An artificial intelligence-based sensor failure prediction method

Abstract

This application provides an artificial intelligence-based sensor fault prediction method, belonging to the field of artificial intelligence, to achieve relatively accurate sensor fault prediction. The method includes: acquiring the detection error information of multiple sensors within a nuclear power system; analyzing the logical relationship between the nuclear power system's operations or production and the operations or production of the multiple sensors using an AI / ML model to obtain the topological relationship of at least two sensors among the multiple sensors, wherein at least two sensors participate in the detection of operations or production, and the topological relationship of the at least two sensors describes the sequential detection logical relationship of the at least two sensors for operations or production; and predicting whether a faulty sensor exists among the at least two sensors based on the topological relationship of the at least two sensors and the detection error information of the at least two sensors.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence, and in particular to a sensor fault prediction method based on artificial intelligence. Background Technology

[0002] With the continuous development of industrial automation and intelligent manufacturing, sensors are playing an increasingly important role in industrial production processes. As key data acquisition devices, sensors can monitor and record various parameters in the production process in real time, providing crucial information for production decisions. However, sensors may malfunction for various reasons during long-term operation, which can not only affect production efficiency but also lead to product quality problems or even safety accidents. Therefore, predicting sensor malfunctions and maintaining them in a timely manner are essential measures to ensure the stable operation of industrial production.

[0003] Sensor malfunctions can lead to inaccurate or incomplete data collection, affecting the monitoring and control of the production process. Production interruptions: Sensor malfunctions may cause production lines to stop or reduce production efficiency. Sensor malfunctions may also lead to improper control of critical parameters during production, affecting product quality. Sensor malfunctions may cause abnormal equipment operation, increasing the risk of safety accidents.

[0004] Sensor fault prediction technology can analyze the operating status and historical data of sensors to detect potential fault signs in advance, thereby taking preventive measures or carrying out maintenance in advance to avoid failures. This technology is of great significance for improving production efficiency, ensuring product quality, and guaranteeing production safety. Summary of the Invention

[0005] This application provides an artificial intelligence-based sensor fault prediction method to achieve more accurate sensor fault prediction.

[0006] To achieve the above objectives, this application adopts the following technical solution:

[0007] Firstly, an artificial intelligence-based sensor fault prediction method is provided, which includes: acquiring the detection error status of multiple sensors in a nuclear power system; analyzing the business or production logic relationship between the nuclear power system and the multiple sensors through an AI / ML model to obtain the topological relationship of at least two sensors among the multiple sensors, wherein at least two sensors participate in the detection of business or production, and the topological relationship of at least two sensors is used to describe the sequential detection logic relationship of at least two sensors for business or production; and predicting whether there is a faulty sensor among the at least two sensors based on the topological relationship of at least two sensors and the detection error status of at least two sensors.

[0008] Optionally, the business or production logic relationship between the nuclear power system and multiple sensors is analyzed through an AI / ML model to obtain the topological relationship of multiple sensors. This includes: analyzing the business or production logic relationship between the business or production information and the information of multiple sensors through an AI / ML model to obtain the topological relationship of at least two sensors output by the AI / ML model. The business or production information includes information on the equipment involved in performing the business or production, and the information of multiple sensors is used to indicate that each sensor is set in the corresponding equipment and the business or production detection type of each sensor.

[0009] Optionally, the AI / ML model is used to analyze the business or production information and the information from multiple sensors to obtain the topological relationship of at least two sensors output by the AI / ML model. This includes: preprocessing the information from multiple sensors and the business or production information to determine that at least two of the multiple sensors are set on the equipment involved in performing the business or production and participate in the detection of the business or production, thereby determining that at least two sensors participate in the detection of the business or production, and the business or production detection type of at least two sensors indicates that at least two sensors participate in the detection of the business or production; inputting the information from at least two sensors and the business or production information into the AI / ML model to analyze the business or production logic relationship, thereby obtaining the topological relationship of at least two sensors output by the AI / ML model.

[0010] Optionally, based on the topological relationship of at least two sensors and the detection error of at least two sensors, predicting whether there is a faulty sensor among the at least two sensors includes: if, based on the topological relationship of at least two sensors and the detection error of at least two sensors, it is determined that the detection error changes of three of the at least two sensors satisfy a first preset relationship, then it is preset that there is a faulty sensor among the three sensors.

[0011] Optionally, the three sensors include a first sensor, a second sensor, and a third sensor. The topological relationship of at least two sensors is characterized as follows: the topological direction between the first and second sensors is from the first sensor to the second sensor, and the topological direction between the second and third sensors is from the second sensor to the third sensor. Based on this, if, according to the topological relationship of the at least two sensors and the detection error of the at least two sensors, it is determined that the detection error changes of three of the at least two sensors satisfy a first preset relationship, then it is predicted that there is a faulty sensor among the three sensors. This includes: if, according to the detection error of the at least two sensors, it is determined that the error accumulation direction between the first and second sensors is the same as the topological direction between the first and second sensors, and the error accumulation direction between the second and third sensors is the same as the topological direction between the second and third sensors, then it is predicted that there is a faulty sensor among the three sensors. If the topological orientations of the sensors are opposite, then the sensor with a fault among the three sensors is predicted to be the second sensor. The conditions for satisfying the first preset relationship include: if the error accumulation of the first sensor is positive and the error accumulation of the second sensor is also positive, or the error accumulation of the first sensor is negative and the error accumulation of the second sensor is also negative, then the error accumulation directions of the first and second sensors are the same as their topological orientations; if the error accumulation of the second sensor is positive and the error accumulation of the third sensor is negative, or the error accumulation of the second sensor is negative and the error accumulation of the third sensor is positive, then the error accumulation directions of the second and third sensors are opposite to their topological orientations.

[0012] Optionally, based on the topological relationship of at least two sensors and the detection error of at least two sensors, predicting whether there is a faulty sensor among the at least two sensors includes: if, based on the topological relationship of at least two sensors and the detection error of at least two sensors, it is determined that the detection error changes of three of the at least two sensors satisfy a second preset relationship, then it is preset that there is a faulty sensor among the three sensors.

[0013] Optionally, the three sensors include a first sensor, a second sensor, and a third sensor. The topological relationship of at least two sensors is characterized as follows: the topological direction between the first and second sensors is from the first sensor to the second sensor, and the topological direction between the second and third sensors is from the second sensor to the third sensor, and the topological direction between the first and third sensors is from the first sensor to the third sensor. Based on this, if, according to the topological relationship of the at least two sensors and the detection error of the at least two sensors, it is determined that the detection error changes of three of the at least two sensors satisfy a second preset relationship, then it is preset that one of the three sensors has a fault, including: if, according to the detection error of the at least two sensors, it is determined that the error accumulation direction of the first and second sensors is the same as the topological direction of the first and second sensors, the error accumulation direction of the second and third sensors is opposite to the topological direction of the second and third sensors, and the error accumulation direction of the first and third sensors is opposite to the topological direction of the first and third sensors, then it is predicted that one of the three sensors has a fault. The sensor is the second sensor; wherein, satisfying the second preset relationship includes: if the error accumulation of the first sensor is positive error accumulation and the error accumulation of the second sensor is also positive error accumulation, or the error accumulation of the first sensor is negative error accumulation and the error accumulation of the second sensor is also negative error accumulation, then the error accumulation direction of the first sensor and the second sensor is the same as the topological direction of the first sensor and the second sensor; if the error accumulation of the second sensor is positive error accumulation and the error accumulation of the third sensor is negative error accumulation, or the error accumulation of the second sensor is negative error accumulation and the error accumulation of the third sensor is positive error accumulation, then the error accumulation direction of the second sensor and the third sensor is opposite to the topological direction of the second sensor and the third sensor; if the error accumulation of the first sensor is positive error accumulation and the error accumulation of the third sensor is negative error accumulation, or the error accumulation of the first sensor is negative error accumulation and the error accumulation of the third sensor is positive error accumulation, then the error accumulation direction of the first sensor and the third sensor is opposite to the topological direction of the first sensor and the third sensor.

[0014] Optionally, based on the topological relationship of at least two sensors and the detection error of at least two sensors, predicting whether there is a faulty sensor among the at least two sensors includes: if, based on the topological relationship of at least two sensors and the detection error of at least two sensors, it is determined that the detection error changes of four of the at least two sensors satisfy a third preset relationship, then it is preset that there is a faulty sensor among the four sensors.

[0015] Optionally, the three sensors include a first sensor, a second sensor, a third sensor, and a fourth sensor. The topological relationship of at least two sensors is characterized as follows: the topological direction between the first and second sensors is from the first sensor to the second sensor; the topological direction between the second and third sensors is from the second sensor to the third sensor; and the topological direction between the second and fourth sensors is from the second sensor to the fourth sensor. Based on this, if, according to the topological relationship of the at least two sensors and their detection errors, it is determined that the detection error changes of four of the at least two sensors satisfy a third preset relationship, then it is presumed that one of the four sensors has a fault. This includes: if, according to the detection error conditions of the at least two sensors, it is determined that the error accumulation direction between the first and second sensors is the same as the topological direction between the first and second sensors, the error accumulation direction between the second and third sensors is opposite to the topological direction between the second and third sensors, and the error accumulation direction between the first and third sensors is opposite to the topological direction between the first and third sensors, then it is predicted that one of the three sensors has a fault. The faulty sensor is the second sensor; wherein, satisfying the third preset relationship includes: if the error accumulation of the first sensor is positive and the error accumulation of the second sensor is also positive, or the error accumulation of the first sensor is negative and the error accumulation of the second sensor is also negative, then the error accumulation direction of the first and second sensors is the same as the topological direction of the first and second sensors; if the error accumulation of the second sensor is positive and the error accumulation of the third sensor is negative, or the error accumulation of the second sensor is negative and the error accumulation of the third sensor is positive, then the error accumulation direction of the second and third sensors is opposite to the topological direction of the second and third sensors; if the error accumulation of the second sensor is positive and the error accumulation of the fourth sensor is negative, or the error accumulation of the second sensor is negative and the error accumulation of the fourth sensor is positive, then the error accumulation direction of the second and fourth sensors is opposite to the topological direction of the second and fourth sensors.

[0016] Secondly, an artificial intelligence-based sensor fault prediction device is provided, the device comprising:

[0017] The error acquisition module is used to acquire the detection error information of multiple sensors in the nuclear power system.

[0018] The relationship acquisition module is used to analyze the logical relationship between the business or production of the nuclear power system and the business or production of the multiple sensors through an AI / ML model, and to obtain the topological relationship of the multiple sensors, which are used for the detection of the business or production.

[0019] The fault prediction module is used to predict whether there is a faulty sensor among the multiple sensors based on the topological relationship of the multiple sensors and the detection error of the multiple sensors.

[0020] The apparatus described in the second aspect is specifically used to perform the functions of the method described in the first aspect.

[0021] Thirdly, a computer-readable storage medium is provided, comprising: a computer program or instructions; when the computer program or instructions are executed on a computer, the computer causes the computer to perform the method described in the first aspect.

[0022] The above-mentioned method and apparatus have the following technical effects: In industrial scenarios, sensors used for production line detection are set up along with the production line, which can also be understood as being set up according to business or production execution logic. In this case, the detection error of the sensors may accumulate with the execution logic of business or production. Based on this, electronic devices can obtain the topological relationship of at least two sensors through AI / ML model analysis, that is, the sequential detection logic relationship of at least two sensors for business or production. Thus, based on the topological relationship of at least two sensors and the detection error of at least two sensors, that is, based on whether the accumulation of error is normal, electronic devices can predict whether there is a faulty sensor among the at least two sensors, thereby achieving relatively accurate sensor fault prediction. Attached Figure Description

[0023] Figure 1 A flowchart illustrating the AI-based sensor fault prediction method provided in this application embodiment;

[0024] Figure 2 A schematic diagram illustrating an application scenario of the AI-based sensor fault prediction method provided in this application embodiment;

[0025] Figure 3 This is a schematic diagram of the structure of an artificial intelligence sensor fault prediction device according to another embodiment of the present invention;

[0026] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0027] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0028] This application will present various aspects, embodiments, or features relating to systems that may include multiple devices, components, modules, etc. It should be understood and appreciated that individual systems may include additional devices, components, modules, etc., and / or may not include all the devices, components, modules, etc. discussed in conjunction with the accompanying drawings. Furthermore, combinations of these approaches are also possible.

[0029] Furthermore, in the embodiments of this application, the words "exemplary," "for example," etc., are used to indicate that they are examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" in this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the term "exemplary" is intended to present the concept in a concrete manner.

[0030] The network architecture and business or production scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business or production scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0031] For example, Figure 1 This application provides a flowchart illustrating an artificial intelligence-based sensor fault prediction method. This method can be applied to the interaction of electronic devices.

[0032] like Figure 1 As shown, the process of this AI-based sensor fault prediction method is as follows:

[0033] S110. Obtain the detection error information of multiple sensors within the nuclear power system.

[0034] The detection error of multiple sensors can be specifically identified as the detection error of each individual sensor. This can be achieved by performing error detection on each sensor twice at different time intervals, obtaining two error values ​​for each sensor. The direction of error accumulation represented by these two error values ​​indicates the detection error situation. In other words, the detection error situation of each sensor indicates whether the sensor is accumulating positive or negative errors. For example, if error value #1 is detected first, and then error value #2 is detected later, if error value #1 is less than error value #2, it indicates positive error accumulation; conversely, if error value #1 is greater than error value #2, it indicates negative error accumulation.

[0035] It is understandable that error detection can be achieved using existing technologies, such as having a sensor detect a standard quantity, and the difference between the detected value and the standard quantity is the error value.

[0036] S120. Analyze the business or production logic relationship between the nuclear power system and multiple sensors through AI / ML models to obtain the topological relationship of at least two sensors among the multiple sensors.

[0037] The aforementioned at least two sensors participate in the detection of business or production, and the topological relationship of the at least two sensors is used to describe the sequential detection logic relationship of the at least two sensors for business or production.

[0038] For example, electronic devices can use AI / ML models to analyze business or production information and information from multiple sensors to obtain the topological relationship of at least two sensors output by the AI / ML model.

[0039] The information regarding the business or production includes information about the equipment involved in performing the business or production, such as the business or production identifier. This system could be a specific process, instrumentation, or electrical system in a nuclear power plant. The business or production could be within an industrial manufacturing scenario, such as a product manufacturing production line. The business or production identifier can uniquely identify the business or production, and can indicate the production line for that product. If a product has multiple production lines, there will be multiple identifiers, each uniquely indicating one production line. The equipment information can include identifiers for various types of manufacturing equipment within the production line. Since these devices belong to the production line, the working logic between them follows the sequential logic of the business or production process. For example, equipment #1 first performs processing #1 on the product, such as assembly, and then equipment #1 performs processing #2 on the product, such as polishing.

[0040] Information from multiple sensors is used to indicate that each sensor is set up in a corresponding device, and the business or production detection type of each sensor, such as the identifier of the device where each sensor is located, and the identifier of the business or production detected by each sensor, i.e., the business or production detection type of each sensor.

[0041] Specifically, electronic devices can preprocess information from multiple sensors and business or production information to determine that at least two of the multiple sensors are located on equipment involved in performing business or production and participate in business or production detection. That is, the equipment information indicates that the equipment belongs to the equipment in the production line indicated by the identifier of the business or production, and the business or production detection type contains the identifier of the business or production. Thus, it is determined that at least two sensors participate in business or production detection, and the business or production detection type of at least two sensors indicates that at least two sensors participate in business or production detection.

[0042] It is understood that the detection logic between at least two sensors described in this application also follows the sequential logic of business or production. For example, sensor #1 detects the time when the product has completed processing #1 as t1. This t1 can be an incremental time relative to the previous completed processing step. Sensor #1 sends t1 to sensor #2. Sensor #2 determines the absolute time when the product has completed processing #1 based on t1, such as x year x month x minute x second, and then detects the time when the product has completed processing #2 as t2. This t2 can be an incremental time relative to this absolute time. Therefore, the error of t1 will accumulate in t2, i.e., accumulated error. It should be understood that the above is an example of time detection, and other scenarios can also be applied, such as temperature detection. The principle is similar, and will not be elaborated further.

[0043] Therefore, electronic devices can input information from at least two sensors along with business or production information into an artificial intelligence (AI) / machine learning (ML) model to analyze the logical relationships between business and production processes, obtaining the topological relationship of at least two sensors output by the AI / ML model. The AI / ML model can be a deep neural network. Since the information from at least two sensors and the business or production information can represent the correspondence between each sensor and the device, and since the business or production information can represent the sequential logical relationships of these devices performing business or production processes, the AI / ML model can construct the topological relationship of at least two sensors based on this information. This topological relationship is consistent with the sequential logical relationships of these devices performing business or production processes.

[0044] S130. Based on the topological relationship of at least two sensors and the detection error of at least two sensors, predict whether there is a faulty sensor among the at least two sensors.

[0045] Scenario 1:

[0046] If an electronic device determines, based on the topological relationship of at least two sensors and the detection error of at least two sensors, that the detection error changes of three of the at least two sensors satisfy a first preset relationship, then the electronic device presets that one of the three sensors is faulty.

[0047] For example, three sensors include a first sensor, a second sensor, and a third sensor, and the topological relationship of at least two sensors is characterized as follows: the topological direction between the first sensor and the second sensor is that the first sensor points to the second sensor, and the topological direction between the second sensor and the third sensor is that the second sensor points to the third sensor.

[0048] Based on this, if the electronic device determines, according to the detection error of at least two sensors, that the error accumulation direction between the first sensor and the second sensor is the same as the topological direction between the first sensor and the second sensor, and the error accumulation direction between the second sensor and the third sensor is opposite to the topological direction between the second sensor and the third sensor, then the electronic device predicts that the second sensor is the faulty sensor among the three sensors.

[0049] like Figure 2 As shown in (a), satisfying the first preset relationship includes: if the error accumulation of the first sensor is positive and the error accumulation of the second sensor is also positive, or the error accumulation of the first sensor is negative and the error accumulation of the second sensor is also negative, then the error accumulation direction of the first and second sensors is the same as the topological direction of the first and second sensors; if the error accumulation of the second sensor is positive and the error accumulation of the third sensor is negative, or the error accumulation of the second sensor is negative and the error accumulation of the third sensor is positive, then the error accumulation direction of the second and third sensors is opposite to the topological direction of the second and third sensors. In other words, according to business or production logic, the failure of one sensor may cause problems with the error of the next sensor. Therefore, the fact that the error accumulation direction of the second and third sensors is opposite to the topological direction of the second and third sensors is most likely due to a failure of the second sensor, and thus the faulty sensor is the second sensor.

[0050] Scenario 2:

[0051] If an electronic device determines, based on the topological relationship of at least two sensors and the detection error of at least two sensors, that the detection error changes of three of the at least two sensors satisfy a second preset relationship, then the electronic device presets that one of the three sensors is faulty.

[0052] For example, the three sensors include a first sensor, a second sensor, and a third sensor, and the topological relationship of at least two sensors is characterized as follows: the topological direction between the first sensor and the second sensor is that the first sensor points to the second sensor, and the topological direction between the second sensor and the third sensor is that the second sensor points to the third sensor, and the topological direction between the first sensor and the third sensor is that the first sensor points to the third sensor.

[0053] Based on this, if the electronic device determines, according to the detection errors of at least two sensors, that the error accumulation direction between the first and second sensors is the same as the topological direction between the first and second sensors, and the error accumulation direction between the second and third sensors is opposite to the topological direction between the second and third sensors, and the error accumulation direction between the first and third sensors is opposite to the topological direction between the first and third sensors, then the electronic device predicts that the faulty sensor among the three sensors is the second sensor; that is, since the business or production logic ultimately points from the first sensor to the third sensor, it can be considered that the error accumulation direction between the first and third sensors is opposite to the topological direction between the first and third sensors because of the fault of the second sensor, therefore the faulty sensor is the second sensor.

[0054] It should be understood that topology direction refers to the direction of business or production execution.

[0055] like Figure 2 As shown in (b), satisfying the first preset relationship includes: if the error accumulation of the first sensor is positive and the error accumulation of the second sensor is also positive, or the error accumulation of the first sensor is negative and the error accumulation of the second sensor is also negative, then the error accumulation direction of the first sensor and the second sensor is the same as the topological direction of the first sensor and the second sensor; if the error accumulation of the second sensor is positive and the error accumulation of the third sensor is negative, or the error accumulation of the second sensor is negative and the error accumulation of the third sensor is positive, then the error accumulation direction of the second sensor and the third sensor is opposite to the topological direction of the second sensor and the third sensor; if the error accumulation of the first sensor is positive and the error accumulation of the third sensor is negative, or the error accumulation of the first sensor is negative and the error accumulation of the third sensor is positive, then the error accumulation direction of the first sensor and the third sensor is opposite to the topological direction of the first sensor and the third sensor.

[0056] It should be understood that Case 1 and Case 2 correspond to two different business or production logic relationships.

[0057] Scenario 3:

[0058] If an electronic device determines, based on the topological relationship of at least two sensors and the detection error of at least two sensors, that the detection error changes of four of the at least two sensors satisfy a third preset relationship, then the electronic device presets that there is a faulty sensor among the four sensors.

[0059] For example, the three sensors include a first sensor, a second sensor, a third sensor, and a fourth sensor, and the topological relationship of at least two sensors is characterized as follows: the topological direction between the first sensor and the second sensor is that the first sensor points to the second sensor, the topological direction between the second sensor and the third sensor is that the second sensor points to the third sensor, and the topological direction between the second sensor and the fourth sensor is that the second sensor points to the fourth sensor.

[0060] Based on this, if the electronic device determines, according to the detection error of at least two sensors, that the error accumulation direction of the first sensor and the second sensor is the same as the topological direction of the first sensor and the second sensor, the error accumulation direction of the second sensor and the third sensor is opposite to the topological direction of the second sensor and the third sensor, and the error accumulation direction of the first sensor and the third sensor is opposite to the topological direction of the first sensor and the third sensor, then the electronic device predicts that the sensor with a fault among the three sensors is the second sensor.

[0061] like Figure 2 As shown in (c), satisfying the third preset relationship includes: if the error accumulation of the first sensor is positive and the error accumulation of the second sensor is also positive, or the error accumulation of the first sensor is negative and the error accumulation of the second sensor is also negative, then the error accumulation direction of the first sensor and the second sensor is the same as the topological direction of the first sensor and the second sensor; if the error accumulation of the second sensor is positive and the error accumulation of the third sensor is negative, or the error accumulation of the second sensor is negative and the error accumulation of the third sensor is positive, then the error accumulation direction of the second sensor and the third sensor is opposite to the topological direction of the second sensor and the third sensor; if the error accumulation of the second sensor is positive and the error accumulation of the fourth sensor is negative, or the error accumulation of the second sensor is negative and the error accumulation of the fourth sensor is positive, then the error accumulation direction of the second sensor and the fourth sensor is opposite to the topological direction of the second sensor and the fourth sensor.

[0062] It should be understood that the principle of case 3 is similar to that of case 2, and can be understood by referring to it.

[0063] In summary, in industrial scenarios, sensors used for production line inspection are set up according to the production line, or in other words, according to the business or production execution logic. In this case, the detection error of the sensors may accumulate with the execution logic of the business or production. Based on this, electronic devices can use AI / ML models to analyze and obtain the topological relationship of at least two sensors, that is, the sequential detection logic relationship of at least two sensors for the business or production. Thus, based on the topological relationship of at least two sensors and the detection error of at least two sensors, that is, based on whether the accumulation of error is normal, the electronic device can predict whether there is a faulty sensor among the at least two sensors. In this way, relatively accurate sensor fault prediction can be achieved.

[0064] The above combination Figure 1 This application provides a detailed description of an AI-based sensor fault prediction method. The following details an AI-based sensor fault prediction apparatus for implementing the AI-based sensor fault prediction method provided in this application.

[0065] Figure 3 This is a schematic diagram of a sensor fault prediction device based on artificial intelligence, provided as another embodiment of the present invention. Figure 3 As shown, the device includes:

[0066] Error acquisition module 310 is used to acquire the detection error of multiple sensors in the nuclear power system;

[0067] The relationship acquisition module 320 is used to analyze the business or production logic relationship between the nuclear power system and the multiple sensors through an AI / ML model, and obtain the topological relationship of the multiple sensors, which are used for the detection of the business or production.

[0068] The fault prediction module 330 is used to predict whether there is a faulty sensor among the multiple sensors based on the topological relationship of the multiple sensors and the detection error of the multiple sensors.

[0069] The AI-based sensor fault prediction device provided in this embodiment of the invention can execute the AI-based sensor fault prediction method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0070] Optionally, the relationship acquisition module is specifically used to: analyze the business or production logic relationship of the business or production information and the information of the multiple sensors through the AI / ML model, and obtain the topological relationship of the at least two sensors output by the AI / ML model. The business or production information includes the information of the equipment involved in executing the business or production, and the information of the multiple sensors is used to indicate that each of the multiple sensors is set in the corresponding device, and the business or production detection type of each of the multiple sensors.

[0071] Optionally, the relationship acquisition module is specifically used to: preprocess the information from the plurality of sensors and the business or production information to determine that at least two of the plurality of sensors are set on the device that participates in executing the business or production and participate in the detection of the business or production, thereby determining that the at least two sensors participate in the detection of the business or production, and the business or production detection type of the at least two sensors indicates that the at least two sensors participate in the detection of the business or production; input the information from the at least two sensors and the business or production information into the AI / ML model to analyze the business or production logical relationship, and obtain the topological relationship of the at least two sensors output by the AI / ML model.

[0072] Optionally, the fault prediction module 330 includes:

[0073] The first fault detection unit is configured to, based on the topological relationship of the at least two sensors and the detection error of the at least two sensors, determine that the detection error changes of three of the at least two sensors satisfy a first preset relationship, and then presuppose that one of the three sensors is faulty.

[0074] Optionally, the three sensors include a first sensor, a second sensor, and a third sensor, and the topological relationship of the at least two sensors is characterized as follows: the topological direction between the first sensor and the second sensor is that the first sensor points to the second sensor, and the topological direction between the second sensor and the third sensor is that the second sensor points to the third sensor;

[0075] Based on this, the first fault detection unit is specifically used to predict that if, according to the detection error of the at least two sensors, the error accumulation direction between the first sensor and the second sensor is the same as the topological direction between the first sensor and the second sensor, and the error accumulation direction between the second sensor and the third sensor is opposite to the topological direction between the second sensor and the third sensor, then the faulty sensor among the three sensors is the second sensor.

[0076] The first preset relationship includes: if the error accumulation of the first sensor is positive and the error accumulation of the second sensor is also positive, or the error accumulation of the first sensor is negative and the error accumulation of the second sensor is also negative, then the error accumulation direction of the first sensor and the second sensor is the same as the topological direction of the first sensor and the second sensor; if the error accumulation of the second sensor is positive and the error accumulation of the third sensor is negative, or the error accumulation of the second sensor is negative and the error accumulation of the third sensor is positive, then the error accumulation direction of the second sensor and the third sensor is opposite to the topological direction of the second sensor and the third sensor.

[0077] Optionally, the fault prediction module 330 includes:

[0078] The second fault detection unit is used to determine, based on the topological relationship of the at least two sensors and the detection error of the at least two sensors, that the detection error changes of three of the at least two sensors satisfy a second preset relationship, and then preset that one of the three sensors is faulty.

[0079] Optionally, the three sensors include a first sensor, a second sensor, and a third sensor, and the topological relationship of the at least two sensors is characterized as follows: the topological direction between the first sensor and the second sensor is that the first sensor points to the second sensor, and the topological direction between the second sensor and the third sensor is that the second sensor points to the third sensor, and the topological direction between the first sensor and the third sensor is that the first sensor points to the third sensor.

[0080] Based on this, the second fault detection unit is specifically used for:

[0081] If, based on the detection error of the at least two sensors, it is determined that the error accumulation direction between the first sensor and the second sensor is the same as the topological direction between the first sensor and the second sensor, the error accumulation direction between the second sensor and the third sensor is opposite to the topological direction between the second sensor and the third sensor, and the error accumulation direction between the first sensor and the third sensor is opposite to the topological direction between the first sensor and the third sensor, then it is predicted that the sensor with a fault among the three sensors is the second sensor.

[0082] The condition of satisfying the second preset relationship includes: if the error accumulation of the first sensor is positive and the error accumulation of the second sensor is also positive, or the error accumulation of the first sensor is negative and the error accumulation of the second sensor is also negative, then the error accumulation direction of the first sensor and the second sensor is the same as the topological direction of the first sensor and the second sensor; if the error accumulation of the second sensor is positive and the error accumulation of the third sensor is negative, or the error accumulation of the second sensor is negative and the error accumulation of the third sensor is positive, then the error accumulation direction of the second sensor and the third sensor is opposite to the topological direction of the second sensor and the third sensor; if the error accumulation of the first sensor is positive and the error accumulation of the third sensor is negative, or the error accumulation of the first sensor is negative and the error accumulation of the third sensor is positive, then the error accumulation direction of the first sensor and the third sensor is opposite to the topological direction of the first sensor and the third sensor.

[0083] Optional, the fault prediction module 330 includes:

[0084] The third fault detection unit is used to determine, based on the topological relationship of the at least two sensors and the detection error of the at least two sensors, that the detection error changes of four of the at least two sensors satisfy a third preset relationship, and then preset that one of the four sensors is faulty.

[0085] Optionally, the three sensors include a first sensor, a second sensor, a third sensor, and a fourth sensor, and the topological relationship of the at least two sensors is characterized as follows: the topological direction between the first sensor and the second sensor is that the first sensor points to the second sensor, the topological direction between the second sensor and the third sensor is that the second sensor points to the third sensor, and the topological direction between the second sensor and the fourth sensor is that the second sensor points to the fourth sensor.

[0086] Based on this, the third fault detection unit is specifically used for:

[0087] If, based on the detection error of the at least two sensors, it is determined that the error accumulation direction between the first sensor and the second sensor is the same as the topological direction between the first sensor and the second sensor, the error accumulation direction between the second sensor and the third sensor is opposite to the topological direction between the second sensor and the third sensor, and the error accumulation direction between the first sensor and the third sensor is opposite to the topological direction between the first sensor and the third sensor, then it is predicted that the sensor with a fault among the three sensors is the second sensor.

[0088] The third preset relationship includes: if the error accumulation of the first sensor is positive error accumulation and the error accumulation of the second sensor is also positive error accumulation, or the error accumulation of the first sensor is negative error accumulation and the error accumulation of the second sensor is also negative error accumulation, then the error accumulation direction of the first sensor and the second sensor is the same as the topological direction of the first sensor and the second sensor.

[0089] If the error accumulation of the second sensor is positive and the error accumulation of the third sensor is negative, or if the error accumulation of the second sensor is negative and the error accumulation of the third sensor is positive, then it means that the error accumulation directions of the second sensor and the third sensor are opposite to the topological directions of the second sensor and the third sensor.

[0090] If the error accumulation of the second sensor is positive and the error accumulation of the fourth sensor is negative, or if the error accumulation of the second sensor is negative and the error accumulation of the fourth sensor is positive, then it means that the error accumulation directions of the second sensor and the fourth sensor are opposite to their topological directions.

[0091] The AI-based sensor fault prediction device described in further detail can also execute the AI-based sensor fault prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0092] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Exemplarily, the electronic device may be a terminal device, or a chip (system) or other component or assembly that can be disposed in the terminal device. Figure 4As shown, the electronic device 400 may include a processor 401. Optionally, the electronic device 400 may also include a memory 402 and / or a transceiver 403. The processor 401 is coupled to the memory 402 and the transceiver 403, for example, they can be connected via a communication bus. Alternatively, the electronic device 400 may also be a chip, such as including the processor 401; in this case, the transceiver may be the chip's input / output interface.

[0093] The following is combined Figure 4 The various components of electronic device 400 are described in detail below:

[0094] The processor 401 is the control center of the electronic device 400. It can be a single processor or a collective term for multiple processing elements. For example, the processor 401 can be one or more central processing units (CPUs), application-specific integrated circuits (ASICs), or one or more integrated circuits configured to implement the embodiments of this application, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0095] Optionally, the processor 401 can perform various functions of the electronic device 400 by running or executing software programs stored in the memory 402 and calling data stored in the memory 402, such as performing the aforementioned functions. Figure 1 The method shown is an AI-based sensor fault prediction method.

[0096] In a specific implementation, as one example, processor 401 may include one or more CPUs, for example... Figure 4 CPU0 and CPU1 are shown in the diagram.

[0097] In a specific implementation, as one example, the electronic device 400 may also include multiple processors. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). Here, a processor may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer programs or instructions).

[0098] The memory 402 is used to store the software program that executes the solution of this application, and is controlled by the processor 401 to execute it. The specific implementation method can be referred to the above method embodiment, and will not be repeated here.

[0099] Optionally, the memory 402 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory 402 may be integrated with the processor 401 or may exist independently and be accessible through the interface circuit of the electronic device 400. Figure 4 (Not shown in the image) is coupled to processor 401, and this embodiment of the application does not specifically limit this.

[0100] Transceiver 403 is used for communication with other electronic devices. For example, if electronic device 400 is a terminal device, transceiver 403 can be used to communicate with a network device or with another terminal device. As another example, if electronic device 400 is a network device, transceiver 403 can be used to communicate with a terminal device or with another network device.

[0101] Alternatively, transceiver 403 may include a receiver and a transmitter. Figure 4 (Not shown separately). The receiver is used to implement the receiving function, and the transmitter is used to implement the sending function.

[0102] Alternatively, the transceiver 403 can be integrated with the processor 401, or it can exist independently and be connected via the interface circuit of the electronic device 400. Figure 4 (Not shown in the image) is coupled to processor 401, and this embodiment of the application does not specifically limit this.

[0103] Understandable Figure 4 The structure of the electronic device 400 shown does not constitute a limitation on the electronic device. Actual electronic devices may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0104] Furthermore, the technical effects of the electronic device 400 can be referred to the technical effects of the methods described in the above method embodiments, and will not be repeated here.

[0105] It should be understood that the processor in the embodiments of this application can be a central processing unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0106] It should also be understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0107] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0108] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0109] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0110] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0111] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0112] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0113] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0114] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0115] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0116] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0117] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for predicting sensor failure based on artificial intelligence, characterized by, The method includes: To obtain the detection error information of multiple sensors within the nuclear power system; The business or production logic relationship between the nuclear power system and the business or production logic relationship between the multiple sensors is analyzed by AI / ML model to obtain the topological relationship of at least two of the multiple sensors. The at least two sensors participate in the detection of the business or production. The topological relationship of the at least two sensors is used to describe the sequential detection logic relationship of the at least two sensors for the business or production. Based on the topological relationship of the at least two sensors and the detection error of the at least two sensors, predict whether there is a faulty sensor among the at least two sensors; wherein, the detection error is obtained by performing error detection on each sensor twice in different time periods, and the error accumulation direction represented by the two error values ​​of each sensor.

2. The method of claim 1, wherein, By analyzing the business or production logic relationships between the nuclear power system and the multiple sensors using AI / ML models, the topological relationships of the multiple sensors are obtained, including: The AI / ML model analyzes the business or production information and the information from the multiple sensors to determine the business or production logic relationship, thereby obtaining the topological relationship of at least two sensors output by the AI / ML model. The business or production information includes information about the equipment involved in executing the business or production, and the information from the multiple sensors is used to indicate that each of the multiple sensors is set in a corresponding device, as well as the business or production detection type of each of the multiple sensors.

3. The method of claim 2, wherein, The AI / ML model analyzes the business or production information and the information from the multiple sensors to determine the business or production logic relationships, resulting in the topological relationships of at least two sensors output by the AI / ML model, including: By preprocessing the information from the plurality of sensors and the business or production information, it is determined that at least two of the plurality of sensors are set on the equipment that participates in the execution of the business or production and participate in the detection of the business or production, thereby determining that the at least two sensors participate in the detection of the business or production, and the business or production detection type of the at least two sensors indicates that the at least two sensors participate in the detection of the business or production. The information from the at least two sensors and the business or production information are input into the AI / ML model to analyze the business or production logic relationship, and the topological relationship of the at least two sensors is obtained from the output of the AI / ML model.

4. The method according to claim 1, characterized in that, Based on the topological relationship of the at least two sensors and the detection error of the at least two sensors, predict whether there is a faulty sensor among the at least two sensors, including: If, based on the topological relationship of the at least two sensors and the detection error of the at least two sensors, it is determined that the detection error changes of three of the at least two sensors satisfy a first preset relationship, then it is predicted that one of the three sensors is faulty.

5. The method according to claim 4, characterized in that, The three sensors include a first sensor, a second sensor, and a third sensor. The topological relationship of the at least two sensors is characterized as follows: the topological direction between the first sensor and the second sensor is that the first sensor points to the second sensor, and the topological direction between the second sensor and the third sensor is that the second sensor points to the third sensor. Based on this, if, according to the topological relationship of the at least two sensors and the detection error of the at least two sensors, it is determined that the detection error changes of three of the at least two sensors satisfy a first preset relationship, then it is predicted that one of the three sensors is faulty, including: If, based on the detection error of the at least two sensors, it is determined that the error accumulation direction between the first sensor and the second sensor is the same as the topological direction between the first sensor and the second sensor, and the error accumulation direction between the second sensor and the third sensor is opposite to the topological direction between the second sensor and the third sensor, then it is predicted that the second sensor is the sensor with a fault among the three sensors. The first preset relationship includes: if the error accumulation of the first sensor is positive and the error accumulation of the second sensor is also positive, or the error accumulation of the first sensor is negative and the error accumulation of the second sensor is also negative, then the error accumulation direction of the first sensor and the second sensor is the same as the topological direction of the first sensor and the second sensor; if the error accumulation of the second sensor is positive and the error accumulation of the third sensor is negative, or the error accumulation of the second sensor is negative and the error accumulation of the third sensor is positive, then the error accumulation direction of the second sensor and the third sensor is opposite to the topological direction of the second sensor and the third sensor.

6. The method according to claim 1, characterized in that, Based on the topological relationship of the at least two sensors and the detection error of the at least two sensors, predict whether there is a faulty sensor among the at least two sensors, including: If, based on the topological relationship of the at least two sensors and the detection error of the at least two sensors, it is determined that the detection error changes of three of the at least two sensors satisfy a second preset relationship, then it is predicted that one of the three sensors is faulty.

7. The method according to claim 6, characterized in that, The three sensors include a first sensor, a second sensor, and a third sensor. The topological relationship of the at least two sensors is characterized as follows: the topological direction between the first sensor and the second sensor is that the first sensor points to the second sensor, and the topological direction between the second sensor and the third sensor is that the second sensor points to the third sensor, and the topological direction between the first sensor and the third sensor is that the first sensor points to the third sensor. Based on this, if, according to the topological relationship of the at least two sensors and the detection error of the at least two sensors, it is determined that the detection error changes of three of the at least two sensors satisfy a second preset relationship, then it is predicted that one of the three sensors is faulty, including: If, based on the detection error of the at least two sensors, it is determined that the error accumulation direction between the first sensor and the second sensor is the same as the topological direction between the first sensor and the second sensor, the error accumulation direction between the second sensor and the third sensor is opposite to the topological direction between the second sensor and the third sensor, and the error accumulation direction between the first sensor and the third sensor is opposite to the topological direction between the first sensor and the third sensor, then it is predicted that the sensor with a fault among the three sensors is the second sensor. The condition of satisfying the second preset relationship includes: if the error accumulation of the first sensor is positive and the error accumulation of the second sensor is also positive, or the error accumulation of the first sensor is negative and the error accumulation of the second sensor is also negative, then the error accumulation direction of the first sensor and the second sensor is the same as the topological direction of the first sensor and the second sensor; if the error accumulation of the second sensor is positive and the error accumulation of the third sensor is negative, or the error accumulation of the second sensor is negative and the error accumulation of the third sensor is positive, then the error accumulation direction of the second sensor and the third sensor is opposite to the topological direction of the second sensor and the third sensor; if the error accumulation of the first sensor is positive and the error accumulation of the third sensor is negative, or the error accumulation of the first sensor is negative and the error accumulation of the third sensor is positive, then the error accumulation direction of the first sensor and the third sensor is opposite to the topological direction of the first sensor and the third sensor.

8. The method according to claim 1, characterized in that, Based on the topological relationship of the at least two sensors and the detection error of the at least two sensors, predict whether there is a faulty sensor among the at least two sensors, including: If, based on the topological relationship of the at least two sensors and the detection error of the at least two sensors, it is determined that the detection error changes of four of the at least two sensors satisfy a third preset relationship, then it is predicted that one of the four sensors is faulty.

9. The method according to claim 8, characterized in that, The three sensors include a first sensor, a second sensor, a third sensor, and a fourth sensor. The topological relationship of the at least two sensors is characterized as follows: the topological direction between the first sensor and the second sensor is that the first sensor points to the second sensor; the topological direction between the second sensor and the third sensor is that the second sensor points to the third sensor; and the topological direction between the second sensor and the fourth sensor is that the second sensor points to the fourth sensor. Based on this, if, according to the topological relationship of the at least two sensors and the detection error of the at least two sensors, it is determined that the detection error changes of four of the at least two sensors satisfy a third preset relationship, then it is predicted that one of the four sensors is faulty, including: If, based on the detection error of the at least two sensors, it is determined that the error accumulation direction between the first sensor and the second sensor is the same as the topological direction between the first sensor and the second sensor, the error accumulation direction between the second sensor and the third sensor is opposite to the topological direction between the second sensor and the third sensor, and the error accumulation direction between the first sensor and the third sensor is opposite to the topological direction between the first sensor and the third sensor, then it is predicted that the sensor with a fault among the three sensors is the second sensor. The third preset relationship includes: if the error accumulation of the first sensor is positive error accumulation and the error accumulation of the second sensor is also positive error accumulation, or the error accumulation of the first sensor is negative error accumulation and the error accumulation of the second sensor is also negative error accumulation, then the error accumulation direction of the first sensor and the second sensor is the same as the topological direction of the first sensor and the second sensor. If the error accumulation of the second sensor is positive and the error accumulation of the third sensor is negative, or if the error accumulation of the second sensor is negative and the error accumulation of the third sensor is positive, then it means that the error accumulation directions of the second sensor and the third sensor are opposite to the topological directions of the second sensor and the third sensor. If the error accumulation of the second sensor is positive and the error accumulation of the fourth sensor is negative, or if the error accumulation of the second sensor is negative and the error accumulation of the fourth sensor is positive, then it means that the error accumulation directions of the second sensor and the fourth sensor are opposite to their topological directions.

10. A sensor fault prediction device based on artificial intelligence, characterized in that, The device includes: The error acquisition module is used to acquire the detection error information of multiple sensors in the nuclear power system. The relationship acquisition module is used to analyze the logical relationship between the business or production of the nuclear power system and the business or production of the multiple sensors through an AI / ML model, and to obtain the topological relationship of the multiple sensors, which are used for the detection of the business or production. The fault prediction module is used to predict whether there is a faulty sensor among the multiple sensors based on the topological relationship of the multiple sensors and the detection error of the multiple sensors; wherein, the detection error is obtained by performing two error detections on each sensor at different time periods, and the error accumulation direction represented by the two error values ​​of each sensor.

Images