Lighting lamp fault detection method and system based on neural network model
Through the lighting fixture fault detection method based on neural network model, the tunnel street lamp fault and its association relationship are automatically identified, and the problem of manual detection affecting road safety and fault association identification in the existing technology is solved, and efficient fault expansion accident chain identification is achieved and residual fault unit identification.
Patent Information
- Application Number
- CN202411066406.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-05
- Publication Date
- 2024-12-03
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing tunnel lighting detection methods require manual testing, which affects road safety and vehicle traffic, and it is difficult to identify the relationship between faulty street lights when a fault occurs, resulting in difficulty in identifying fault expansion accidents.
The fault detection method of lighting fixtures based on neural network model is adopted, street light information is collected through vehicle-mounted image brightness meter, faulty street light units are preprocessed and combined, and the degree of correlation between faulty street lights is analyzed using a pre-trained neural network model to identify faulty expansion accidents. Chain and residual faulty street light units.
Automatic fault detection and correlation analysis are realized, the accuracy and operability of detection are improved, manual intervention is reduced, and fault expansion accident chain can be effectively identified and extended, and subsequent manual processing is guided.
Smart Images

Figure CN119066509A_ABST
Abstract
Description
Background Art
[0002] At present, the main testing method for lighting testing in daily tunnel maintenance is to use a illuminance meter to perform manual testing, and combine it with the standardized empirical coefficient method to convert the brightness of the test area. At the same time, this testing method needs to be carried out on a closed road, which has a great impact on road safety and vehicle traffic, and has huge labor and social costs. In particular, daily maintenance work is full of a large amount of manual repetitive labor. In the prior art, in the field of tunnel lighting detection technology, most studies focus on fault finding and identification. However, in actual situations, the occurrence of a fault is often related to other faults and form a fault expansion accident. Therefore, it is particularly important to identify the correlation between faulty street lamps.
[0003] In view of this technical background, a lighting fixture fault detection method and system based on a neural network model is proposed. While identifying faulty street lamps, it can intuitively reflect the correlation and degree of correlation between faulty street lamps, and identify the fault extension accident chain and residual faulty street lamp units, providing guidance for manual processing after the fault occurs. Summary of the invention
[0004] The main purpose of the present invention is to provide a lighting fixture fault detection method based on a neural network model, and further to provide a lighting fixture fault detection system based on a neural network model that can run and implement the above method, so as to effectively solve the above problems mentioned in the background technology.
[0005] The technical solution of the present invention is as follows:
[0006] In a first aspect, a lighting fixture fault detection method based on a neural network model is proposed, the method comprising the following steps:
[0007] S1. Use the vehicle-mounted imaging luminance meter to collect the lighting information of all street lamp units in the tunnel, pre-process the information, and extract the faulty street lamp information;
[0008] S2, combine all faulty street lamp units in pairs to form a detection pair, use a pre-trained neural network model to perform correlation analysis on the faulty street lamp units in the detection pair, and output the analysis results;
[0009] S3. According to the analysis results, the fault extension accident chain of the faulty street light unit and the residual faulty street light units are identified.
[0010] A further improvement of the present invention is that the specific steps of S1 are:
[0011] S11. Using a vehicle-mounted imaging brightness meter to collect the fault occurrence time of all faulty street lamp units in the tunnel, arranging all the faulty street lamp units in the order of the fault occurrence time and marking the serial numbers;
[0012] S12, in the order of arrangement, collect the fault characteristic data of all faulty street lamp units in turn to form a faulty street lamp characteristic data set (A1, A2, ..., A i ,...,A j ,...,A n ), where subscript n represents the faulty street light unit n, A n is the fault characteristic data of the faulty street lamp unit n.
[0013] A further improvement of the present invention is that the specific steps of S2 are:
[0014] S21, combining all faulty street lamp units in pairs to form a detection pair;
[0015] S22. According to the detection pair, extract the corresponding faulty street lamp feature data in the faulty street lamp feature data set to form a detection pair feature data set. A single detection pair feature data set is represented by (A i ,A j ), where i<j;
[0016] S23. Use a pre-trained neural network model to analyze and detect the correlation between faulty street lamp units.
[0017] A further improvement of the present invention is that the training method of the neural network model in S23 is:
[0018] S231, counting the probability of the occurrence of faulty street light unit j after the occurrence of faulty street light unit i in historical fault events;
[0019] S232, after the faulty street lamp unit i appears in the historical fault event, the probability of the faulty street lamp unit j appearing, the detection pair feature data set (A i ,A j ) as the training data of the neural network, to obtain the conditional probability of the occurrence of faulty street light unit j after the occurrence of faulty street light unit i as the output, to use the actual conditional probability as the prediction target, and to minimize the sum of the prediction accuracies of all predicted conditional probabilities as the training target;
[0020] S233, the calculation formula of the prediction accuracy is z=(pi→j-Pi→j) 2 , p i→j is the conditional probability of the occurrence of faulty street light unit j after the predicted faulty street light unit i occurs, P i→j is the conditional probability of the occurrence of faulty street light unit j after the actual faulty street light unit i appears, z is the prediction accuracy, and the neural network model is trained until the sum of the prediction accuracies reaches convergence and the training is stopped.
[0021] A further improvement of the present invention is that the specific content of the correlation relationship between the faulty street lamp units in the analysis and detection in S23 is: according to the prediction result output by the neural network model, if the faulty street lamp unit i appears, the conditional probability p of the faulty street lamp unit j appearing i→j >0, it is judged that the faulty street lamp unit i and the faulty street lamp unit j have an associated relationship, otherwise it is judged that the faulty street lamp unit i and the faulty street lamp unit j have no associated relationship.
[0022] A further improvement of the present invention is that the step of identifying the fault extension accident chain of the faulty street lamp unit in S3 comprises the following specific steps:
[0023] S31, identifying an initial faulty street lamp unit according to the fault occurrence time of all faulty street lamp units;
[0024] S32, extract all detection pairs containing the initial faulty street lamp unit, arrange the conditional probability values predicted by the neural network model in descending order from large to small, identify the faulty street lamp unit with the greatest correlation with the initial faulty street lamp unit, and obtain the first-level faulty street lamp unit expanded from the initial faulty street lamp unit;
[0025] S33. Repeat the above steps until all faulty street light units are taken into consideration, and obtain the fault extension accident chain of the faulty street light unit.
[0026] A further improvement of the present invention is that the residual faulty street light units in S3 are faulty street light units that have no association with other faulty street light units, that is, discrete faulty street light units outside the fault extension accident chain.
[0027] In the second aspect, a lighting fixture fault detection system based on a neural network model is proposed, the system comprising:
[0028] Fault collection module, correlation analysis module, fault expansion module;
[0029] The fault collection module is used to collect the lighting information of all street lamp units in the tunnel using the vehicle-mounted imaging luminance meter, pre-process the information, and extract the faulty street lamp information;
[0030] The association analysis module is used to combine all faulty street lamp units in pairs to form a detection pair, use a pre-trained neural network model to perform a correlation degree analysis on the faulty street lamp units in the detection pair, and output the analysis results;
[0031] The fault extension module is used to identify the fault extension accident chain of the faulty street light unit and the residual faulty street light units according to the analysis result.
[0032] In a third aspect, a computer-readable storage medium is proposed, on which a computer program is stored. When the computer program is executed by a processor, the lighting fixture fault detection method based on a neural network model as described in any one of the above items is implemented.
[0033] In a fourth aspect, an electronic device is proposed, comprising a memory for storing instructions; and a processor for executing the instructions, so that the device implements a lighting fixture fault detection method based on a neural network model.
[0034] The technical effects of the present invention are as follows:
[0035] A lighting fixture fault detection method based on a neural network model is constructed. The fault information of all faulty street lamp units is collected and preprocessed, and then all faulty street lamp units are combined into detection pairs. The pre-trained neural network model is used to analyze the degree of association of the faulty street lamp units in the detection pairs, and the fault extension accident chain of the faulty street lamp unit and the residual faulty street lamp unit are identified based on the analysis results. While identifying the fault, the conditional probability value predicted by the neural network model is used to reflect the correlation relationship and degree of association between the faulty street lamps, and the fault extension accident chain and the residual faulty unit are identified, so the method has good operability, high accuracy and high flexibility. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:
[0037] Figure 1 A schematic diagram of a flow chart of a lighting fixture fault detection method based on a neural network model of the present invention;
[0038] Figure 2 It is a structural schematic diagram of a lighting fixture fault detection system based on a neural network model of the present invention. DETAILED DESCRIPTION
[0039] The present invention aims to propose a lighting fixture fault detection method based on a neural network model, by collecting fault information of all faulty street lamp units, pre-processing the information, then combining all faulty street lamp units in pairs to form a detection pair, using a pre-trained neural network model to perform correlation analysis on the faulty street lamp units in the detection pair, and according to the analysis results, identifying the fault extension accident chain of the faulty street lamp unit and the residual faulty street lamp unit. While identifying the fault, the conditional probability value predicted by the neural network model is used to reflect the correlation relationship and correlation degree between the faulty street lamps, and the fault extension accident chain and the residual faulty unit are identified, so the operability is good, the accuracy is high, and the flexibility is high.
[0040] Embodiment 1:
[0041] This embodiment proposes a lighting fixture fault detection method based on a neural network model, such as Figure 1 As shown, the specific steps include:
[0042] S1. Use the vehicle-mounted imaging luminance meter to collect the lighting information of all street lamp units in the tunnel, pre-process the information, and extract the faulty street lamp information;
[0043] S2, combine all faulty street lamp units in pairs to form a detection pair, use a pre-trained neural network model to perform correlation analysis on the faulty street lamp units in the detection pair, and output the analysis results;
[0044] S3. According to the analysis results, the fault extension accident chain of the faulty street light unit and the residual faulty street light units are identified.
[0045] In this embodiment, the specific steps of S1 are:
[0046] S11. Using a vehicle-mounted imaging brightness meter to collect the fault occurrence time of all faulty street lamp units in the tunnel, arranging all the faulty street lamp units in the order of the fault occurrence time and marking the serial numbers;
[0047] S12, in the order of arrangement, collect the fault characteristic data of all faulty street lamp units in turn to form a faulty street lamp characteristic data set (A1, A2, ..., A i ,...,A j ,...,A n ), where subscript n represents the faulty street light unit n, A n is the fault characteristic data of the faulty street lamp unit n.
[0048] In this embodiment, the specific steps of S2 are:
[0049] S21, combining all faulty street lamp units in pairs to form a detection pair;
[0050] S22. According to the detection pair, extract the corresponding faulty street lamp feature data in the faulty street lamp feature data set to form a detection pair feature data set. A single detection pair feature data set is represented by (A i ,A j ), where i<j;
[0051] S23. Use a pre-trained neural network model to analyze and detect the correlation between faulty street lamp units.
[0052] In this embodiment, the training method of the neural network model in S23 is:
[0053] S231, counting the probability of the occurrence of faulty street light unit j after the occurrence of faulty street light unit i in historical fault events;
[0054] S232, after the faulty street lamp unit i appears in the historical fault event, the probability of the faulty street lamp unit j appearing, the detection pair feature data set (A i ,A j ) as the training data of the neural network, to obtain the conditional probability of the occurrence of faulty street light unit j after the occurrence of faulty street light unit i as the output, to use the actual conditional probability as the prediction target, and to minimize the sum of the prediction accuracies of all predicted conditional probabilities as the training target;
[0055] S233, the calculation formula of the prediction accuracy is z=(pi→j-Pi→j) 2 , p i→j is the conditional probability of the occurrence of faulty street light unit j after the predicted faulty street light unit i occurs, P i→j is the conditional probability of the occurrence of faulty street light unit j after the actual faulty street light unit i appears, z is the prediction accuracy, and the neural network model is trained until the sum of the prediction accuracies reaches convergence and the training is stopped.
[0056] In this embodiment, the specific content of the correlation relationship between the faulty street lamp units in the analysis and detection in S23 is: according to the prediction result output by the neural network model, if the faulty street lamp unit i appears, the conditional probability p of the faulty street lamp unit j appearing i→j >0, it is judged that the faulty street lamp unit i and the faulty street lamp unit j have an associated relationship, otherwise it is judged that the faulty street lamp unit i and the faulty street lamp unit j have no associated relationship.
[0057] In this embodiment, the identification of the fault extension accident chain of the faulty street lamp unit in S3 includes the following specific steps:
[0058] S31, identifying an initial faulty street lamp unit according to the fault occurrence time of all faulty street lamp units;
[0059] S32, extract all detection pairs containing the initial faulty street lamp unit, arrange the conditional probability values predicted by the neural network model in descending order from large to small, identify the faulty street lamp unit with the greatest correlation with the initial faulty street lamp unit, and obtain the first-level faulty street lamp unit expanded from the initial faulty street lamp unit;
[0060] S33. Repeat the above steps until all faulty street light units are taken into consideration, and obtain the fault extension accident chain of the faulty street light unit.
[0061] In this embodiment, the residual faulty street light units in S3 are faulty street light units that have no association with other faulty street light units, that is, discrete faulty street light units outside the fault extension accident chain.
[0062] Embodiment 2:
[0063] This embodiment proposes a lighting fixture fault detection system based on a neural network model, such as Figure 2 As shown, it includes: a fault collection module, a correlation analysis module, and a fault expansion module;
[0064] The fault collection module is used to collect the lighting information of all street lamp units in the tunnel using the vehicle-mounted imaging luminance meter, pre-process the information, and extract the faulty street lamp information;
[0065] The association analysis module is used to combine all faulty street lamp units in pairs to form a detection pair, use a pre-trained neural network model to perform a correlation degree analysis on the faulty street lamp units in the detection pair, and output the analysis results;
[0066] The fault extension module is used to identify the fault extension accident chain of the faulty street light unit and the residual faulty street light units according to the analysis result.
[0067] In this embodiment, the specific implementation steps of the fault collection module are as follows: first, the fault occurrence time of all faulty street lamp units in the tunnel is collected using a vehicle-mounted imaging brightness meter, and all faulty street lamp units are arranged in the order of the fault occurrence time and marked with serial numbers; then, the fault feature data of all faulty street lamp units are collected in sequence according to the arrangement order to form a faulty street lamp feature data set (A1, A2, ..., A i ,...,A j ,...,A n ), where subscript n represents the faulty street light unit n, A n is the fault characteristic data of the faulty street lamp unit n.
[0068] In this embodiment, the specific implementation steps of the association analysis module are as follows: first, all faulty street lamp units are combined into detection pairs, and n faulty units are combined into Then, according to the detection pair, the corresponding faulty street lamp feature data in the faulty street lamp feature data set is extracted to form a detection pair feature data set. A single detection pair feature data set is represented as (A i ,A j ), where i<j; finally, the pre-trained neural network model is used to analyze the correlation between the faulty street lamp units in the detection pair, and the analysis of all faulty pairs is completed.
[0069] In this embodiment, the training method of the neural network model is as follows: first, the probability of the occurrence of the faulty street lamp unit j after the occurrence of the faulty street lamp unit i in the historical fault events is statistically analyzed; second, the probability of the occurrence of the faulty street lamp unit j after the occurrence of the faulty street lamp unit i in the historical fault events and the detection feature data set (A i ,A j ) as the training data of the neural network, to obtain the conditional probability of the occurrence of the faulty street light unit j after the occurrence of the faulty street light unit i as the output, to take the actual conditional probability as the prediction target, to minimize the sum of the prediction accuracy of all predicted conditional probabilities as the training target; finally, the calculation formula of the prediction accuracy is z = (pi→j-Pi→j) 2 , p i→j is the conditional probability of the occurrence of faulty street light unit j after the predicted faulty street light unit i occurs, P i→j is the conditional probability of the occurrence of faulty street light unit j after the actual faulty street light unit i appears, z is the prediction accuracy, and the neural network model is trained until the sum of the prediction accuracies reaches convergence and the training is stopped.
[0070] In this embodiment, the specific content of the correlation relationship between the faulty street lamp units in the analysis and detection is: according to the prediction result output by the neural network model, if the faulty street lamp unit i appears, the conditional probability p of the faulty street lamp unit j appearing i→j >0, it is judged that the faulty street lamp unit i and the faulty street lamp unit j have an associated relationship, otherwise it is judged that the faulty street lamp unit i and the faulty street lamp unit j have no associated relationship.
[0071] In this embodiment, the identification of the fault extension accident chain of the faulty street lamp unit includes the following specific steps:
[0072] Firstly, the initial faulty street light unit is identified according to the fault occurrence time of all faulty street light units; secondly, all detection pairs containing the initial faulty street light unit are extracted, and the conditional probability values predicted by the neural network model are arranged in descending order from large to small, and the faulty street light unit with the largest correlation with the initial faulty street light unit is identified, and the first-level faulty street light unit extended from the initial faulty street light unit is obtained; finally, the above steps are repeated until all faulty street light units are taken into account, and the fault extension accident chain of the faulty street light unit is obtained.
[0073] In this embodiment, the residual faulty street light unit in S3 is a faulty street light unit that has no association with other faulty street light units, that is, a discrete faulty street light unit outside the fault extension accident chain. In particular, when the earliest faulty street light unit has no association with other faulty street light units, it is regarded as a residual faulty street light unit, and the above steps are repeated until the initial faulty street light unit that triggers the fault extension accident chain is found.
[0074] Embodiment 3:
[0075] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the above-mentioned lighting fixture fault detection method based on the neural network model by calling the computer program stored in the memory.
[0076] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the lighting fixture fault detection method based on the neural network model provided by the above method embodiment. The electronic device may also include other components for implementing the functions of the device, for example, the electronic device may also have components such as a wired or wireless network interface and an input / output interface for data input and output. This embodiment will not be described in detail here.
[0077] Those skilled in the art know that the present invention can be implemented as a system, method or computer program product. Therefore, the present disclosure can be specifically implemented in the following forms, namely: it can be complete hardware, it can be complete software (including firmware, resident software, microcode, etc.), and it can also be a combination of hardware and software, which is generally referred to as "circuit", "module" or "system" herein. In addition, in some embodiments, the present invention can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code.
[0078] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.
[0079] The present invention is described with reference to flowcharts and block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process or block in the flowchart and block diagram, as well as the combination of processes and blocks in the flowchart or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts. Figure 1 Process or multiple processes and boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0080] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 Process or multiple processes and boxes Figure 1 The steps for the functions specified in one or more boxes.
[0081] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.
Claims
1. A lighting fixture fault detection method based on a neural network model, characterized in that: The specific steps include: S1. Use the vehicle-mounted imaging luminance meter to collect the lighting information of all street lamp units in the tunnel, pre-process the information, and extract the faulty street lamp information; S2, combine all faulty street lamp units in pairs to form a detection pair, use a pre-trained neural network model to perform correlation analysis on the faulty street lamp units in the detection pair, and output the analysis results; S3. According to the analysis results, the fault extension accident chain of the faulty street light unit and the residual faulty street light units are identified.
2. The lighting fixture fault detection method based on a neural network model according to claim 1, characterized in that: The specific steps of S1 are: S11. Using a vehicle-mounted imaging brightness meter to collect the fault occurrence time of all faulty street lamp units in the tunnel, arranging all the faulty street lamp units in the order of the fault occurrence time and marking them with serial numbers; S12, in the order of arrangement, collect the fault characteristic data of all faulty street lamp units in turn to form a faulty street lamp characteristic data set (A1, A2, ..., A i ,...,A j ,...,A n ), where subscript n represents the faulty street light unit n, A n is the fault characteristic data of the faulty street lamp unit n.
3. The lighting fixture fault detection method based on a neural network model according to claim 2, characterized in that: The specific steps of S2 are: S21, combining all faulty street lamp units in pairs to form a detection pair; S22. According to the detection pair, extract the corresponding faulty street lamp feature data in the faulty street lamp feature data set to form a detection pair feature data set. A single detection pair feature data set is represented by (A i ,A j ), where i<j; S23. Use a pre-trained neural network model to analyze and detect the correlation between faulty street lamp units.
4. The lighting fixture fault detection method based on a neural network model according to claim 3, characterized in that: The training method of the neural network model in S23 is: S231, counting the probability of the occurrence of faulty street light unit j after the occurrence of faulty street light unit i in historical fault events; S232, after the faulty street lamp unit i appears in the historical fault event, the probability of the faulty street lamp unit j appearing, the detection pair feature data set (A i ,A j ) as the training data of the neural network, to obtain the conditional probability of the occurrence of faulty street light unit j after the occurrence of faulty street light unit i as the output, to use the actual conditional probability as the prediction target, and to minimize the sum of the prediction accuracies of all predicted conditional probabilities as the training target; S233, the calculation formula of the prediction accuracy is z=(pi→j-Pi→j) 2 , p i→j is the conditional probability of the occurrence of faulty street light unit j after the predicted faulty street light unit i occurs, P i→j is the conditional probability of the occurrence of faulty street light unit j after the actual faulty street light unit i appears, z is the prediction accuracy, and the neural network model is trained until the sum of the prediction accuracies reaches convergence and the training is stopped.
5. The lighting fixture fault detection method based on a neural network model according to claim 4, characterized in that: The specific content of the correlation relationship between the faulty street lamp units in the analysis and detection in S23 is: according to the prediction result output by the neural network model, if the faulty street lamp unit i appears, the conditional probability p of the faulty street lamp unit j appearing i→j >0, it is judged that the faulty street lamp unit i and the faulty street lamp unit j have an associated relationship, otherwise it is judged that the faulty street lamp unit i and the faulty street lamp unit j have no associated relationship.
6. The lighting fixture fault detection method based on a neural network model according to claim 5, characterized in that: The fault extension accident chain of identifying the faulty street lamp unit in S3 includes the following specific steps: S31, identifying an initial faulty street lamp unit according to the fault occurrence time of all faulty street lamp units; S32, extract all detection pairs containing the initial faulty street lamp unit, arrange the conditional probability values predicted by the neural network model in descending order from large to small, identify the faulty street lamp unit with the greatest correlation with the initial faulty street lamp unit, and obtain the first-level faulty street lamp unit expanded from the initial faulty street lamp unit; S33. Repeat the above steps until all faulty street light units are taken into consideration, and obtain the fault extension accident chain of the faulty street light unit.
7. The lighting fixture fault detection method based on a neural network model according to claim 6, characterized in that: The residual faulty street light units in S3 are faulty street light units that have no association with other faulty street light units, that is, discrete faulty street light units outside the fault extension accident chain.
8. A lighting fixture fault detection system based on a neural network model, implemented based on a lighting fixture fault detection method based on a neural network model according to any one of claims 1 to 7, characterized in that: include: Fault collection module, correlation analysis module, fault expansion module; The fault collection module is used to collect the lighting information of all street lamp units in the tunnel using the vehicle-mounted imaging luminance meter, pre-process the information, and extract the faulty street lamp information; The association analysis module is used to combine all faulty street lamp units in pairs to form a detection pair, use a pre-trained neural network model to perform a correlation degree analysis on the faulty street lamp units in the detection pair, and output the analysis results; The fault extension module is used to identify the fault extension accident chain of the faulty street light unit and the residual faulty street light units according to the analysis result.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, a lighting fixture fault detection method based on a neural network model as described in any one of claims 1 to 7 is implemented.
10. An electronic device, characterized in that: It includes a memory for storing instructions; a processor for executing the instructions, so that the device implements a lighting fixture fault detection method based on a neural network model as described in any one of claims 1-7.
Citation Information
Patent Citations
Power grid cascading failure warning method and system
CN112736878A
Electric power communication fault analysis and detection method and system based on neural network
CN114462464A
Cited By
Illumination system fault intelligent diagnosis method and system based on multi-sensor fusion
CN120742168A
