Equipment defect diagnosis method and system based on artificial intelligence knowledge graph

Abstract

The invention relates to the technical field of equipment defect diagnosis, and discloses an artificial intelligence knowledge graph-based equipment defect diagnosis method and system, and the method comprises the steps: presetting a monitoring period and an updating period, obtaining first data, second data and third data, training a defect diagnosis knowledge graph, and carrying out the single-side defect diagnosis and cooperative defect diagnosis. And updating the defect diagnosis knowledge graph. The system corresponds to the method. According to the method and the device, single-side defect diagnosis of the primary equipment is realized by acquiring the first data, single-side defect diagnosis of the secondary equipment is realized by acquiring the second data, collaborative defect diagnosis of the primary equipment and the secondary equipment is realized by acquiring the third data, and a data basis is provided for full-cycle data mining and artificial intelligence knowledge graph technology improvement; and full-cycle data mining is realized by combining a monitoring cycle and an updating cycle, improvement of an artificial intelligence knowledge graph technology is realized by combining collaborative defect diagnosis, and finally equipment defect diagnosis based on the artificial intelligence knowledge graph is realized.

Description

Technical Field

[0001] The present application relates to the technical field of equipment defect diagnosis, and specifically to an equipment defect diagnosis method and system based on artificial intelligence knowledge graph. Background Art

[0002] As the hardware foundation for maintaining the stable operation of the equipment network, it is necessary to supervise the equipment. The existing equipment supervision can collect data on the entire operation cycle of the equipment and issue warnings when equipment defects occur. However, it is not difficult to find that these data actually contain key information such as the defects before the defects occur, the corresponding defects and the corresponding effective solutions. The rational use of this information can not only realize equipment defect diagnosis, but also realize equipment defect early warning. In actual applications, these data are idle due to the difficulty of use. Therefore, mining the data of the entire operation cycle of the equipment is a reasonable technical direction to optimize the diagnosis of equipment defects.

[0003] Artificial intelligence knowledge graph technology is an emerging comprehensive technology that can quickly retrieve matching information from a large amount of data. Its existing technical framework can be applied to equipment defect diagnosis after adaptive modification. Therefore, improving artificial intelligence knowledge graph technology to make it more suitable for defect diagnosis is a reasonable technical direction to achieve optimized equipment defect diagnosis.

[0004] In the equipment network, primary equipment and secondary equipment are an effectively combined whole, but the existing equipment supervision often focuses on the supervision of a single device, ignoring its relevance as a whole. Therefore, exploring the relevance between primary and secondary equipment and achieving collaborative diagnosis is a reasonable technical direction for optimizing equipment defect diagnosis.

[0005] Chinese patent number CN202010937208.1 discloses a method, system, device and storage medium for diagnosing defects in power secondary equipment, but the acquisition of diagnostic basis only relies on a preset defect library and only supervises the secondary equipment, which cannot fully utilize the data and comprehensively supervise the equipment.

[0006] In summary, the existing technology urgently needs a technical solution that can realize collaborative defect diagnosis of primary and secondary equipment based on full-cycle data mining and artificial intelligence knowledge graph technology. Summary of the invention

[0007] The purpose of this application is to provide an equipment defect diagnosis method and system based on artificial intelligence knowledge graph to solve the technical problems raised in the above background technology.

[0008] To achieve the above objectives, this application discloses the following technical solutions:

[0009] In a first aspect, the present application discloses a method for diagnosing equipment defects based on an artificial intelligence knowledge graph, the method comprising:

[0010] S1: Preset a monitoring period and an update period, wherein the update period is a positive integer multiple of the monitoring period;

[0011] S2: Acquire first data of a primary device, second data of a secondary device, and third data associated with the first and second devices for training a preset defect diagnosis knowledge graph; the first data is used to characterize a first operating state, a first defect, and a corresponding first solution of the primary device; the second data is used to characterize a second operating state, a second defect, and a corresponding second solution of the secondary device; the third data is used to characterize the associated operating state, associated defect, and corresponding associated solution between the primary and secondary devices;

[0012] S3: training the defect diagnosis knowledge graph; the defect diagnosis knowledge graph includes a unilateral graph and a collaborative graph, and is used for defect diagnosis and early warning; the defect diagnosis knowledge graph stores an expert defect library and a data defect library; the expert defect library is obtained from the professional knowledge of domain experts, and the data defect library stores the results obtained from data analysis;

[0013] S4: Based on the first data and using the single-side map, perform single-side defect diagnosis of the equipment and output a first defect diagnosis result;

[0014] S5: Based on the second data and using the one-side map, diagnose one-side defects of the secondary equipment and output a second defect diagnosis result;

[0015] S6: Based on the third data and using the collaborative map, perform collaborative defect diagnosis of the primary and secondary equipment, and output a third defect diagnosis result;

[0016] S7: Obtain defect diagnosis records and warning records, and update the defect diagnosis knowledge graph.

[0017] Through the above, unilateral defect diagnosis of primary equipment is achieved by acquiring the first data, unilateral defect diagnosis of secondary equipment is achieved by acquiring the second data, and collaborative defect diagnosis of primary and secondary equipment is achieved by acquiring the third data. In addition, the acquisition of the first data, the second data and the third data provides a data basis for full-cycle data mining and artificial intelligence knowledge graph technology improvement, and full-cycle data mining is achieved in combination with the monitoring cycle and the update cycle, and artificial intelligence knowledge graph technology improvement is achieved in combination with collaborative defect diagnosis. Collaborative defect diagnosis of primary and secondary equipment is achieved based on full-cycle data mining and artificial intelligence knowledge graph technology improvement without affecting unilateral defect diagnosis of primary or secondary equipment.

[0018] Preferably, the acquisition and processing of the first data and the second data specifically includes:

[0019] Acquire corresponding first original data and second original data using a collection device provided on the device and the corresponding communication interface;

[0020] Preprocessing the first original data and the second original data to obtain first training data and second training data;

[0021] The first training data and the second training data are feature extracted using a preset expert defect library, so that the data are stored in the form of an associated data chain of operating status defect solutions to obtain the corresponding first data and the second data.

[0022] Preferably, the acquisition and processing of the third data specifically includes:

[0023] Acquire the first data and the second data, and match the first data and the second data based on time series;

[0024] A correlation time threshold is preset, and when the absolute value of the difference between the occurrence time of the defect of the primary device in the first data and the occurrence time of the defect of the secondary device in the second data is less than or equal to the correlation time threshold, the expert defect database is traversed, and when the same defect is not matched, the first data and the second data are associated and defined as candidate third data;

[0025] A preset association number threshold is set. When the number of times the candidate third data appears in an update cycle is greater than or equal to the association number threshold, the candidate third data is stored in the form of an associated operating status associated defect associated solution measure associated data chain to obtain the third data and store it in the data defect library.

[0026] Preferably, the training process of the unilateral atlas specifically includes the following steps:

[0027] A1: storing the first data and the second data into a preset single-side graph architecture;

[0028] A2: training the unilateral graph architecture after executing step A1, so that it parses the input first data or the second data to obtain the corresponding first operating state or the second operating state;

[0029] A3: Using the first operating state or the second operating state obtained in step A2, unilateral equipment identification, unilateral relationship matching and unilateral knowledge representation are performed; the unilateral equipment identification is used to identify the corresponding primary equipment or secondary equipment based on the operating state; the unilateral relationship matching is used to match the corresponding first defect and the corresponding first solution and the second defect and the corresponding second solution based on the operating state using the expert defect library and the data defect library; the unilateral knowledge representation is used to represent the operating state, the corresponding primary equipment or secondary equipment, and the corresponding first defect and the corresponding first solution and the second defect and the corresponding second solution;

[0030] A4: Output the one-sided map architecture after executing step A3 and define it as the one-sided map.

[0031] Preferably, the collaborative graph training process specifically includes the following steps:

[0032] B1: storing the third data into a preset collaborative graph framework;

[0033] B2: training the collaborative graph architecture after executing step B1, so that it parses the input third data to obtain the corresponding associated running state;

[0034] B3: Using the corresponding associated operating state obtained in step B2, collaborative device identification, collaborative relationship matching and collaborative knowledge representation are performed; the collaborative device identification is used to identify the corresponding primary and secondary device associations based on the associated operating state; the collaborative relationship matching is used to match the corresponding third defect and the corresponding third solution based on the associated operating state using the expert defect library and the data defect library; the collaborative knowledge representation is used to represent the associated operating state, the corresponding primary and secondary device associations, and the corresponding third defect and the corresponding third solution;

[0035] B4: Output the collaborative graph architecture after executing step B3 and define it as the collaborative graph.

[0036] Preferably, the output process of the first defect diagnosis result and the second defect diagnosis result specifically includes the following steps:

[0037] C1: Acquire the real-time first data and the real-time second data at the end of the monitoring cycle, and execute steps C2 and C3 in parallel;

[0038] C2: inputting the real-time first data into the unilateral map and running it, performing the corresponding unilateral knowledge representation when matching the first defect, outputting the result of the unilateral knowledge representation and defining it as the first defect diagnosis result;

[0039] C3: Input the real-time second data into the unilateral map and run it, and when the second defect is matched, perform the corresponding unilateral knowledge representation, output the result of the unilateral knowledge representation and define it as the second defect diagnosis result.

[0040] Preferably, the output process of the third defect diagnosis result specifically includes the following steps:

[0041] D1: Acquire the real-time third data at the end of one monitoring cycle, and execute step D2 in parallel;

[0042] D2: Input the real-time third data into the collaborative graph and run it, and when the third defect is matched, perform the corresponding collaborative knowledge representation, output the result of the collaborative knowledge representation and define it as the third defect diagnosis result.

[0043] Preferably, the output process of the third defect diagnosis result further includes the following steps:

[0044] D3: parsing the matched third defect, and executing step D4 when the first defect exists or the second defect does not occur;

[0045] D4: Based on the third defect diagnosis result, obtain the first device or the second device corresponding to the first defect or the second defect that has not occurred, and output the corresponding warning generated by the first device or the second device.

[0046] Preferably, the obtaining of defect diagnosis records and warning records and updating of the defect diagnosis knowledge graph specifically includes:

[0047] Acquiring the defect diagnosis record including the diagnosis results of the unilateral defect diagnosis and the collaborative defect diagnosis based on the monitoring period, judging the accuracy of the diagnosis result, and updating the expert defect database and the data defect database using the judgment result;

[0048] Based on the update cycle, the data defect database is updated when the newly added third data appears.

[0049] In a second aspect, the present application discloses an equipment defect diagnosis system based on an artificial intelligence knowledge graph, the system is applicable to the equipment defect diagnosis method based on an artificial intelligence knowledge graph as described in any of the above items, and the system includes:

[0050] A time module, wherein the time module is configured to preset a monitoring period and an update period; the update period is a positive integer multiple of the monitoring period;

[0051] A data module, wherein the data module is configured to: obtain first data of a primary device, second data of a secondary device, and third data associated with the first and second devices for training a preset defect diagnosis knowledge graph; the first data is used to characterize a first operating state, a first defect, and a corresponding first solution of the primary device; the second data is used to characterize a second operating state, a second defect, and a corresponding second solution of the secondary device; the third data is used to characterize an associated operating state, an associated defect, and a corresponding associated solution between the primary and secondary devices;

[0052] A training module, wherein the training module is configured to: train the defect diagnosis knowledge graph; the defect diagnosis knowledge graph includes a unilateral graph and a collaborative graph, and is used for defect diagnosis and early warning; the defect diagnosis knowledge graph stores an expert defect library and a data defect library; the expert defect library is obtained from the professional knowledge of domain experts, and the data defect library stores the results obtained from data analysis;

[0053] An application module, wherein the application module is configured to: based on the first data and using the single-sided map, perform single-sided defect diagnosis of a primary device and output a first defect diagnosis result; based on the second data and using the single-sided map, perform single-sided defect diagnosis of a secondary device and output a second defect diagnosis result; based on the third data and using the collaborative map, perform collaborative defect diagnosis of the primary and secondary devices and output a third defect diagnosis result;

[0054] An update module, wherein the update module is configured to: obtain defect diagnosis records and warning records, and update the defect diagnosis knowledge graph.

[0055] Beneficial effects: The equipment defect diagnosis method and system based on artificial intelligence knowledge graph of the present application realize unilateral defect diagnosis of primary equipment by acquiring first data, realize unilateral defect diagnosis of secondary equipment by acquiring second data, and realize collaborative defect diagnosis of primary and secondary equipment by acquiring third data. The acquisition of first data, second data and third data provides a data basis for full-cycle data mining and artificial intelligence knowledge graph technology improvement, realizes full-cycle data mining in combination with monitoring cycle and update cycle, and realizes artificial intelligence knowledge graph technology improvement in combination with collaborative defect diagnosis. It realizes collaborative defect diagnosis of primary and secondary equipment based on full-cycle data mining and artificial intelligence knowledge graph technology improvement without affecting unilateral defect diagnosis of primary or secondary equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0057] Figure 1 A flowchart of a device defect diagnosis method based on an artificial intelligence knowledge graph provided in an embodiment of the present application;

[0058] Figure 2 A structural block diagram of the equipment defect diagnosis system based on artificial intelligence knowledge graph provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] The technical solutions in the embodiments of the present application are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0060] In this article, the term "comprising" is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, the elements defined by the sentence "comprising..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0061] In a first aspect, this embodiment discloses Figure 1 A device defect diagnosis method based on artificial intelligence knowledge graph is shown, the method comprising:

[0062] S1: Preset monitoring period and update period, the update period is a positive integer multiple of the monitoring period.

[0063] S2: Obtain the first data of the primary equipment, the second data of the secondary equipment and the third data associated with the first and second equipment for training the preset defect diagnosis knowledge graph; the first data is used to characterize the first operating state, the first defect and the corresponding first solution of the primary equipment; the second data is used to characterize the second operating state, the second defect and the corresponding second solution of the secondary equipment; the third data is used to characterize the associated operating state, the associated defect and the corresponding associated solution between the primary and secondary equipment; in a simple example, the primary equipment can be but is not limited to equipment directly used for production, transportation and distribution, such as generators, transformers, circuit breakers and busbars; the secondary equipment can be but is not limited to equipment for monitoring, controlling, adjusting and protecting the primary equipment, such as relay protection devices, measuring instruments and control loops.

[0064] S3: training defect diagnosis knowledge graph; the defect diagnosis knowledge graph includes a unilateral graph and a collaborative graph, and is used for defect diagnosis and early warning; the defect diagnosis knowledge graph stores an expert defect library and a data defect library; the expert defect library is obtained from the professional knowledge of domain experts, and the data defect library is stored from the results of data analysis; it should be noted that the expert defect library in this embodiment also needs to pass the test of data analysis.

[0065] S4: Based on the first data and using the single-side map, perform a single-side defect diagnosis of the equipment and output a first defect diagnosis result.

[0066] S5: Based on the second data and using the one-sided map, perform one-sided defect diagnosis of the secondary equipment and output a second defect diagnosis result.

[0067] S6: Based on the third data and using the collaborative map, collaborative defect diagnosis of the primary and secondary equipment is performed, and the third defect diagnosis result is output.

[0068] S7: Obtain defect diagnosis records and warning records, and update the defect diagnosis knowledge graph.

[0069] By acquiring the first data, unilateral defect diagnosis of primary equipment is achieved, by acquiring the second data, unilateral defect diagnosis of secondary equipment is achieved, and by acquiring the third data, collaborative defect diagnosis of primary and secondary equipment is achieved. The acquisition of the first data, the second data and the third data provides a data basis for full-cycle data mining and artificial intelligence knowledge graph technology improvement, and the full-cycle data mining is achieved in combination with the monitoring cycle and the update cycle, and the artificial intelligence knowledge graph technology improvement is achieved in combination with the collaborative defect diagnosis. The collaborative defect diagnosis of primary and secondary equipment is achieved based on the full-cycle data mining and artificial intelligence knowledge graph technology improvement without affecting the unilateral defect diagnosis of primary or secondary equipment.

[0070] Specifically, the acquisition and processing of the first data and the second data specifically include:

[0071] The corresponding first original data and second original data are acquired by using the acquisition device arranged on the device and the corresponding communication interface; in a simple example, for example, the first original data includes electrical parameters, environmental parameters, vibration data, partial discharge data and insulation resistance, etc., and the second original data includes the action signal and fault record of the protection device, the status information of the control loop and the automated operation data.

[0072] The first original data and the second original data are preprocessed to obtain first training data and second training data.

[0073] The first training data and the second training data are feature extracted using a preset expert defect library, so that the data are stored in the form of an associated data chain of operating status defect solutions to obtain corresponding first data and second data.

[0074] Acquiring the first data and the second data provides a data basis for single-sided defect diagnosis, and storing them in the form of a data chain associated with operating status defect solutions provides technical support for constructing a single-sided map, which ensures the normal implementation of conventional single-sided equipment defect diagnosis.

[0075] Specifically, the acquisition and processing of the third data includes:

[0076] Acquire first data and second data, and match the first data and the second data based on a time series;

[0077] A preset association time threshold is set. When the absolute value of the difference between the occurrence time of the defect of the primary equipment in the first data and the occurrence time of the defect of the secondary equipment in the second data is less than or equal to the association time threshold, the expert defect library is traversed. When the same defect is not matched, the first data and the second data are associated and defined as candidate third data. The comparison with the association time threshold provides an initial judgment basis for data association.

[0078] A preset association count threshold is set. When the number of times the candidate third data appears in an update cycle is greater than or equal to the association count threshold, the candidate third data is stored in the form of an associated operating status associated defect associated solution associated data chain to obtain the third data and store it in a data defect library. Comparison with the association count threshold provides a final judgment basis for data association.

[0079] Acquiring third-party data provides a data basis for collaborative defect diagnosis, and storing it in the form of associated operating status, associated defects, associated solutions, and associated data chains provides technical support for building a collaborative graph. It improves on existing artificial intelligence knowledge graph technology and provides the necessary technical means for more comprehensive defect diagnosis of the effective combination of primary and secondary equipment.

[0080] Specifically, the training process of the unilateral atlas includes the following steps:

[0081] A1: The first data and the second data are stored in a preset single-side graph architecture.

[0082] A2: training the unilateral graph architecture after executing step A1, so that it can parse the input first data or second data to obtain the corresponding first operating state or second operating state.

[0083] A3: Using the corresponding first operating state or second operating state obtained in step A2, perform unilateral equipment identification, unilateral relationship matching and unilateral knowledge representation; unilateral equipment identification is used to identify the corresponding primary equipment or secondary equipment based on the operating state; unilateral relationship matching is used to match the corresponding first defect and the corresponding first solution and the second defect and the corresponding second solution based on the operating state using the expert defect library and the data defect library; unilateral knowledge representation is used to represent the operating state, the corresponding primary equipment or secondary equipment, and the corresponding first defect and the corresponding first solution and the second defect and the corresponding second solution.

[0084] A4: Output the one-sided graph architecture after executing step A3 and define it as a one-sided graph.

[0085] Training the unilateral atlas provides technical support for unilateral defect diagnosis.

[0086] Specifically, the collaborative graph training process includes the following steps:

[0087] B1: Store the third data into the preset collaborative graph architecture.

[0088] B2: Train the collaborative graph architecture after executing step B1, so that it can parse the input third data to obtain the corresponding associated operating status.

[0089] B3: Use the corresponding associated operating status obtained in step B2 to perform collaborative equipment identification, collaborative relationship matching and collaborative knowledge representation; collaborative equipment identification is used to identify the corresponding primary and secondary equipment associations based on the associated operating status; collaborative relationship matching is used to match the corresponding third defect and the corresponding third solution based on the associated operating status using the expert defect library and the data defect library; collaborative knowledge representation is used to represent the associated operating status, the corresponding primary and secondary equipment associations, and the corresponding third defect and the corresponding third solution.

[0090] B4: Output the collaborative graph architecture after executing step B3 and define it as a collaborative graph.

[0091] Training collaborative graphs provides technical support for collaborative defect diagnosis.

[0092] Specifically, the output process of the first defect diagnosis result and the second defect diagnosis result specifically includes the following steps:

[0093] C1: Acquire the real-time first data and the real-time second data at the end of a monitoring cycle, and execute steps C2 and C3 in parallel; it should be noted that the parallel execution in this embodiment is intended to improve the timeliness of single-side defect monitoring, so that the results of defect diagnosis are more timely.

[0094] C2: Input the real-time first data into the unilateral map and run it. When the first defect is matched, perform the corresponding unilateral knowledge representation. Output the result of the unilateral knowledge representation and define it as the first defect diagnosis result.

[0095] C3: Input the real-time second data into the unilateral map and run it. When the second defect is matched, perform the corresponding unilateral knowledge representation. Output the result of the unilateral knowledge representation and define it as the second defect diagnosis result.

[0096] By outputting any one or more of the first defect result and the second defect result, the equipment management personnel can obtain the single-side defect situation and the corresponding equipment and corresponding solutions in a timely manner, thereby improving the intelligent level of equipment defect diagnosis.

[0097] Specifically, the output process of the third defect diagnosis result includes the following steps:

[0098] D1: Acquire the real-time third data at the end of a monitoring cycle, and execute step D2 in parallel.

[0099] D2: Input the real-time third data into the collaborative graph and run it. When the third defect is matched, perform the corresponding collaborative knowledge representation. Output the result of the collaborative knowledge representation and define it as the third defect diagnosis result.

[0100] By outputting the third defect diagnosis result, the equipment management personnel can obtain the related defect conditions, the corresponding equipment and the corresponding solutions in a timely manner, thereby improving the intelligent level of equipment defect diagnosis.

[0101] Specifically, the output process of the third defect diagnosis result further includes the following steps:

[0102] D3: Analyze the matched third defect and execute step D4 when the first defect exists or the second defect does not occur.

[0103] D4: Based on the third defect diagnosis result, the first device or second device corresponding to the first defect or the second defect that has not occurred is obtained, and the corresponding warning generated by the first device or the second device is output; it should be noted that the judgment based on the associated time threshold in this embodiment provides a buffer time between the occurrence of defects in the primary device or the secondary device, thereby increasing the possibility of issuing a warning and realizing early prevention of equipment defects.

[0104] By outputting corresponding warnings, equipment management personnel can take corresponding solutions to corresponding equipment in advance before related defects occur, thereby improving the level of protection for the equipment and the level of intelligence of equipment defect diagnosis.

[0105] Specifically, obtain defect diagnosis records and warning records, and update the defect diagnosis knowledge graph, including:

[0106] Based on the monitoring period, defect diagnosis records including the diagnosis results of unilateral defect diagnosis and collaborative defect diagnosis are obtained, the accuracy of the diagnosis results is judged, and the judgment results are used to update the expert defect library and the data defect library.

[0107] Based on the update cycle, the data defect database is updated when newly added third data appears.

[0108] By periodically updating the expert defect library and the data defect library, full-cycle data mining is achieved, which improves data utilization and optimizes data integration effects. It also provides data support for improving the application of artificial intelligence knowledge graph technology in equipment defect diagnosis.

[0109] In a second aspect, this embodiment discloses Figure 2 An equipment defect diagnosis system based on artificial intelligence knowledge graph is shown, and the system is applicable to the equipment defect diagnosis method based on artificial intelligence knowledge graph as described in any of the above items, and the system includes:

[0110] Time module: The time module is configured with preset monitoring period and update period; the update period is a positive integer multiple of the monitoring period;

[0111] A data module, wherein the data module is configured to: obtain first data of a primary device, second data of a secondary device, and third data associated with the first and second devices for training a preset defect diagnosis knowledge graph; the first data is used to characterize a first operating state, a first defect, and a corresponding first solution of the primary device; the second data is used to characterize a second operating state, a second defect, and a corresponding second solution of the secondary device; the third data is used to characterize the associated operating state, associated defect, and corresponding associated solution between the primary and secondary devices;

[0112] Training module, the training module is configured as follows: training defect diagnosis knowledge graph; the defect diagnosis knowledge graph includes a unilateral graph and a collaborative graph, and is used for defect diagnosis and early warning; the defect diagnosis knowledge graph stores an expert defect library and a data defect library; the expert defect library is obtained from the professional knowledge of domain experts, and the data defect library is stored from the results of data analysis;

[0113] The application module is configured to: perform unilateral defect diagnosis of a primary device based on the first data and using the unilateral map, and output a first defect diagnosis result; perform unilateral defect diagnosis of a secondary device based on the second data and using the unilateral map, and output a second defect diagnosis result; perform collaborative defect diagnosis of the primary and secondary devices based on the third data and using the collaborative map, and output a third defect diagnosis result;

[0114] Update module, the update module is configured to: obtain defect diagnosis records and warning records, and update the defect diagnosis knowledge graph.

[0115] It should be noted that the equipment defect diagnosis system based on artificial intelligence knowledge graph in this embodiment corresponds to the aforementioned equipment defect diagnosis method based on artificial intelligence knowledge graph. Therefore, the contents not specifically described in the equipment defect diagnosis system based on artificial intelligence knowledge graph in this embodiment, including but not limited to specific functional definitions, working principles and technical effects, are the same as those of the aforementioned equipment defect diagnosis method based on artificial intelligence knowledge graph, and this text will not go into details here.

[0116] In summary, the equipment defect diagnosis method and system based on artificial intelligence knowledge graph of this embodiment realizes unilateral defect diagnosis of primary equipment by acquiring first data, realizes unilateral defect diagnosis of secondary equipment by acquiring second data, and realizes collaborative defect diagnosis of primary and secondary equipment by acquiring third data. The acquisition of first data, second data and third data provides a data basis for full-cycle data mining and artificial intelligence knowledge graph technology improvement, realizes full-cycle data mining in combination with monitoring cycle and update cycle, and realizes artificial intelligence knowledge graph technology improvement in combination with collaborative defect diagnosis. It realizes collaborative defect diagnosis of primary and secondary equipment based on full-cycle data mining and artificial intelligence knowledge graph technology improvement without affecting unilateral defect diagnosis of primary or secondary equipment.

[0117] In the embodiments provided in the present application, it should be understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code or any appropriate combination thereof. For hardware implementation, the processor can be implemented in one or more of the following units: application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing device (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), processor, controller, microcontroller, microprocessor, other electronic units designed to implement the functions described herein or their combination. For software implementation, part or all of the flow of the embodiment can be completed by instructing the relevant hardware through a computer program. When implemented, the above program can be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on a computer-readable storage medium. Computer-readable storage media include computer storage media and communication media, wherein the communication medium includes any medium that is convenient for transmitting a computer program from one place to another. The storage medium can be any available medium that a computer can access. The computer-readable storage medium can include but is not limited to RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer.

[0118] Finally, it should be noted that the above is only a preferred embodiment of the present application and is not intended to limit the present application. Although the present application has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for equipment defect diagnosis based on artificial intelligence knowledge graph, characterized in that: The method includes: S1: Preset a monitoring period and an update period, wherein the update period is a positive integer multiple of the monitoring period; S2: Acquire first data of a primary device, second data of a secondary device, and third data associated with the first and second devices for training a preset defect diagnosis knowledge graph; the first data is used to characterize a first operating state, a first defect, and a corresponding first solution of the primary device; the second data is used to characterize a second operating state, a second defect, and a corresponding second solution of the secondary device; the third data is used to characterize the associated operating state, associated defect, and corresponding associated solution between the primary and secondary devices; S3: training the defect diagnosis knowledge graph; the defect diagnosis knowledge graph includes a unilateral graph and a collaborative graph, and is used for defect diagnosis and early warning; the defect diagnosis knowledge graph stores an expert defect library and a data defect library; the expert defect library is obtained from the professional knowledge of domain experts, and the data defect library stores the results obtained from data analysis; S4: Based on the first data and using the single-side map, perform single-side defect diagnosis of the equipment and output a first defect diagnosis result; S5: Based on the second data and using the one-side map, diagnose one-side defects of the secondary equipment and output a second defect diagnosis result; S6: Based on the third data and using the collaborative map, perform collaborative defect diagnosis of the primary and secondary equipment, and output a third defect diagnosis result; S7: Obtain defect diagnosis records and warning records, and update the defect diagnosis knowledge graph.

2. The equipment defect diagnosis method based on artificial intelligence knowledge graph according to claim 1 is characterized in that: The acquisition and processing of the first data and the second data specifically include: Acquire corresponding first original data and second original data using a collection device provided on the device and the corresponding communication interface; Preprocessing the first original data and the second original data to obtain first training data and second training data; The first training data and the second training data are feature extracted using a preset expert defect library, so that the data are stored in the form of an associated data chain of operating status defect solutions to obtain the corresponding first data and the second data.

3. The equipment defect diagnosis method based on artificial intelligence knowledge graph according to claim 1 is characterized in that: The acquisition and processing of the third data specifically includes: Acquire the first data and the second data, and match the first data and the second data based on time series; A correlation time threshold is preset, and when the absolute value of the difference between the occurrence time of the defect of the primary device in the first data and the occurrence time of the defect of the secondary device in the second data is less than or equal to the correlation time threshold, the expert defect database is traversed, and when the same defect is not matched, the first data and the second data are associated and defined as candidate third data; A preset association number threshold is set. When the number of times the candidate third data appears in an update cycle is greater than or equal to the association number threshold, the candidate third data is stored in the form of an associated operating status associated defect associated solution measure associated data chain to obtain the third data and store it in the data defect library.

4. The equipment defect diagnosis method based on artificial intelligence knowledge graph according to claim 1 is characterized in that: The training process of the unilateral atlas specifically includes the following steps: A1: storing the first data and the second data into a preset single-side graph architecture; A2: training the unilateral graph architecture after executing step A1, so that it parses the first data or the second data input to obtain the corresponding first operating state or the second operating state; A3: Using the first operating state or the second operating state obtained in step A2, unilateral equipment identification, unilateral relationship matching and unilateral knowledge representation are performed; the unilateral equipment identification is used to identify the corresponding primary equipment or secondary equipment based on the operating state; the unilateral relationship matching is used to match the corresponding first defect and the corresponding first solution and the second defect and the corresponding second solution based on the operating state using the expert defect library and the data defect library; the unilateral knowledge representation is used to represent the operating state, the corresponding primary equipment or secondary equipment, and the corresponding first defect and the corresponding first solution and the second defect and the corresponding second solution; A4: Output the one-sided map architecture after executing step A3 and define it as the one-sided map.

5. The equipment defect diagnosis method based on artificial intelligence knowledge graph according to claim 1 is characterized in that: The training process of the collaborative graph specifically includes the following steps: B1: storing the third data into a preset collaborative graph framework; B2: training the collaborative graph architecture after executing step B1, so that it parses the input third data to obtain the corresponding associated running state; B3: Using the corresponding associated operating state obtained in step B2, collaborative device identification, collaborative relationship matching and collaborative knowledge representation are performed; the collaborative device identification is used to identify the corresponding primary and secondary device associations based on the associated operating state; the collaborative relationship matching is used to match the corresponding third defect and the corresponding third solution based on the associated operating state using the expert defect library and the data defect library; the collaborative knowledge representation is used to represent the associated operating state, the corresponding primary and secondary device associations, and the corresponding third defect and the corresponding third solution; B4: Output the collaborative graph architecture after executing step B3 and define it as the collaborative graph.

6. The equipment defect diagnosis method based on artificial intelligence knowledge graph according to claim 4 is characterized in that: The output process of the first defect diagnosis result and the second defect diagnosis result specifically includes the following steps: C1: Acquire the real-time first data and the real-time second data at the end of the monitoring cycle, and execute steps C2 and C3 in parallel; C2: inputting the real-time first data into the unilateral map and running it, performing the corresponding unilateral knowledge representation when matching the first defect, outputting the result of the unilateral knowledge representation and defining it as the first defect diagnosis result; C3: Input the real-time second data into the unilateral map and run it, and when the second defect is matched, perform the corresponding unilateral knowledge representation, output the result of the unilateral knowledge representation and define it as the second defect diagnosis result.

7. The equipment defect diagnosis method based on artificial intelligence knowledge graph according to claim 5 is characterized in that: The output process of the third defect diagnosis result specifically includes the following steps: D1: Acquire the real-time third data at the end of one monitoring cycle, and execute step D2 in parallel; D2: Input the real-time third data into the collaborative graph and run it, and when the third defect is matched, perform the corresponding collaborative knowledge representation, output the result of the collaborative knowledge representation and define it as the third defect diagnosis result.

8. The equipment defect diagnosis method based on artificial intelligence knowledge graph according to claim 7 is characterized in that: The output process of the third defect diagnosis result further includes the following steps: D3: parsing the matched third defect, and executing step D4 when the first defect exists or the second defect does not occur; D4: Based on the third defect diagnosis result, obtain the first device or the second device corresponding to the first defect or the second defect that has not occurred, and output the corresponding warning generated by the first device or the second device.

9. The equipment defect diagnosis method based on artificial intelligence knowledge graph according to claim 1 is characterized in that: The obtaining of defect diagnosis records and warning records and updating of the defect diagnosis knowledge graph specifically includes: Acquiring the defect diagnosis record including the diagnosis results of the unilateral defect diagnosis and the collaborative defect diagnosis based on the monitoring period, judging the accuracy of the diagnosis result, and updating the expert defect database and the data defect database using the judgment result; Based on the update cycle, the data defect database is updated when the newly added third data appears.

10. An equipment defect diagnosis system based on artificial intelligence knowledge graph, the system is applicable to the equipment defect diagnosis method based on artificial intelligence knowledge graph as described in any one of claims 1 to 9, characterized in that: The system includes: A time module, wherein the time module is configured to preset a monitoring period and an update period; the update period is a positive integer multiple of the monitoring period; A data module, wherein the data module is configured to: obtain first data of a primary device, second data of a secondary device, and third data associated with the first and second devices for training a preset defect diagnosis knowledge graph; the first data is used to characterize a first operating state, a first defect, and a corresponding first solution of the primary device; the second data is used to characterize a second operating state, a second defect, and a corresponding second solution of the secondary device; the third data is used to characterize an associated operating state, an associated defect, and a corresponding associated solution between the primary and secondary devices; A training module, wherein the training module is configured to: train the defect diagnosis knowledge graph; the defect diagnosis knowledge graph includes a unilateral graph and a collaborative graph, and is used for defect diagnosis and early warning; the defect diagnosis knowledge graph stores an expert defect library and a data defect library; the expert defect library is obtained from the professional knowledge of domain experts, and the data defect library stores the results obtained from data analysis; An application module, wherein the application module is configured to: based on the first data and using the single-sided map, perform single-sided defect diagnosis of a primary device and output a first defect diagnosis result; based on the second data and using the single-sided map, perform single-sided defect diagnosis of a secondary device and output a second defect diagnosis result; based on the third data and using the collaborative map, perform collaborative defect diagnosis of the primary and secondary devices and output a third defect diagnosis result; An update module, wherein the update module is configured to: obtain defect diagnosis records and warning records, and update the defect diagnosis knowledge graph.

Images