A fault positioning method and system for a weak current engineering monitoring large screen
By constructing a fault preprocessing model and standardized hierarchical troubleshooting logic, the system achieves rapid and accurate fault location for monitoring screens, solving the problems of low efficiency and poor accuracy in existing technologies, and ensuring the high reliability and real-time performance of monitoring screens.
Patent Information
- Application Number
- CN202610246239.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-03-02
- Publication Date
- 2026-06-16
AI Technical Summary
Existing technologies are inefficient and inaccurate in fault location for monitoring large screens in low-voltage engineering. They are difficult to achieve synchronous collection and fusion analysis of data across the entire chain and multiple dimensions, and lack a systematic fault preprocessing and intelligent identification mechanism. This makes fault location complex and difficult to meet the operational requirements of high reliability and high real-time performance.
A fault preprocessing model for the monitoring dashboard is constructed. Through multi-dimensional data collection and CNN feature extraction, the deep integration of the entire link operation data is achieved. Combined with standardized hierarchical troubleshooting logic, fault location at the link level, module level, and component level is realized. A fault type intelligent identification model is used for accurate identification.
It enables rapid fault location and root cause tracing, shortens fault location time, reduces operation and maintenance costs and system downtime risk, and ensures the stable operation of the monitoring screen.
Smart Images
Figure CN122218339A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of fault location technology, specifically to a fault location method and system for a large monitoring screen in low-voltage engineering. Background Technology
[0002] With the rapid development of security monitoring technology, large monitoring screens, as core display terminals in low-voltage engineering, have been widely used in many key fields such as security monitoring, traffic management, industrial automation, energy dispatching, and emergency command. They undertake important functions such as real-time information presentation, event early warning, and dispatching and command. Their stable and efficient operation directly determines the overall effectiveness and application value of the low-voltage monitoring system. In recent years, as large monitoring screens have rapidly upgraded towards higher resolution, larger size, and multi-module splicing, their internal structure has become increasingly complex, integrating multiple core components such as display modules, signal transmission links, and low-voltage power supply systems. At the same time, affected by multiple factors such as differences in installation environment, long-term continuous operation and aging of equipment, and interference from low-voltage wiring, the probability of failure has increased significantly, and the types of failures have become more diverse and complex. Therefore, developing a fault location method for large monitoring screens in low-voltage engineering is crucial.
[0003] There are still some shortcomings in the existing technology for fault location of monitoring screens in low-voltage engineering, which are reflected in the following aspects: (1) In the existing technology system, the fault location of monitoring screens in low-voltage engineering mostly adopts the traditional manual inspection or single parameter monitoring method. On the one hand, the traditional manual inspection relies on the professional experience of operation and maintenance personnel, and requires manual inspection of links, modules and components one by one. Not only is the inspection efficiency low, but the average fault location time is often tens of minutes or even hours, which is difficult to meet the needs of real-time operation and maintenance. It is also easy to misjudge or miss faults due to experience differences. Especially in complex splicing screen scenarios, the accuracy of fault location is difficult to guarantee. On the other hand, the single parameter monitoring method can only collect the operation data of a certain link of the screen. It cannot realize the synchronous collection and fusion analysis of full-link and multi-dimensional data. It is easy to have problems such as data fragmentation and feature loss. It is difficult to capture the abnormal trend of parameters before the fault occurs, and it is impossible to realize early warning and accurate location of faults. It can only respond passively after the fault occurs, which leads to the expansion of the fault impact range and increases the operation and maintenance cost and system downtime risk.
[0004] (2) Although some existing fault location technologies attempt to introduce simple data monitoring and analysis methods, they lack systematic model support and have not built a complete fault preprocessing and intelligent identification mechanism. This makes it difficult to achieve deep integration of historical fault data, real-time operation data and auxiliary samples, resulting in insufficient accuracy in abnormal data screening and low reliability in fault type identification and development trend prediction. At the same time, existing technologies have not formed a standardized hierarchical investigation logic. There is a lack of standardized procedures for fault investigation at the link level, module level and component level, making it difficult to achieve hierarchical fault location and root cause tracing. This further exacerbates the difficulty and complexity of fault operation and maintenance, and cannot adapt to the current high reliability and high real-time operation requirements of large monitoring screens. It is also difficult to meet the trend of large-scale and intelligent operation and maintenance of low-voltage engineering. Summary of the Invention
[0005] To address the aforementioned technical shortcomings, the present invention aims to provide a fault location method and system for a large monitoring screen in low-voltage engineering.
[0006] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: The first aspect of the present invention provides a fault location method for a monitoring screen of a low-voltage engineering project, including: Step 1, obtaining the full-link operation data of the historical monitoring screen from the data storage center, and constructing a fault preprocessing model of the monitoring screen.
[0007] Step 2: Obtain the abnormal data set of the monitoring screen through the fault preprocessing model of the monitoring screen, construct the fault layering logic, investigate the preliminary abnormal data set, and then analyze to obtain the fault location of the monitoring screen.
[0008] Step 3: Predict the fault type of the located fault.
[0009] The first aspect of this invention provides a fault location system for a monitoring screen in a low-voltage engineering project, comprising: a data acquisition and analysis module: used to build a multi-dimensional data acquisition architecture, acquire the full-link operation data of the historical monitoring screen, and construct a fault preprocessing model for the monitoring screen.
[0010] Fault location module: It is used to obtain the abnormal data set of the monitoring screen through the fault preprocessing model of the monitoring screen, construct the fault layering logic, investigate the preliminary abnormal data set, and then analyze to obtain the fault location of the monitoring screen.
[0011] Fault type analysis module: used to predict the fault type of the located fault.
[0012] The beneficial effects of the present invention are as follows: (1) The present invention collects four categories of full-link operation data, including display module, signal transmission link, weak current power supply and environmental impact, synchronously, covering key parameters such as pixel brightness, signal attenuation value, power supply ripple coefficient, and ambient temperature and humidity. By dynamically adjusting the acquisition frequency and data noise reduction algorithm, the accuracy and timeliness of the collected data are ensured. At the same time, a fault preprocessing model containing an input layer, a CNN feature extraction layer and a big data fusion layer is constructed based on the full-link data. This achieves deep fusion of historical fault data, real-time operation data and auxiliary samples, which can accurately screen out real abnormal data and provide reliable data support for subsequent fault location. This completely solves the problem of location deviation caused by fragmentation and feature loss of existing single parameter monitoring data.
[0013] (2) This invention achieves rapid fault location and root cause tracing by constructing a standardized hierarchical troubleshooting logic, which greatly improves operation and maintenance efficiency. This invention clearly proposes a three-layer fault troubleshooting logic of link level, module level, and component level. First, the faulty link is located through link connectivity test and signal loopback test. Then, the faulty module is located through standard test signal transmission and other methods. Finally, the faulty component is located, forming a standardized and process-oriented troubleshooting system. The entire location process of this invention does not rely on the experience judgment of operation and maintenance personnel. It can realize automated hierarchical fault troubleshooting, greatly shorten the fault location time, and solve the pain points of low efficiency and high dependence on professional experience in traditional manual troubleshooting.
[0014] (3) The present invention achieves accurate identification of fault types. Based on the simulation model of the monitoring screen, the present invention generates a large number of fault training samples, which can accurately identify fault types such as display faults, signal transmission faults and weak current power supply faults, and clarify the quantitative judgment criteria of various faults, which makes it easier for maintenance personnel to deal with the fault according to the severity of the fault, effectively reducing the scope of fault impact, reducing the risk of system downtime and maintenance costs, and ensuring the stable operation of the monitoring screen system. Attached Figure Description
[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention 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 only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0016] Figure 1 This is a schematic diagram of the implementation steps of the method of the present invention.
[0017] Figure 2 This is a schematic diagram of the system structure connection of the present invention. Detailed Implementation
[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0019] Reference Figure 1 As shown, the first aspect of the present invention provides a fault location method for a monitoring screen of a low-voltage engineering project, including: Step 1, obtaining the full-link operation data of the historical monitoring screen from the data storage center, and constructing a fault preprocessing model of the monitoring screen.
[0020] In a specific example, the end-to-end operational data includes display module operating parameters, signal transmission link parameters, low-voltage power supply parameters, and environmental impact parameters.
[0021] It should be noted that the display module operating parameters include pixel brightness, module drive current, display refresh rate, and module interface transmission rate; signal transmission link parameters include signal attenuation, link bit error rate, transmission delay, and interface plug-in / plug-out detection signal; low-voltage power supply parameters include input voltage, output current, power supply ripple coefficient, and power failure warning signal; environmental impact parameters include ambient temperature, humidity, dust concentration, and electromagnetic interference intensity around the large screen; the acquisition frequency is set to 100ms / time, and high-frequency interference signals are filtered through a data noise reduction algorithm during acquisition to ensure the accuracy of the acquired data. The data noise reduction algorithm is an existing algorithm technology, so it will not be described in detail.
[0022] In a specific example, the fault preprocessing model for the monitoring screen is constructed as follows: The fault preprocessing model for the monitoring screen includes an input layer, a feature preprocessing layer, a CNN feature extraction layer, a big data fusion layer, and an output layer.
[0023] The input layer adopts a multi-channel input design, with each channel corresponding to the display module operating parameters, signal transmission link parameters, low-voltage power supply parameters, and environmental impact parameters of the monitoring screen. At the same time, a data cache unit is embedded to store the historical full-link data of the monitoring screen.
[0024] The feature preprocessing layer embeds a Min-Max normalization unit and an anomaly preliminary screening unit. The Min-Max normalization unit is used to normalize various parameters, and the anomaly preliminary screening unit is used to perform preliminary screening of abnormal data through preset judgment logic.
[0025] The feature extraction layer of a CNN is a CNN convolutional neural network.
[0026] It should be noted that CNN (Convolutional Neural Network) is an existing neural network technology, so it will not be discussed further.
[0027] The big data fusion layer is used to construct a data sample fusion pool and fusion strategy, and then perform feature-level fusion and sample-level fusion of the features extracted by the CNN feature extraction layer.
[0028] It should be noted that the data fusion sample pool construction process is as follows: real-time collection of full-link operation data from the monitoring screen; acquisition of historical fault data from the monitoring screen from the data storage center (including operating parameters, fault type, and fault location data at the time of past faults); the data fusion sample pool adopts distributed storage and supports real-time updates; the fusion strategy construction process is as follows: a dual fusion strategy of feature-level fusion and sample-level fusion is adopted to avoid feature loss caused by single fusion: feature-level fusion means weighted fusion of deep features extracted by the CNN layer with features in the big data sample (such as parameter features corresponding to historical faults and parameter offset features corresponding to equipment aging); sample-level fusion means randomly shuffling and fusion of real-time collected samples with historical fault samples and auxiliary samples, dividing the training samples and validation samples in an 8:2 ratio to ensure the diversity of training samples to cover different equipment operating states and different fault scenarios.
[0029] The output layer is used to output a preliminary set of abnormal data.
[0030] In a specific example, the preliminary screening of abnormal data is performed through a preset judgment logic. The specific process is as follows: The preprocessed full-link operation data of the monitoring screen is compared with a preset standard data range. Full-link operation data that does not belong to the preset standard data range is recorded as suspected abnormal data, and otherwise it is recorded as normal data. Based on this, all suspected abnormal data in the full-link operation data of the monitoring screen is obtained. For any suspected abnormal data, the associated data of the suspected abnormal data is obtained. If there is no suspected abnormal data in the associated data of the suspected abnormal data, the suspected abnormal data is updated to normal data. If there is suspected abnormal data in the associated data of the suspected abnormal data, the suspected abnormal data is not updated.
[0031] It should be noted that the preset standard data range is the baseline data range for judging whether the entire chain operation data of the monitoring screen is abnormal. It is set by the relevant staff and no specific restrictions are imposed here.
[0032] Step 2: Obtain the abnormal data set of the monitoring screen through the fault preprocessing model of the monitoring screen, construct the fault layering logic, investigate the preliminary abnormal data set, and then analyze to obtain the fault location of the monitoring screen.
[0033] In a specific example, the process of obtaining the abnormal data set of the monitoring screen through the fault preprocessing model of the monitoring screen is as follows: each collection node is deployed at a preset location on the monitoring screen, and a data aggregation node is set up. The data collected by each collection node is synchronously transmitted to the data aggregation node to obtain the full-link operation data of the monitoring screen. This data is then input into the fault preprocessing model to obtain the abnormal data set of the monitoring screen.
[0034] In a specific instance, the fault hierarchy logic includes link-level faults, module-level faults, and component-level faults.
[0035] It should be noted that the links of the monitoring screen include signal transmission links, low-voltage power supply links, and display driver links; the modules include display modules, signal processors, power supply modules, and interface modules; and the components include driver chips, capacitors, resistors, and interface pins.
[0036] In a specific example, the construction of fault layering logic, the investigation of the preliminary abnormal data set, and the analysis to obtain the fault location of the monitoring screen are carried out as follows: First, link connectivity test and signal loopback test are performed on each link of the monitoring screen, and each link that fails the link connectivity test or signal loopback test is recorded as a faulty link.
[0037] It should be noted that the link connectivity test and signal loopback test are performed on each link of the monitoring screen. The specific process is as follows: A detection signal with a frequency of 100MHz is sent to the transmission link, the reflected signal is received and the reflection time and reflection intensity are obtained. The reflection time and reflection intensity are compared with the set reflection time threshold and reflection intensity threshold, respectively. Links with a reflection time greater than the set reflection time threshold or a reflection intensity greater than the set reflection intensity threshold are recorded as faulty links. The reflection time threshold is proportional to the length of the transmission link, with a ratio of 100m / 1us, and the reflection intensity threshold is -30dB.
[0038] Then, perform independent power supply tests and separate signal transmission tests on each module of the monitoring screen, and record each module that fails the independent power supply test or separate signal transmission test as a faulty module.
[0039] It should be noted that independent power supply tests and individual signal transmission tests were performed on each module of the monitoring screen. The specific process is as follows: For the independent power supply test, a portable temporary power supply module with a rated voltage of 5V / 12V was used to power one module while the other modules were powered off. The module was then observed to see if it could start normally and output signals. If it could operate normally, the module was fault-free; otherwise, the module was faulty. For the individual signal transmission test, a signal generator was used to send a standard test signal (1920×1080 resolution, 60Hz refresh rate) to one module. The module's signal reception and output were observed. If there was no signal attenuation or distortion, the module was fault-free; otherwise, the module was faulty.
[0040] Finally, the parameters of each component in each fault module are tested, and the components that fail the parameter test are recorded as faulty components.
[0041] It should be noted that parameter testing is performed on each component within each faulty module. The specific process is as follows: Component parameter comparison: Real-time component parameters are collected using a portable parameter tester and compared with the component's factory standard parameters and historical normal operating parameters. If the difference exceeds a preset threshold (resistance difference not exceeding ±5%, capacitance difference not exceeding ±10%, and driver chip operating current difference not exceeding ±8%), the component is determined to be faulty. Pin continuity test: A multimeter is used to detect the pin continuity status. If the continuity resistance exceeds 100Ω, the pin is determined to be poorly soldered or damaged. At the same time, infrared thermography is used to detect the pin temperature. If the pin temperature exceeds 85℃, the pin is determined to be overheated and damaged. During the location process, the investigation results and test data at each level are recorded. The specific recorded content includes: reflection time and reflection intensity of each link, power supply voltage and signal attenuation value of each module, and real-time parameters, continuity resistance, and temperature data of each component.
[0042] Step 3: Predict the fault type of the located fault.
[0043] In a specific example, the process of predicting the fault type of the located fault is as follows: the working parameters of each fault link, each fault module, and each fault component within a preset period are collected by each deployed acquisition node; the working parameters of each fault link, each fault module, and each fault component within the preset period are input into a pre-trained fault type intelligent identification model; and the fault type of each fault link, each fault module, and each fault component is output through the fault type intelligent identification model.
[0044] In a specific example, the intelligent fault type identification model is trained as follows: Based on the actual composition structure of the monitoring screen, a simulation model of the monitoring screen is constructed in relevant simulation software. Based on the simulation model of the monitoring screen, various fault test sets are set, wherein each fault test set includes fault types of each link, fault types of each module, and fault types of each component. Based on each fault test set, fault tests are performed on the simulation model of the monitoring screen, and the working parameters of each fault test set corresponding to each fault link, each fault module, and each fault component are collected during the test. Each fault test set and the working parameters of each fault test set corresponding to each fault link, each fault module, and each fault component are recorded as the training sample set.
[0045] It should be noted that the types of faults include display faults, signal transmission faults, low-voltage power supply faults, interface faults, and environmental compatibility faults. Display faults include screen flickering, black screens, blurriness, abnormal brightness, and color distortion; signal transmission faults include signal interruption, signal stuttering, and excessive signal attenuation; low-voltage power supply faults include voltage fluctuations, power outages, and excessive ripple; interface faults include loose interfaces, damaged interfaces, and poor contact; and environmental compatibility faults include display abnormalities caused by high temperature overheating, humidity short circuits, dust blockage, and electromagnetic interference. The specific criteria for judging various faults are as follows: Screen flickering is judged by a pixel brightness disorder rate exceeding 10%; black screen is judged by a pixel brightness rate below 5%; blurriness is judged by a display clarity below 80% of the preset standard value; abnormal brightness is judged by a difference between actual brightness and preset brightness exceeding ±30%; color distortion is judged by an RGB three-color deviation exceeding ±15%; signal interruption is judged by a signal transmission interruption duration exceeding 1 second; signal stuttering is judged by a signal frame loss rate exceeding 10% per second; excessive signal attenuation is judged by a signal attenuation value exceeding 20dB; voltage instability is judged by voltage fluctuation exceeding ±10%; power supply interruption is judged by an output current of 0 and... The following conditions are considered inappropriate for a connection type: Duration exceeding 500ms; ripple exceeding the standard is defined as a power supply ripple coefficient exceeding 0.5%; interface looseness is defined as three consecutive disconnections of the interface insertion / removal detection signal, each disconnection lasting no more than 1 second; interface damage is defined as no signal transmission at the interface and pin on-resistance exceeding 1kΩ; poor contact is defined as intermittent interface signal transmission and signal attenuation fluctuation exceeding 5dB; overheating is defined as a temperature around the large screen exceeding 60℃ for more than 5 minutes; dampness short circuit is defined as humidity exceeding 85%RH and leakage current exceeding 1mA in the power supply link; dust blockage is defined as dust concentration exceeding 0.5mg / m³. 3 Furthermore, the heat dissipation efficiency of the display module decreased by 30%, and the display abnormality caused by electromagnetic interference was determined to be when the electromagnetic interference intensity exceeded 40dBμV / m and the display abnormality and interference signal appeared simultaneously.
[0046] After preprocessing the training sample set, it is divided into a training set and a validation set according to a preset ratio. The CNN neural network model is then trained and validated to obtain an intelligent fault type recognition model for the monitoring screen.
[0047] It should be noted that preprocessing includes data normalization, data interpolation and supplementation, and outlier removal. Among these, data normalization, data interpolation and supplementation, and outlier removal are existing technologies, so they will not be described in detail.
[0048] Reference Figure 2 As shown, the second aspect of the present invention provides a fault location system for a monitoring screen of a low-voltage engineering project, comprising: a data acquisition and analysis module: used to build a multi-dimensional data acquisition architecture, acquire the full-link operation data of the historical monitoring screen, and construct a fault preprocessing model for the monitoring screen.
[0049] Fault location module: It is used to obtain the abnormal data set of the monitoring screen through the fault preprocessing model of the monitoring screen, construct the fault layering logic, investigate the preliminary abnormal data set, and then analyze to obtain the fault location of the monitoring screen.
[0050] Fault type analysis module: used to predict the fault type of the located fault.
[0051] The examples described in this invention are not limited to the specific embodiments listed above. The examples are merely illustrative to facilitate understanding of the invention and do not constitute a limitation on the scope of protection of this invention. Any modifications, equivalent substitutions, etc., made within the spirit and principles of this invention should be included within the scope of protection.
[0052] The above description is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined in this specification, they should all fall within the protection scope of the present invention.
Claims
1. A fault location method for a large monitoring screen in a low-voltage electrical engineering project, characterized in that, Includes the following steps: Step 1: Obtain the full-link operation data of the historical monitoring screen from the data storage center, and build a fault preprocessing model for the monitoring screen; Step 2: Obtain the abnormal data set of the monitoring screen through the fault preprocessing model of the monitoring screen, construct the fault layering logic, investigate the preliminary abnormal data set, and then analyze to obtain the fault location of the monitoring screen. Step 3: Predict the type of fault for the located fault.
2. The fault location method for a large monitoring screen for low-voltage engineering according to claim 1, characterized in that, The end-to-end operational data includes display module operating parameters, signal transmission link parameters, low-voltage power supply parameters, and environmental impact parameters.
3. The fault location method for a large monitoring screen for low-voltage engineering according to claim 2, characterized in that, The specific construction process of the fault preprocessing model for building the monitoring dashboard is as follows: The fault preprocessing model for the monitoring screen includes an input layer, a feature preprocessing layer, a CNN feature extraction layer, a big data fusion layer, and an output layer. The input layer adopts a multi-channel input design, with each channel corresponding to the display module operating parameters, signal transmission link parameters, low-voltage power supply parameters, and environmental impact parameters of the monitoring screen. At the same time, a data cache unit is embedded to store the historical full-link data of the monitoring screen. The feature preprocessing layer embeds a Min-Max normalization unit and an anomaly preliminary screening unit. The Min-Max normalization unit is used to normalize various parameters, and the anomaly preliminary screening unit is used to perform preliminary screening of abnormal data through preset judgment logic. The feature extraction layer of a CNN is a CNN convolutional neural network; The big data fusion layer is used to construct a data sample fusion pool and fusion strategy, and then perform feature-level fusion and sample-level fusion on the features extracted by the CNN feature extraction layer. The output layer is used to output a preliminary set of abnormal data.
4. The fault location method for a large monitoring screen for low-voltage engineering according to claim 3, characterized in that, The preliminary screening of abnormal data is performed through a preset judgment logic. The specific process is as follows: The preprocessed end-to-end operational data of the monitoring screen is compared with a preset standard data range. End-to-end operational data that does not belong to the preset standard data range is recorded as suspected abnormal data, and vice versa. Based on this, all suspected abnormal data in the end-to-end operational data of the monitoring screen is obtained. For any suspected abnormal data, all related data of the suspected abnormal data are obtained. If there is no suspected abnormal data in the related data of the suspected abnormal data, the suspected abnormal data is updated to normal data. If there is suspected abnormal data in the related data of the suspected abnormal data, the suspected abnormal data is not updated.
5. The fault location method for a large monitoring screen for low-voltage engineering according to claim 4, characterized in that, The process of obtaining the abnormal data set of the monitoring screen through the fault preprocessing model of the monitoring screen is as follows: Data acquisition nodes are deployed at preset locations on the monitoring screen, and a data aggregation node is set up. Data collected by each acquisition node is synchronously transmitted to the data aggregation node to obtain the full-link operation data of the monitoring screen. This data is then input into the fault preprocessing model to obtain the abnormal data set of the monitoring screen.
6. The fault location method for a large monitoring screen for low-voltage engineering according to claim 5, characterized in that, The fault hierarchy logic includes link-level faults, module-level faults, and component-level faults.
7. The fault location method for a large monitoring screen for low-voltage engineering according to claim 6, characterized in that, The process of constructing fault hierarchy logic, investigating the initial abnormal data set, and then analyzing it to locate the fault on the monitoring screen is as follows: First, perform link connectivity tests and signal loopback tests on each link of the monitoring screen, and record each link that fails the link connectivity test or signal loopback test as a faulty link. Then, perform independent power supply tests and separate signal transmission tests on each module of the monitoring screen, and record each module that fails the independent power supply test or separate signal transmission test as a faulty module. Finally, the parameters of each component in each fault module are tested, and the components that fail the parameter test are recorded as faulty components.
8. The fault location method for a large monitoring screen for low-voltage engineering according to claim 7, characterized in that, The specific process for predicting the fault type of the located fault is as follows: The system collects the operating parameters of each faulty link, faulty module, and faulty component within a preset period by deploying various acquisition nodes. The operating parameters of each faulty link, faulty module, and faulty component within a preset period are then input into a pre-trained intelligent fault type identification model. The intelligent fault type identification model then outputs the fault type of each faulty link, faulty module, and faulty component.
9. The fault location method for a large monitoring screen for low-voltage engineering according to claim 8, characterized in that, The specific training process for the intelligent fault type identification model is as follows: Based on the actual structure of the monitoring screen, a simulation model of the monitoring screen is constructed in relevant simulation software. Based on the simulation model of the monitoring screen, various fault test sets are set up, including fault types of each link, fault types of each module, and fault types of each component. Based on each fault test set, fault tests are performed on the simulation model of the monitoring screen, and the working parameters of each fault test set corresponding to each fault link, each fault module, and each fault component are collected during the test. Each fault test set and the working parameters of each fault test set corresponding to each fault link, each fault module, and each fault component are recorded as the training sample set. After preprocessing the training sample set, it is divided into a training set and a validation set according to a preset ratio. The CNN neural network model is then trained and validated to obtain an intelligent fault type recognition model for the monitoring screen.
10. A system that utilizes the fault location method of a large monitoring screen for low-voltage engineering according to any one of claims 1-9, characterized in that, include: Data acquisition and analysis module: used to build a multi-dimensional data acquisition architecture, obtain the full-link operation data of the historical monitoring screen, and build a fault preprocessing model for the monitoring screen; Fault location module: Used to obtain the abnormal data set of the monitoring screen through the fault preprocessing model of the monitoring screen, construct fault hierarchical logic, investigate the preliminary abnormal data set, and then analyze to obtain the fault location of the monitoring screen. Fault type analysis module: used to predict the fault type of the located fault.