A fault analysis system and method for AC and DC turnouts based on fault tree analysis

Abstract

The present invention relates to the field of fault analysis of AC and DC turnout electrical systems, and in particular to an AC and DC turnout fault analysis system and method based on fault tree analysis. The content includes: extracting and normalizing multi-dimensional electrical features to obtain standardized electrical features; introducing feature influence weight matrices to calculate the mapping values ​​of standardized electrical features to fault events; designing feedback factors, and dynamically adjusting the feedback factors according to the standardized electrical features; generating the overall system failure probability based on the adjusted feedback factors and the mapping values ​​of standardized electrical features to fault events; calculating the failure probability of fault events based on the overall system failure probability, and generating the failure probability of basic events based on the failure probability of fault events. The problem of failing to comprehensively consider the interrelationships between multi-dimensional electrical features, failing to fully consider the interactions between levels, and lacking a dynamic feedback mechanism, which makes it impossible to adaptively adjust the probability of fault events, is solved.

Description

Technical Field

[0001] The invention relates to the field of fault analysis of AC and DC turnout electrical systems, and in particular to an AC and DC turnout fault analysis system and method based on fault tree analysis. Background Art

[0002] With the rapid expansion of urban rail transit networks, the reliability and safety of electrical equipment have become increasingly important. As an important component connecting different power supply modes, the AC and DC turnout electrical system has a direct impact on the normal operation and overall safety of the train. Therefore, timely and accurate diagnosis of AC and DC turnout electrical system faults and ensuring its efficient operation are crucial to ensuring the safety and stability of rail transit.

[0003] With the continuous advancement of electrical equipment technology, fault analysis methods are also evolving, but traditional fault analysis methods often fail to fully consider the complexity of AC and DC turnout electrical systems and the correlation between multi-dimensional electrical characteristics. Modern turnout electrical systems have diverse electrical characteristics, such as AC voltage, current, and DC voltage, and changes in these electrical characteristics may affect each other, leading to faults.

[0004] At the same time, existing fault analysis methods also have the problem of failing to comprehensively consider the interrelationships between multi-dimensional electrical characteristics, resulting in incomplete identification of fault causes and easy omission of potential faults, thus affecting the accuracy of fault analysis; and failing to fully consider the interactions between levels, resulting in a lack of systematic analysis of fault events and failure to accurately reflect changes in the overall system state; lacking a dynamic feedback mechanism, and being unable to adaptively adjust the probability of fault events, making it difficult to make timely and effective responses when faced with emergencies.

[0005] Therefore, there is an urgent need for a fault analysis method that can integrate multi-dimensional electrical features to improve the accuracy and real-time performance of fault detection. Summary of the invention

[0006] The present invention provides an AC / DC turnout fault analysis system and method based on fault tree analysis, so as to solve the problems that the mutual relationship between multi-dimensional electrical characteristics cannot be comprehensively considered, resulting in incomplete identification of fault causes and easy omission of potential faults, thus affecting the accuracy of fault analysis; the interaction between levels cannot be fully considered, resulting in the lack of systematic analysis of fault events and the inability to accurately reflect the changes in the overall system state; and there is a lack of dynamic feedback mechanism, which makes it impossible to adaptively adjust the probability of fault events, thus making it difficult to make timely and effective responses when facing emergencies.

[0007] The present invention provides an AC / DC turnout fault analysis system and method based on fault tree analysis, which specifically includes the following technical solutions:

[0008] A fault analysis method for AC and DC turnouts based on fault tree analysis comprises the following steps:

[0009] S1. Collect electrical characteristic data in real time, extract multi-dimensional electrical characteristics based on the electrical characteristic data, and normalize the multi-dimensional electrical characteristics to obtain standardized electrical characteristics; introduce a characteristic influence weight matrix, calculate the correlation between the standardized electrical characteristics and the fault event, and quantify the contribution of the standardized electrical characteristics to the fault event; calculate the mapping value of the standardized electrical characteristics to the fault event based on the characteristic influence weight matrix;

[0010] S2. Design feedback factors and dynamically adjust the feedback factors according to standardized electrical characteristics; generate the overall system failure probability based on the mapping value of the adjusted feedback factors and the standardized electrical characteristics to the fault events; calculate the failure probability of the fault events based on the overall system failure probability; construct a hierarchical structure of the fault tree, and generate the failure probability of the basic events based on the failure probability of the fault events.

[0011] Preferably, the S1 specifically includes:

[0012] Elements of the feature influence weight matrix Calculated by the following formula:

[0013]

[0014] in, Represents standardized electrical characteristics Fault events The association weight between them; , They are the standardized electrical characteristics and the ordinal number of the fault event, respectively; Standardized electrical characteristics Fault events The covariance of , indicating the abnormality of the feature; and The standardized electrical characteristics are and fault events The standard deviation of .

[0015] Preferably, the S2 specifically includes:

[0016] The probability of each fault event is iteratively updated through the feedback factor; at initialization, all feedback factors Set to 1; dynamically adjust the feedback factor as the real-time electrical characteristics change. The update formula of the feedback factor is:

[0017]

[0018] in, For the Level 1 fault events Feedback factor after iterations; is the adjustment factor; Standardized electrical characteristics The mean value of the electrical characteristics normalized to their history Deviation; To prevent the denominator from being zero; Represents a standardized electrical characteristic number.

[0019] Preferably, the S2 specifically includes:

[0020] The iterated feedback factor is combined with the mapping value of the standardized electrical characteristics to the fault event through a hierarchical fault probability superposition formula to form the final overall system failure probability.

[0021] Preferably, the S2 specifically includes:

[0022] The failure probability superposition formula is as follows:

[0023]

[0024] in, Represents the overall failure probability of the system; Indicates the number of fault events; Represents standardized electrical characteristics For fault events The mapping value of is the characteristic adjustment coefficient.

[0025] Preferably, the S2 specifically includes:

[0026] When the overall failure probability of the system exceeds the preset threshold, the reverse deduction process is triggered; in the reverse deduction process, the failure probability of each level of failure events is calculated based on the overall failure probability of the system, and the failure probability of each level of failure events is transferred to the basic event.

[0027] Preferably, the S2 specifically includes:

[0028] Establish a hierarchical structure of the fault tree, list the fault events and corresponding basic events at each level, and identify the logical relationship; the failure probability calculation formula of the basic event is as follows:

[0029]

[0030] in, Is the basic event The probability of failure; Indicates Failure probability of level 1 failure event; For the Level 1 fault events Feedback factor after iterations; The basic event Impact factors under high-level fault events.

[0031] An AC and DC turnout fault analysis system based on fault tree analysis includes the following parts:

[0032] Data acquisition module, data preprocessing module, feature influence weight calculation module, feature mapping module, dynamic feedback adjustment module, fault probability superposition module, reverse deduction module, monitoring module;

[0033] The data acquisition module is responsible for acquiring electrical characteristic data in real time and extracting multi-dimensional electrical characteristics; the data acquisition module is connected to the data preprocessing module;

[0034] The data preprocessing module normalizes the multi-dimensional electrical characteristics to obtain standardized electrical characteristics; the data preprocessing module is connected to the characteristic influence weight calculation module;

[0035] The feature impact weight calculation module calculates the feature impact weight matrix according to the correlation between the standardized electrical features and the fault events; the feature impact weight calculation module is connected to the feature mapping module;

[0036] A feature mapping module combines the feature impact weight matrix with the standardized electrical features to calculate the mapping value of the standardized electrical features to the fault event; the feature mapping module is connected to the dynamic feedback adjustment module;

[0037] The dynamic feedback adjustment module dynamically adjusts the feedback factor according to the changes in real-time electrical characteristics; based on the standardized electrical characteristics, the feedback factor of each level of fault events is updated in real time; the dynamic feedback adjustment module is connected to the fault probability superposition module;

[0038] The fault probability superposition module combines the feedback factor and the mapping value of the standardized electrical characteristics to the fault event through a hierarchical fault probability superposition formula to calculate the overall fault probability of the system; the fault probability superposition module is connected to the reverse derivation module;

[0039] The reverse deduction module triggers the reverse deduction process when the overall failure probability of the system exceeds the preset threshold, calculates the failure probability of each level of failure events according to the overall failure probability of the system, and sequentially passes it down to each basic event to obtain the failure probability of the basic event; the reverse deduction module is connected to the monitoring module;

[0040] The monitoring module is responsible for real-time monitoring of electrical characteristic data, and dynamically updates the failure probability of fault events and the failure probability of basic events in combination with the overall failure probability of the system.

[0041] The beneficial effects of the technical solution of the present invention are:

[0042] 1. By establishing a feature influence weight matrix, the contribution of different electrical features to fault events can be quantified. Based on the correlation between electrical features and fault events, the AC / DC turnout electrical system can better understand the dynamic relationship between electrical features and fault events, thereby improving the accuracy of fault analysis. A feedback factor is introduced to adjust the probability of fault events in real time. The update of the feedback factor is based on the abnormality of the electrical features, so that the AC / DC turnout electrical system can respond quickly to the real-time fluctuations of electrical characteristics, enhancing the adaptability of the fault analysis system in complex environments.

[0043] 2. Through the hierarchical fault probability superposition formula, the interaction between multiple levels can be comprehensively considered to reflect the failure risk of the entire AC and DC turnout electrical system, ensuring that the fault events at each level can fully reflect the changes in the status of the overall AC and DC turnout electrical system, and optimizing the fault identification and handling plan; by establishing a hierarchical structure of the fault tree, the logical relationship between each fault event and the basic event is clarified, providing a clear fault analysis path, making the derivation and handling of faults more efficient.

[0044] 3. The AC / DC turnout electrical system can obtain the electrical characteristic data of the turnout system in real time during each monitoring process, and dynamically update the failure probability of the fault event in combination with the existing overall system failure probability, and then update the failure probability of the basic event, ensuring that the failure probability always reflects the actual status of the current AC / DC turnout electrical system, and improving the accuracy and real-time performance of fault analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is a structural diagram of an AC / DC turnout fault analysis system based on fault tree analysis according to the present invention;

[0046] Figure 2 The present invention provides a flow chart of an AC / DC turnout fault analysis method based on fault tree analysis. DETAILED DESCRIPTION

[0047] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0049] The specific scheme of an AC / DC turnout fault analysis system and method based on fault tree analysis provided by the present invention is described in detail below with reference to the accompanying drawings.

[0050] See attached Figure 1 , which shows a structure diagram of an AC / DC turnout fault analysis system based on fault tree analysis provided by an embodiment of the present invention, the system includes the following parts:

[0051] Data acquisition module, data preprocessing module, feature influence weight calculation module, feature mapping module, dynamic feedback adjustment module, fault probability superposition module, reverse deduction module, monitoring module;

[0052] The data acquisition module is responsible for acquiring the electrical characteristic data of the AC and DC turnout electrical system in real time, and performs high-frequency acquisition through the sensor network to ensure the timeliness and accuracy of the electrical characteristic data; and extracts multi-dimensional electrical characteristics from the sensor network of the AC and DC turnout electrical system; the data acquisition module is connected to the data preprocessing module;

[0053] The data preprocessing module normalizes the multi-dimensional electrical characteristics to obtain standardized electrical characteristics; the data preprocessing module is connected to the characteristic influence weight calculation module;

[0054] The feature impact weight calculation module calculates the feature impact weight matrix according to the correlation between the standardized electrical features and the fault events; the feature impact weight calculation module is connected to the feature mapping module;

[0055] A feature mapping module combines the feature impact weight matrix with the standardized electrical features to calculate the mapping value of the standardized electrical features to the fault event; the feature mapping module is connected to the dynamic feedback adjustment module;

[0056] The dynamic feedback adjustment module is responsible for dynamically adjusting the feedback factor according to the changes in real-time electrical characteristics, and updating the feedback factor of each level of fault events in real time according to the abnormality of the standardized electrical characteristics; the dynamic feedback adjustment module is connected to the fault probability superposition module;

[0057] The fault probability superposition module combines the feedback factor and the mapping value of the standardized electrical characteristics to the fault event through a hierarchical fault probability superposition formula to calculate the overall fault probability of the system; the fault probability superposition module is connected to the reverse derivation module;

[0058] Reverse deduction module: When the overall failure probability of the system exceeds the preset threshold, the AC and DC turnout electrical system automatically triggers the adaptive reverse deduction process, realizing the transmission of the failure probability of high-level failure events to low-level basic events. The probability of each level of failure events is calculated according to the overall failure probability of the system, and is sequentially transmitted downward to each basic event to obtain the failure probability of the basic event. The reverse deduction module is connected to the monitoring module;

[0059] The monitoring module is responsible for real-time monitoring of the electrical characteristic data of the AC and DC turnout electrical systems, and dynamically updates the failure probability of fault events and the failure probability of basic events in combination with the existing overall system failure probability.

[0060] See attached Figure 2 , which shows a flow chart of an AC / DC turnout fault analysis method based on fault tree analysis provided by an embodiment of the present invention, the method comprising the following steps:

[0061] S1. Collect electrical characteristic data in real time, extract multi-dimensional electrical characteristics based on the electrical characteristic data, and normalize the multi-dimensional electrical characteristics to obtain standardized electrical characteristics; introduce a characteristic influence weight matrix, calculate the correlation between the standardized electrical characteristics and the fault event, and quantify the contribution of the standardized electrical characteristics to the fault event; calculate the mapping value of the standardized electrical characteristics to the fault event based on the characteristic influence weight matrix;

[0062] The electrical characteristic data of the AC / DC turnout electrical system is collected in real time through the sensor network, and multi-dimensional electrical characteristics are extracted from the sensor network of the AC / DC turnout electrical system, including important parameters such as AC voltage, AC current, DC voltage, DC current, and current fluctuation rate. In order to ensure the calculation consistency of each electrical characteristic data in subsequent steps, the multi-dimensional electrical characteristics need to be normalized to obtain standardized electrical characteristics.

[0063] Standardized electrical characteristics are used to describe the electrical state of the AC / DC turnout electrical system under different power supply modes, and are the basis for subsequent calculations. In order to quantify the contribution of each electrical characteristic to different fault events, a feature impact weight matrix is ​​introduced to reflect the dynamic correlation structure between electrical characteristics and fault events. The elements are characterized by standardized electrical characteristics Fault events The correlation is calculated. , are the standardized electrical characteristics and the ordinal number of the fault event respectively. Set the feature influence weight matrix for Dimension, where represents the standardized electrical characteristic number, Represents the number of failure events. Elements of the feature impact weight matrix Calculated by the following formula:

[0064]

[0065] in, Represents standardized electrical characteristics Fault events The association weight between them; Standardized electrical characteristics Fault events The covariance of , which indicates the characteristic abnormality, is used to describe the standardized electrical characteristics Fault events The correlation between and The standardized electrical characteristics are and fault events The standard deviation of is used to standardize the covariance so that the correlation between different electrical characteristics is consistent. The feature influence weight matrix obtained by calculation It can reasonably reflect the actual impact of electrical characteristics on each fault event, avoid unnecessary feature calculations, and improve overall efficiency. The final feature impact weight matrix is ​​as follows:

[0066]

[0067] The relationship between each electrical characteristic parameter and different fault events can be quantitatively described through the characteristic influence weight matrix. In order to further obtain the mapping value of each standardized electrical characteristic and describe the contribution relationship of the electrical characteristic to different fault events, each standardized electrical characteristic is weighted, and the characteristic mapping formula is used:

[0068]

[0069] in, Represents standardized electrical characteristics For fault events After the random mapping is completed, the mapping values ​​of all standardized electrical characteristics will be used in the dynamic feedback iteration process to further improve the accuracy of fault diagnosis.

[0070] S2. Design feedback factors and dynamically adjust the feedback factors according to standardized electrical characteristics; generate the overall system failure probability based on the mapping value of the adjusted feedback factors and the standardized electrical characteristics to the fault events; calculate the failure probability of the fault events based on the overall system failure probability; construct a hierarchical structure of the fault tree, and generate the failure probability of the basic events based on the failure probability of the fault events.

[0071] After the mapping value is determined, the dynamic feedback iteration process is entered to achieve the adaptive association between the feature mapping and the system fault, and to design a dynamic feedback factor to iteratively update the probability of each fault event. Set to 1; as the real-time electrical characteristics of the AC and DC turnout electrical system change, the feedback factor is dynamically adjusted according to the abnormality of the standardized electrical characteristics to improve the responsiveness of the AC and DC turnout electrical system to real-time changes. The update formula of the feedback factor is:

[0072]

[0073] in, For the Level 1 fault events The feedback factor after the iteration is used to reflect the impact of the change of standardized electrical characteristics on the event probability; is the adjustment coefficient, which is used to adjust the amplitude of feedback change; Standardized electrical characteristics The mean value of the electrical characteristics normalized to their history The deviation is used to describe the degree of deviation between the current standardized electrical characteristics and the stable state, reflecting the abnormal state of the electrical characteristics; To prevent the denominator from being a constant of zero, the feedback factor is updated according to the characteristic abnormality after each iteration, thereby ensuring that the fault probability dynamically adapts to the changes in the electrical characteristics of the turnout in a complex environment and improving the analysis accuracy.

[0074] After the feedback factor is updated, the iterated feedback factor is combined with the mapping value of the standardized electrical characteristics to the fault event through the hierarchical fault probability superposition formula to form the final overall system fault probability; due to the multi-level structure of the AC and DC turnout electrical system, the interaction between multiple levels needs to be considered when calculating the fault probability. The fault probability superposition formula is defined as follows:

[0075]

[0076] in, It represents the overall failure probability of the system, reflecting the overall failure risk of the AC and DC turnout electrical system; is the characteristic adjustment coefficient, which further corrects the influence of the standardized electrical characteristics on the overall failure probability of the system. Through the fault probability superposition formula, the overall failure probability of the system can be obtained under the superposition of multi-dimensional characteristics, and the real-time monitoring of AC and DC turnout electrical system faults can be realized.

[0077] When the overall failure probability of the system exceeds the threshold preset according to the expert experience method, the AC / DC turnout electrical system automatically triggers the adaptive reverse deduction process to reversely deduce the top-level fault events; during the reverse deduction process, the AC / DC turnout electrical system first calculates the probability of the first-level fault events based on the overall failure probability of the system, and then passes the failure probability of the first-level fault events to the lower-level basic events to ensure that each level of fault events can reflect the changes in the overall system status; basic events are the basic elements that constitute higher-level fault events, and the impact of the occurrence of each basic event on the overall system cannot be ignored; through the hierarchical reverse deduction formula, step by step backtracking, ensure that all fault events can be evaluated under the guidance of the overall failure probability of the system, thereby optimizing fault identification and handling solutions. The failure probability calculation formula for level 1 failure events is:

[0078]

[0079] in, Indicates The failure probability of the level failure event reflects the relative risk level of each failure event through the combination of the overall failure probability of the system and the feedback factor; The function is used to deviate from the feature, i.e. , nonlinear processing is performed to limit the excessive impact of characteristic deviation on the failure probability and maintain the stability of the recursive process; For the Level 1 fault events The feedback factor after iterations.

[0080] Based on Failure probability of level 1 failure event , defines the probability of each lower-level basic event. In order to calculate the probability of the basic event, the logical structure of the fault tree is used to set the relationship between the basic event and the high-level fault event. The hierarchical reverse deduction formula is used to dynamically adjust the fault events at each level. The specific steps are as follows:

[0081] Establish a hierarchical structure of the fault tree. The fault events at each level and their corresponding basic events are clearly listed and their logical relationships are identified. By reverse derivation of the formula, Failure probability of level 1 failure event Start from, and pass it down to each basic event in turn. The failure probability of the basic event is defined as:

[0082]

[0083] in, Is the basic event The probability of failure; The basic event The impact factor under the high-level fault event reflects the impact of the high-level fault event on the basic event. The gradual transmission ensures that the changes of the high-level fault event can be fed back to all related basic events in a timely manner.

[0084] During each monitoring process, the electrical characteristic data of the AC and DC turnout electrical system is obtained in real time, and the failure probability of the fault event is dynamically updated in combination with the existing overall system failure probability. Through dynamic adjustment, the failure probability of the basic event will also be updated to ensure that the current system status of the AC and DC turnout electrical system is reflected.

[0085] In summary, a fault tree analysis-based AC and DC turnout fault analysis system and method are completed.

[0086] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0087] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0088] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A method for analyzing AC and DC turnout faults based on fault tree analysis, characterized in that: The following steps are involved: S1. Collect electrical characteristic data in real time, extract multi-dimensional electrical characteristics based on the electrical characteristic data, and normalize the multi-dimensional electrical characteristics to obtain standardized electrical characteristics; The feature impact weight matrix is ​​introduced to quantify the contribution of standardized electrical features to fault events by calculating the correlation between the standardized electrical features and fault events. Based on the feature impact weight matrix, the mapping value of the standardized electrical feature to the fault event is calculated; S2. Design the feedback factor and dynamically adjust the feedback factor according to the standardized electrical characteristics; The adjusted feedback factor is combined with the mapping value of the standardized electrical characteristics to the fault event through a hierarchical fault probability superposition formula to generate the overall system fault probability; the fault probability superposition formula is as follows: , in, Represents the overall failure probability of the system; Indicates the number of fault events; For the Level 1 fault events Feedback factor after iterations; Represents a standardized electrical characteristic number; Represents standardized electrical characteristics For fault events The mapping value of is the characteristic adjustment coefficient; represents the mean of the historically normalized electrical characteristics; Standardized electrical characteristics The standard deviation of To prevent the denominator from being zero; , They are the standardized electrical characteristics and the ordinal number of the fault event, respectively; The failure probability of the fault event is calculated based on the overall failure probability of the system; a hierarchical structure of the fault tree is constructed, and the failure probability of the basic event is generated based on the failure probability of the fault event.

2. The AC / DC turnout fault analysis method based on fault tree analysis according to claim 1 is characterized in that: The S1 specifically includes: Elements of the feature influence weight matrix Calculated by the following formula: , in, Represents standardized electrical characteristics Fault events The association weight between them; Standardized electrical characteristics Fault events The covariance of , indicating the abnormality of the feature; and The standardized electrical characteristics are and fault events The standard deviation of .

3. The AC / DC turnout fault analysis method based on fault tree analysis according to claim 1 is characterized in that: The S2 specifically includes: The probability of each fault event is iteratively updated through the feedback factor; at initialization, all feedback factors Set to 1; dynamically adjust the feedback factor as the real-time electrical characteristics change. The update formula of the feedback factor is: , in, For the Level 1 fault events Feedback factor after iterations; is the adjustment factor; Standardized electrical characteristics The mean value of the electrical characteristics normalized to their history deviation.

4. The AC / DC turnout fault analysis method based on fault tree analysis according to claim 1 is characterized in that: The S2 specifically includes: When the overall failure probability of the system exceeds the preset threshold, the reverse deduction process is triggered; in the reverse deduction process, the failure probability of each level of failure events is calculated based on the overall failure probability of the system, and the failure probability of each level of failure events is transferred to the basic event.

5. The AC / DC turnout fault analysis method based on fault tree analysis according to claim 4 is characterized in that: The S2 specifically includes: Establish a hierarchical structure of the fault tree, list the fault events and corresponding basic events at each level, and identify the logical relationship; the failure probability calculation formula of the basic event is as follows: , in, Is the basic event The probability of failure; Indicates Failure probability of level 1 failure event; For the Level 1 fault events Feedback factor after iterations; The basic event Impact factors under high-level fault events.

6. An AC / DC turnout fault analysis system based on fault tree analysis, applied to the AC / DC turnout fault analysis method based on fault tree analysis according to claim 1, characterized in that: Includes the following parts: Data acquisition module, data preprocessing module, feature influence weight calculation module, feature mapping module, dynamic feedback adjustment module, fault probability superposition module, reverse deduction module, monitoring module; The data acquisition module is responsible for acquiring electrical characteristic data in real time and extracting multi-dimensional electrical features; The data acquisition module is connected to the data preprocessing module; The data preprocessing module normalizes the multi-dimensional electrical characteristics to obtain standardized electrical characteristics; The data preprocessing module is connected to the feature influence weight calculation module; A feature impact weight calculation module calculates a feature impact weight matrix based on the correlation between the standardized electrical features and the fault events; feature The influence weight calculation module is connected to the feature mapping module; A feature mapping module combines the feature impact weight matrix with the standardized electrical features to calculate the mapping value of the standardized electrical features to the fault event; the feature mapping module is connected to the dynamic feedback adjustment module; The dynamic feedback adjustment module dynamically adjusts the feedback factor according to the changes in real-time electrical characteristics; based on the standardized electrical characteristics, the feedback factor of each level of fault events is updated in real time; the dynamic feedback adjustment module is connected to the fault probability superposition module; The fault probability superposition module combines the feedback factor and the mapping value of the standardized electrical characteristics to the fault event through a hierarchical fault probability superposition formula to calculate the overall fault probability of the system; the fault probability superposition module is connected to the reverse derivation module; The reverse deduction module triggers the reverse deduction process when the overall failure probability of the system exceeds the preset threshold, calculates the failure probability of each level of failure events according to the overall failure probability of the system, and sequentially passes it down to each basic event to obtain the failure probability of the basic event; the reverse deduction module is connected to the monitoring module; The monitoring module is responsible for real-time monitoring of electrical characteristic data, and dynamically updates the failure probability of fault events and the failure probability of basic events in combination with the overall failure probability of the system.

Images