Intelligent analysis and diagnosis method and system for faults of urban rail power supply equipment

Abstract

The invention relates to the technical field of intelligent operation and maintenance, and discloses an intelligent fault analysis and diagnosis method and system for urban rail power supply equipment, and the method comprises the steps: obtaining the operation data and fault data of the urban rail power supply equipment; performing fault early warning analysis according to the operation data to obtain a fault early warning result; fault recording diagnosis is carried out according to the fault data, and a preliminary fault diagnosis result is obtained; and performing comprehensive diagnosis according to the fault early warning result and the preliminary fault diagnosis result to obtain a final fault diagnosis result. According to the method, early warning can be carried out by finding the early fault hidden danger of the power supply equipment, comprehensive diagnosis is carried out according to the fault early warning result and the preliminary fault diagnosis result, the fault reason can be quickly positioned, the professional ability requirement of operation personnel is greatly reduced, the fault handling efficiency is improved, and the reduction of the operation manpower cost and the time cost is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent operation and maintenance, and more specifically, to a method and system for intelligent analysis and diagnosis of faults of urban rail power supply equipment. Background Art

[0002] With the rapid development of urban rail transit in my country, a large number of new lines have been put into operation, which has brought great challenges to the operation and management of urban rail transit. As one of the three core systems of urban rail transit, the safety and reliability of the power supply system are directly related to the safety of trains and passengers. However, the current rail transit power supply system is not highly intelligent and only has basic information monitoring functions. It is unable to realize early fault perception and cannot effectively assist operation and maintenance personnel to quickly diagnose and handle faults after they occur.

[0003] At present, solving power supply system failure problems mainly relies on the experience and expertise of operation and maintenance personnel, combined with the technical support of equipment manufacturers, and supplemented by intelligent systems for fault recording data analysis, real-time monitoring and alarm functions, and advanced fault diagnosis systems to assist in fault location. However, these technical methods still have obvious shortcomings. First, the existing technology lacks the ability to perceive early faults in power supply equipment, resulting in faults often being discovered only after causing serious problems such as equipment shutdown. This is because the existing monitoring system mainly focuses on the current status of the equipment and does not have predictive analysis capabilities. Secondly, the fault data analysis process is highly professional and lacks comprehensive analysis and diagnosis methods. Although the existing intelligent system can assist in data analysis, it still requires highly professional manual interpretation and cannot automatically integrate multi-source data for comprehensive analysis. This results in long fault handling time and increased operating cost losses. Summary of the invention

[0004] In order to overcome the defects of low fault handling efficiency and high operating cost of urban rail power supply equipment in the prior art, the present invention proposes the following technical solutions:

[0005] In a first aspect, the present invention provides a method for intelligent analysis and diagnosis of urban rail power supply equipment faults, comprising:

[0006] Obtain operation data and fault data of urban rail power supply equipment.

[0007] Perform fault warning analysis based on the operating data to obtain a fault warning result.

[0008] Perform fault recording diagnosis based on the fault data to obtain a preliminary fault diagnosis result.

[0009] A comprehensive diagnosis is performed based on the fault warning result and the preliminary fault diagnosis result to obtain a final fault diagnosis result.

[0010] As a preferred technical solution, a fault warning analysis is performed according to the operation data to obtain a fault warning result, including:

[0011] Establish early warning rules.

[0012] Extracting characteristic values ​​of the operation data.

[0013] The characteristic value of the operation data is compared with the conditions in the warning rule. When the characteristic value of the operation data meets the conditions of a certain warning rule, the warning type corresponding to the warning rule is used as the current fault warning result.

[0014] As a preferred technical solution, an early warning is issued when the temperature of the urban rail power supply equipment exceeds a threshold.

[0015] When the amplitude of the partial discharge signal of the urban rail power supply equipment exceeds the threshold, an early warning is issued.

[0016] An early warning is issued when the dissolved gas content in the transformer oil exceeds the threshold.

[0017] When the circuit breaker opening and closing time deviation exceeds the threshold, an early warning is issued.

[0018] When the concentration of sulfur hexafluoride gas in the substation exceeds the threshold, an early warning is issued.

[0019] An early warning will be issued when the change trend of key operating parameters of urban rail power supply equipment exceeds the threshold.

[0020] An early warning will be issued when the key operating parameters of the urban rail power supply equipment exceed the upper and lower limits.

[0021] When the environmental parameters in the substation exceed the threshold, an early warning is issued.

[0022] As a preferred technical solution, a fault recording diagnosis is performed according to the fault data to obtain a preliminary fault diagnosis result, including:

[0023] According to the acquired fault data of the urban rail power supply equipment, a fault recording analysis and diagnosis model is constructed and trained using the MultiRocket algorithm. The fault data includes instantaneous parameter waveform data of the urban rail power supply equipment.

[0024] The fault data is input into the trained fault recording analysis and diagnosis model for fault recording diagnosis to obtain preliminary fault diagnosis results.

[0025] The fault recording diagnosis classification model adopts a supervised learning method to extract and map the feature vector of the fault data with the corresponding fault type label, and outputs the corresponding fault type as a preliminary fault diagnosis result.

[0026] As a preferred technical solution, after acquiring the fault data and before performing fault recording diagnosis according to the fault data, the method further includes:

[0027] Construct fault cleaning judgment rules;

[0028] According to the fault cleaning judgment rule, the fault data is associated and judged to obtain the real fault data and the incidental fault data;

[0029] retaining the real fault data and filtering the accompanying fault data;

[0030] Wherein, the fault cleaning judgment rules include:

[0031] When a single fault of a specific type occurs, the acquired fault data is judged as real fault data;

[0032] When two or more related faults occur simultaneously, the acquired fault data is judged as real fault data;

[0033] When the interlocking logic and joint adjustment logic inside the urban rail power supply equipment triggers a fault in other auxiliary equipment, the acquired fault data is judged as incidental fault data.

[0034] As a preferred technical solution, after obtaining the final fault diagnosis result, the method further includes:

[0035] According to the fault diagnosis results, the cause and type of the fault are analyzed, and according to the fault analysis results, the corresponding type of fault handling suggestions are retrieved from the threshold fault handling database for output.

[0036] In a second aspect, the present invention further proposes an intelligent analysis and diagnosis system for urban rail power supply equipment faults, which is applied to the intelligent analysis and diagnosis method for urban rail power supply equipment faults as described in any scheme of the first aspect, and includes: a data analysis platform, a data acquisition device and a fiber optic ring network.

[0037] The data acquisition device is arranged in the substation of the urban rail power supply system, and is used to obtain and upload the operation data and fault data of the urban rail power supply equipment to the data analysis platform through the optical fiber ring network.

[0038] The data analysis platform includes a fault early warning unit, a fault recording diagnosis unit based on the operating data, and a comprehensive fault diagnosis unit.

[0039] The fault warning unit is used to perform fault warning analysis according to the operation data to obtain a fault warning result.

[0040] The fault recording diagnosis unit is used to perform fault recording diagnosis according to the fault data to obtain a preliminary fault diagnosis result.

[0041] The comprehensive fault diagnosis unit is used to perform comprehensive diagnosis based on the fault warning result and the preliminary fault diagnosis result to obtain a final fault diagnosis result.

[0042] As a preferred technical solution, the data acquisition device includes an urban rail power supply equipment monitoring unit, a substation environment monitoring unit, a PSCADA data acquisition unit and an offline data acquisition unit.

[0043] The urban rail power supply equipment monitoring unit is used to monitor and obtain status data and fault data of the urban rail power supply equipment.

[0044] The substation environment monitoring unit is used to monitor and obtain the environment data inside the substation.

[0045] The PSCADA data acquisition unit is used to acquire telesignaling and telemetry data of urban rail power supply equipment.

[0046] The offline data acquisition unit is used to acquire historical operation and maintenance data of urban rail power supply equipment.

[0047] As a preferred technical solution, the urban rail power supply equipment monitored by the urban rail power supply equipment monitoring unit includes at least one of the following: a dry-type transformer, an energy feedback device, a medium-voltage switchgear, a DC switchgear, a low-voltage switchgear, a rectifier, an AC / DC panel, an oil-immersed transformer, a high-voltage switchgear, a lightning arrester, a mutual inductor and a reactive compensation device.

[0048] As a preferred technical solution, a water immersion sensor is used to monitor the water leakage status of the substation and the water immersion status of the cable trench.

[0049] Noise sensor is used to monitor the noise of transformer in substation.

[0050] Temperature and humidity sensors are used to monitor the temperature and humidity in the substation.

[0051] Gas sensors are used to monitor oxygen and sulfur hexafluoride concentrations in cable trenches.

[0052] Dust sensor is used to monitor PM10 concentration in the substation.

[0053] The beneficial effects of the present invention include at least:

[0054] (1) The intelligent analysis and diagnosis method for urban rail power supply equipment faults provided by the present invention can achieve multiple advantages by obtaining equipment operation data and performing fault warning analysis, real-time fault diagnosis and comprehensive diagnosis. First, the method can timely discover the early fault hazards of the equipment and perform planned preventive inspection and maintenance on the equipment, which not only ensures the safety and reliability of the power supply system, but also greatly reduces the operating cost losses caused by equipment failures. Secondly, through intelligent analysis and diagnosis of fault recording data, the cause of the fault can be quickly located without relying on the participation of professional equipment manufacturers, thereby reducing operation and maintenance costs. In addition, the use of comprehensive analysis to diagnose fault information greatly reduces the professional ability requirements of operating personnel, improves the efficiency of fault handling, and achieves a reduction in operating manpower and time costs.

[0055] (2) The intelligent analysis and diagnosis system for urban rail power supply equipment faults provided by the present invention monitors the key environmental factors of the substation in real time by deploying an environmental monitoring unit in the substation. On the one hand, it can timely discover abnormal conditions in the substation environment, provide a basis for preventing equipment failures, and help ensure the safe operation of the power supply system. On the other hand, after an equipment failure occurs, the analysis of the substation environmental data can provide reference information for troubleshooting the cause of the failure and improve the efficiency of fault handling. In addition, continuous monitoring of substation environmental factors helps to optimize the operation and management of the equipment and ensure the normal operation of the equipment, thereby improving the reliability and service life of the equipment and reducing maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a flow chart of the intelligent analysis and diagnosis method for urban rail power supply equipment faults provided in Example 1.

[0057] Figure 2 This is a schematic diagram of the process of performing fault warning analysis provided in Example 2.

[0058] Figure 3 This is a schematic diagram of the comprehensive fault diagnosis process provided in Example 2.

[0059] Figure 4 This is an architectural diagram of the urban rail power supply equipment fault intelligent analysis and diagnosis system provided in Example 3. DETAILED DESCRIPTION

[0060] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred technical solutions. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred technical solutions are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0061] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0062] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0063] Example 1

[0064] This embodiment proposes an intelligent analysis and diagnosis method for urban rail power supply equipment faults, such as Figure 1 As shown, Figure 1 A flow chart of a method for intelligent analysis and diagnosis of urban rail power supply equipment faults provided in this embodiment, the method comprising the following steps:

[0065] S1: Obtain the operation data and fault data of urban rail power supply equipment.

[0066] S2: Performing fault warning analysis according to the operation data to obtain a fault warning result.

[0067] S3: Perform fault recording diagnosis according to the fault data to obtain a preliminary fault diagnosis result.

[0068] S4: Perform comprehensive diagnosis based on the fault warning result and the preliminary fault diagnosis result to obtain a final fault diagnosis result.

[0069] It is understandable that by obtaining equipment operation data and performing fault warning analysis, real-time fault diagnosis and comprehensive diagnosis, many advantages can be achieved. First, this method can promptly detect the early fault hazards of equipment and carry out planned preventive maintenance of the equipment, which not only ensures the safety and reliability of the power supply system, but also greatly reduces the operating cost losses caused by equipment failure. Secondly, through intelligent analysis and diagnosis of fault recording data, the cause of the fault can be quickly located without relying on the participation of professional equipment manufacturers, thereby reducing operation and maintenance costs. In addition, the use of comprehensive analysis to diagnose fault information greatly reduces the professional ability requirements of operators, improves the efficiency of fault handling, and reduces operating labor costs and time costs.

[0070] Example 2

[0071] This embodiment makes improvements based on the intelligent analysis and diagnosis method for urban rail power supply equipment faults proposed in the first embodiment.

[0072] In this embodiment, a fault warning analysis is performed based on the operation data to obtain a fault warning result, including:

[0073] Establish early warning rules.

[0074] Extracting characteristic values ​​of the operation data.

[0075] The characteristic value of the operation data is compared with the conditions in the warning rule. When the characteristic value of the operation data meets the conditions of a certain warning rule, the warning type corresponding to the warning rule is used as the current fault warning result.

[0076] In the specific implementation process, Figure 2 As shown in the figure, first, various power monitoring data of the power supply equipment are collected through the real-time data acquisition system. At the same time, intelligent sensing equipment is used to collect non-power parameters, such as temperature and vibration. These data are crucial for a comprehensive assessment of the equipment status. In addition, it also includes the collection of offline data of the equipment, such as factory test records and regular test data. These historical information helps to understand the performance trends and potential problems of the equipment. After the data collection is completed, data preprocessing is performed, including cleaning, formatting and normalization to ensure the accuracy and consistency of the data. Subsequently, key feature values ​​are extracted from the preprocessed data through data mining and machine learning techniques. These feature values ​​can reflect the actual operating status of the equipment.

[0077] Based on feature extraction, early warning rules are formulated according to historical fault data and expert experience. These rules define abnormal patterns of equipment status, such as a sudden drop in voltage or an abnormal increase in temperature. Next, the extracted feature values ​​are compared with the conditions in the early warning rules. This step can be achieved by setting thresholds or using classification algorithms. When the feature value meets the conditions of a certain early warning rule, the system will automatically mark the early warning type corresponding to the rule as the current fault early warning result. The fault early warning results will be output to the monitoring system in real time for operation and maintenance personnel to view and analyze. Depending on the severity of the early warning results, corresponding preventive measures or emergency response measures can be taken, such as adjusting equipment operating parameters or arranging maintenance personnel to conduct inspections. In addition, the accuracy and effectiveness of fault early warnings are reviewed and analyzed regularly, and the early warning rules are adjusted and optimized based on actual operation and maintenance experience to improve the accuracy and timeliness of fault early warnings. Through this continuous and dynamic early warning analysis process, the failure of urban rail power supply equipment can be effectively prevented and reduced, the stable operation of the power supply system can be guaranteed, and serious consequences such as vehicle shutdowns caused by equipment failures can be avoided.

[0078] In this embodiment, an early warning is issued when the temperature of the urban rail power supply equipment exceeds a threshold value.

[0079] When the amplitude of the partial discharge signal of the urban rail power supply equipment exceeds the threshold, an early warning is issued.

[0080] An early warning is issued when the dissolved gas content in the transformer oil exceeds the threshold.

[0081] When the circuit breaker opening and closing time deviation exceeds the threshold, an early warning is issued.

[0082] When the concentration of sulfur hexafluoride gas in the substation exceeds the threshold, an early warning is issued.

[0083] An early warning will be issued when the change trend of key operating parameters of urban rail power supply equipment exceeds the threshold.

[0084] An early warning will be issued when the key operating parameters of the urban rail power supply equipment exceed the upper and lower limits.

[0085] When the environmental parameters in the substation exceed the threshold, an early warning is issued.

[0086] In the specific implementation process, first of all, the system will monitor the key operating parameters of the urban rail power supply equipment in real time, including temperature, partial discharge signal, dissolved gas content in transformer oil, circuit breaker opening and closing time, sulfur hexafluoride gas concentration, equipment operating parameter change trend, etc. When any of these parameters exceeds the preset safety threshold, the system will immediately issue a corresponding fault warning. For example, when the equipment temperature is higher than the set value, a temperature abnormality warning is issued; when the amplitude of the partial discharge signal exceeds the standard, a partial discharge abnormality warning is issued; when the dissolved gas content in the transformer oil is too high, an oil chromatogram abnormality warning is issued.

[0087] In this embodiment, after the fault data is obtained, the fault data is cleaned as follows:

[0088] Construct fault cleaning judgment rules.

[0089] According to the fault cleaning judgment rule, the fault data is associated and judged to obtain the real fault data and the incidental fault data.

[0090] The real fault data is retained, and the accompanying fault data is filtered.

[0091] Wherein, the fault cleaning judgment rules include:

[0092] When a single fault of a specific type occurs, the acquired fault data is determined to be true fault data.

[0093] When two or more related faults occur simultaneously, the acquired fault data is determined to be true fault data.

[0094] When the interlocking logic and joint adjustment logic inside the urban rail power supply equipment triggers a fault in other auxiliary equipment, the acquired fault data is judged as incidental fault data.

[0095] In the specific implementation process, assuming that a power supply failure occurs on a certain urban rail line, the relevant fault data is first obtained. After analysis, it is found that in addition to the core problem that causes the current power supply failure, some incidental faults have also occurred, such as contact network disconnection and pantograph failure. The occurrence of these incidental faults is likely to be caused by the triggering of the interlocking logic and joint adjustment logic within the urban rail system. In response to this situation, first of all, according to the working principle and fault characteristics of the urban rail power supply equipment, the fault cleaning judgment rules are constructed in advance. These include: when a single fault of a specific type such as a power supply failure occurs, the acquired data is judged as a real fault; when two related faults such as contact network disconnection and pantograph failure occur at the same time, the acquired data is also judged as a real fault; and when other auxiliary equipment faults are triggered due to the interlocking logic, the acquired data is judged as an incidental fault.

[0096] After obtaining the actual fault data, the fault data was analyzed in association with these pre-established cleaning rules. Through this step, the real fault data and incidental fault data were successfully distinguished. The real fault of power supply failure was retained for subsequent fault recording diagnosis and analysis; while incidental faults such as contact network disconnection and pantograph failure were filtered to remove the interference information caused by the system interlocking logic.

[0097] Finally, through effective fault data cleaning, the root cause of the current power supply failure was accurately found, which improved the accuracy of fault analysis. At the same time, it also greatly reduced the impact of interference information on subsequent fault troubleshooting work and significantly improved the overall efficiency of fault handling.

[0098] In this embodiment, a fault recording diagnosis is performed according to the fault data to obtain a preliminary fault diagnosis result, including:

[0099] According to the acquired fault data of the urban rail power supply equipment, a fault recording analysis and diagnosis model is constructed and trained using the MultiRocket algorithm. The fault data includes instantaneous parameter waveform data of the urban rail power supply equipment.

[0100] The fault data is input into the trained fault recording analysis and diagnosis model for fault recording diagnosis to obtain preliminary fault diagnosis results.

[0101] The fault recording diagnosis classification model adopts a supervised learning method to extract and map the feature vector of the fault data with the corresponding fault type label, and outputs the corresponding fault type as a preliminary fault diagnosis result.

[0102] In the specific implementation process, when the urban rail power supply equipment fails, the equipment's protection device will be directly connected through the on-site data acquisition device to remotely obtain the equipment's fault recording data. These fault recording data include waveform data of multi-dimensional parameters such as the equipment's instantaneous voltage, current, and temperature. The collected real-time fault recording data are input into the fault diagnosis classification model that was pre-trained and constructed using the MultiRocket algorithm. The model uses supervised learning to extract the feature vector of the fault data and associate it with the pre-defined fault type label to map it, so that it can output preliminary fault diagnosis results and give the specific fault type.

[0103] For example, when an abnormal opening and closing time of a circuit breaker is detected, the fault recording data of the circuit breaker will be immediately obtained and imported into the diagnostic model for analysis. The model will quickly identify the fault as a circuit breaker fault type based on the characteristics of the waveform data, and thus give a preliminary diagnostic result. Based on this preliminary result, combined with other fault warning information, further comprehensive analysis can be carried out to determine the root cause of the fault.

[0104] This intelligent analysis and diagnosis method of fault recording data can not only greatly improve the efficiency of fault analysis and processing, but also continuously optimize and improve the fault diagnosis model as the operating time increases, realize automatic analysis and diagnosis of most faults, and quickly give the root cause of the fault, thereby greatly improving the reliability and safety of urban rail power supply equipment.

[0105] In this embodiment, after obtaining the final fault diagnosis result, the method further includes:

[0106] According to the fault diagnosis results, the cause and type of the fault are analyzed, and according to the fault analysis results, the corresponding type of fault handling suggestions are retrieved from the threshold fault handling database for output.

[0107] In the specific implementation process, Figure 3 As shown in the figure, first, the fault information is automatically reported through the PSCADA system (Power System Control And Data Acquisition, power monitoring system) and uploaded to the line-level data analysis platform. After receiving the fault data, the platform performs fault cleaning, which is a step to filter out irrelevant interference information and ensure the accuracy of subsequent analysis. The cleaned data will be used in the fault tree analysis model, which uses logical judgment and decision tree algorithm to preliminarily locate the fault and identify possible fault sources.

[0108] After completing the initial location, the platform further uses device-level correlation data analysis to conduct in-depth analysis of the fault. This includes fault recording analysis, which identifies fault characteristics by analyzing the changes in current and voltage waveforms when the fault occurs. Intelligent monitoring data analysis uses real-time monitoring data to compare with historical data to discover abnormal patterns. Similar fault analysis extracts common features and assists in diagnosis by comparing historical similar fault cases.

[0109] During the automatic diagnosis process, the fault analysis results will be updated in real time, and the corresponding fault handling suggestions will be retrieved from the fault handling database based on these results. The database has preset handling suggestions for various faults, including the specific terminal numbers of the devices that need to be checked, the specific schematic drawings related to the faults, the specific steps of troubleshooting, etc., to provide detailed fault handling guidance for operators. If the automatic diagnosis results cannot completely solve the problem and professional technicians are required to further investigate and analyze, data support for manual fault handling can be provided. This includes detailed viewing of fault recording data, real-time and historical data analysis of related equipment, review of historical fault handling records, and viewing of drawings such as schematics and wiring diagrams. All of these data and information will be displayed centrally to improve data acquisition efficiency and assist technicians in quickly and accurately diagnosing and handling faults.

[0110] In addition, the fault handling process also involves substation-level and equipment-level fault handling, including correlation analysis of specific equipment, such as 35kV switchgear, 1500V switchgear, dry-type transformers, energy feedback devices, and rectifiers. These devices may require special attention and analysis because they are key components in the power supply system. After the initial positioning, further positioning is required, which may involve more detailed data analysis and diagnosis to ensure the accurate identification of the fault source. The entire comprehensive fault diagnosis process is a combination of automation and manual analysis, aiming to achieve fast and accurate fault location and disposal through the integration of intelligent data analysis and expert experience, thereby ensuring the stable operation of the urban rail power supply system.

[0111] It is understandable that by obtaining equipment operation data and performing fault warning analysis, real-time fault diagnosis and comprehensive diagnosis, many advantages can be achieved. First, this method can promptly detect the early fault hazards of equipment and carry out planned preventive maintenance of the equipment, which not only ensures the safety and reliability of the power supply system, but also greatly reduces the operating cost losses caused by equipment failure. Secondly, through intelligent analysis and diagnosis of fault recording data, the cause of the fault can be quickly located without relying on the participation of professional equipment manufacturers, thereby reducing operation and maintenance costs. In addition, the use of comprehensive analysis to diagnose fault information greatly reduces the professional ability requirements of operators, improves the efficiency of fault handling, and reduces operating labor costs and time costs.

[0112] Example 3

[0113] like Figure 4 As shown, this embodiment proposes an intelligent analysis and diagnosis system for urban rail power supply equipment faults, which is applied to the intelligent analysis and diagnosis method for urban rail power supply equipment faults as described in the above embodiment, including: a data analysis platform, a data acquisition device and a fiber optic ring network.

[0114] The data acquisition device is arranged in the substation of the urban rail power supply system, and is used to obtain and upload the operation data and fault data of the urban rail power supply equipment to the data analysis platform through the optical fiber ring network.

[0115] The data analysis platform is arranged on a cloud platform, and includes a fault early warning unit, a fault recording diagnosis unit according to the operation data, and a fault comprehensive diagnosis unit.

[0116] The fault warning unit is used to perform fault warning analysis according to the operation data to obtain a fault warning result.

[0117] The fault recording diagnosis unit is used to perform fault recording diagnosis according to the fault data to obtain a preliminary fault diagnosis result.

[0118] The comprehensive fault diagnosis unit is used to perform comprehensive diagnosis based on the fault warning result and the preliminary fault diagnosis result to obtain a final fault diagnosis result.

[0119] In this embodiment, the data acquisition device includes an urban rail power supply equipment monitoring unit, a substation environment monitoring unit, a PSCADA data acquisition unit and an offline data acquisition unit.

[0120] The urban rail power supply equipment monitoring unit is used to monitor and obtain status data and fault data of the urban rail power supply equipment.

[0121] The substation environment monitoring unit is used to monitor and obtain the environment data inside the substation.

[0122] The PSCADA data acquisition unit is used to acquire telesignaling and telemetry data of urban rail power supply equipment.

[0123] The offline data acquisition unit is used to acquire historical operation and maintenance data of urban rail power supply equipment.

[0124] In this embodiment, the urban rail power supply equipment monitored by the urban rail power supply equipment monitoring unit includes: dry-type transformers, energy feedback devices, medium-voltage switch cabinets, DC switch cabinets, low-voltage switch cabinets, rectifiers, AC and DC panels, oil-immersed transformers, high-voltage switch cabinets, lightning arresters, mutual inductors and reactive power compensation devices. Corresponding sensors and analysis terminals are arranged on various types of equipment to complete the collection and analysis of key status data. The data analysis results and original data are uniformly uploaded to the on-site data acquisition device server. The specific monitoring items of each device are shown in Tables 1-12:

[0125] Table 1 Monitoring items for dry-type transformers

[0126]

[0127]

[0128] Table 2 Monitoring items of energy feedback device

[0129]

[0130]

[0131] Table 3 Monitoring items of medium voltage switchgear

[0132]

[0133]

[0134] Table 4 DC switch cabinet monitoring items

[0135]

[0136] Table 5 Monitoring items of low voltage switch cabinet

[0137]

[0138]

[0139] Table 6 Rectifier cabinet monitoring points

[0140]

[0141] Table 7 AC and DC screen monitoring items

[0142]

[0143]

[0144] Table 8 AC and DC screen monitoring items

[0145]

[0146] Table 9 High-voltage switchgear monitoring items

[0147]

[0148] Table 10 Lightning arrester monitoring points

[0149]

[0150] Table 11 Transformer monitoring items

[0151]

[0152] Table 12 Monitoring items of reactive power compensation device

[0153]

[0154] In this embodiment, in addition to analyzing and diagnosing the equipment data, various environmental monitoring sensors are arranged in the substation to conduct a real-time assessment of the overall environmental conditions of the substation. These monitoring sensors can fully grasp the environmental parameters such as temperature, humidity, dust concentration, etc. in the substation, and reflect the working environment conditions of the power supply equipment. Environmental monitoring data can not only provide a basis for fault warning, but also issue timely warnings when the environment is abnormal to ensure the safe operation of the power supply system. Moreover, after a fault occurs, by comparing the environmental conditions at the time of the fault, valuable reference information can also be provided for the investigation of the cause of the fault. For example, if it is found that the ambient temperature suddenly rises when a fault occurs, it can be inferred that the fault may be related to overheating of the equipment. Such environmental data plays an important auxiliary role in fault diagnosis. Therefore, using environmental monitoring as an important supplementary means for fault diagnosis of urban rail power supply equipment can more comprehensively and accurately analyze the root cause of the fault and improve the efficiency of fault handling. The specific monitoring items of the substation environment are shown in Table 13:

[0155] Table 13 Environmental monitoring items for substations

[0156]

[0157]

[0158] In this embodiment, the telesignaling and telemetry data of various primary equipment are obtained from the control signal panel communication management machine arranged in the substation by the PSCADA system. The standard IEC60870-5-104 communication protocol is used to exchange data with the PSCADA system. After receiving the real-time monitoring data of various equipment transmitted by PSCADA, these original data are first parsed and sorted to ensure the integrity of the data format and content. Then, these pre-processed equipment operation data are packaged together with the data obtained from other monitoring devices and uploaded to the line-level data analysis platform. These data include multi-dimensional monitoring indicators such as electrical quantity, temperature, vibration, etc. of the equipment, providing comprehensive data support for subsequent fault analysis and diagnosis.

[0159] By using standard communication protocols to seamlessly connect with the PSCADA system, real-time operating data of various equipment in the substation can be obtained efficiently and reliably. When uploading these data to the analysis platform, the uniformity and integrity of the data format are also ensured, which is conducive to subsequent intelligent analysis and application. This link is one of the key links in data collection for the urban rail power supply equipment fault diagnosis system.

[0160] In this embodiment, through the human-computer interaction terminal, the operation and maintenance personnel can import various offline operation and maintenance data accumulated during the operation cycle into the data analysis platform. These offline data include test reports when the equipment leaves the factory, test records of regular inspections, etc. These offline data provide an additional data source for the platform, which will become an important supplement for early fault warning and fault analysis and diagnosis.

[0161] After these offline data are imported into the platform, the system will integrate and analyze them with the real-time monitoring data. For example, the performance parameters of the equipment when it leaves the factory can be used as a normal benchmark, compared with the real-time monitoring data, and abnormal change trends can be found, thereby achieving early warning of the equipment status. Or when analyzing faults, combine the historical test records of the equipment to find out the potential factors that may cause the fault. Therefore, making full use of various offline maintenance data accumulated during operation and incorporating them into the big data system of the data analysis platform can not only enhance the data foundation of the platform, but also improve the accuracy of fault warning and diagnosis, and provide stronger support for improving the reliability and safety of the urban rail power supply system.

[0162] In this embodiment, the data acquisition system of each substation is connected to the line-level data analysis platform by arranging an optical fiber ring network. The construction of the optical fiber ring network can adopt the mode of borrowing the spare optical fiber of the existing communication system, but independently configure the ring network switch. This not only ensures the reliability of communication, even if the main communication link fails, the ring network structure can ensure the smooth transmission of data, but also effectively reduces the cost investment of the construction of the optical fiber ring network. The optical fiber ring network adopts a ring topology structure, and each substation is equipped with an optical fiber ring network switch to connect the data acquisition equipment in the station to the ring network. When any section of the optical fiber line fails, the ring network structure can automatically switch the link to ensure the continuous transmission of data. At the same time, the ring network switch can also aggregate and encode the transmitted data to improve the data transmission efficiency. This method of using existing optical fiber resources but independently constructing the ring network switch not only has high reliability, but also greatly reduces the construction cost of the optical fiber ring network. Through this reliable data transmission channel, the equipment operation data of each substation can be stably and efficiently uploaded to the line-level data analysis platform, providing strong data support for subsequent fault warning and diagnosis.

[0163] It is understandable that by deploying environmental monitoring units in substations and monitoring the key environmental factors of substations in real time, on the one hand, it is possible to timely discover abnormal conditions in the substation environment, provide a basis for preventing equipment failures, and help ensure the safe operation of the power supply system. On the other hand, after an equipment failure occurs, the analysis of substation environmental data can provide reference information for troubleshooting the cause of the failure and improve the efficiency of fault handling. In addition, continuous monitoring of substation environmental factors helps to optimize the operation and management of equipment and ensure the normal operation of equipment, thereby improving the reliability and service life of equipment and reducing maintenance costs.

[0164] It should be noted that the aforementioned explanation of the embodiment of the method for intelligent analysis and diagnosis of urban rail power supply equipment faults is also applicable to the intelligent analysis and diagnosis system for urban rail power supply equipment faults of this embodiment, and will not be repeated here.

[0165] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms are not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0166] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0167] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0168] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array, a field programmable gate array, etc.

[0169] A person skilled in the art may understand that all or part of the steps in the above-mentioned embodiment method may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0170] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. An intelligent analysis and diagnosis method for urban rail power supply equipment faults, characterized in that: include: Obtain operation data and fault data of urban rail power supply equipment; Perform fault warning analysis according to the operating data to obtain a fault warning result; Perform fault recording diagnosis according to the fault data to obtain a preliminary fault diagnosis result; A comprehensive diagnosis is performed based on the fault warning result and the preliminary fault diagnosis result to obtain a final fault diagnosis result.

2. The intelligent analysis and diagnosis method for urban rail power supply equipment fault according to claim 1 is characterized in that: Performing fault warning analysis according to the operation data to obtain fault warning results includes: Formulate early warning rules; extracting characteristic values ​​of the operating data; The characteristic value of the operation data is compared with the conditions in the warning rule. When the characteristic value of the operation data meets the conditions of a certain warning rule, the warning type corresponding to the warning rule is used as the current fault warning result.

3. The intelligent analysis and diagnosis method for urban rail power supply equipment fault according to claim 2 is characterized in that: The warning rules include at least one of the following: Issue an early warning when the temperature of the urban rail power supply equipment exceeds the threshold; When the amplitude of the partial discharge signal of the urban rail power supply equipment exceeds the threshold, an early warning is issued; Issue an early warning when the dissolved gas content in transformer oil exceeds the threshold; When the circuit breaker opening and closing time deviation exceeds the threshold, an early warning is issued; When the sulfur hexafluoride gas concentration in the substation exceeds the threshold, an early warning is issued; Issue an early warning when the change trend of key operating parameters of urban rail power supply equipment exceeds the threshold; Issue an early warning when the key operating parameters of the urban rail power supply equipment exceed the upper and lower limits; When the environmental parameters in the substation exceed the threshold, an early warning is issued.

4. The intelligent analysis and diagnosis method for urban rail power supply equipment fault according to claim 1 is characterized in that: Perform fault recording diagnosis according to the fault data to obtain preliminary fault diagnosis results, including: According to the acquired fault data of the urban rail power supply equipment, a fault recording analysis and diagnosis model is constructed and trained using the MultiRocket algorithm; the fault data includes instantaneous parameter waveform data of the urban rail power supply equipment; The fault data is input into the trained fault recording analysis and diagnosis model to perform fault recording diagnosis and obtain preliminary fault diagnosis results; The fault recording diagnosis classification model adopts a supervised learning method to extract and map the feature vector of the fault data with the corresponding fault type label, and outputs the corresponding fault type as a preliminary fault diagnosis result.

5. The intelligent analysis and diagnosis method for urban rail power supply equipment fault according to claim 1 is characterized in that: After acquiring the fault data and before performing fault recording diagnosis according to the fault data, the method further includes: Construct fault cleaning judgment rules; According to the fault cleaning judgment rule, the fault data is associated and judged to obtain the real fault data and the incidental fault data; retaining the real fault data and filtering the accompanying fault data; Wherein, the fault cleaning judgment rules include: When a single fault of a specific type occurs, the acquired fault data is judged as real fault data; When two or more related faults occur simultaneously, the acquired fault data is judged as real fault data; When the interlocking logic and joint adjustment logic inside the urban rail power supply equipment triggers a fault in other auxiliary equipment, the acquired fault data is judged as incidental fault data.

6. The intelligent analysis and diagnosis method for urban rail power supply equipment fault according to claim 1 is characterized in that: After obtaining the final fault diagnosis result, the method further includes: According to the fault diagnosis results, the cause and type of the fault are analyzed, and according to the fault analysis results, the corresponding type of fault handling suggestions are retrieved from the threshold fault handling database for output.

7. An intelligent analysis and diagnosis system for urban rail power supply equipment faults, characterized in that: include: Data analysis platform, data acquisition device and optical fiber ring network; The data acquisition device is arranged in the substation of the urban rail power supply system, and is used to obtain and upload the operation data and fault data of the urban rail power supply equipment to the data analysis platform through the optical fiber ring network; The data analysis platform includes a fault early warning unit, a fault recording diagnosis unit based on the operation data, and a fault comprehensive diagnosis unit; The fault warning unit is used to perform fault warning analysis according to the operation data to obtain a fault warning result; The fault recording diagnosis unit is used to perform fault recording diagnosis according to the fault data to obtain a preliminary fault diagnosis result; The comprehensive fault diagnosis unit is used to perform comprehensive diagnosis based on the fault warning result and the preliminary fault diagnosis result to obtain a final fault diagnosis result.

8. The intelligent analysis and diagnosis system for urban rail power supply equipment fault according to claim 7 is characterized in that: The data acquisition device includes an urban rail power supply equipment monitoring unit, a substation environment monitoring unit, a PSCADA data acquisition unit and an offline data acquisition unit; The urban rail power supply equipment monitoring unit is used to monitor and obtain status data and fault data of the urban rail power supply equipment; The substation environment monitoring unit is used to monitor and obtain the environmental data inside the substation; The PSCADA data acquisition unit is used to acquire telesignaling and telemetry data of urban rail power supply equipment; The offline data acquisition unit is used to acquire historical operation and maintenance data of urban rail power supply equipment.

9. The intelligent analysis and diagnosis system for urban rail power supply equipment fault according to claim 8 is characterized in that: The urban rail power supply equipment monitored by the urban rail power supply equipment monitoring unit includes at least one of the following: a dry-type transformer, an energy feedback device, a medium-voltage switch cabinet, a DC switch cabinet, a low-voltage switch cabinet, a rectifier, an AC / DC panel, an oil-immersed transformer, a high-voltage switch cabinet, a lightning arrester, a mutual inductor and a reactive power compensation device.

10. The intelligent analysis and diagnosis system for urban rail power supply equipment fault according to claim 8, characterized in that: The substation environment monitoring unit includes at least one of the following: Water immersion sensor, used to monitor the water leakage status of the substation and the water immersion status of the cable trench; Noise sensor, used to monitor the noise of transformers in substations; Temperature and humidity sensors are used to monitor the temperature and humidity in the substation; Gas sensors to monitor oxygen and sulfur hexafluoride concentrations in cable trenches; Dust sensor is used to monitor PM10 concentration in the substation.

Images