Pressure sensor fault detection method and system and electronic equipment

Abstract

The invention discloses a pressure sensor fault detection method and system and electronic equipment. The method comprises the steps of collecting historical working pressure data of a plurality of pressure sensors; constructing a prediction model based on the historical working pressure data of the plurality of pressure sensors, wherein the output of the prediction model is a predicted pressure value of the to-be-detected pressure sensor; comparing the actual pressure value of the to-be-detected pressure sensor with the corresponding predicted pressure value passing through the prediction model to generate a residual value; each statistical feature is compared with a corresponding threshold value to judge whether the to-be-detected pressure sensor breaks down or not, each statistical feature comprises a moving average value, a moving root-mean-square, a moving variance and moving energy, and each statistical feature is obtained through the residual value. According to the invention, accurate fault detection can be carried out on the pressure sensor, and the accuracy of fault detection of the pressure sensor is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of pressure sensors, and in particular relates to a pressure sensor fault detection method, system and electronic equipment. Background Art

[0002] Among all kinds of sensors, pressure sensors have the advantages of light weight, small size, stability and reliability, high sensitivity, low cost, and easy integration. However, long-term operation of sensors may lead to degradation of sensor performance and increased probability of failure. Therefore, fault detection of pressure sensors is an important guarantee to ensure their stable operation. Summary of the invention

[0003] The purpose of the present invention is to provide a pressure sensor fault detection method, system and electronic equipment to solve the problems existing in the prior art.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions:

[0005] The present invention provides a pressure sensor fault detection method, comprising:

[0006] Collect historical working pressure data of several pressure sensors;

[0007] Building a prediction model based on historical working pressure data of a plurality of pressure sensors, wherein the output of the prediction model is a predicted pressure value of the pressure sensor to be tested;

[0008] Compare the actual pressure value of the pressure sensor to be detected with the corresponding predicted pressure value after the prediction model to generate a residual value;

[0009] Each statistical feature is compared with a corresponding threshold value to determine whether the pressure sensor to be detected is faulty, wherein each statistical feature includes a moving average, a moving root mean square, a moving variance and a moving energy, wherein each statistical feature is obtained by the residual value.

[0010] Optionally, comparing each statistical feature with a corresponding threshold value to determine whether the pressure sensor to be detected is faulty includes:

[0011] Respectively obtain a moving average value, a moving root mean square, a moving variance and a moving energy and corresponding moving average value threshold, moving root mean square threshold, moving variance threshold and moving energy threshold, wherein the moving average value, the moving root mean square, the moving variance and the moving energy are obtained by the residual value;

[0012] When it is detected that any value among the moving average value, the moving root mean square value, the moving variance and the moving energy exceeds the corresponding threshold value, it is determined that the pressure sensor to be detected is faulty.

[0013] Optionally, a prediction model is constructed based on historical operating pressure data of several pressure sensors, including:

[0014] Performing data preprocessing on the collected historical working pressure data of the plurality of pressure sensors, wherein the data preprocessing includes filtering abnormal working pressure data and normalizing the filtered working pressure data;

[0015] The working pressure data after data preprocessing is input into the neural network model for training, and a prediction model is obtained after the training is completed. The input of the prediction model is the working pressure data within a sliding window, and the output of the prediction model is the predicted pressure value of the pressure sensor to be detected at a certain sampling time after the sliding window.

[0016] Optionally, the method further comprises performing a self-test process on the pressure sensor to be detected that is determined to be faulty.

[0017] The self-testing process of the pressure sensor to be detected that is determined to be faulty includes:

[0018] Obtaining the vibration amplitude value of the faulty pressure sensor to be detected;

[0019] Determine whether the vibration amplitude value of the faulty pressure sensor to be detected is greater than a preset vibration amplitude value;

[0020] If it is greater than the preset vibration amplitude value, the prediction model is retrained;

[0021] If it is less than or equal to the preset vibration amplitude value, no processing is performed.

[0022] Optionally, the moving average is obtained according to the following formula:

[0023]

[0024] Where, MAI t represents the moving average at sampling time t, e t-i Represents the residual value at the ti×T sampling time in the sliding window, T represents the unit time, w represents the window width and is a multiple of the unit time T.

[0025] Optionally, the movement energy is obtained according to the following formula:

[0026] The movement energy is obtained according to the following formula:

[0027]

[0028] In the formula, MEI t represents the moving energy at sampling time t, et-i Represents the residual value at the ti×T sampling time in the sliding window, T represents the unit time, w represents the window width and is a multiple of the unit time T.

[0029] Optionally, the moving root mean square is obtained according to the following formula:

[0030]

[0031] In the formula, MRI t represents the moving RMS at sampling time t, e t-i Represents the residual value at the ti×T sampling time in the sliding window, T represents the unit time, w represents the window width and is a multiple of the unit time T.

[0032] Optionally, the moving variance is obtained according to the following formula:

[0033]

[0034] Where, MVI t represents the moving variance at sampling time t, represents the mean value of the residual samples, e t-i Represents the residual value at the ti×T sampling time in the sliding window, T represents the unit time, w represents the window width and is a multiple of the unit time T.

[0035] The present application also provides a pressure sensor fault detection method, which is characterized by comprising:

[0036] An acquisition module, used to acquire historical working pressure data of several pressure sensors;

[0037] A model building module, used to build a prediction model based on historical working pressure data of a plurality of pressure sensors, wherein the output of the prediction model is a predicted pressure value of the pressure sensor to be tested;

[0038] A residual value generating module, used for comparing the actual pressure value of the pressure sensor to be detected with the corresponding predicted pressure value after the prediction model is used to generate a residual value;

[0039] The fault detection module is used to compare each statistical feature with a corresponding threshold value to determine whether the pressure sensor to be detected has a fault, wherein each statistical feature includes a moving average, a moving root mean square, a moving variance and a moving energy, wherein each statistical feature is obtained by the residual value.

[0040] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the steps of the method are implemented when the processor executes the computer program.

[0041] Beneficial effects:

[0042] The present application uses the acquired historical working pressure data of the sensor to construct a prediction module, obtains the predicted value of the pressure sensor to be detected through the prediction model, and finally obtains the residual between the predicted value and the actual value. Based on the residual, various statistical features are calculated, and each statistical feature is compared with the corresponding threshold to determine whether the pressure sensor to be detected is faulty. Through each statistical feature, the change trend, fluctuation degree, change amplitude and energy characteristics of the data can be captured from different angles, thereby improving the accuracy of pressure sensor fault detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The drawings constituting a part of this application are used to provide a further understanding of this application, so that other features, purposes and advantages of this application become more obvious. The schematic embodiment drawings and their descriptions of this application are used to explain this application and do not constitute an improper limitation on this application. In the drawings:

[0044] Figure 1 A flow chart of a pressure sensor fault detection method provided in an embodiment of the present application;

[0045] Figure 2 A schematic diagram of the structure of a pressure sensor fault detection method system provided in an embodiment of the present application;

[0046] Figure 3 A schematic diagram of the physical structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in combination with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the structure of the drawings is only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.

[0048] It should be understood that although the terms first, second, etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another unit. For example, a first unit can be referred to as a second unit, and similarly, a second unit can be referred to as a first unit without departing from the scope of the exemplary embodiments of the present invention.

[0049] It should be understood that the term "and / or" that may appear in this article is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B can represent three situations: A exists alone, B exists alone, and A and B exist at the same time. The term " / and" that may appear in this article describes another type of association object relationship, indicating that two relationships may exist. For example, A / and B can represent two situations: A exists alone, and A and B exist alone. In addition, the character " / " that may appear in this article generally indicates that the previous and next associated objects are in an "or" relationship.

[0050] Embodiment 1:

[0051] like Figure 1 FIG. 1 is a flow chart of a pressure sensor fault detection method according to an embodiment of the present invention, comprising:

[0052] S1. Collect historical working pressure data of several pressure sensors.

[0053] Specifically, a pressure sensor is a device that can sense pressure signals and convert them into usable output electrical signals according to certain rules. This application collects historical working pressure data of several pressure sensors and performs data analysis to build a prediction model.

[0054] S2. Build a prediction model based on the historical working pressure data of several pressure sensors.

[0055] Specifically, data preprocessing is performed on the historical working pressure data of several pressure sensors collected, and the data preprocessing includes filtering abnormal working pressure data and normalizing the filtered working pressure data. The working pressure data after data preprocessing is input into the neural network model for training, and a prediction model is obtained after the training is completed. The input of the prediction model is the working pressure data within a sliding window, and the output of the prediction model is the working pressure data at a certain sampling time after the sliding window.

[0056] S3. Compare the actual pressure value of the pressure sensor to be detected with the corresponding predicted pressure value after the prediction model is used to generate a residual value.

[0057] Specifically, by analyzing the residual value between the output value of the prediction model (the predicted pressure value of the pressure sensor to be detected) and the actual measurement value, it is further determined whether the pressure sensor is faulty.

[0058]

[0059] The pressure value collected by the sensor at time t is . Therefore, the residual between the predicted pressure value and the actual measured value of the pressure sensor to be tested can be obtained through this formula.

[0060] S4. Compare each statistical feature with a corresponding threshold value to determine whether the pressure sensor to be detected is faulty, wherein each statistical feature includes a moving average, a moving root mean square, a moving variance and a moving energy, wherein each statistical feature is obtained by the residual value.

[0061] Specifically, each statistical feature is compared with a corresponding threshold value to determine whether the pressure sensor to be detected is faulty, wherein each statistical feature includes a moving average, a moving root mean square, a moving variance, and a moving energy, wherein each statistical feature is obtained by the residual value. Each statistical feature captures the change trend, fluctuation degree, change amplitude, and energy characteristics of the data from different angles, thereby improving the accuracy of pressure sensor fault detection.

[0062] As an embodiment of the present application, the moving average is obtained according to the following formula:

[0063]

[0064] Where, MAI t represents the moving average at sampling time t, e t-i Represents the residual value at the ti×T sampling time in the sliding window, T represents the unit time, w represents the window width and is a multiple of the unit time T.

[0065] Specifically, the present application introduces a sliding window mechanism to calculate the moving average, calculates the moving average on the window, analyzes the trend change of the sensor residual signal, and helps identify persistent deviations. The moving average fluctuates steadily when the pressure sensor is in a normal state, and changes immediately after a fault occurs.

[0066] As an embodiment of the present application, the movement energy is obtained according to the following formula:

[0067]

[0068] In the formula, MEI t represents the moving energy at sampling time t, e t-i Represents the residual value at the ti×T sampling time in the sliding window, T represents the unit time, w represents the window width and is a multiple of the unit time T.

[0069] Specifically, this application introduces a sliding window mechanism to calculate the movement energy, and calculates the movement energy on the window, MEI t Used to evaluate energy changes in the residual signal to help identify potential faulty behavior. In the event of a pressure sensor failure, the mobile energy will change significantly.

[0070] As an embodiment of the present application, the moving root mean square is obtained according to the following formula:

[0071]

[0072] In the formula, MRI t represents the moving RMS at sampling time t, e t-i Represents the residual value at the ti×T sampling time in the sliding window, T represents the unit time, w represents the window width and is a multiple of the unit time T.

[0073] Specifically, the moving RMS within each iteration window is calculated by sliding the window to quantify the fluctuation of the residual and help identify abnormal fluctuations. t The pressure sensor exhibits smooth fluctuations when in a healthy state, but shows significant changes during a fault.

[0074] As an embodiment of the present application, the moving variance is obtained according to the following formula:

[0075]

[0076] Where, MVI t represents the moving variance at sampling time t, represents the mean value of the residual samples, e t-i Represents the residual value at the ti×T sampling time in the sliding window, T represents the unit time, w represents the window width and is a multiple of the unit time T.

[0077] Specifically, MVI t Can help identify changes in stability. When the sensor is operating normally, MVI t It is manifested as a smooth and continuous small fluctuation. When the sensor fails, MVI t There will be significant changes.

[0078] In order to determine whether the pressure sensor is faulty, in a preferred embodiment of the present solution, each statistical feature is compared with a corresponding threshold value to determine whether the pressure sensor to be detected is faulty, including:

[0079] The moving average, moving root mean square, moving variance and moving energy and the corresponding moving average threshold, moving root mean square threshold, moving variance threshold and moving energy threshold are obtained respectively. When it is detected that any value of the moving average, moving root mean square, moving variance and moving energy exceeds the corresponding threshold, it is determined that the pressure sensor to be detected has a fault, wherein the moving average, the moving root mean square, the moving variance and the moving energy are obtained through the residual value.

[0080] As an embodiment of the present application, the moving average threshold, moving root mean square threshold, moving variance threshold and moving energy threshold are obtained according to the interquartile range method. The interquartile range, as a non-parametric statistical method, relies on the percentiles of the data without presupposing that the data follows a normal distribution or any specific distribution. It effectively identifies abnormal data points that are inconsistent with the overall data pattern by considering the degree of discreteness of the data.

[0081] In order to further confirm whether the determination result of the pressure sensor to be detected that is determined to be faulty is correct, in a preferred embodiment of the present solution, the method further includes performing a self-test process on the pressure sensor to be detected that is determined to be faulty.

[0082] The self-testing process of the pressure sensor to be detected that is determined to be faulty includes:

[0083] Obtaining the vibration amplitude value of the faulty pressure sensor to be detected;

[0084] Determine whether the vibration amplitude value of the faulty pressure sensor to be detected is greater than a preset vibration amplitude value;

[0085] If it is greater than the preset vibration amplitude value, the prediction model is retrained;

[0086] If it is less than or equal to the preset vibration amplitude value, no processing is performed.

[0087] Specifically, for example, the performance parameters of the micro pressure sensor in terms of vibration amplitude mainly include its ability to withstand shock and vibration. Micro pressure sensors usually have a certain ability to resist shock and vibration. The Kulite XCS-IC-093 model micro pressure sensor adopts silicon integration technology and has high sensitivity and high signal-to-noise ratio. Its pressure range is 0.35BAR to 3.5BAR. By obtaining the vibration amplitude value of the faulty pressure sensor to be detected, it is determined whether the vibration amplitude value of the faulty pressure sensor to be detected is greater than the preset vibration amplitude value. If it is greater than the preset vibration amplitude value, it means that the judgment result of the faulty pressure sensor to be detected is incorrect, so the prediction model is retrained. If it is less than or equal to the preset vibration amplitude value, no processing is performed.

[0088] The present application uses the acquired historical working pressure data of the sensor to construct a prediction module, obtains the predicted value of the pressure sensor to be detected through the prediction model, and finally obtains the residual between the predicted value and the actual value. Based on the residual, various statistical features are calculated, and each statistical feature is compared with the corresponding threshold to determine whether the pressure sensor to be detected is faulty. Through each statistical feature, the change trend, fluctuation degree, change amplitude and energy characteristics of the data can be captured from different angles, thereby improving the accuracy of pressure sensor fault detection.

[0089] Embodiment 2:

[0090] With the rapid development of the sports industry, spurs are one of the commonly used auxiliary tools for riders in equestrian sports. In modern equestrian competitions, athletes tend to use excessive force when using spurs, causing discomfort or even pain to the horses. Therefore, a pressure sensor is designed to detect the pressure acting on the horse in real time. Specifically, the pressure sensor uses a thin film pressure sensor, which is installed at the contact point between the spur and the horse to detect the pressure applied by the spur to the horse. Due to long-term use and uncertain external working environment (high temperature, rain, etc.), the pressure sensor is prone to failure. A method that can detect pressure sensor failure is needed to ensure its stable operation, which specifically includes the following steps:

[0091] Step 1, collecting historical working pressure data of a plurality of pressure sensors acting on the horse;

[0092] Step 2: preprocess the collected historical working pressure data of several pressure sensors acting on the horses, the data preprocessing includes filtering abnormal working pressure data and normalizing the filtered working pressure data, inputting the preprocessed working pressure data into the neural network model for training, and obtaining a prediction model after the training is completed. The output of the prediction model is the predicted pressure value of the pressure sensor to be detected.

[0093] Step 3: Compare the actual pressure value of the pressure sensor to be tested with the corresponding predicted pressure value after the prediction model to generate a residual value;

[0094] Step 4: Compare each statistical feature with a corresponding threshold value to determine whether the pressure sensor to be detected is faulty, wherein each statistical feature includes a moving average, a moving root mean square, a moving variance, and a moving energy, wherein each statistical feature is obtained by the residual value. Compare each statistical feature with a corresponding threshold value to determine whether the pressure sensor to be detected is faulty, including: respectively obtaining a moving average, a moving root mean square, a moving variance, and a moving energy, and corresponding moving average thresholds, moving root mean square thresholds, moving variance thresholds, and moving energy thresholds, and when it is detected that any value of the moving average, the moving root mean square, the moving variance, and the moving energy exceeds the corresponding threshold value, it is determined that the pressure sensor to be detected is faulty.

[0095] The present application uses the acquired historical working pressure data of the sensor to construct a prediction module, obtains the predicted value of the pressure sensor to be detected through the prediction model, and finally obtains the residual between the predicted value and the actual value. Based on the residual, various statistical features are calculated, and each statistical feature is compared with the corresponding threshold to determine whether the pressure sensor to be detected is faulty. Through each statistical feature, the change trend, fluctuation degree, change amplitude and energy characteristics of the data can be captured from different angles, thereby improving the accuracy of pressure sensor fault detection.

[0096] Figure 2 A schematic diagram of the structure of a pressure sensor fault detection system provided by the present invention includes:

[0097] The acquisition module 10 is used to acquire historical working pressure data of a plurality of pressure sensors;

[0098] A model building module 20, used to build a prediction model based on historical working pressure data of a plurality of pressure sensors, wherein the output of the prediction model is a predicted pressure value of the pressure sensor to be tested;

[0099] A residual value generating module 30, used for comparing the actual pressure value of the pressure sensor to be detected with the corresponding predicted pressure value after the prediction model is used to generate a residual value;

[0100] The fault detection module 40 is used to compare each statistical feature with a corresponding threshold value to determine whether the pressure sensor to be detected has a fault, wherein each statistical feature includes a moving average, a moving root mean square, a moving variance and a moving energy, wherein each statistical feature is obtained through the residual value.

[0101] Figure 3 A schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention, such as Figure 3 As shown, the electronic device 60 includes: a processor 601 (processor), a memory 602 (memory) and a bus 603;

[0102] The processor 601 and the memory 602 communicate with each other via the bus 603;

[0103] The processor 601 is used to call the program instructions in the memory 602 to execute the methods provided by the above-mentioned method embodiments. The device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative labor.

[0104] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0105] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. 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.

[0106] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A pressure sensor fault detection method, characterized in that: include: Collect historical working pressure data of several pressure sensors; Building a prediction model based on historical working pressure data of a plurality of pressure sensors, wherein the output of the prediction model is a predicted pressure value of the pressure sensor to be tested; Compare the actual pressure value of the pressure sensor to be detected with the corresponding predicted pressure value after the prediction model to generate a residual value; Each statistical feature is compared with a corresponding threshold value to determine whether the pressure sensor to be detected is faulty, wherein each statistical feature includes a moving average, a moving root mean square, a moving variance and a moving energy, wherein each statistical feature is obtained by the residual value.

2. The method according to claim 1, characterized in that Comparing each statistical feature with a corresponding threshold value to determine whether the pressure sensor to be detected is faulty includes: Respectively obtain a moving average value, a moving root mean square, a moving variance and a moving energy and corresponding moving average value threshold, moving root mean square threshold, moving variance threshold and moving energy threshold, wherein the moving average value, the moving root mean square, the moving variance and the moving energy are obtained by the residual value; When it is detected that any value among the moving average value, the moving root mean square value, the moving variance and the moving energy exceeds the corresponding threshold value, it is determined that the pressure sensor to be detected is faulty.

3. The method according to claim 1, characterized in that A prediction model is built based on historical operating pressure data of several pressure sensors, including: Performing data preprocessing on the collected historical working pressure data of the plurality of pressure sensors, wherein the data preprocessing includes filtering abnormal working pressure data and normalizing the filtered working pressure data; The work pressure data after data preprocessing is input into the neural network model for training, and a prediction model is obtained after the training is completed. The input item of the prediction model is the work pressure data within a sliding window, and the output item of the prediction model is the work pressure data at a certain sampling time after the sliding window.

4. The method according to claim 1, characterized in that: The method further includes performing a self-test process on the pressure sensor to be detected that is determined to be faulty. The self-testing process of the pressure sensor to be detected that is determined to be faulty includes: Obtaining the vibration amplitude value of the faulty pressure sensor to be detected; Determine whether the vibration amplitude value of the faulty pressure sensor to be detected is greater than a preset vibration amplitude value; If it is greater than the preset vibration amplitude value, the prediction model is retrained; If it is less than or equal to the preset vibration amplitude value, no processing is performed.

5. The method according to claim 1, characterized in that The moving average is obtained according to the following formula: Where, MAI t represents the moving average at sampling time t, e t-i Represents the residual value at the ti×T sampling time in the sliding window, T represents the unit time, w represents the window width and is a multiple of the unit time T.

6. The method according to claim 1, characterized in that The movement energy is obtained according to the following formula: In the formula, MEI t represents the moving energy at sampling time t, e t-i Represents the residual value at the ti×T sampling time in the sliding window, T represents the unit time, w represents the window width and is a multiple of the unit time T.

7. The method according to claim 1, characterized in that The moving root mean square is obtained according to the following formula: In the formula, MRI t represents the moving RMS at sampling time t, e t-i Represents the residual value at the ti×T sampling time in the sliding window, T represents the unit time, w represents the window width and is a multiple of the unit time T.

8. The method according to claim 1, characterized in that The moving variance is obtained according to the following formula: Where, MVI t represents the moving variance at sampling time t, represents the mean value of the residual samples, e t-i Represents the residual value at the ti×T sampling time in the sliding window, T represents the unit time, w represents the window width and is a multiple of the unit time T.

9. A pressure sensor fault detection system, characterized in that: include: An acquisition module, used to acquire historical working pressure data of several pressure sensors; A model building module, used to build a prediction model based on historical working pressure data of a plurality of pressure sensors, wherein the output of the prediction model is a predicted pressure value of the pressure sensor to be tested; A residual value generating module, used for comparing the actual pressure value of the pressure sensor to be detected with the corresponding predicted pressure value after the prediction model is used to generate a residual value; The fault detection module is used to compare each statistical feature with a corresponding threshold value to determine whether the pressure sensor to be detected has a fault, wherein each statistical feature includes a moving average, a moving root mean square, a moving variance and a moving energy, wherein each statistical feature is obtained through the residual value.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the pressure sensor failure detection method according to any one of claims 1 to 8 are implemented.

Images