Equipment fault positioning method and system based on artificial intelligence

Abstract

The invention relates to the technical field of mechanical equipment production, operation and maintenance, and provides an artificial intelligence-based equipment fault positioning method and system, and the method comprises the steps: constructing an artificial intelligence model according to the structural characteristics of equipment parts, and substituting the vibration data and fault data corresponding to a fault into the artificial intelligence model, learning training is carried out, so that a transmission characteristic relation among nodes in the model can reflect vibration transmission characteristics of equipment parts; the real-time vibration data of the equipment is obtained and substituted into the artificial intelligence model, the vibration source is identified and positioned, the part where the fault occurs is determined, the part where the fault occurs in the equipment is accurately identified, real-time fault positioning can be carried out continuously, the operation stability of the equipment and the maintenance timeliness are improved, and the production of the equipment is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of mechanical equipment production and operation and maintenance, and in particular to an equipment fault locating method and system based on artificial intelligence. Background Art

[0002] In existing industrial production, long-term operation of equipment may cause failure of equipment components due to mechanical fatigue or lubrication consumption. Traditional equipment fault detection methods mainly rely on manual inspections and simple sensor detection, which have problems such as low detection efficiency, inaccurate fault diagnosis, and inability to provide early warning. Manual inspections require a lot of manpower and time, and are easily affected by subjective factors, making it difficult to detect potential faults in a timely manner. Traditional sensor monitoring can only detect changes in the surface parameters of the equipment, and is insufficient in its ability to analyze the deep-seated causes of complex faults, making it impossible to accurately locate the fault, which is not conducive to the stability of equipment product production. Summary of the invention

[0003] The present invention provides an equipment fault location method based on artificial intelligence, which is used to solve the problem of low efficiency of component fault location during equipment operation in the prior art.

[0004] A first aspect of the present invention provides an artificial intelligence-based device fault location method, comprising:

[0005] Establish an artificial intelligence model based on the structure and transmission connection relationship of the current equipment components; obtain the setting position of the vibration sensor on the current equipment, and obtain the vibration data of the position of the vibration sensor based on the current equipment to obtain standard vibration data;

[0006] Obtain fault vibration history data and fault location data, and identify fault vibration data in the fault vibration history data according to standard vibration data; substitute the fault vibration data and fault location data into the artificial intelligence model, substitute the fault vibration data into the corresponding nodes in the model according to the location of the vibration sensor of the data source, learn the correlation characteristics of the nodes between the fault vibration data and the fault location data, and correct the scaling coefficient of the transmission vector between the nodes in the artificial intelligence model;

[0007] Monitor the real-time vibration data of the current equipment, and determine whether there is vibration data exceeding the threshold in the real-time vibration data based on the standard vibration data. If so, substitute the vibration data into the artificial intelligence model to identify the location of the fault in the current equipment.

[0008] Optionally, after substituting the fault vibration data and the fault location data into the artificial intelligence model, the method further includes:

[0009] Obtain the equipment power parameter data for the time period corresponding to the fault history data, identify the electric control data corresponding to different components in the power parameter data, and input the electric control data into the artificial intelligence model based on the corresponding nodes of the components to learn the characteristics of the impact of component failures on the electric control data.

[0010] Optionally, the establishing of the artificial intelligence model according to the structure and transmission connection relationship of the current equipment components further includes: obtaining the working mode of the current equipment, and establishing different artificial intelligence models according to the structures of the component actions under different working modes;

[0011] Substituting the fault vibration data and the fault location data into the artificial intelligence model specifically also includes: identifying the working mode corresponding to the fault vibration data, and substituting the fault vibration data and the fault location data into the artificial intelligence model corresponding to the working mode.

[0012] The second aspect of the present application provides an artificial intelligence-based equipment fault location system, comprising:

[0013] The model building module is used to establish an artificial intelligence model according to the structure and transmission connection relationship of the current equipment components; obtain the setting position of the vibration sensor on the current equipment, and obtain the vibration data of the position of the vibration sensor according to the current equipment to obtain standard vibration data;

[0014] A model training module is used to obtain fault vibration historical data and fault location data, identify fault vibration data in the fault vibration historical data according to standard vibration data; substitute the fault vibration data and fault location data into the artificial intelligence model, substitute the fault vibration data into the corresponding nodes in the model according to the location of the vibration sensor of the data source, learn the correlation characteristics of the nodes between the fault vibration data and the fault location data, and correct the scaling coefficient of the transmission vector between the nodes in the artificial intelligence model;

[0015] The fault location module is used to monitor the real-time vibration data of the current equipment and determine whether there is vibration data exceeding the threshold in the real-time vibration data based on the standard vibration data. If so, the vibration data is substituted into the artificial intelligence model to identify the location of the fault in the current equipment.

[0016] Optionally, in the model training module, after the fault vibration data and the fault location data are substituted into the artificial intelligence model, the following steps are further included:

[0017] Obtain the equipment power parameter data for the time period corresponding to the fault history data, identify the electric control data corresponding to different components in the power parameter data, and input the electric control data into the artificial intelligence model based on the corresponding nodes of the components to learn the characteristics of the impact of component failures on the electric control data.

[0018] Optionally, in the model building module, the artificial intelligence model is established according to the structure and transmission connection relationship of the current equipment components, and further includes: obtaining the working mode of the current equipment, and establishing different artificial intelligence models according to the structure of the component actions under different working modes;

[0019] In the model training module, the fault vibration data and the fault location data are substituted into the artificial intelligence model, which specifically also includes: identifying the working mode corresponding to the fault vibration data, and substituting the fault vibration data and the fault location data into the artificial intelligence model corresponding to the working mode.

[0020] The third aspect of the present application provides a method and device for locating device faults based on artificial intelligence, the device comprising a processor and a memory:

[0021] The memory is used to store program code and transmit the program code to the processor;

[0022] The processor is used to execute an artificial intelligence-based equipment fault location method as described in any one of the first aspects of the present invention according to the instructions in the program code.

[0023] The fourth aspect of the present application provides a computer-readable storage medium, which is used to store program code, and the program code is used to execute an artificial intelligence-based device fault location method as described in any one of the first aspects of the present invention.

[0024] It can be seen from the above technical scheme that the present invention has the following advantages: by constructing an artificial intelligence model according to the structural characteristics of equipment components, and substituting the vibration data and fault data corresponding to the fault into the artificial intelligence model, learning and training enable the transmission characteristic relationship between the nodes in the model to reflect the vibration transmission characteristics of the equipment components; obtaining the real-time vibration data of the equipment and substituting it into the artificial intelligence model, identifying and locating the source of the vibration, determining the component where the fault occurs, accurately identifying the component where the fault is located in the equipment, and being able to perform real-time fault location uninterruptedly, thereby improving the stability of equipment operation and the timeliness of maintenance, and ensuring equipment production. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present invention 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 invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0026] Figure 1 It is a flow chart of a method for locating equipment faults based on artificial intelligence;

[0027] Figure 2 This is a structural diagram of an equipment fault location system based on artificial intelligence. DETAILED DESCRIPTION

[0028] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, 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 embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] The present invention provides an equipment fault location method based on artificial intelligence, which is used to solve the problem of low efficiency of component fault location during equipment operation in the prior art.

[0030] See also Figure 1 , Figure 1 The present invention provides a first flowchart of an artificial intelligence-based device fault location method according to an embodiment of the present invention.

[0031] S100, establishing an artificial intelligence model according to the structure and transmission connection relationship of the current equipment components; obtaining the setting position of the vibration sensor on the current equipment, and obtaining vibration data of the position of the vibration sensor according to the current equipment to obtain standard vibration data;

[0032] It should be noted that the three-dimensional model of the current equipment is used to obtain its component structure. The three-dimensional model can reflect the type and shape of the equipment components and the connection relationship of the internal structure. The motion state of the structure can be determined according to the type and shape of the components, such as the reciprocating motion direction and motion amplitude of the connecting rod component, and the rotation axis of the gear component in the three-dimensional space. The transmission connection relationship is obtained according to the contact and connection between different components in the three-dimensional model. For example, a worm is connected to a gear and there is a transmission relationship between the two. The artificial intelligence model in this embodiment adopts a graph neural network, which can well learn the relationship characteristics between equipment components. It takes the various structural components of the current equipment as nodes, establishes links between corresponding nodes according to the adjacent and connection relationships of the components, and based on the motion corresponding to the structure of each component The unit transmission vector between nodes is set by the direction and movement amplitude. For example, two parts are connected for transmission, but due to different parts structures and connection methods, the corresponding movement directions are also different, so the vibrations that can be transmitted between the two parts are also different. Generally, if there is a fault vibration based on the original part vibration, it should also be consistent with the movement direction of its parts. For example, part A rotates, and part B reciprocates. The direction of the vector transmitted from the node corresponding to part A to part B corresponds to the characteristics of the rotation direction, and the direction of the vector transmitted from the node corresponding to part B to part A corresponds to the characteristics of the reciprocating direction. The vector is transmitted bidirectionally between nodes, and the modulus length of the transmission vector of adjacent parts can be set according to the movement amplitude of the parts. The vector direction and modulus length reflect the basic situation of vibration transmission between the corresponding parts of the nodes.

[0033] A vibration sensor is also required in the equipment to detect impact force. Mechanical, electrical or optical sensors can be used. They are generally installed on parts of the equipment that are more prone to failure and vibration, or on key parts. The setting position of the vibration sensor in the current equipment is the set part. Vibration monitoring of a device generally requires multiple vibration sensors. When the current equipment is operating in a normal working state, vibration data can be obtained based on the vibration sensor. At this time, the vibration data obtained by the vibration sensor is that there is no harmful vibration, only regular periodic mechanical wave vibration caused by normal movement between mechanical structures, then standard vibration data can be obtained.

[0034] S200, acquiring fault vibration history data and fault location data, identifying fault vibration data in the fault vibration history data according to standard vibration data; substituting the fault vibration data and fault location data into an artificial intelligence model, substituting the fault vibration data into corresponding nodes in the model according to the location of the vibration sensor of the data source, learning the correlation characteristics of the nodes between the fault vibration data and the fault location data, and correcting the scaling coefficient of the transmission vector between the nodes in the artificial intelligence model;

[0035] It should be noted that after the vibration sensor is set up in the above steps, after a period of equipment use, the vibration sensor will collect vibration data, and the vibration data collected by the vibration sensor after a device failure occurs during the use of the equipment can include data on fault vibration, and the cause of the fault is determined by manual detection to determine the faulty component, and the fault location data is obtained, and the vibration data of a preset time length can be intercepted at the time of manual fault detection as fault vibration history data; vibration is a normal mechanical motion state, so it will not cause obvious damage to mechanical equipment; in engineering machinery, vibration is mainly caused by the unbalanced movement of mechanical equipment such as engines and hydraulic pumps. Due to the impact and irregularity of vibration, it will cause greater damage to mechanical equipment and shorten the life of mechanical equipment; and vibration is a mechanical wave, which has the characteristics of instantaneity, impact and irregularity; the vibration data detected by the vibration sensor is waveform data, and the fault vibration history data at this time contains the normal vibration of the component movement and the vibration caused by the fault, so the fault vibration history data can be regarded as a synthetic wave after the fusion of two waveform signals, based on the standard vibration data in the above steps, the synthetic wave of the fault vibration history data is separated, and the waveform signal corresponding to the fault vibration data is separated and identified;

[0036] The fault vibration data can be determined according to the component where the vibration sensor from which it is obtained is set, to determine the node where the fault vibration data is input into the artificial intelligence model; and the faulty component is determined according to the fault location data of manual inspection. The fault location data also includes specific information about the equipment fault, and the original fault vibration data preset according to the specific type and degree of the equipment component fault, that is, the vibration waveform data caused by the detected fault vibration on the component where it is located, such as scratches, foreign matter and insufficient lubrication. Different vibration waveform data are preset, and are set and adjusted according to the specific component structure requirements. The fault location data can be substituted into the node corresponding to the faulty component in the artificial intelligence model;

[0037] In the current equipment, due to the fault defects of the components, vibration is generated at the location of the faulty component during operation, and is transmitted to other components according to the connection relationship of the components, and is detected by the vibration sensors installed on other components; the transmission of vibration between adjacent connected components is reflected in the artificial intelligence model as a transmission vector with a preset modulus and direction of the adjacent nodes, but the transmission vector is set based on the component situation, and the specific vibration transmission will be reduced due to the contact situation or the actual connection relationship. Therefore, after substituting the fault vibration data and the fault location data into the artificial intelligence model, it can learn to correct the scaling coefficient of the transmission vector between each node. For example, three components ABC in the equipment are connected in sequence, the fault occurs on component A, and the vibration sensor is set on component C. In the established artificial intelligence model, the vector for transmitting vibration from component A to component B is set to The vector of vibration transmitted from component B to component C is set as The fault location data corresponding to the manual fault detection in component A, that is, the fault vibration generated is regarded as The fault vibration data detected and processed by the vibration sensor in component C is Learning in AI models How to pass through the corresponding node of component ABC is detected as To obtain the corrected scaling factor between components ABC.

[0038] S300, monitor the real-time vibration data of the current device, and determine whether there is vibration data exceeding the threshold in the real-time vibration data based on the standard vibration data. If so, substitute the vibration data into the artificial intelligence model to identify the location of the fault in the current device.

[0039] It should be noted that the vibration sensor will monitor and collect vibration data in real time. The vibration data collected when the current equipment is in normal operation should be similar to the standard vibration data. When the real-time vibration data is collected, it will be compared with the standard vibration data, and the vibration data will be separated by synthetic wave separation. It can be judged whether it exceeds the threshold value according to the frequency of the vibration data waveform. The threshold value can be set based on the fault vibration data in the fault data in the aforementioned step S200. Because the amplitude intensity will be weakened under vibration transmission but the frequency will not change, it can effectively identify whether it is a bad vibration rather than vibration caused by mechanical movement. When there is vibration data exceeding the threshold, it can be regarded as a fault in the current equipment; by substituting the vibration data detected in the vibration sensor into the artificial intelligence model, it can be identified at which node the source of the vibration is, and the corresponding equipment component with faults can be obtained and located; after the fault is located, a prompt or alarm message will be sent to the management personnel to arrange equipment inspection and maintenance, effectively avoiding production delays caused by equipment failure; further, on the basis of identifying the fault location, the artificial intelligence model can also predict the occurrence of faults according to the changing trend of the vibration signal and issue an alarm in advance.

[0040] In this embodiment, an artificial intelligence model is constructed according to the structural characteristics of equipment components, and the vibration data and fault data corresponding to the fault are substituted into the artificial intelligence model. Learning and training are performed so that the transmission characteristic relationship between the nodes in the model can reflect the vibration transmission characteristics of the equipment components. The real-time vibration data of the equipment is obtained and substituted into the artificial intelligence model to identify and locate the source of the vibration, determine the component where the fault occurs, accurately identify the component where the fault is located in the equipment, and continuously perform real-time fault location, thereby improving the stability of equipment operation and the timeliness of maintenance, and ensuring equipment production.

[0041] The above is a detailed description of the first embodiment of an artificial intelligence-based device fault location method provided by the present application. The following is a detailed description of the second embodiment of an artificial intelligence-based device fault location method provided by the present application.

[0042] In this embodiment, a method for locating equipment faults based on artificial intelligence is further provided. In the aforementioned step S200, after the fault vibration data and the fault location data are substituted into the artificial intelligence model, the method further includes: obtaining equipment power parameter data of a time period corresponding to the fault history data, identifying electric control data corresponding to different components in the power parameter data, and inputting the electric control data into the artificial intelligence model based on the corresponding nodes of the components, and learning the characteristics of the impact of component faults on the electric control data;

[0043] It should be noted that production equipment generally uses electric drive and control, and needs to maintain the rotation speed or movement speed during mechanical movement. When there is a component failure such as cracks or foreign body wear, it will cause the friction of the component to increase so that a higher voltage or current is needed to increase the rotation speed. According to the fault category under the structural characteristics of different components, the characteristics of the electronic control parameter data can be identified to identify the fault type, and the relationship characteristics between the power parameters at different nodes can be learned in the artificial intelligence model. The power parameter changes caused by the difficulty of connecting the components due to the failure of a certain component should also be reflected in the artificial intelligence model; the parameters of the electronic control part of the current equipment can be monitored, specifically the parameter data such as voltage, current and power. After extraction, the data needs to be cleaned and feature extracted to extract the feature information related to the equipment failure; the long short-term memory network (LSTM) can be used to train the data for the artificial intelligence model. The trained artificial intelligence model can warn of the overload risk of the equipment based on the real-time power parameter data to ensure the stable operation of the power system.

[0044] Furthermore, in the aforementioned step S100, the artificial intelligence model is established according to the structure and transmission connection relationship of the current equipment components, and further includes:

[0045] Obtain the working mode of the current equipment, and establish different artificial intelligence models according to the structure of component actions under different working modes; substituting the fault vibration data and the fault location data into the artificial intelligence model specifically also includes: identifying the working mode corresponding to the fault vibration data, and substituting the fault vibration data and the fault location data into the artificial intelligence model corresponding to the working mode.

[0046] It should be noted that the components that move under different working states of the current equipment are different, the components that generate mechanical movement and vibration are different, and even if the components that do not participate in the operation have fault defects, they will not generate vibration due to non-movement. Therefore, nodes can be set according to the different component action structures under different working modes of the current equipment to establish a corresponding artificial intelligence model; in the subsequent step of substituting data into the model, the corresponding artificial intelligence model is selected according to the working mode when the fault vibration data is obtained, and the node corresponding to the input data is selected and converted into a vector.

[0047] The above is a detailed description of an artificial intelligence-based equipment fault location method provided in the first aspect of the present application. The following is a detailed description of an embodiment of an artificial intelligence-based equipment fault location system provided in the second aspect of the present application.

[0048] See also Figure 2 , Figure 2 This embodiment provides a device fault location system based on artificial intelligence, including:

[0049] The model building module 10 is used to establish an artificial intelligence model according to the structure and transmission connection relationship of the current equipment components; obtain the setting position of the vibration sensor on the current equipment, and obtain the vibration data of the position of the vibration sensor according to the current equipment to obtain standard vibration data;

[0050] The model training module 20 is used to obtain fault vibration history data and fault location data, identify fault vibration data in the fault vibration history data according to the standard vibration data; substitute the fault vibration data and the fault location data into the artificial intelligence model, substitute the fault vibration data into the corresponding node in the model according to the location of the vibration sensor of the data source, learn the correlation characteristics of the nodes between the fault vibration data and the fault location data, and correct the scaling coefficient of the transmission vector between the nodes in the artificial intelligence model;

[0051] The fault location module 30 is used to monitor the real-time vibration data of the current equipment, and determine whether there is vibration data exceeding the threshold in the real-time vibration data based on the standard vibration data. If so, the vibration data is substituted into the artificial intelligence model to identify the location of the fault in the current equipment.

[0052] Furthermore, in the model training module 20, after the fault vibration data and the fault location data are substituted into the artificial intelligence model, the following steps are further included:

[0053] Obtain the equipment power parameter data for the time period corresponding to the fault history data, identify the electric control data corresponding to different components in the power parameter data, and input the electric control data into the artificial intelligence model based on the corresponding nodes of the components to learn the characteristics of the impact of component failures on the electric control data.

[0054] Furthermore, in the model building module 10, the artificial intelligence model is established according to the structure and transmission connection relationship of the current equipment components, and further includes: obtaining the working mode of the current equipment, and establishing different artificial intelligence models according to the structure of the component actions under different working modes;

[0055] In the model training module 20, the fault vibration data and the fault location data are substituted into the artificial intelligence model, which specifically includes: identifying the working mode corresponding to the fault vibration data, and substituting the fault vibration data and the fault location data into the artificial intelligence model corresponding to the working mode.

[0056] The third aspect of the present application also provides an artificial intelligence-based equipment fault location method device, including a processor and a memory: the memory is used to store program code and transfer the program code to the processor; the processor is used to execute the above-mentioned artificial intelligence-based equipment fault location method according to the instructions in the program code.

[0057] The fourth aspect of the present application provides a computer-readable storage medium, characterized in that the computer-readable storage medium is used to store program code, and the program code is used to execute the above-mentioned artificial intelligence-based equipment fault location method.

[0058] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and equipment can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0059] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0060] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0061] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0062] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0063] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for locating equipment faults based on artificial intelligence, characterized in that include: An artificial intelligence model is established according to the structure and transmission connection relationship of the current equipment components; the setting position of the vibration sensor on the current equipment is obtained, and the vibration data of the position of the vibration sensor is obtained according to the current equipment to obtain standard vibration data; Acquire fault vibration history data and fault location data, and identify fault vibration data in the fault vibration history data according to standard vibration data; Substituting the fault vibration data and the fault location data into the artificial intelligence model, the fault vibration data is substituted into the corresponding node in the model according to the location of the vibration sensor of the data source, learning the correlation characteristics of the nodes between the fault vibration data and the fault location data, and correcting the scaling coefficient of the transmission vector between the nodes in the artificial intelligence model; Monitor the real-time vibration data of the current equipment, and determine whether there is vibration data exceeding the threshold in the real-time vibration data based on the standard vibration data. If so, substitute the vibration data into the artificial intelligence model to identify the location of the fault in the current equipment.

2. According to the artificial intelligence-based equipment fault location method of claim 1, it is characterized in that: After the fault vibration data and the fault location data are substituted into the artificial intelligence model, the method further includes: Obtain the equipment power parameter data for the time period corresponding to the fault history data, identify the electric control data corresponding to different components in the power parameter data, and input the electric control data into the artificial intelligence model based on the corresponding nodes of the components to learn the characteristics of the impact of component failures on the electric control data.

3. The method for locating equipment faults based on artificial intelligence according to claim 1, characterized in that: The establishing of the artificial intelligence model according to the structure and transmission connection relationship of the current equipment components also includes: obtaining the working mode of the current equipment, and establishing different artificial intelligence models according to the structure of the component actions under different working modes; Substituting the fault vibration data and the fault location data into the artificial intelligence model specifically also includes: identifying the working mode corresponding to the fault vibration data, and substituting the fault vibration data and the fault location data into the artificial intelligence model corresponding to the working mode.

4. An artificial intelligence-based equipment fault location system, characterized in that: include: The model building module is used to establish an artificial intelligence model according to the structure and transmission connection relationship of the current equipment components; obtain the setting position of the vibration sensor on the current equipment, and obtain the vibration data of the position of the vibration sensor according to the current equipment to obtain standard vibration data; A model training module is used to obtain fault vibration history data and fault location data, and identify fault vibration data in the fault vibration history data according to standard vibration data; Substituting the fault vibration data and the fault location data into the artificial intelligence model, the fault vibration data is substituted into the corresponding node in the model according to the location of the vibration sensor of the data source, learning the correlation characteristics of the nodes between the fault vibration data and the fault location data, and correcting the scaling coefficient of the transmission vector between the nodes in the artificial intelligence model; The fault location module is used to monitor the real-time vibration data of the current equipment and determine whether there is vibration data exceeding the threshold in the real-time vibration data based on the standard vibration data. If so, the vibration data is substituted into the artificial intelligence model to identify the location of the fault in the current equipment.

5. The artificial intelligence-based equipment fault location system according to claim 4, characterized in that: In the model training module, after the fault vibration data and the fault location data are substituted into the artificial intelligence model, the following is also included: Obtain the equipment power parameter data for the time period corresponding to the fault history data, identify the electric control data corresponding to different components in the power parameter data, and input the electric control data into the artificial intelligence model based on the corresponding nodes of the components to learn the characteristics of the impact of component failures on the electric control data.

6. The artificial intelligence-based equipment fault location system according to claim 4, characterized in that: In the model building module, an artificial intelligence model is established according to the structure and transmission connection relationship of the current equipment components, and also includes: obtaining the working mode of the current equipment, and establishing different artificial intelligence models according to the structure of the component actions under different working modes; In the model training module, the fault vibration data and the fault location data are substituted into the artificial intelligence model, which specifically also includes: identifying the working mode corresponding to the fault vibration data, and substituting the fault vibration data and the fault location data into the artificial intelligence model corresponding to the working mode.

7. An artificial intelligence-based equipment fault location device, characterized in that: The device comprises a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute an artificial intelligence-based equipment fault location method as described in any one of claims 1-3 according to the instructions in the program code.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store program code, and the program code is used to execute the artificial intelligence-based equipment fault location method described in any one of claims 1-3.

Images