Automatic cable aging detection method and device based on combination of chemical mechanism and AI

Abstract

The invention discloses an automatic cable aging detection method and an automatic cable aging detection device based on combination of a chemical mechanism and AI, which are combined with the mechanism change of a cable material and an external visual perception technology, and are combined with a general large model, a latest cable material internal self-detection experiment knowledge base, a case library and other knowledge. A cable aging detection large model is constructed in a mode of combining a general large model, a general knowledge base and a self-diagnosis professional knowledge graph. According to the method, cable aging mechanism knowledge and related detection business processes are fused in combination with an AI large model, full automation of a cable aging detection process is realized, an integrated process from cable diagnosis to diagnosis evaluation analysis and action suggestion is realized, the detection accuracy and credibility are improved, and the labor cost and time are reduced at the same time.

Description

Technical Field

[0001] The present invention relates to a cable detection method, and more particularly to an automated cable aging detection method and device based on a combination of chemical mechanism and AI. Background Art

[0002] New energy systems, aerospace systems, power transmission and transformation systems, rail transit systems, etc. are very likely to cause electrical aging of dielectric polymer insulation materials under harsh operating conditions. If not discovered and maintained in time, it will lead to electrical breakdown of key equipment, resulting in huge economic losses. However, electrical aging usually starts in a small area and does not cause significant changes in the overall electrical properties of the material in the early stage. Therefore, it is extremely difficult to detect and becomes a major hidden danger threatening the safe operation of electrical and electronic equipment.

[0003] At present, the electrical aging and electrical damage problems on the surface of external insulation materials are usually detected by appearance inspection, infrared thermal imaging, ultraviolet imaging, acoustic wave measurement and electric field measurement; the internal electrical degradation problems of internal insulation materials are usually detected by partial discharge or ultrasonic flaw detection. The above external detection methods need to combine certain expert knowledge to analyze and interpret the test results, which consumes a lot of manpower costs and is difficult to detect insulation material aging problems in a timely, accurate and automatic manner.

[0004] "An Electrical Aging Self-diagnostic Insulating Material and Its Preparation Method" provides an electrical aging self-diagnostic insulating material and its preparation method. The material spontaneously induces the organic small molecule indicator in the matrix to produce chemical structure changes through the free radicals with strong chemical activity generated during the electrical aging process, so that new chromophores appear in the indicator structure, causing the aging area to produce color changes that can be identified by the naked eye or optical monitoring equipment, thereby achieving early warning of electrical equipment failures. This method provides a method for material self-diagnosis, but does not provide how to combine self-diagnosis with appearance perception detection, nor does it provide a specific detection process. Summary of the invention

[0005] The purpose of the present invention is to address the deficiencies of the prior art and provide an automated cable aging detection method and device based on a combination of chemical mechanism and AI.

[0006] The object of the present invention is achieved through the following technical solution: an automated cable aging detection method based on a combination of chemical mechanism and AI, comprising the following steps:

[0007] (1) preparing a plurality of electrical aging self-diagnosis insulating materials, performing image detection on each electrical aging self-diagnosis insulating material to obtain a corresponding detection image, and constructing a cable self-diagnosis detection sample data set consisting of all the detection images;

[0008] (2) A general knowledge base is constructed by collecting relevant general cable material knowledge manuals and papers and standards related to cable materials; then a cable self-diagnosis knowledge graph is constructed by constructing cable self-diagnosis related knowledge;

[0009] (3) Training a ResNet classification model based on the cable self-diagnosis detection sample data set to obtain a cable classification model;

[0010] (4) Based on the general knowledge base and the cable self-diagnosis knowledge graph, the general large model is fine-tuned and trained in a P-Tuning manner to obtain a large model for cable aging detection;

[0011] (5) The real-time cable detection data is automatically input into the constructed cable classification model for classification: if it is classified as not aged, the next cable detection data is detected; if it is classified as aged, the general knowledge base is searched through the current cable detection data to obtain the corresponding knowledge vector information, and the cable self-diagnosis knowledge graph is searched through the current cable detection data to obtain the corresponding knowledge graph information. The retrieved knowledge vector information and knowledge graph information are integrated and transformed to obtain the prompt word corresponding to the current cable detection data, and the abnormal result is generated according to the prompt word through the large model of cable aging detection. The abnormal result includes the cause analysis of the aging of the cable detection data and repair suggestions.

[0012] Furthermore, the construction process of the cable self-diagnosis knowledge graph is specifically as follows:

[0013] a.1) Establish the ontology of cable self-diagnosis related knowledge, including ontology objects and object attributes;

[0014] a.2) Extract all entities corresponding to the ontology objects from the ontology of cable self-diagnosis related knowledge by manual or algorithmic extraction, and construct corresponding triples [T i ,R i,j ,T j ], where T i and T j Represents any entity, R i,j Represents entity T i and entity T j the relationship between;

[0015] a.3) All triples constructed in step (a.2) constitute the cable self-diagnosis knowledge graph.

[0016] Furthermore, the general big model includes the Zhipu big model.

[0017] The present invention also includes an automated cable aging detection device based on a combination of chemical mechanism and AI, comprising a memory and one or more processors, wherein the memory stores executable code, and when the one or more processors execute the executable code, it is used for the above-mentioned automated cable aging detection method based on a combination of chemical mechanism and AI.

[0018] The present invention also includes a computer-readable storage medium on which a program is stored. When the program is executed by a processor, the above-mentioned automatic cable aging detection method based on the combination of chemical mechanism and AI is implemented.

[0019] The beneficial effects of the present invention are as follows: the present invention realizes a fully automated cable aging detection process and method by integrating the mechanism change of cable materials with appearance detection, reducing labor costs and time. The method combines the latest cable material self-diagnosis method with artificial intelligence external detection, improves the accuracy of diagnosis, realizes the method process of integrated detection and evaluation, and improves the credibility of cable aging detection. It is beneficial for new energy system operators to discover and repair problems in a timely manner, increase safety and improve economy. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a flow chart of an automated cable aging detection method based on a combination of chemical mechanism and AI;

[0021] Figure 2 This is a structural diagram of an automated cable aging detection device based on a combination of chemical mechanism and AI. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical scheme and advantages of the present invention more clear, the present invention is further described in detail in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0023] Example 1

[0024] like Figure 1 As shown, the present invention provides an automated cable aging detection method based on a combination of chemical mechanism and AI, comprising the following steps:

[0025] (1) A plurality of electrical aging self-diagnostic insulating materials are prepared using the preparation method of electrical aging self-diagnostic insulating materials provided by Chinese patent CN117343543A "An electrical aging self-diagnostic insulating material and preparation method thereof". The electrical aging self-diagnostic insulating materials prepared by the preparation method can be divided into aged electrical aging self-diagnostic insulating materials and unaged electrical aging self-diagnostic insulating materials. Image detection is performed on each electrical aging self-diagnostic insulating material to obtain a corresponding detection image, and a cable self-diagnosis detection sample data set consisting of all detection images is constructed.

[0026] (2) Based on the R&D experiments of self-diagnosis samples, a knowledge base of "cable aging self-diagnosis insulation materials and their preparation" and its corresponding case library are constructed. The general knowledge base is constructed by collecting relevant general cable material knowledge manuals and papers and standards related to cable materials; then the cable self-diagnosis knowledge graph is obtained by constructing the cable self-diagnosis related knowledge.

[0027] The construction process of the cable self-diagnosis knowledge graph is specifically as follows:

[0028] a.1) Establish the ontology of cable self-diagnosis related knowledge, including ontology objects and object attributes;

[0029] a.2) Extract all entities corresponding to the ontology objects from the ontology of cable self-diagnosis related knowledge by manual or algorithmic extraction, and construct corresponding triples [T i ,R i,j ,T j ], where T i and T j Represents any entity, R i,j Represents entity T i and entity T j the relationship between;

[0030] a.3) All triples constructed in step (a.2) constitute the cable self-diagnosis knowledge graph.

[0031] (3) A ResNet classification model is trained based on the cable self-diagnosis detection sample data set to obtain a cable classification model; the cable classification model can be used to determine whether the input self-diagnosis insulation material is aged.

[0032] (4) fine-tuning the general large model using the P-Tuning method based on the general knowledge base and the cable self-diagnosis knowledge graph to obtain a large model for cable aging detection; the general large model includes the Zhipu large model;

[0033] (5) The real-time cable detection data is automatically input into the constructed cable classification model for classification: if it is classified as not aged, the next cable detection data is detected; if it is classified as aged, the general knowledge base is searched through the current cable detection data to obtain the corresponding knowledge vector information, and the cable self-diagnosis knowledge graph is searched through the current cable detection data to obtain the corresponding knowledge graph information. The retrieved knowledge vector information and knowledge graph information are integrated and transformed to obtain the prompt word corresponding to the current cable detection data, and the abnormal result is generated according to the prompt word through the large model of cable aging detection. The abnormal result includes the cause analysis of the aging of the cable detection data and repair suggestions.

[0034] Example 2

[0035] This embodiment relates to an automated cable aging detection device based on a combination of chemical mechanism and AI, including a memory and one or more processors, wherein the memory stores executable code, and when the one or more processors execute the executable code, it is used for an automated cable aging detection method based on a combination of chemical mechanism and AI in the above-mentioned embodiment 1; the device embodiment can be applied to any device with data processing capabilities, and the any device with data processing capabilities can be a device or apparatus such as a computer.

[0036] like Figure 2 At the hardware level, the model watermark device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 Of course, in addition to the software implementation, the present invention does not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0037] For the improvement of a technology, it can be clearly distinguished whether it is a hardware improvement (for example, improvement of the circuit structure of diodes, transistors, switches, etc.) or a software improvement (improvement of the method flow). However, with the development of technology, many improvements of the method flow today can be regarded as direct improvements of the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be implemented with a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming themselves, without having to ask chip manufacturers to design and make dedicated integrated circuit chips. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0038] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

[0039] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0040] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0041] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0042] The present invention may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0043] Example 3

[0044] An embodiment of the present invention further provides a computer-readable storage medium having a program stored thereon. When the program is executed by a processor, an automated cable aging detection method based on a combination of chemical mechanism and AI according to the above-mentioned embodiment 1 is implemented.

[0045] The above description is only a preferred embodiment of the present invention and is not intended to limit 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. An automated cable aging detection method based on a combination of chemical mechanism and AI, characterized in that: The following steps are involved: (1) preparing a plurality of electrical aging self-diagnosis insulating materials, performing image detection on each electrical aging self-diagnosis insulating material to obtain a corresponding detection image, and constructing a cable self-diagnosis detection sample data set consisting of all the detection images; (2) A general knowledge base is constructed by collecting relevant general cable material knowledge manuals and papers and standards related to cable materials; Then, the cable self-diagnosis knowledge graph is obtained by constructing the cable self-diagnosis related knowledge; (3) Training a ResNet classification model based on the cable self-diagnosis detection sample data set to obtain a cable classification model; (4) Based on the general knowledge base and the cable self-diagnosis knowledge graph, the general large model is fine-tuned and trained in a P-Tuning manner to obtain a large model for cable aging detection; (5) The real-time cable detection data is automatically input into the constructed cable classification model for classification: if it is classified as not aged, the next cable detection data is detected; if it is classified as aged, the general knowledge base is searched through the current cable detection data to obtain the corresponding knowledge vector information, and the cable self-diagnosis knowledge graph is searched through the current cable detection data to obtain the corresponding knowledge graph information. The retrieved knowledge vector information and knowledge graph information are integrated and transformed to obtain the prompt word corresponding to the current cable detection data, and the abnormal result is generated according to the prompt word through the large model of cable aging detection. The abnormal result includes the cause analysis of the aging of the cable detection data and repair suggestions.

2. According to claim 1, an automated cable aging detection method based on a combination of chemical mechanism and AI is characterized in that: The construction process of the cable self-diagnosis knowledge graph is specifically as follows: a.1) Establish the ontology of cable self-diagnosis related knowledge, including ontology objects and object attributes; a.2) Extract all entities corresponding to the ontology objects from the ontology of cable self-diagnosis related knowledge by manual or algorithmic extraction, and construct corresponding triples [T i ,R i,j ,T j ], where T i and T j Represents any entity, R i,j Represents entity T i and entity T j the relationship between; a.3) All triples constructed in step (a.2) constitute the cable self-diagnosis knowledge graph.

3. The automatic cable aging detection method based on the combination of chemical mechanism and AI according to claim 1 is characterized in that: The general big model includes the Zhipu big model.

4. An automated cable aging detection device based on a combination of chemical mechanism and AI, characterized in that: It comprises a memory and one or more processors, wherein the memory stores executable code, and when the one or more processors execute the executable code, it is used to implement an automated cable aging detection method based on a combination of chemical mechanism and AI as described in any one of claims 1 to 3.

5. A computer-readable storage medium, characterized in that: A program is stored thereon, and when the program is executed by a processor, an automated cable aging detection method based on a combination of chemical mechanism and AI as described in any one of claims 1 to 3 is implemented.

Images