sequence to obtain the diagnosis results; The first-level threshold comparison diagnosis includes: comparing the running characteristic parameters with the preset parameter safety threshold range; if the parameter exceeds the safety threshold range, it is determined to be an obvious fault, and the fault type and fault location are output. The secondary feature value matching diagnosis includes: extracting the fluctuation feature values ​​of the operating feature parameters that have not triggered threshold abnormalities but have parameter fluctuations, constructing a fault feature map, matching the fault feature map with the latent fault feature samples in the preset fault feature database, and determining the latent fault when the similarity reaches the preset matching threshold, and completing the fault level classification based on the matching degree. The three-level coupled logic source tracing diagnosis includes: when at least two subsystems are detected to have abnormal operating characteristic parameters at the same time, and the abnormality is not eliminated after handling a single fault, a fault causal logic chain is constructed based on the linkage operation mechanism of the three subsystems, and the root cause node of the coupled fault is located through reverse reasoning and joint probability calculation. The core technical concept of this application lies in constructing a three-tiered progressive intelligent diagnostic model: "threshold triggering – feature matching – mechanism tracing." This model changes the traditional simple mode of single threshold judgment, and through hierarchical diagnostic logic, achieves full-type fault coverage, from rapid identification of explicit faults to intelligent prediction of implicit faults, and then to in-depth tracing of coupled faults. The first level achieves second-level response to explicit faults based on dynamic thresholds; the second level achieves early warning of implicit faults based on feature map matching; and the third level achieves root cause localization of coupled faults based on causal reasoning, forming a complete intelligent diagnostic closed loop.

[0035] Optionally, a three-level progressive diagnostic model covering explicit faults, implicit faults, and coupled faults can be constructed. This model sequentially performs first-level threshold comparison diagnosis, second-level feature value matching diagnosis, and third-level coupled logic tracing diagnosis to achieve intelligent identification and localization of all types of faults. The first-level threshold comparison diagnosis is a rapid identification of explicit faults based on dynamic thresholds. It compares each operating characteristic parameter with the preset dynamic safety threshold range. If the parameter exceeds the safety threshold range, it is directly determined as an explicit single fault, and the fault type and fault location are output, achieving a response time of seconds.

[0036] Optionally, the dynamic threshold can be calibrated based on the design rated parameters of the fast gate, industry operation and maintenance specifications, and actual engineering operation data, and can be adaptively adjusted according to the service life of the gate, operating conditions, and environmental conditions.

[0037] The secondary feature value matching diagnosis is a latent fault intelligent prediction based on feature map matching. For operating feature parameters that have not triggered threshold anomalies but have parameter fluctuations, the fluctuation feature values ​​are extracted to construct a fault feature map. This map is then intelligently matched with latent fault feature samples in a preset fault feature database. When the matching similarity reaches a preset matching threshold, it is determined to be a latent fault. Based on the matching degree, the fault level is determined (mild / moderate / severe), thus achieving early warning before the fault occurs.

[0038] Preferably, the trend feature values ​​of the operating feature parameters over a period of time (such as the average daily growth rate, fluctuation variance, etc.) are extracted and intelligently matched with the latent fault feature samples in the preset fault feature database.

[0039] Alternatively, the similarity matching algorithm can employ Euclidean distance or cosine similarity algorithm.

[0040] Optionally, the preset matching threshold can be 95%. When the matching similarity is ≥95%, it is determined to be a hidden fault.

[0041] For example, the system detected a slow upward trend in the "water-stopping leakage characteristic index". The system extracted the trend characteristic value of this parameter over the past week and matched it with samples in the fault characteristic database. It found that the similarity with the sample "minor leakage in the early stage of aging of water-stopping rubber" reached 96%. Based on this, the system determined that a hidden fault had occurred and classified it as "minor".

[0042] Optionally, the fault feature database is a multi-dimensional feature vector space containing feature parameter samples of all explicit and implicit faults in the three subsystems of the fast gate. It integrates historical fault data, simulation data, industry standards and operation and maintenance experience maps, and supports deep learning algorithms to dynamically optimize feature weights.

[0043] The three-level coupled logic source tracing diagnosis is a deep source tracing of coupled faults based on causal reasoning. When at least two subsystems are detected to have abnormal operating characteristic parameters at the same time, and the abnormality is not eliminated after handling a single fault, the system automatically triggers the three-level diagnosis. Based on the linkage operation mechanism of the three subsystems, a fault causal logic chain is constructed, and the root node of the coupled fault is located through reverse reasoning and joint probability calculation.

[0044] For example, the system simultaneously detects an abnormally large increase in the pressure difference between the inlet and outlet of the hydraulic cylinder (hydraulic parameter) and a gate travel speed lower than the set value (electronic control parameter), and the two occur in a related manner. The algorithm traces back to the first parameter that causes the anomaly and finds that the decrease in travel speed begins several seconds earlier than the increase in pressure difference. Through reverse reasoning and joint probability calculation, the root cause of the fault is located as mechanical jamming caused by foreign object accumulation or local deformation in the gate slot or guide rail, while the increase in hydraulic pressure difference is a secondary phenomenon.

[0045] Level 1 diagnosis is a basic screening that quickly identifies easily detectable obvious faults with a fast response; Level 2 diagnosis is a deep identification that performs feature matching for hidden faults to achieve early warning; Level 3 diagnosis is root cause tracing that establishes a causal logic chain for coupled faults to accurately locate the root cause of the fault, solving the pain point that existing technologies cannot identify coupled faults.

[0046] Step S3: Generate the corresponding fault handling strategy based on the diagnostic results.

[0047] Optionally, based on the diagnostic results, a corresponding fault handling strategy is generated, and a graded audible and visual early warning signal is issued. For severe faults and coupled faults, the emergency protection action of the fast gate is triggered simultaneously.

[0048] The intelligent fault diagnosis method for fast gates provided in this application constructs a three-level progressive intelligent diagnostic model covering explicit faults, implicit faults, and coupled faults: "threshold triggering – feature matching – mechanism tracing." This changes the traditional single-threshold judgment diagnostic mode. The first-level threshold comparison diagnosis can quickly identify explicit faults with parameters exceeding limits, directly outputting the fault type and location with a fast response speed. The second-level feature matching diagnosis performs feature map matching on parameters that have not triggered the threshold but show fluctuation trends, enabling the identification and classification of implicit faults before the fault occurs, achieving early warning before the fault occurs and solving the problem of missed detection of implicit faults in existing technologies. The third-level coupled logic tracing diagnosis constructs a fault causal logic chain of three subsystems, combined with reverse reasoning and joint probability calculation, which can accurately locate the root node of coupled faults in multiple systems, solving the fundamental defect of existing technologies that can only detect phenomena but cannot trace the source of coupled faults. At the same time, fault handling strategies are automatically generated based on the diagnostic results, forming an automated response closed loop from "fault identification" to "fault handling". This achieves an intelligent leap from "alarm after fault occurs" to "early warning before fault occurs and source tracing after fault occurs", improving the fault diagnosis accuracy of the fast gate and thus enhancing the operational reliability and emergency response capability of the fast gate.

[0049] In some embodiments, step S1 specifically includes: The system collects data on the following parameters: door leaf vibration amplitude and frequency, frictional resistance between guide rail and slider, leakage of water-stopping device, door leaf verticality deviation, door groove siltation thickness, rotational torque of lifting lug shaft, hydraulic system oil pressure, cylinder inlet and outlet pressure difference, hydraulic oil temperature, hydraulic oil cleanliness, accumulator nitrogen pressure, oil pump motor speed and current, hydraulic pipeline flow rate, PLC input and output signal amplitude, stroke sensor feedback value, limit switch on / off status, inverter operating current and voltage, UPS backup power supply voltage, and electromagnetic interference intensity.

[0050] This parameter list covers the core operational indicators of high-incidence characteristic points of rapid gate failures—mechanical parameters including gate leaf vibration, guide rail friction resistance, and water leakage, reflecting the structural health status; hydraulic parameters including oil pressure, cylinder inlet and outlet pressure difference, and accumulator nitrogen pressure, reflecting the hydraulic system's operating status; and electrical parameters including PLC signals, stroke feedback, and inverter operating status, reflecting the control system's working status. These parameters are all key characteristic parameters directly related to rapid gate failures. The absence of redundant data collection ensures both the comprehensiveness and accuracy of the data required for diagnosis while reducing data processing pressure. This allows the three-level progressive diagnostic model to perform fault identification, prediction, and tracing based on sufficient and accurate multi-dimensional data, thereby effectively improving the accuracy of fault identification and reducing the missed and false positive rates.

[0051] In some embodiments, the method further includes: The operating characteristic parameters are filtered for noise reduction, outlier removal, and normalization.

[0052] Optionally, the operating characteristic parameters can be filtered and denoised first. A Kalman filter algorithm can be used to remove high-frequency spikes in the vibration signal caused by water flow turbulence.

[0053] Optionally, after filtering and noise reduction, outlier values ​​are removed from the operating characteristic parameters, and obviously erroneous values ​​are removed based on the physical limits of the sensor.

[0054] Optionally, a normalization process is performed at the end to map the values ​​of different dimensions such as pressure, flow rate, and current to the interval [0, 1].

[0055] Through the above preprocessing, invalid data caused by external factors such as water flow impact and electromagnetic interference are effectively eliminated, and the validity rate of the preprocessed parameters is ≥99%.

[0056] In some embodiments, step S2, which constructs a fault causal logic chain based on the linkage mechanism of the three subsystems, locates the root cause node of the coupled fault through reverse reasoning and joint probability calculation, including: Step S21: Based on the operating mechanism of the fast gate, a causal relationship model integrating Bayesian network and fault tree is constructed. The causal relationship model is used to characterize the linkage relationship of the three subsystems. Step S22: Based on the causal relationship model, through reverse reasoning and joint probability calculation, trace the fault point corresponding to the first abnormal parameter, which is the root node of the coupled fault.

[0057] Optionally, a coupled fault tracing algorithm based on causal reasoning is used to locate the root cause of coupled faults. The core logic is as follows: a causal relationship model integrating Bayesian network and fault tree is constructed based on the operating mechanism of the fast gate to clarify the linkage relationship of the three subsystems. Mechanical faults in the gate body will lead to increased load on the hydraulic opening and closing mechanism, causing abnormal hydraulic parameters; faults in the hydraulic opening and closing mechanism will lead to distortion of the feedback signal of the electrical control system, causing abnormal electrical parameters; faults in the electrical control system will lead to malfunction of the hydraulic mechanism, thereby aggravating the wear and deformation of the mechanical structure. A causal logic chain is established through this linkage relationship. By using reverse reasoning and joint probability calculation, the fault point corresponding to the first abnormal parameter is located, which is the root cause of the coupled fault. This solves the technical problem that existing technologies cannot identify the root cause of coupled faults.

[0058] In some embodiments, the fault levels include minor fault, moderate fault, and severe fault, wherein: Minor faults are hidden minor faults that do not affect the normal opening and closing of the gate, and only a warning is issued; A moderate fault is a fault that affects the gate's opening and closing efficiency but does not lose its core function. An audible and visual warning will be issued and handling suggestions will be pushed out. A severe fault is a fault or coupled fault that causes the gate to fail to open or close or lose its emergency flow interruption function. An emergency audible and visual warning is issued, and the emergency protection action of the linkage execution unit is triggered simultaneously. The emergency protection action includes: hydraulic system depressurization, oil pump shutdown, electrical control system power failure protection, and emergency gate closing or position holding.

[0059] Optionally, the design of graded early warning and coordinated response enables full-process control of minor fault indication, moderate fault handling, and severe fault emergency protection, preventing minor faults from escalating into major accidents. The emergency protection action is linked with the original protection system of the fast gate without conflict or interference, ensuring high safety.

[0060] Optionally, when issuing graded audible and visual warning signals, minor faults (such as aging of the sealing rubber) will only push a yellow warning message to the human-machine interaction unit; moderate faults (such as internal leakage of the hydraulic system) will trigger a slow flashing of the on-site audible and visual alarm and push handling suggestions; severe faults (such as oil pipe rupture or the root cause of coupling faults) will trigger a red emergency audible and visual alarm and send instructions to the hydraulic control cabinet through the linkage execution unit to perform emergency protection actions such as emergency shutdown of the oil pump, system depressurization, and triggering of the backup door closing mechanism.

[0061] In some embodiments, the method further includes: After the diagnosis is completed, the diagnosed fault parameters, fault type, and handling results are stored in the preset fault feature database.

[0062] Optionally, all raw data, feature values, diagnostic process, results, and subsequent confirmations by maintenance personnel are encrypted and packaged. The embedded industrial control computer stores short-term data and periodically synchronizes the data packets to the cloud server. The cloud server uses new fault case data to expand the fault feature database and uses deep learning algorithms (preferably gradient descent, backpropagation, etc.) to fine-tune the feature matching weight parameters and optimize the causal model of the coupled fault tracing logic algorithm. The updated model parameters can be distributed to the edge industrial control computer to achieve continuous self-learning and improvement of diagnostic accuracy.

[0063] By continuously accumulating fault data, optimizing the fault feature database and diagnostic model, the diagnostic accuracy can be continuously improved over time, exhibiting adaptability and iterativeness.

[0064] Figure 2 This is a schematic diagram of the structure of the intelligent fault diagnosis system for fast-acting gates provided in the embodiments of this application, as shown below. Figure 2 As shown, in one embodiment of this application, a smart fault diagnosis system for fast-acting gates is provided. This system is a hardware device, and the functions of each unit work together to form a complete diagnostic closed loop, including: The multi-dimensional sensing and acquisition unit is used to collect all-dimensional operating characteristic parameters of the fast gate body, hydraulic opening and closing mechanism, and electrical control system. It includes mechanical sensor groups, hydraulic sensor groups, and electrical sensor groups. All sensor groups are waterproof, electromagnetic interference resistant, and resistant to mud and sand erosion industrial-grade sensors, which are deployed at high-fault characteristic points. The data transmission unit consists of a wired fiber optic transmission module and a wireless 4G / 5G backup transmission module, used to transmit parameter data from the multi-dimensional sensing and acquisition unit to the core diagnostic processing unit in real time, and has the functions of preventing data loss and resuming interrupted transmission. The core diagnostic processing unit is a dual-processing architecture consisting of an embedded industrial computer and a cloud server. It has a built-in fault feature database, threshold judgment model, coupled fault tracing logic algorithm and parameter preprocessing program. It is the core control unit of the entire system and is used to complete parameter processing, hierarchical diagnosis, fault location and strategy generation. The fault early warning unit includes an on-site audible and visual early warning module, a remote SMS and platform early warning module, which are used to issue corresponding graded early warning signals according to the fault level; The linkage execution unit is electrically connected to the hydraulic control cabinet and electrical PLC control cabinet of the fast gate. It is used to receive instructions from the core diagnostic processing unit and trigger corresponding emergency protection actions and fault handling actions. The human-machine interaction unit includes a field touch screen and a remote monitoring terminal, which is used to display the operating parameters, fault diagnosis results and handling strategies of the fast gate in real time, and supports manual intervention and manual calibration of parameter thresholds; The power supply unit, including the mains power supply module and the UPS uninterruptible backup power supply module, provides a stable power supply for the entire system and ensures the normal operation of diagnostic functions under power outage conditions.

[0065] Among them, the multi-dimensional sensing and acquisition unit is the sensing end, the data transmission unit is the transmission end, the core diagnostic processing unit is the brain end, the fault early warning unit is the early warning end, the linkage execution unit is the execution end, the human-machine interaction unit is the interaction end, and the power supply unit is the protection end. Each unit performs its own function and none can be missing, realizing full-process automation from parameter acquisition to fault handling.

[0066] Optionally, in the dual-processing architecture of the core diagnostic processing unit, the embedded industrial control computer completes real-time on-site diagnosis and rapid handling, while the cloud server completes fault data storage, self-learning evolution of the diagnostic model, and analysis of historical fault data. The two communicate bidirectionally and achieve continuous improvement in diagnostic accuracy through a collaborative mechanism of cloud training and edge inference.

[0067] Optionally, the system is compatible with all specifications of hydraulic and winch-type fast gates. The placement of the sensor array can be flexibly adjusted according to the water head, size, and opening / closing mechanism type of the fast gate, thus possessing versatility and adaptability.

[0068] In one embodiment of this application, early warning of latent faults includes the following steps: 1a. Synchronous Acquisition of Feature Parameters: During continuous system operation, the multi-dimensional sensing acquisition unit synchronously acquires feature parameters of the three subsystems at a preset frequency. In this embodiment, as a preferred option, the sampling frequency is set to 10Hz during normal operation and automatically switches to 100Hz high-frequency sampling during the opening and closing process. Operating parameters of the hydraulic opening and closing mechanism include: hydraulic system oil pressure, cylinder inlet and outlet pressure difference, hydraulic oil temperature, hydraulic oil cleanliness, and accumulator nitrogen pressure, etc.

[0069] 2a. Parameter Preprocessing: The core diagnostic processing unit processes the above raw data. First, it performs filtering and noise reduction (using Kalman filtering to remove high-frequency spikes in the vibration signal caused by water flow turbulence); then it performs outlier removal (based on the physical limits of the sensor, it removes obviously erroneous values, such as pressure values ​​exceeding twice the system's rated value); finally, it performs normalization processing, mapping the values ​​of different dimensions such as pressure, flow rate, and current to the [0, 1] interval.

[0070] 3a. Secondary Feature Value Matching Diagnosis: The system detects a slow downward trend in the "accumulator nitrogen pressure" parameter, but it has not yet triggered a threshold alarm. The system extracts the trend feature values ​​of this parameter over the past 30 days (daily average decrease rate 0.3%, fluctuation variance 0.02) to construct a fault feature map. In this embodiment, the Euclidean distance algorithm is preferably used for similarity calculation. The feature map is then intelligently matched with latent fault feature samples in a pre-set fault feature database. The matching calculation shows that the similarity between this feature and the "accumulator bladder micro-leakage" sample reaches 96.5%, and the rate of decrease matches early leakage characteristics. Based on this, the system determines that a latent fault has occurred and classifies it as "mild" according to the matching degree.

[0071] 4a. Fault handling and early warning: The fault early warning unit pushes a yellow text warning message on the monitoring screen of the human-machine interaction unit: "Attention: The nitrogen pressure of the accumulator of No. 1 fast gate is slowly decreasing, suspected to be a micro-leakage of the bladder. It is recommended to arrange maintenance and inspection." It does not trigger the audible and visual alarm.

[0072] 5a. Data Update and Self-Learning: The diagnostic data was synchronized to the cloud server to optimize the feature weight of "accumulator micro-leakage" in the fault feature database and improve the accuracy of subsequent diagnosis.

[0073] In one embodiment of this application, taking a hoist-type fast gate in a pumping station as an example, a deep source tracing of coupling faults includes the following steps: 1b. Synchronous acquisition of characteristic parameters: The system synchronously acquires mechanical characteristic parameters (door leaf vibration amplitude, guide rail friction resistance), hydraulic parameters (oil pressure, flow rate), and electrical parameters (motor current, stroke feedback).

[0074] 2b. Parameter preprocessing: Preprocess the raw data.

[0075] 3b. Level 1 Threshold Comparison Diagnosis: The system detects an abnormal increase in the pressure difference between the inlet and outlet of the hydraulic cylinder (exceeding the threshold by 20%), and at the same time, the motor current increases (exceeding the threshold by 15%), and reports two explicit faults: "high hydraulic resistance" and "motor overload".

[0076] 4b. Single fault handling: After the maintenance personnel checked the hydraulic system according to the prompts and replaced the hydraulic oil filter element, the abnormality still existed.

[0077] 5b. Three-level Coupled Logic Source Tracing Diagnosis: The system automatically triggers three-level diagnosis. A coupled fault source tracing algorithm based on causal reasoning is initiated, constructing a fault causal logic chain: Increased motor current → may be due to increased mechanical load → Increased load leads to increased effort in cylinder operation and increased inlet / outlet pressure difference → Increased mechanical load may originate from door jamming. The algorithm traces the timing of the first abnormal parameter, finding that the abnormal increase in "door leaf vibration amplitude" started several minutes earlier than the increase in pressure difference and current. Through reverse reasoning and joint probability calculation, the system locates the root cause of the fault as: mechanical jamming caused by foreign object accumulation in the door slot, while the increased hydraulic pressure difference and increased motor current are secondary phenomena.

[0078] 6b. Fault Handling and Early Warning: The system triggers a red emergency audible and visual warning and pushes the following message to the human-machine interface unit: "Root cause of the fault: Mechanical jamming caused by blockage in the gate slot; it is recommended to clean the gate slot immediately; Note: The hydraulic system and motor are overloaded, it is recommended to check them simultaneously." Simultaneously, the system sends a command to the electrical control cabinet via the linkage execution unit to suspend gate operation and prevent equipment damage.

[0079] 7b. Data Update and Self-Learning: The data package of this coupled fault case is synchronized to the cloud server to optimize the causal model of the coupled fault tracing algorithm and improve the tracing accuracy of similar faults in the future.

[0080] The intelligent fault diagnosis device for fast gates provided in this application is described below. The intelligent fault diagnosis device for fast gates described below can be referred to in correspondence with the intelligent fault diagnosis method for fast gates described above.

[0081] Figure 3 This is a schematic diagram of the structure of a fast-acting gate intelligent fault diagnosis device provided in an embodiment of this application, as shown below. Figure 3 As shown, the device 300 includes: The acquisition module 310 is used to acquire the operating characteristic parameters of three subsystems, including the mechanical structure of the fast gate body, the hydraulic opening and closing actuator, and the electrical control system. The diagnostic module 320 is used to sequentially perform first-level threshold comparison diagnosis, second-level feature value matching diagnosis, and third-level coupled logic tracing diagnosis based on the running feature parameters to obtain the diagnostic results. The first-level threshold comparison diagnosis includes: comparing the running characteristic parameters with the preset parameter safety threshold range; if the parameter exceeds the safety threshold range, it is determined to be an obvious fault, and the fault type and fault location are output. The secondary feature value matching diagnosis includes: extracting the fluctuation feature values ​​of the operating feature parameters that have not triggered threshold abnormalities but have parameter fluctuations, constructing a fault feature map, matching the fault feature map with the latent fault feature samples in the preset fault feature database, and determining the latent fault when the similarity reaches the preset matching threshold, and completing the fault level classification based on the matching degree. The three-level coupled logic source tracing diagnosis includes: when at least two subsystems are detected to have abnormal operating characteristic parameters at the same time, and the abnormality is not eliminated after handling a single fault, a fault causal logic chain is constructed based on the linkage operation mechanism of the three subsystems, and the root cause node of the coupled fault is located through reverse reasoning and joint probability calculation. The generation module 330 is used to generate corresponding fault handling strategies based on the diagnostic results.

[0082] It should be understood that the above-described device is used to execute the methods in the above embodiments. The implementation principle and technical effect of the corresponding program modules in the device are similar to those described in the above methods. The working process of the device can be referred to the corresponding process in the above methods, and will not be repeated here.

[0083] Based on the methods in the above embodiments, Figure 4 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 4 As shown in the illustration, this application provides an electronic device that may include a processor 410, a communication interface 420, a memory 430, and a communication bus 440. The processor 410, communication interface 420, and memory 430 communicate with each other via the communication bus 440. The processor 410 can call logical instructions stored in the memory 430 to execute the fast gate intelligent fault diagnosis method described in the above embodiment.

[0084] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the intelligent fault diagnosis method for fast gates described in the various embodiments of this application.

[0085] Based on the methods in the above embodiments, this application provides a computer-readable storage medium storing a computer program. When the computer program runs on a processor, it causes the processor to execute the fast gate intelligent fault diagnosis method in the above embodiments.

[0086] Based on the methods in the above embodiments, this application provides a computer program product that, when run on a processor, causes the processor to execute the fast gate intelligent fault diagnosis method in the above embodiments.

[0087] It is understood that the processor in the embodiments of this application can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor can be a microprocessor or any conventional processor.

[0088] The method steps in this application embodiment can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, portable hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can reside in an ASIC.

[0089] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0090] It is understood that the various numerical designations used in the embodiments of this application are merely for the convenience of description and are not intended to limit the scope of the embodiments of this application.

[0091] Those skilled in the art will readily understand that the above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for intelligent fault diagnosis of a fast-acting gate, characterized in that, include: The operational characteristic parameters of three subsystems are collected. The three subsystems include the mechanical structure of the fast gate body, the hydraulic opening and closing actuator, and the electrical control system. Based on the aforementioned operational characteristic parameters, the first-level threshold comparison diagnosis, the second-level feature value matching diagnosis, and the third-level coupling logic tracing diagnosis are executed sequentially to obtain the diagnostic results. The first-level threshold comparison diagnosis includes: comparing the operating characteristic parameters with the preset parameter safety threshold range; if the parameters exceed the safety threshold range, it is determined to be an obvious fault, and the fault type and fault location are output. The secondary feature value matching diagnosis includes: extracting fluctuation feature values ​​for operating feature parameters that have not triggered threshold abnormalities but have parameter fluctuations, constructing a fault feature map, matching the fault feature map with the latent fault feature samples in the preset fault feature database, and determining the latent fault when the similarity reaches the preset matching threshold, and completing the fault level classification based on the matching degree. The three-level coupled logic source tracing diagnosis includes: when at least two subsystems are detected to have abnormal operating characteristic parameters at the same time, and the abnormality is not eliminated after handling a single fault, a fault causal logic chain is constructed based on the linkage operation mechanism of the three subsystems, and the root cause node of the coupled fault is located through reverse reasoning and joint probability calculation. Based on the diagnostic results, a corresponding fault handling strategy is generated.

2. The intelligent fault diagnosis method for fast-acting gates according to claim 1, characterized in that, The collected operational characteristic parameters of the three subsystems include: The system collects data on the following parameters: door leaf vibration amplitude and frequency, frictional resistance between guide rail and slider, leakage of water-stopping device, door leaf verticality deviation, door groove siltation thickness, rotational torque of lifting lug shaft, hydraulic system oil pressure, cylinder inlet and outlet pressure difference, hydraulic oil temperature, hydraulic oil cleanliness, accumulator nitrogen pressure, oil pump motor speed and current, hydraulic pipeline flow rate, PLC input and output signal amplitude, stroke sensor feedback value, limit switch on / off status, inverter operating current and voltage, UPS backup power supply voltage, and electromagnetic interference intensity.

3. The intelligent fault diagnosis method for fast-acting gates according to claim 1, characterized in that, The method further includes: The operational characteristic parameters are subjected to filtering and noise reduction, outlier removal, and normalization.

4. The intelligent fault diagnosis method for fast-acting gates according to claim 1, characterized in that, The fault causal logic chain is constructed based on the linkage operation mechanism of the three subsystems. Through reverse reasoning and joint probability calculation, the root cause node of the coupled fault is located, including: Based on the operating mechanism of the fast gate, a causal relationship model integrating Bayesian network and fault tree is constructed. The causal relationship model is used to characterize the linkage relationship of the three subsystems. Based on the causal relationship model, by reverse reasoning and joint probability calculation, the fault point corresponding to the first abnormal parameter is traced, which is the root node of the coupled fault.

5. The intelligent fault diagnosis method for fast-acting gates according to claim 1, characterized in that, The fault levels include minor faults, moderate faults, and severe faults, wherein: Minor faults are hidden minor faults that do not affect the normal opening and closing of the gate, and only a warning is issued; A moderate fault is a fault that affects the gate's opening and closing efficiency but does not lose its core function. An audible and visual warning will be issued and handling suggestions will be pushed out. A severe fault is a fault or coupled fault that causes the gate to fail to open or close or lose its emergency flow interruption function. An emergency audible and visual warning is issued, and the emergency protection action of the linkage execution unit is triggered simultaneously. The emergency protection action includes: hydraulic system depressurization, oil pump shutdown, electrical control system power failure protection, and emergency gate closing or position holding.

6. The intelligent fault diagnosis method for fast-acting gates according to claim 1, characterized in that, The method further includes: After the diagnosis is completed, the diagnosed fault parameters, fault type, and handling results are stored in the preset fault feature database.

7. A fast-acting intelligent fault diagnosis device for gates, characterized in that, include: The acquisition module is used to collect the operating characteristic parameters of three subsystems, which include the mechanical structure of the fast gate body, the hydraulic opening and closing actuator, and the electrical control system. The diagnostic module is used to perform first-level threshold comparison diagnosis, second-level feature value matching diagnosis, and third-level coupling logic tracing diagnosis sequentially based on the aforementioned operational feature parameters to obtain diagnostic results. The first-level threshold comparison diagnosis includes: comparing the operating characteristic parameters with the preset parameter safety threshold range; if the parameters exceed the safety threshold range, it is determined to be an obvious fault, and the fault type and fault location are output. The secondary feature value matching diagnosis includes: extracting fluctuation feature values ​​for operating feature parameters that have not triggered threshold abnormalities but have parameter fluctuations, constructing a fault feature map, matching the fault feature map with the latent fault feature samples in the preset fault feature database, and determining the latent fault when the similarity reaches the preset matching threshold, and completing the fault level classification based on the matching degree. The three-level coupled logic source tracing diagnosis includes: when at least two subsystems are detected to have abnormal operating characteristic parameters at the same time, and the abnormality is not eliminated after handling a single fault, a fault causal logic chain is constructed based on the linkage operation mechanism of the three subsystems, and the root cause node of the coupled fault is located through reverse reasoning and joint probability calculation. The generation module is used to generate corresponding fault handling strategies based on the diagnostic results.

8. An electronic device, characterized in that, include: At least one memory for storing computer programs; At least one processor is configured to execute a program stored in the memory, wherein when the program stored in the memory is executed, the processor is configured to perform the intelligent fault diagnosis method for fast gates as described in any one of claims 1-6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is run on the processor, the processor performs the fast gate intelligent fault diagnosis method as described in any one of claims 1-6.

10. A computer program product, characterized in that, When the computer program product is run on the processor, the processor performs the fast gate intelligent fault diagnosis method as described in any one of claims 1-6.

Images