Equipment fault positioning method and system based on fault record knowledge base

Abstract

The invention discloses an equipment fault positioning method and system based on a fault record knowledge base, and relates to the technical field of fault detection and positioning, and the method comprises the steps: building a fault record knowledge base according to the historical fault data of each piece of equipment; judging and obtaining a fault symptom of the to-be-detected equipment through the operation parameters, and obtaining at least one piece of fault information corresponding to the fault symptom of the to-be-detected equipment based on a fault record knowledge base; on the basis of the at least one piece of fault information, through the characteristic value of the operation parameter and by using a decision tree algorithm or a Bayesian formula, calculating a prediction probability, and determining the fault information with the maximum prediction probability as target information; maintaining the to-be-detected equipment according to the initial maintenance scheme and the actual solution in the target information until the maintenance result is that the to-be-detected equipment returns to normal; by constructing a knowledge base based on historical fault data, engineers are helped to quickly and accurately diagnose equipment faults, the downtime of the equipment is shortened, and the method is suitable for the requirements of various medical equipment and complex fault scenes.

Description

Technical Field

[0001] The present invention relates to the technical field of fault detection and positioning, and more specifically, to a method and system for positioning equipment faults based on a fault record knowledge base. Background Art

[0002] As the complexity and scope of use of medical equipment continue to expand, equipment failures are increasing. Traditional fault diagnosis methods rely more on the experience of engineers, and the following problems often occur during the diagnosis process:

[0003] 1. Insufficient fault data management: Traditional fault records lack structured management, making it difficult to extract valuable information from massive fault data;

[0004] 2. Low fault diagnosis efficiency: In the existing technology, engineers rely on experience and judgment, which makes the diagnosis process slow and prone to misjudgment;

[0005] 3. Poor support for multiple devices: Existing fault location methods usually target a single device or a single fault type, and lack comprehensive support for multiple devices and multiple types of faults;

[0006] 4. Unable to perform intelligent analysis: Traditional methods have limited analytical capabilities for historical fault data and are unable to improve the accuracy and efficiency of fault diagnosis through technologies such as data mining.

[0007] Therefore, how to systematically and intelligently record and manage equipment failure data, and use historical data for intelligent fault location, has become an urgent problem to be solved in the field of equipment management. Summary of the invention

[0008] The purpose of the present invention is to provide a method and system for locating equipment faults based on a fault record knowledge base. By constructing a knowledge base based on historical fault data and utilizing a fault location algorithm, the method and system can help engineers quickly and accurately diagnose equipment faults, improve maintenance efficiency, reduce equipment downtime, and adapt to the needs of various medical devices and complex fault scenarios.

[0009] The above technical objectives of the present invention are achieved through the following technical solutions:

[0010] In a first aspect, the present application provides a method for locating a device fault based on a fault record knowledge base, comprising the following specific steps:

[0011] A fault record knowledge base is established based on the historical fault data of each device. The fault record knowledge base represents the fault symptoms of each device each time a fault occurs, as well as the fault information corresponding to the fault symptoms. The fault information includes the fault type, fault cause, initial repair plan and actual solution;

[0012] Acquire operating parameters of the device to be detected, determine the fault symptoms of the device to be detected through the operating parameters, and obtain at least one fault information corresponding to the fault symptoms of the device to be detected based on a fault record knowledge base;

[0013] Based on at least one fault information, by running the characteristic value of the parameter and using the decision tree algorithm or the Bayesian formula, the predicted probability of the fault information in the at least one fault information is calculated, and the fault information with the largest predicted probability is determined as the target information;

[0014] The equipment to be inspected is repaired according to the initial repair plan and the actual solution in the target information. If the repair result is not restored to normal, the fault information corresponding to the target information is removed from at least one fault information, and new target information is re-determined until the repair result is restored to normal.

[0015] The beneficial effects of the present invention are as follows: in this solution, firstly, an efficient fault record knowledge base for storing fault records and related data of the equipment is constructed through the historical fault data of each device, and an intelligent fault location algorithm based on historical data is used to help engineers quickly and accurately identify equipment faults and their causes; secondly, the operating parameters of the equipment to be detected are obtained by using sensors or monitoring systems, including but not limited to temperature, pressure, current, voltage, etc., which are determined according to the type of equipment; the fault symptoms of the collected operating parameters are matched with those in the knowledge base, and when the fault symptoms of the operating parameters are matched in the knowledge base, the fault type of the matched fault symptoms, as well as information such as the cause of the fault, the initial maintenance plan and the actual solution can be queried in the knowledge base, based on the obtained fault type, combined with the historical fault records and maintenance plans of the equipment, a fault location algorithm such as a decision tree or a Bayesian network is applied to further analyze and infer the cause of the fault, and the algorithm makes probabilistic inferences on different fault causes based on the historical data of the fault type, thereby determining the most likely cause of the fault; finally, a corresponding maintenance plan is recommended according to the located fault type, and information such as historical maintenance records and feedback from maintenance personnel is included to help engineers quickly take repair measures.

[0016] In this solution, a fault record knowledge base is established to solve the problem that traditional fault records lack structured management and it is difficult to extract valuable information from massive fault data; fault location algorithms such as decision trees or Bayesian networks are used for fault diagnosis to reduce misjudgments while improving diagnostic efficiency, solving the current problem of relying on experience-based judgments, and the slow diagnostic process and prone to misjudgments; the fault record knowledge base is constructed through historical fault data of various types of equipment to solve the problem of lack of comprehensive support for multiple devices and multiple types of faults; fault analysis is performed based on the fault record knowledge base and using fault location algorithms such as decision trees or Bayesian networks, fully mining historical data and improving analysis capabilities, thereby improving the accuracy and efficiency of fault diagnosis.

[0017] Based on the above technical solution, the present invention can also be improved as follows.

[0018] Furthermore, if the maintenance result is restoration to normal, the fault record knowledge base is updated using the fault symptoms and target information of the device to be detected.

[0019] The beneficial effect of adopting the above further scheme is that when the maintenance personnel complete the repair operation, the data of the maintenance process (such as repair time, repair cost, fault type, processing plan, etc.) will be fed back to update the knowledge base and further optimize the positioning method provided in this application.

[0020] Furthermore, the above-mentioned fault symptoms of the equipment to be detected are obtained by judging the operating parameters, specifically:

[0021] If the device temperature or the device current is not lower than the corresponding temperature threshold or the corresponding current threshold, a judgment result of the fault symptom of abnormal temperature or abnormal current is obtained, and the operating parameters include the device temperature and the device current.

[0022] The beneficial effect of adopting the above further solution is that the fault symptoms can be identified by threshold judgment, that is, symptom matching is performed through a predefined rule set. For example, if the temperature exceeds 70°C and the current is unstable, it may be that the cooling system of the equipment is faulty.

[0023] Furthermore, the characteristic value of the above operating parameters is the standard deviation, specifically:

[0024] in,

[0025] In the formula, σ represents the standard deviation, μ represents the mean, and x i is the ith data point.

[0026] Furthermore, the above-mentioned prediction probability is calculated using the decision tree algorithm, specifically:

[0027]

[0028] Where, P(fault type=T|X1,X2,…,X n ) represents the predicted probability of fault type T, P(T) represents the prior probability of fault type T, P(X i |T) represents the conditional probability, X1,X2,…,X n Represents the characteristic value of the same variable in the operating parameters.

[0029] Furthermore, the prediction probability is calculated using the Bayesian formula, specifically:

[0030]

[0031] In the formula, P(T|X1,X2,…,X n ) represents the predicted probability of fault type T, X1, X2,…, X n represents the characteristic value of the same variable in the operating parameters, P(X1,X2,…,X n |T) represents the likelihood function, P(X1,X2,…,X n ) represents evidence, and P(T) represents the prior probability of fault type T, where the prior probability refers to the estimate of the probability of an event based on past experience or knowledge before considering any new evidence or information. In the context of fault types, it refers to the estimate of the probability of various fault types based on historical data, experience, and other factors before any fault detection or diagnosis operations are performed.

[0032] In a second aspect, the present application provides a device fault location system based on a fault record knowledge base, which is applied to a device fault location method based on a fault record knowledge base in any one of the first aspects, including:

[0033] The knowledge base construction module is used to establish a fault record knowledge base based on the historical fault data of each device. The fault record knowledge base represents the fault symptoms of each device each time a fault occurs, as well as the fault information corresponding to the fault symptoms. The fault information includes the fault type, fault cause, initial maintenance plan and actual solution;

[0034] A fault symptom identification module is used to obtain operating parameters of the device to be detected, determine the fault symptoms of the device to be detected through the operating parameters, and obtain at least one fault information corresponding to the fault symptoms of the device to be detected based on a fault record knowledge base;

[0035] A fault type location module is used to calculate the predicted probability of the fault information in the at least one fault information based on the at least one fault information by using the characteristic value of the operating parameter and the decision tree algorithm or the Bayesian formula, and determine the fault information with the largest predicted probability as the target information;

[0036] The maintenance plan execution module is used to repair the equipment to be tested according to the initial maintenance plan and the actual solution in the target information. If the maintenance result is not restored to normal, the fault information corresponding to the target information is removed from at least one fault information, and new target information is re-determined until the maintenance result is restored to normal.

[0037] Furthermore, the above system also includes:

[0038] The data feedback optimization module is used to update the fault record knowledge base using the fault symptoms and target information of the equipment to be detected if the maintenance result is restored to normal.

[0039] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any one of the methods in the first aspect when executing the computer program.

[0040] In a fourth aspect, the present application provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions enable a computer to execute any one of the methods in the first aspect.

[0041] Compared with the prior art, the present invention has at least the following beneficial effects:

[0042] In the present application, firstly, an efficient fault record knowledge base for storing the fault records and related data of the equipment is constructed through the historical fault data of each device, and an intelligent fault location algorithm based on historical data is used to help engineers quickly and accurately identify equipment faults and their causes; secondly, the operating parameters of the equipment to be detected are obtained by using sensors or monitoring systems, including but not limited to temperature, pressure, current, voltage, etc., which are determined according to the type of equipment; the fault symptoms of the collected operating parameters are matched with the knowledge base. When the fault symptoms of the operating parameters are matched in the knowledge base, the fault type of the matched fault symptoms, as well as the fault cause, initial maintenance plan and actual solution information can be queried in the knowledge base. Based on the obtained fault type, combined with the historical fault records and maintenance plans of the equipment, a fault location algorithm such as a decision tree or a Bayesian network is applied to further analyze and infer the cause of the fault. The algorithm makes probabilistic inferences on different fault causes based on the historical data of the fault type, thereby determining the most likely fault cause; finally, a corresponding maintenance plan is recommended based on the located fault type, and information such as historical maintenance records and feedback from maintenance personnel is included to help engineers quickly take repair measures.

[0043] In the present application, a fault record knowledge base is established to solve the problem that traditional fault records lack structured management and it is difficult to extract valuable information from massive fault data; fault location algorithms such as decision trees or Bayesian networks are used for fault diagnosis to improve diagnostic efficiency while reducing misjudgments, solving the current problem of relying on experience-based judgments, and the slow diagnostic process and prone to misjudgments; the fault record knowledge base is constructed through historical fault data of various types of equipment to solve the problem of lack of comprehensive support for multiple devices and multiple types of faults; fault analysis is performed based on the fault record knowledge base and using fault location algorithms such as decision trees or Bayesian networks, fully mining historical data and improving analysis capabilities, thereby improving the accuracy and efficiency of fault diagnosis.

[0044] In the present application, after the maintenance personnel complete the repair operation, the data of the maintenance process (such as repair time, repair cost, fault type, treatment plan, etc.) will be fed back to update the knowledge base and further optimize the positioning method provided in the present application; when identifying fault symptoms, it can be done by threshold judgment, that is, symptom matching is performed through a predefined set of rules. If the temperature exceeds 70°C and the current is unstable, it may be a failure of the equipment's cooling system; the equipment fault positioning method based on the fault record knowledge base provided in the present application, through the combination of intelligent knowledge base management and intelligent algorithms, greatly improves the accuracy and efficiency of equipment fault diagnosis. Through structured data management, symptom identification and cause location based on historical data, and feedback optimization mechanism, the present invention can effectively support intelligent diagnosis of multiple device faults and continuously optimize system performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0046] Figure 1 A flowchart of a positioning method according to an embodiment of the present invention;

[0047] Figure 2 A connection diagram of a positioning system in an embodiment of the present invention;

[0048] Figure 3 Schematic diagram of the connection of electronic equipment in an embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0050] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. 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.

[0051] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0052] In the description of the embodiments of the present invention, "plurality" means at least 2.

[0053] Embodiment 1: In order to solve the current problems of insufficient fault data management, low fault diagnosis efficiency, poor multi-device support, and inability to perform intelligent analysis, this embodiment provides a device fault location method based on a fault record knowledge base, such as Figure 1 As shown, the following specific steps are included:

[0054] S1. A fault record knowledge base is established based on the historical fault data of each device. The fault record knowledge base represents the fault symptoms of each device each time a fault occurs, as well as the fault information corresponding to the fault symptoms. The fault information includes the fault type, fault cause, initial maintenance plan and actual solution.

[0055] The fault record knowledge base may be composed of multiple table structures, each table storing different information related to equipment faults; the design goal of the knowledge base is to efficiently store equipment fault data and support fast query and update, and the multiple table structures include but are not limited to the following tables:

[0056] 1. Fault symptom table: record the symptoms and related indicators of equipment faults. Each record includes the fault symptom name, description, symptom manifestation (such as temperature, vibration, power consumption, etc.), and whether it is an emergency fault;

[0057] 2. Fault type table: records various fault types of the equipment. Each fault type is associated with specific symptoms and possible causes;

[0058] 3. Fault cause table: record the potential causes of the fault. Associate each cause with the fault type, and provide relevant technical documents and repair cases;

[0059] 4. Maintenance history table: records historical maintenance operations and repair results. Each record includes the maintenance plan, time required for repair, materials used, maintenance personnel, etc.

[0060] Specifically, the fault record knowledge base can be stored in a relational database (such as MySQL, PostgreSQL) or a non-relational database (such as MongoDB) to ensure efficient data management and query; in terms of data storage, tabular management is used to ensure efficient data access; in terms of data update, the system can update fault records and repair plans in real time, and automatically classify the latest fault information; in terms of multi-dimensional query, it can support querying fault data based on multiple dimensions such as symptoms, equipment type, and fault cause, which is convenient for engineers to quickly locate the fault type.

[0061] S2, obtaining operating parameters of the device to be detected, determining the fault symptoms of the device to be detected through the operating parameters, and obtaining at least one fault information corresponding to the fault symptoms of the device to be detected based on a fault record knowledge base.

[0062] The operating parameters of the equipment can be collected by sensors or monitoring systems. The operating parameters collected include but are not limited to: temperature, power consumption, current, voltage, pressure, etc. Specifically, the fault symptoms of the equipment to be detected can be obtained by judging the operating parameters, specifically:

[0063] If the device temperature or the device current is not lower than the corresponding temperature threshold or the corresponding current threshold, a judgment result of the fault symptom of abnormal temperature or abnormal current is obtained, and the operating parameters include the device temperature and the device current.

[0064] Among them, when performing threshold judgment, such as whether the temperature exceeds the preset value, whether the current exceeds the standard, etc., if the temperature exceeds 70°C and the current is unstable, it may be a heat dissipation system failure.

[0065] S3, based on at least one fault information, by running the characteristic value of the parameter and using the decision tree algorithm or the Bayesian formula, calculate the predicted probability of the fault information in the at least one fault information, and determine the fault information with the largest predicted probability as the target information.

[0066] Optionally, the characteristic value of the above operating parameter may be a standard deviation, a mean, a variance or an extreme value, wherein the standard deviation is specifically:

[0067] in,

[0068] In the formula, σ represents the standard deviation, μ represents the mean, and x i is the ith data point. When the characteristic value of the operating parameter is the mean, it can be directly calculated using the above formula.

[0069] Furthermore, the above-mentioned prediction probability is calculated using the decision tree algorithm, specifically:

[0070]

[0071] Where, P(fault type=T|X1,X2,…,X n ) represents the predicted probability of fault type T, P(T) represents the prior probability of fault type T, P(X i |T) represents the conditional probability, X1,X2,…,X n Represents the characteristic value of the same variable in the operating parameters.

[0072] Furthermore, the prediction probability is calculated using the Bayesian formula, specifically:

[0073]

[0074] In the formula, P(T|X1,X2,…,X n ) represents the predicted probability of fault type T, X1, X2,…, X n represents the characteristic value of the same variable in the operating parameters, P(X1,X2,…,X n |T) represents the likelihood function, P(X1,X2,…,X n) represents evidence, and P(T) represents the prior probability of fault type T, where the prior probability refers to the estimate of the probability of an event based on past experience or knowledge before considering any new evidence or information. In the context of fault types, it refers to the estimate of the probability of various fault types based on historical data, experience, and other factors before any fault detection or diagnosis operations are performed.

[0075] S4, repair the equipment to be tested according to the initial maintenance plan and the actual solution in the target information. If the maintenance result is not restored to normal, remove the fault information corresponding to the target information from at least one fault information, and re-determine new target information until the maintenance result is restored to normal.

[0076] When the cause of the fault is inferred, a corresponding maintenance operation is recommended according to the cause of the fault, such as "replace component A" or "check circuit connection".

[0077] Optionally, the above method may further include:

[0078] S5, if the maintenance result is restored to normal, the fault record knowledge base is updated using the fault symptoms and target information of the device to be detected.

[0079] After completing the maintenance, the maintenance personnel will input the maintenance data (including the maintenance process, repair results, accessories used, etc.) into the system. These data will be fed back to the knowledge base as new fault records to further enrich the fault data and maintenance plans; specifically, the newly added fault records can be marked and stored in the knowledge base for subsequent queries.

[0080] The device fault location method based on the fault record knowledge base provided by the present invention greatly improves the accuracy and efficiency of equipment fault diagnosis by combining intelligent knowledge base management with intelligent algorithms. Through structured data management, symptom identification and cause location based on historical data, and feedback optimization mechanism, the present invention can effectively support intelligent diagnosis of multiple device faults and continuously optimize system performance.

[0081] Embodiment 2: The present application provides a device fault location system based on a fault record knowledge base, which is applied to a device fault location method based on a fault record knowledge base in any one of Embodiment 1, such as Figure 2 As shown, including:

[0082] The knowledge base construction module is used to establish a fault record knowledge base based on the historical fault data of each device. The fault record knowledge base represents the fault symptoms of each device each time a fault occurs, as well as the fault information corresponding to the fault symptoms. The fault information includes the fault type, fault cause, initial maintenance plan and actual solution;

[0083] A fault symptom identification module is used to obtain operating parameters of the device to be detected, determine the fault symptoms of the device to be detected through the operating parameters, and obtain at least one fault information corresponding to the fault symptoms of the device to be detected based on a fault record knowledge base;

[0084] A fault type location module is used to calculate the predicted probability of the fault information in the at least one fault information based on the at least one fault information by using the characteristic value of the operating parameter and the decision tree algorithm or the Bayesian formula, and determine the fault information with the largest predicted probability as the target information;

[0085] The maintenance plan execution module is used to repair the equipment to be tested according to the initial maintenance plan and the actual solution in the target information. If the maintenance result is not restored to normal, the fault information corresponding to the target information is removed from at least one fault information, and new target information is re-determined until the maintenance result is restored to normal.

[0086] Optionally, the above system further includes:

[0087] The data feedback optimization module is used to update the fault record knowledge base using the fault symptoms and target information of the equipment to be detected if the maintenance result is restored to normal.

[0088] Embodiment 3: The present application provides an electronic device, such as Figure 3 As shown, it includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, any method in Embodiment 1 is implemented.

[0089] Embodiment 4: The present application provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions enable a computer to execute any one of the methods in Embodiment 1.

[0090] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for locating equipment faults based on a fault record knowledge base, characterized in that: The specific steps include: Establishing a fault record knowledge base based on the historical fault data of each device, wherein the fault record knowledge base represents the fault symptoms of each device each time a fault occurs, and the fault information corresponding to the fault symptoms, wherein the fault information includes the fault type, fault cause, initial repair plan and actual solution; Acquire operating parameters of the device to be detected, determine the fault symptoms of the device to be detected based on the operating parameters, and obtain at least one fault information corresponding to the fault symptoms of the device to be detected based on the fault record knowledge base; Based on the at least one fault information, a predicted probability of the fault information in the at least one fault information is calculated by using the characteristic value of the operating parameter and a decision tree algorithm or a Bayesian formula, and the fault information with the highest predicted probability is determined as the target information; The equipment to be inspected is repaired according to the initial repair plan and the actual solution in the target information. If the repair result is that the equipment has not been restored to normal, the fault information corresponding to the target information is removed from at least one fault information, and new target information is re-determined until the repair result is that the equipment has been restored to normal.

2. The device fault location method based on the fault record knowledge base according to claim 1 is characterized in that: The method further comprises: if the maintenance result is restoration to normal, updating the fault record knowledge base using the fault symptoms and target information of the device to be detected.

3. The device fault location method based on the fault record knowledge base according to claim 1 is characterized in that: The fault symptoms of the equipment to be detected are obtained by judging the operating parameters, specifically: If the device temperature or the device current is not lower than the corresponding temperature threshold or the corresponding current threshold, a judgment result of the fault symptom of abnormal temperature or abnormal current is obtained, and the operating parameters include the device temperature and the device current.

4. The device fault location method based on the fault record knowledge base according to claim 1 is characterized in that: The characteristic value of the operating parameter is the standard deviation, specifically: in, In the formula, σ represents the standard deviation, μ represents the mean, and x i is the ith data point.

5. The device fault location method based on the fault record knowledge base according to claim 1 is characterized in that: The prediction probability is calculated using the decision tree algorithm, specifically: Where, P(fault type=T|X1,X2,…,X n ) represents the predicted probability of fault type T, P(T) represents the prior probability of fault type T, P(X i |T) represents the conditional probability, X1,X2,…,X n Represents the characteristic value of the same variable in the operating parameters.

6. The device fault location method based on the fault record knowledge base according to claim 1 is characterized in that: The prediction probability is calculated using the Bayesian formula, specifically: In the formula, P(T|X1,X2,…,X n ) represents the predicted probability of fault type T, X1, X2,…, X n represents the characteristic value of the same variable in the operating parameters, P(X1,X2,…,X n |T) represents the likelihood function, P(X1,X2,…,X n ) represents the evidence, and P(T) represents the prior probability of fault type T.

7. A device fault location system based on a fault record knowledge base, applied to a device fault location method based on a fault record knowledge base as claimed in any one of claims 1 to 6, characterized in that: include: A knowledge base construction module is used to establish a fault record knowledge base based on the historical fault data of each device, wherein the fault record knowledge base represents the fault symptoms of each device each time a fault occurs, and the fault information corresponding to the fault symptoms, wherein the fault information includes the fault type, fault cause, initial maintenance plan and actual solution; a fault symptom identification module, configured to obtain operating parameters of the device to be detected, determine the fault symptom of the device to be detected by the operating parameters, and obtain at least one fault information corresponding to the fault symptom of the device to be detected based on the fault record knowledge base; A fault type location module, configured to calculate the predicted probability of the fault information in the at least one fault information based on the at least one fault information by using the characteristic value of the operating parameter and a decision tree algorithm or a Bayesian formula, and determine the fault information with the highest predicted probability as the target information; A maintenance plan execution module is used to repair the equipment to be detected according to the initial maintenance plan and the actual solution in the target information. If the maintenance result is not restored to normal, the fault information corresponding to the target information is removed from at least one fault information, and new target information is re-determined until the maintenance result is restored to normal.

8. The equipment fault location system based on the fault record knowledge base according to claim 7 is characterized in that: The system further comprises: The data feedback optimization module is used to update the fault record knowledge base using the fault symptoms and target information of the equipment to be detected if the maintenance result is restored to normal.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the method according to any one of claims 1 to 6 is implemented when the processor executes the computer program.

10. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer instructions, which enable a computer to execute the method of any one of claims 1-6.

Images