Booster station equipment fault identification system and method based on multi-mode perception

Abstract

The invention relates to the technical field of power equipment detection, and particularly provides a booster station equipment fault identification system and method based on multi-mode perception, and the system comprises a first identification module which is used for obtaining an infrared image and an ultraviolet image of target equipment, and carrying out the recognition of a fault of the target equipment based on the temperature information in the infrared image and an ultraviolet radiation signal in the ultraviolet image; identifying a local overheat point and a discharge point of the target equipment; the second identification module is used for acquiring dial monitoring data of an instrument associated with the target equipment and performing registration based on the dial standard data so as to evaluate the running state of the target equipment; and the scheduling module is electrically connected with the first identification module and the second identification module and is used for monitoring and scheduling the first identification module and the second identification module based on the meteorological data received by the meteorological module so as to start the corresponding identification modules for different monitoring time periods. According to the invention, the monitoring time periods of the identification modules in different modes are correspondingly regulated and controlled based on the meteorological data, and the flexibility in the equipment monitoring period is improved.

Description

Technical Field

[0001] This application relates to the field of power equipment testing technology, and in particular to a fault identification system and method for booster station equipment based on multimodal perception. Background Technology

[0002] Condition monitoring and fault detection of substation equipment are essential for ensuring the long-term reliable operation of the substation power system. Typical fault types in substation equipment include overheating, open flame, discharge, water and oil leakage, and hardware defects. Among these, overheating and discharge faults often have a potentially significant impact on equipment safety and are often hidden, making equipment inspection difficult. Under the influence of factors such as electric fields, heat, chemicals, mechanical forces, and atmospheric conditions, the insulation performance of equipment within the substation is prone to deterioration, eventually accumulating into insulation defects and faults. When equipment is in various adverse conditions such as poor contact, short circuits, or contaminant coverage, different components, both external and internal to the electrical equipment, may experience different thermal effects exceeding design standards. To ensure good equipment operating conditions, engineering technicians need to frequently monitor the operating electrical equipment and transmission lines to promptly detect abnormal conditions and eliminate potential safety hazards.

[0003] Currently, with the widespread adoption of computer-based testing technology, the inspection of substation equipment and the recording of instrument data are gradually moving towards automation. This has significantly reduced the workload of manual inspections in equipment operation status monitoring and fault identification, while simultaneously improving the stability and safety of the power system. Consequently, a large number of condition monitoring devices have been put into use in the power system, resulting in an explosive increase in the volume of monitoring data on equipment and line status. At the same time, with increasingly stringent safety requirements, minimizing the incidence of insulation faults is a pressing issue that needs to be addressed within the substation system. Summary of the Invention

[0004] To address the aforementioned issues, this application provides a multimodal sensing-based fault identification system and method for booster station equipment. By using multimodal sensing to monitor equipment status under different meteorological conditions, the system improves the flexibility during monitoring.

[0005] To achieve the objectives of this application, the following technical solution is provided: In a first aspect, this application provides a fault identification system for booster station equipment based on multimodal perception, comprising: a first identification module, a second identification module, and a scheduling module, wherein: The first identification module includes an infrared unit and an ultraviolet unit, used to acquire infrared and ultraviolet images of the target device, and identify local hot spots and discharge points of the target device based on temperature information in the infrared image and ultraviolet radiation signals in the ultraviolet image; The second identification module is used to acquire the dial monitoring data of the associated instrument of the target device, and to register the dial monitoring data with the dial standard data to evaluate the operating status of the target device; The scheduling module is electrically connected to the first identification module and the second identification module respectively, and is used to monitor and schedule the first identification module and the second identification module based on the meteorological data received by the meteorological module, so as to activate the corresponding identification module for different monitoring periods.

[0006] In one possible implementation, the scheduling module deploys an adaptive recognition model. The construction process of the adaptive recognition model includes: acquiring meteorological data and monitoring data for each device within the substation; constructing a monitoring dataset containing data under different weather conditions, including the correspondence between each monitoring data point and the weather conditions; the monitoring data being device status data acquired at key nodes of the substation equipment using a first recognition module and a second recognition module; constructing the adaptive recognition model using a neural network model, with model input variables including temperature, light intensity, hotspot data, discharge point data, and dial monitoring data from associated instruments for different time periods; training the adaptive recognition model using the training set of the monitoring dataset, while simultaneously adjusting the weights and biases using an optimization algorithm; evaluating the performance of the adaptive recognition model using a validation set; and predicting the monitoring periods of the first and second recognition modules based on the adaptive recognition model according to the current weather conditions.

[0007] In one possible implementation, after the adaptive identification module determines the first monitoring period and the second monitoring period corresponding to the first identification module and the second identification module respectively based on the current weather conditions, the scheduling module controls the first identification module and the second identification module to acquire equipment status data during the first monitoring period and the second monitoring period respectively, and transmit the data to the scheduling module; wherein the first monitoring period and the monitoring period do not overlap or partially overlap.

[0008] In one possible implementation, the second identification module is further configured to: automatically acquire dial monitoring data of the associated instrument of the target device when the first identification module detects that the target device has the local overheating point or the discharge point, and register the dial monitoring data with the dial standard data to verify and evaluate the actual operating status of the target device.

[0009] In one possible implementation, the second identification module is an image acquisition device, which is used to capture a visible light image of the associated instrument and extract the dial monitoring data from the visible light image; wherein, computer vision technology is used to extract the dial reading detection area and the reading of the dial reading detection area in the visible light image; the associated instrument includes pointer-type instruments and digital instruments.

[0010] In one possible implementation, the scheduling module can store, analyze, and generate data reports based on real-time monitoring and scheduling data, while providing remote monitoring and alarm functions for equipment managers.

[0011] In one possible implementation, the system further includes an ultrasonic sensor detection module; the ultrasonic sensor detection module is used to monitor abnormal noises of the target device in real time during operation.

[0012] In one possible implementation, the scheduling module is further configured to: acquire short-term weather forecast data through a meteorological data interface; analyze the weather forecast data to predict meteorological changes in the next few hours; the meteorological changes data include at least: temperature, light intensity, humidity, and dust concentration.

[0013] Secondly, this application provides a multimodal sensing-based method for identifying faults in booster station equipment, applied to the aforementioned multimodal sensing-based booster station equipment fault identification system, comprising: Meteorological data is received based on the meteorological module; The scheduling module determines the identification module corresponding to the current weather conditions based on the meteorological data; the identification module includes a first identification module and a second identification module; the first identification module is used to acquire infrared and ultraviolet images of the target device in real time, and identify local hot spots and discharge points of the target device based on the temperature information in the infrared image and the ultraviolet radiation signal in the ultraviolet image; the second identification module is used to acquire the dial monitoring data of the associated instruments of the target device, and register the dial monitoring data with the dial standard data to realize the operating status assessment of the target device; Fault analysis is performed based on the aforementioned operational status assessment.

[0014] In one possible implementation, the method further includes: when the first identification module detects that the target device has the discharge point of the local overhot spot, automatically acquiring the dial monitoring data of the associated instrument of the target device, and registering the dial monitoring data with the dial standard data to verify and evaluate the actual operating status of the target device.

[0015] Thirdly, this application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the step-up substation equipment anomaly identification method as described above.

[0016] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the step-up substation equipment anomaly identification method as described above.

[0017] The multimodal sensing-based fault identification system and method for booster station equipment provided in this application enables targeted monitoring of booster station equipment by adjusting the monitoring periods of different modal identification modules according to meteorological data, thereby improving the flexibility of equipment monitoring and greatly reducing the data volume. Attached Figure Description

[0018] The accompanying drawings are provided to further understand this application and form part of the specification. They are used together with the embodiments of this application to explain this application and do not constitute a limitation thereof. Figure 1 A schematic diagram of a multimodal sensing-based fault identification system for booster station equipment provided in an embodiment of this application; Figure 2 A schematic diagram of a multimodal sensing-based fault identification system for booster station equipment provided in this application embodiment; Figure 3 A schematic diagram of an optional process for a multimodal sensing-based fault identification method for booster station equipment provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature; in the description of this application, unless otherwise stated, "multiple" means two or more.

[0021] The stable operation of photovoltaic (PV) booster stations directly affects the overall performance and efficiency of PV power generation systems. Core equipment within these stations, such as transformers, inverters, and direct combiner boxes, operates in a complex environment, susceptible to insulation degradation under the influence of electric fields, heat, chemicals, mechanical forces, and atmospheric conditions, ultimately leading to power station failures. A failure in booster station equipment can significantly reduce power generation efficiency or even cause power transmission interruptions, resulting in severe economic losses for power generation companies. Statistics show that a single power outage caused by a booster station equipment failure can result in losses ranging from tens to hundreds of thousands of yuan, and may also adversely affect the stability of the power grid. Furthermore, with the continuous expansion of PV power station scale and the trend towards intelligent development, traditional manual inspections and simple monitoring methods are no longer sufficient to meet practical needs. On the one hand, inspections are inefficient, costly, and highly susceptible to subjective factors, making it difficult to grasp the equipment's operating status in real time and easily overlooking potential faults. On the other hand, the diverse types and wide distribution of equipment in power stations, along with their complex and variable operating parameters, necessitate more precise and efficient monitoring technologies to achieve comprehensive monitoring and analysis of the equipment.

[0022] Currently, with the promotion of computer detection technology, the inspection of substation equipment and the recording of instrument data are gradually moving towards automation. This has significantly reduced the workload of manual inspection in terms of equipment operation status monitoring and fault identification, while improving the stability and safety of the power system. For example, Chinese patent application number 202411991855.5 discloses an infrared vision AI analysis system for inspection robots. The infrared imaging module is used to capture temperature data of the target equipment and its surrounding environment in real time, generating infrared images. A convolutional neural network is then used to identify temperature anomalies and equipment faults from these infrared images. Simultaneously, the sensor fusion module fuses data from infrared sensors, lidar, and ultrasonic sensors to generate environmental perception data. A three-dimensional environmental model is constructed using lidar and infrared sensors, and machine learning algorithms are combined to optimize the inspection robot's path planning, ensuring safe inspections in complex environments. During this period, the volume of data related to the monitoring, simulation, and analysis of equipment electrical quantities and line status has exploded. Furthermore, with increasingly stringent safety requirements, how to efficiently minimize the incidence of insulation faults is a pressing issue for substation systems.

[0023] To address the aforementioned technical problems, the present invention proposes the following technical solutions and corresponding embodiments.

[0024] The following is combined with Figures 1 to 4 The embodiments shown illustrate the technical solution of the present invention.

[0025] Example 1 Reference Figure 1 , Figure 2As shown, this application provides a multimodal sensing-based fault identification system for booster station equipment, comprising: a first identification module, a second identification module, and a scheduling module; wherein, the first identification module includes an infrared unit and an ultraviolet unit, used to acquire infrared and ultraviolet images of the target equipment based on the monitoring and scheduling of the scheduling module, and to identify the local overheating points and discharge points of the target equipment by identifying the temperature information in the infrared image and the ultraviolet radiation signal in the ultraviolet image; the second identification module is used to acquire the dial monitoring data of the associated instruments of the target equipment, and to register the dial monitoring data with the dial standard data to realize the parameter evaluation of the operating status of the target equipment; the scheduling module is electrically connected to the first and second identification modules, and the scheduling module is used to monitor and schedule the activation of the first and second identification modules based on the meteorological data received by the meteorological module, thereby completing the equipment operation monitoring under different environmental conditions.

[0026] In this embodiment of the application, the substation equipment refers to the primary electrical equipment used for core energy transmission within the substation, which may include high-voltage equipment, switchgear, protection equipment, and instrument transformer equipment. Specifically, high-voltage equipment includes transformers; switchgear includes circuit breakers and disconnectors; protection equipment includes surge arresters and SF6 (sulfur hexafluoride) gas density meters; and instrument transformer equipment includes voltage transformers (PT) and current transformers (CT).

[0027] In this embodiment of the application, the target device is a transformer.

[0028] In this embodiment of the application, during the monitoring period of the first identification module, the infrared unit identifies localized heating points caused by poor contact, overload, or insulation aging by detecting the surface thermal radiation intensity of each device; wherein, through one or more Infrared Imager During monitoring, the condition of the transformer winding connections, bushing roots, and oil conservator valves is detected. In switchgear, the infrared unit uses one or more infrared imagers to detect the surface thermal radiation intensity of circuit breakers and disconnectors, mainly for the contact parts of various devices. The ultraviolet unit can screen for discharge points inside the arc-extinguishing chamber of the circuit breaker and the contact gap of the disconnector. At the same time, the ultraviolet unit can detect partial discharge caused by sealing failure of the surge arrester body. For example, the heating faults detected by the infrared unit mainly include: 1) Current-induced heating faults, which refer to heating faults caused by poor contact and excessive contact resistance at electrical equipment outgoing joints, disconnectors and contacts, wire clamps and internal current-conducting circuit connections, transmission line connections, etc.; 2) Voltage-induced heating faults, which refer to heating faults caused by aging of the internal insulation medium of electrical equipment, increased dielectric loss, poor sealing, water ingress, moisture, or oil deterioration; 3) Other heating faults, including heating faults caused by ferromagnetic loss, lack of oil in current-absorbing or oil-immersed electrical equipment.

[0029] As one feasible implementation, the first identification module is also used for infrared temperature measurement of outdoor equipment such as current transformers, voltage transformers, grounding devices, busbars and insulators.

[0030] In this embodiment, during the monitoring period of the second identification module, a camera is used to photograph the instrument panel to obtain panel monitoring data. This data is then registered with the standard panel data within the system to assess the operating status of the target equipment. The standard panel data can be a preset standard data range, or standard data predicted based on a deep learning model learning from historical panel data. In this embodiment, during the monitoring period of the second identification module, cameras are fixedly installed at corresponding positions on the surge arrester, SF6 gas density meter, and oil level gauge to capture images. These images are used to read the surge arrester reading, oil level gauge reading, and SF6 gas density meter reading at the current moment based on the captured visible light images. This allows for transformer oil level and quality analysis, as well as status analysis of protection equipment (insulation equipment) (such as SF6 gas pressure leakage detection and surge arrester leakage current and number of operations). In some feasible implementations, the oil level gauge can be a pointer-type oil level gauge for different ranges, or a liquid oil level gauge with a white float, or a liquid oil level gauge with different ranges.

[0031] In this embodiment of the application, a temperature threshold corresponding to each device is preset in the first identification module. When the infrared unit detects that the temperature difference of a certain local hot spot reaches the preset threshold, a device fault warning is issued.

[0032] In this embodiment, the scheduling module schedules the first identification module and the second identification module based on weather data; the meteorological data is received through the meteorological module. In this embodiment, the scheduling module presets a first monitoring period and a second monitoring period corresponding to the first and second identification modules respectively for different weather conditions, and then controls the first and second identification modules to acquire equipment status data during the first and second monitoring periods respectively, and transmits it to the scheduling module; the first and second monitoring periods may not overlap or may partially overlap. Here, the first and second monitoring periods can be preset based on experience. In this embodiment, the scheduling module can store, analyze, and generate data reports based on real-time monitoring and scheduling data, while providing remote monitoring and alarm functions for equipment managers.

[0033] As a feasible implementation method, meteorological data can also be obtained through a meteorological data interface.

[0034] As a feasible implementation, an adaptive identification model is deployed in the scheduling module. This adaptive identification model is used to adaptively determine the identification module corresponding to different monitoring periods based on different weather conditions. Specifically, when constructing this adaptive identification model: meteorological data and monitoring data for each device in the booster station are acquired to construct a monitoring dataset containing data under different weather conditions; wherein, based on the parameter characteristics of the type, time, and distribution pattern of the monitoring data, the monitoring periods corresponding to the first identification module and the second identification module under different weather conditions are marked in the monitoring dataset, forming a correspondence between each monitoring data and weather conditions; the monitoring data consists of equipment status data obtained at key nodes of each device using the first and second identification modules; an adaptive identification model is constructed using a neural network model, with model input variables including temperature, light intensity, hot spot data, discharge point data, and dial monitoring data of associated instruments corresponding to different time periods; the adaptive identification model is trained using the training set of the monitoring dataset, while an optimization algorithm is used to adjust the weights and biases to minimize the prediction error; the performance of the adaptive identification model is evaluated using a validation set; and the monitoring periods of the first and second identification modules are predicted based on the current weather conditions using the adaptive identification model. The monitoring dataset in this application is divided into a training set and a validation set in an 8:2 ratio. During the training of the adaptive recognition model using the training set, the model parameters, including batch size and learning rate, are continuously adjusted based on the model's performance. For example, the monitoring dataset may include the monitoring periods corresponding to the first recognition module and the second recognition module under different weather conditions. This could include: monitoring the infrared images of the target device using the first recognition module throughout the night to sunrise period; and simultaneously, on rainy days when the air temperature / humidity exceeds the corresponding preset thresholds, using the second recognition module to identify and register the readings of the oil level gauge and SF6 gas density gauge.

[0035] In this embodiment, feature importance analysis and principal component analysis are performed on the input features in the monitoring dataset to select and optimize the input features. Specifically, the meteorological data and the monitoring data in the monitoring dataset are standardized, the correlation coefficient matrix of the monitoring dataset is calculated, and the covariance matrix is ​​decomposed through eigenvalue decomposition to obtain eigenvalues ​​and their corresponding eigenvectors. Then, the eigenvalues ​​are arranged according to their magnitude, and the eigenvector corresponding to the largest eigenvalue is determined as the principal component; thus, feature importance analysis and principal component analysis are performed.

[0036] Here, the following formula is used to standardize the meteorological data and monitoring data: Formula 1; in, This represents the j-th feature value of the i-th sample after standardization. This represents the j-th feature value of the i-th sample in the original database; The mean of the j-th feature value is represented by the mean of the j-th feature value across all samples, indicating the central tendency of that feature across all samples. represents the standard deviation of the j-th feature value, which measures the dispersion of the feature value; where, the sample represents hotspot data under different weather conditions (such as hotspot data on a certain day); the feature represents the weather factors that affect the hotspot data (such as temperature, light intensity, humidity, etc.); the feature value represents the specific value of a certain weather factor in a specific sample (such as the temperature being 25℃).

[0037] The correlation coefficient matrix of the monitoring dataset is calculated and eigenvalue decomposition is performed using the following formulas 2 and 3: Formula 2; in, The correlation coefficient represents the relationship between feature a and feature b, which measures the strength of the linear relationship between the two features. This represents the value of the a-th feature in the k-th sample; This represents the average value of the a-th feature across all samples; This represents the standard deviation of the a-th feature. This represents the standard deviation of the b-th feature; Indicates the total sample size; Formula 3; in, Represents the covariance matrix or correlation coefficient matrix; The eigenvector matrix contains eigenvectors of a matrix; This represents an eigenvalue diagonal matrix, where the values ​​on the diagonal are... The eigenvalues ​​of the matrix; thus, the main direction of data change can be extracted through eigenvalue decomposition. The principal component contribution rate is calculated using the following formula (Formula 4): Formula 4; in, Represents the cumulative contribution rate, and represents the previous... The cumulative contribution of each principal component to the total variance of the dataset; The eigenvalues ​​of the covariance matrix are represented by the eigenvalues ​​of the first eigenvalue. Variance contribution in each principal component direction; Indicates the number of principal components selected; This represents the total number of feature values, i.e., the number of features in the original dataset.

[0038] In this embodiment, extraction stops when the cumulative contribution rate reaches 80%, and then the selected principal components are used to project the Yuan Shu data to generate a compressed dataset; then the original data is mapped from the high-dimensional space to the low-dimensional space, while preserving the structure and information of the original data as much as possible.

[0039] Among them, the following formula five is used for data dimensionality reduction: Formula 5; in, This represents the dimensionality-reduced dataset, where the number of features for each sample is reduced. This represents the original dataset, containing all samples and features; This represents a matrix composed of the eigenvectors corresponding to the selected principal components, used to project the original data into a lower-dimensional space. Through the above steps, the original dataset can be transformed into a lower-dimensional version while retaining as much key information as possible from the original data.

[0040] Therefore, optimizing the input features in this embodiment can improve the training efficiency and prediction accuracy of the model, and by reducing the number of features, the complexity of the model is reduced, making it easier to train and deploy.

[0041] In this embodiment, when the first identification module detects a localized hot spot or discharge point in the target device, it automatically acquires the dial monitoring data from the oil level gauge and the SF6 gas density gauge, and registers the dial monitoring data with standard dial data to verify and evaluate the actual operating status of the target device. Here, the activation of the second identification module is controlled by the identification result of the first identification module. At this time, the second identification module may not be in the second monitoring period or may be in the second monitoring period itself.

[0042] In this embodiment of the application, the adaptive recognition model is further used to: deploy the trained adaptive recognition model to the substation equipment fault recognition system for testing, evaluate the effectiveness of the model based on the test results, and further optimize the parameters of the adaptive recognition model.

[0043] In this embodiment, computing power and storage resources are dynamically allocated according to the meteorological warning level (e.g., high-frequency sampling of critical equipment is prioritized during a high-temperature orange warning).

[0044] In this embodiment, since high temperature / high humidity weather is prone to oil / gas leakage due to temperature changes, when the weather is determined to be high temperature / high humidity based on meteorological data, the monitoring of the first identification module and the second identification module is activated simultaneously. The first identification module monitors the temperature of the target equipment, and the second identification module monitors the oil level gauge reading and the SF6 gas density gauge. When the weather is determined to be thunderstorm / strong wind weather based on meteorological data, the duration of the second monitoring period is increased, and the monitoring of the number of surge arrester operations is strengthened. When the weather is determined to be rainy / foggy weather based on meteorological data, the discharge monitoring of the ultraviolet unit of the first identification module is activated, and the insulation status of the equipment (such as the humidity of the PT / CT winding) is monitored.

[0045] The multimodal sensing-based fault identification system and method for booster station equipment provided in this application enables targeted monitoring of booster station equipment by adjusting the monitoring periods of different identification modules according to meteorological data, and greatly reduces the data volume.

[0046] Example 2 Based on the foregoing embodiments, this application provides a method for fault identification of booster station equipment based on multimodal sensing, referring to... Figure 3 As shown, the multimodal sensing-based fault identification method for booster station equipment in this application includes steps S301 to S303: Step S301: Receive meteorological data based on the meteorological module.

[0047] Step S302: The scheduling module determines the identification module corresponding to the current weather conditions based on the meteorological data; the identification module includes a first identification module and a second identification module; the first identification module is used to acquire infrared and ultraviolet images of the target device in real time, and identify local hot spots and discharge points of the target device based on the temperature information in the infrared image and the ultraviolet radiation signal in the ultraviolet image; the second identification module is used to acquire the dial monitoring data of the associated instruments of the target device, and register the dial monitoring data with the dial standard data to generate the operating status evaluation result of the target device.

[0048] Step S303: Perform fault analysis based on the operational status assessment results.

[0049] In this embodiment of the application, when the first identification module detects a local overheating discharge point in the target device, it automatically acquires the dial monitoring data of the associated instrument of the target device, and performs registration based on the dial monitoring data and the dial standard data to verify and evaluate the actual operating status of the target device.

[0050] This application also provides an electronic device, such as... Figure 4As shown, the electronic device 400 can be a server. The device 400 includes a processor 401, a memory, a network interface 403, and a database 40213 connected via a system bus 404. The processor 401 provides computing and control capabilities; the memory includes a non-volatile storage medium 4021 and internal memory 4022. The non-volatile storage medium 4021 stores an operating system 40211, a computer program 40212, and a database 40213. The internal memory 4022 provides an environment for the operation of the operating system 40211 and the computer program 40212 stored in the non-volatile storage medium; the database 40213 provides data such as running programs; the network interface 403 communicates with external terminals via a network connection; when the computer program is executed by the processor 401, it implements the multimodal perception-based fault identification method for booster station equipment described in any of the above embodiments.

[0051] This application also provides a computer-readable storage medium storing a computer program. When executed by a processor, the computer programmer implements the substation equipment anomaly identification method of any embodiment of this application. Specifically, a system or apparatus equipped with a storage medium may be provided, on which software program code implementing the functions of any of the above embodiments is stored, and the computer (or CPU or MPU) of the system or apparatus can read and execute the program code stored in the storage medium.

[0052] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), it performs the functions defined above in the system of this application.

[0053] It should be noted that the computer-readable storage medium shown in this invention can be a computer-readable signal medium, a computer-readable storage medium, or any combination thereof. For example, a computer-readable storage medium can be an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable storage medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable storage medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0054] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0055] The units described in the embodiments of the present invention can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0056] It should be noted that although several modules or units of the device for performing actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of the present invention, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0057] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, portable hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the method according to the embodiments of the present invention.

[0058] In the embodiments provided in this application, it should be understood that the disclosed systems, modules, and methods can be implemented in other ways. For example, the module embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between modules or units, and may be electrical, mechanical, or other forms.

[0059] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. This application is not limited to the exact structures described above and illustrated in the accompanying drawings, and it should not be considered that the specific implementation of this application is limited to these descriptions. For those skilled in the art, various changes and modifications made without departing from the concept of this application should be considered to fall within the protection scope of this application.

Claims

1. A fault identification system for booster station equipment based on multimodal sensing, characterized in that, include: The system comprises a first identification module, a second identification module, and a scheduling module, wherein: The first identification module includes an infrared unit and an ultraviolet unit, used to acquire infrared and ultraviolet images of the target device, and identify local hot spots and discharge points of the target device based on temperature information in the infrared image and ultraviolet radiation signals in the ultraviolet image; The second identification module is used to acquire the dial monitoring data of the associated instrument of the target device, and to register the dial monitoring data with the dial standard data to evaluate the operating status of the target device; The scheduling module is electrically connected to the first identification module and the second identification module respectively. The scheduling module is equipped with an adaptive identification model, which is used to monitor and schedule the first identification module and the second identification module based on the meteorological data received by the meteorological module, so as to activate the corresponding identification module for different monitoring periods.

2. The multimodal sensing-based fault identification system for booster station equipment according to claim 1, characterized in that, The construction process of the adaptive recognition model includes: Meteorological data and monitoring data for each device in the booster station are acquired to construct a monitoring dataset containing data under different weather conditions, including the correspondence between each monitoring data and the weather conditions; the monitoring data is the device status data obtained at key nodes of the booster station equipment using a first identification module and a second identification module. An adaptive recognition model is constructed using a neural network model. The input variables of the model include temperature and light intensity corresponding to different time periods, as well as hot spot data, discharge point data, and dial monitoring data of related instruments. The adaptive recognition model is trained using the training set of the monitoring dataset, while the weights and biases are adjusted using an optimization algorithm. The performance of the adaptive recognition model is evaluated using a validation set. Based on the current weather conditions, the monitoring periods of the first and second identification modules are predicted using the adaptive identification model.

3. The multimodal sensing-based fault identification system for booster station equipment according to claim 2, characterized in that, After the adaptive identification module determines the first monitoring period and the second monitoring period corresponding to the first identification module and the second identification module respectively based on the current weather conditions, the scheduling module controls the first identification module and the second identification module to acquire equipment status data during the first monitoring period and the second monitoring period respectively, and transmit it to the scheduling module. The first monitoring period and the second monitoring period do not overlap or only partially overlap.

4. The multimodal sensing-based fault identification system for booster station equipment according to claim 3, characterized in that, The second identification module is also used for: When the first identification module detects that the target device has the local overheating point or the discharge point, it automatically acquires the dial monitoring data of the associated instrument of the target device, and performs registration based on the dial monitoring data and the dial standard data to verify and evaluate the actual operating status of the target device.

5. The multimodal sensing-based fault identification system for booster station equipment according to claim 1, characterized in that, The second identification module is an image acquisition device, which is used to capture a visible light image of the associated instrument and extract the dial monitoring data from the visible light image; Specifically, computer vision technology is used to extract the dial reading detection area and the reading of the dial reading detection area from the visible light image; the types of associated instruments include pointer instruments and digital instruments.

6. The multimodal sensing-based fault identification system for booster station equipment according to claim 1, characterized in that, The scheduling module can store, analyze, and generate data reports based on real-time monitoring and scheduling data, while providing remote monitoring and alarm functions for equipment managers.

7. The multimodal sensing-based fault identification system for booster station equipment according to claim 1, characterized in that, The system also includes an ultrasonic sensor detection module; The ultrasonic sensor detection module is used to monitor abnormal noises of the target device in real time during operation.

8. The multimodal sensing-based fault identification system for booster station equipment according to any one of claims 1-7, characterized in that, The scheduling module is also used for: Obtain short-term weather forecast data through meteorological data interfaces; The weather forecast data is analyzed to predict meteorological changes in the next few hours; The meteorological change data include at least: temperature, light intensity, humidity, and dust concentration.

9. A method for fault identification of booster station equipment based on multimodal sensing, applied to the fault identification system for booster station equipment based on multimodal sensing as described in claims 1-8, characterized in that, include: Meteorological data is received based on the meteorological module; The scheduling module determines the identification module corresponding to the current weather conditions based on the meteorological data; The identification module includes a first identification module and a second identification module; the first identification module is used to acquire infrared and ultraviolet images of the target device in real time, and identify local hot spots and discharge points of the target device based on the temperature information in the infrared image and the ultraviolet radiation signal in the ultraviolet image. The second identification module is used to acquire the dial monitoring data of the associated instrument of the target device, and to register the dial monitoring data with the dial standard data to realize the operation status assessment of the target device; Fault analysis is performed based on the aforementioned operational status assessment.

10. The method for fault identification of booster station equipment based on multimodal perception according to claim 9, characterized in that, The method further includes: When the first identification module detects that the target device has the discharge point of the local overhot spot, it automatically acquires the dial monitoring data of the associated instrument of the target device, and performs registration based on the dial monitoring data and the dial standard data to verify and evaluate the actual operating status of the target device.

Images