A self-diagnosis method, device and electronic equipment for dual redundant pressure sensor

Abstract

The present disclosure provides a self-diagnosis method, device and electronic device for a dual redundant pressure sensor, which determines the stability criterion of the pressure sensor according to the data curve collected by the pressure sensor and the corresponding standard input data set; determines the data confidence criterion and data weight of the pressure sensor according to the data curve; determines the sensitivity weight, temperature weight and offset weight of the pressure sensor according to the sensitivity parameter, ambient temperature curve and offset error parameter of the pressure sensor; integrates the data weight, sensitivity weight, temperature weight and offset weight into the evidence weight of the pressure sensor; determines the normal or abnormal state of the pressure sensor according to the stability criterion, data confidence criterion and evidence weight corresponding to the two pressure sensors. The weight distribution can be dynamically adjusted by integrating multiple data evaluation indicators to improve the detection accuracy and stability of the pressure sensor system.

Description

Technical Field

[0001] The present disclosure relates to the field of sensor technology, and in particular to a self-diagnosis method, device and electronic equipment for a dual redundant pressure sensor. Background Art

[0002] In the fields of industry, aerospace, automobiles, and intelligent manufacturing, pressure sensors are widely used to monitor and control changes in various physical quantities. The accuracy and reliability of their data directly affect the safety and stability of the system. In order to ensure the normal operation of the system in harsh environments or equipment failures, dual redundant pressure sensor systems have gradually become a common solution. By using two sets of independent sensors for data acquisition, when one sensor fails, the signal provided by another sensor can be relied on, reducing the system risk caused by single point failure.

[0003] The existing dual-redundant pressure sensor system mainly relies on simple numerical comparison or fixed threshold judgment mechanism to evaluate the sensor status, lacking the ability to comprehensively analyze data quality and sensor status. This method often cannot accurately locate the fault point when dealing with complex working conditions, multiple interferences or sensor aging, resulting in false alarms or missed alarms. Summary of the invention

[0004] The embodiments of the present disclosure at least provide a self-diagnosis method, device and electronic device for a dual redundant pressure sensor, which can dynamically adjust the weight distribution by fusing multiple data evaluation indicators to improve the detection accuracy and stability of the pressure sensor system.

[0005] The embodiment of the present disclosure provides a self-diagnosis method of a dual redundant pressure sensor, comprising:

[0006] Determine the stability criterion of the pressure sensor according to the data curve collected by the pressure sensor and the corresponding standard input data set;

[0007] Determining the data confidence criterion and data weight of the pressure sensor according to the data curve;

[0008] According to the sensitivity parameter of the pressure sensor, the ambient temperature curve and the offset error parameter, the sensitivity weight, the temperature weight and the offset weight of the pressure sensor are determined respectively;

[0009] integrating the data weight, the sensitivity weight, the temperature weight, and the offset weight into an evidence weight of a pressure sensor;

[0010] The normal or abnormal state of the pressure sensor is determined according to the stability criterion, the data confidence criterion and the weight of evidence corresponding to the two pressure sensors.

[0011] In an optional implementation, the stability criterion of the pressure sensor is determined based on the data curve collected by the pressure sensor and the corresponding standard input data set, specifically including:

[0012] Acquire the data curve collected by the pressure sensor and the standard input data set corresponding to the pressure sensor;

[0013] Inputting the data curve into a preset convolutional neural network, extracting a data curve feature graph and mapping the data curve features reflected in the data curve features to corresponding classification results;

[0014] The stability criterion is determined according to the data curve characteristics and the standard input data set.

[0015] In an optional implementation, determining the data confidence criterion and data weight of the pressure sensor according to the data curve specifically includes:

[0016] Extracting data statistics from the data curve, wherein the data statistics at least include an average value and a median value of the pressure data in the data curve;

[0017] determining a standard error between pressure data in the data curve and the data statistic;

[0018] According to the preset confidence level, find the corresponding standard score value in the preset normal distribution table;

[0019] Determining a target confidence interval corresponding to the pressure data according to the standard score value and the standard error, and using the target confidence interval as a criterion for the data confidence;

[0020] The corresponding data weight is allocated to the pressure data according to the width of the target confidence interval.

[0021] In an optional implementation, the data weight, the sensitivity weight, the temperature weight, and the offset weight are integrated into the evidence weight of the pressure sensor, specifically including:

[0022] Normalizing the data weight, the sensitivity weight, the temperature weight, and the offset weight respectively, and determining corresponding credibility functions and likelihood functions;

[0023] Determining the degree of conflict among the data weight, the sensitivity weight, the temperature weight, and the offset weight according to the belief function and the likelihood function;

[0024] The Dempster synthesis rule is adopted to fuse the data weight, the sensitivity weight, the temperature weight and the offset weight as evidence sources to determine the evidence weight.

[0025] In an optional implementation manner, the stability criterion is used to evaluate the stability index of the pressure sensor;

[0026] The data confidence criterion is used to evaluate the credibility level of the pressure sensor data;

[0027] The weight of evidence is used to describe the credibility assessment of the pressure sensor under the influence of sensitivity, ambient temperature and offset.

[0028] In an optional implementation, determining the normal or abnormal state of the pressure sensor according to the stability criterion, the data confidence criterion and the weight of evidence corresponding to the two pressure sensors specifically includes:

[0029] Respectively obtaining the stability criterion, the data confidence criterion and the evidence weight corresponding to the two pressure sensors;

[0030] Determining hardware stability states corresponding to the two pressure sensors according to the stability criterion and the weight of evidence;

[0031] Determining the data confidence states corresponding to the two pressure sensors according to the data confidence criterion and the evidence weight;

[0032] A normal or abnormal state of the pressure sensor is determined according to the hardware stability state and the data confidence state.

[0033] In an optional implementation, determining the normal or abnormal state of the pressure sensor according to the hardware stability state and the data confidence state specifically includes:

[0034] If the hardware stability states corresponding to the two pressure sensors are both normal, it is determined that the hardware state of the pressure sensor is normal;

[0035] If at least one of the hardware stability states corresponding to the two pressure sensors is in an abnormal state, it is determined that the hardware state of the pressure sensor is abnormal;

[0036] When the hardware status of the pressure sensor is normal, if the difference between the data confidence states corresponding to the two pressure sensors is greater than a preset difference threshold, it is determined that the pressure sensor is in a data abnormal state.

[0037] The embodiment of the present disclosure also provides a self-diagnosis device for a dual redundant pressure sensor, comprising:

[0038] A stability criterion determination module, used to determine the stability criterion of the pressure sensor according to the data curve collected by the pressure sensor and the corresponding standard input data set;

[0039] A confidence criterion module, used to determine the data confidence criterion and data weight of the pressure sensor according to the data curve;

[0040] An evidence source acquisition module, used to determine the sensitivity weight, temperature weight and offset weight of the pressure sensor according to the sensitivity parameter of the pressure sensor, the ambient temperature curve and the offset error parameter;

[0041] an evidence integration module, configured to integrate the data weight, the sensitivity weight, the temperature weight, and the offset weight into an evidence weight of a pressure sensor;

[0042] The diagnosis module is used to determine the normal or abnormal state of the pressure sensor according to the stability criterion, the data confidence criterion and the evidence weight corresponding to the two pressure sensors.

[0043] An embodiment of the present disclosure also provides an electronic device, including: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the self-diagnosis method of the dual redundant pressure sensor or the steps in any possible implementation of the self-diagnosis method of the dual redundant pressure sensor are executed.

[0044] The present disclosure also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the computer program executes the self-diagnosis method of the dual redundant pressure sensor or the steps of any possible implementation of the self-diagnosis method of the dual redundant pressure sensor.

[0045] The present disclosure also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the self-diagnosis method of the dual redundant pressure sensor or the steps of any possible implementation of the self-diagnosis method of the dual redundant pressure sensor.

[0046] The self-diagnosis method, device and electronic device of a dual redundant pressure sensor provided by the embodiment of the present disclosure determine the stability criterion of the pressure sensor according to the data curve collected by the pressure sensor and the corresponding standard input data set; determine the data confidence criterion and data weight of the pressure sensor according to the data curve; determine the sensitivity weight, temperature weight and offset weight of the pressure sensor according to the sensitivity parameter, ambient temperature curve and offset error parameter of the pressure sensor; integrate the data weight, the sensitivity weight, the temperature weight and the offset weight into the evidence weight of the pressure sensor; determine the normal or abnormal state of the pressure sensor according to the stability criterion, the data confidence criterion and the evidence weight corresponding to the two pressure sensors. The weight distribution can be dynamically adjusted by integrating multiple data evaluation indicators to improve the detection accuracy and stability of the pressure sensor system.

[0047] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following is a brief introduction to the drawings required for use in the embodiments. The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used together with the specification to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can also be obtained based on these drawings without creative work.

[0049] Figure 1 A flow chart of a self-diagnosis method of a dual redundant pressure sensor provided by an embodiment of the present disclosure is shown;

[0050] Figure 2 A schematic diagram of the structure of a pressure sensor data confidence evaluation module provided by an embodiment of the present disclosure is shown;

[0051] Figure 3 A schematic diagram of the structure of a pressure sensor sensitivity confidence evaluation module provided by an embodiment of the present disclosure is shown;

[0052] Figure 4 A schematic diagram of the structure of a pressure sensor temperature confidence evaluation module provided by an embodiment of the present disclosure is shown;

[0053] Figure 5 A schematic diagram of the structure of an offset confidence evaluation module provided by an embodiment of the present disclosure is shown;

[0054] Figure 6 A schematic diagram of the structure of a judgment weight integration module provided by an embodiment of the present disclosure is shown;

[0055] Figure 7 A schematic diagram of the structure of a dual redundant self-diagnosis decision tree provided by an embodiment of the present disclosure is shown;

[0056] Figure 8 A schematic diagram of a self-diagnosis device for a dual redundant pressure sensor provided by an embodiment of the present disclosure is shown;

[0057] Fig. 9 A schematic diagram of an electronic device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical scheme and advantages of the embodiments of the present disclosure clearer, the technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The components of the embodiments of the present disclosure generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the present disclosure for protection, but merely represents the selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present disclosure.

[0059] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0060] The term "and / or" herein only describes an association relationship, indicating that three relationships may exist. For example, A and / or B may represent the following three situations: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C may represent including any one or more elements selected from the set consisting of A, B, and C.

[0061] Research has found that the existing dual-redundant pressure sensor system mainly relies on simple numerical comparison or fixed threshold judgment mechanism to evaluate the sensor status, lacking the ability to comprehensively analyze data quality and sensor status. This approach often fails to accurately locate the fault point when dealing with complex working conditions, multiple interferences or sensor aging, resulting in false alarms or missed alarms.

[0062] Based on the above research, the present disclosure provides a self-diagnosis method, device and electronic device for a dual redundant pressure sensor, which determines the stability criterion of the pressure sensor according to the data curve collected by the pressure sensor and the corresponding standard input data set; determines the data confidence criterion and data weight of the pressure sensor according to the data curve; determines the sensitivity weight, temperature weight and offset weight of the pressure sensor according to the sensitivity parameter, ambient temperature curve and offset error parameter of the pressure sensor; integrates the data weight, the sensitivity weight, the temperature weight and the offset weight into the evidence weight of the pressure sensor; determines the normal or abnormal state of the pressure sensor according to the stability criterion, the data confidence criterion and the evidence weight corresponding to the two pressure sensors. The weight distribution can be dynamically adjusted by integrating multiple data evaluation indicators to improve the detection accuracy and stability of the pressure sensor system.

[0063] To facilitate understanding of this embodiment, a self-diagnosis method for a dual redundant pressure sensor disclosed in an embodiment of the present disclosure is first introduced in detail. The execution subject of the self-diagnosis method for a dual redundant pressure sensor provided in an embodiment of the present disclosure is generally a computer device with a certain computing capability, and the computer device includes, for example: a terminal device or a server or other processing device, and the terminal device may be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the self-diagnosis method for the dual redundant pressure sensor may be implemented by a processor calling a computer-readable instruction stored in a memory.

[0064] See also Figure 1 FIG. 1 is a flowchart of a self-diagnosis method for a dual redundant pressure sensor provided by an embodiment of the present disclosure, the method comprising steps S101 to S105, wherein:

[0065] S101 . Determine a stability criterion of the pressure sensor according to a data curve collected by the pressure sensor and a corresponding standard input data set.

[0066] In the specific implementation, the real-time data curve collected by the pressure sensor and a standard input data set (which contains pressure signal data under ideal conditions) are input into a preset pressure sensor stability evaluation module based on a convolutional neural network (CNN) and a data curve, which is used to analyze the data curve of the pressure sensor and evaluate its stability.

[0067] Specifically, the stability criterion of the pressure sensor is determined by following steps 1 to 3:

[0068] Step 1: Acquire the data curve collected by the pressure sensor and the standard input data set corresponding to the pressure sensor;

[0069] Step 2: input the data curve into a preset convolutional neural network, extract the data curve feature graph, and map the data curve features reflected in the data curve features to the corresponding classification results;

[0070] Step 3: Determine the stability criterion according to the data curve characteristics and the standard input data set.

[0071] In the specific implementation, before the raw data curve collected by the pressure sensor is input into the CNN model, it needs to be preprocessed, including normalization processing and adjustment of the data format, to ensure the consistency of the data and the training efficiency of the model.

[0072] Here, in CNN, the convolution layer extracts features from the input pressure data. The convolution operation can identify local features in the data, such as peak values, rate of change, etc. These features help determine the stability of the pressure signal. The convolution layer usually uses multiple convolution kernels (filters) that extract different feature information by scanning the data curve.

[0073] Furthermore, the pooling layer is used to reduce the dimension of the feature map while retaining the key features. Generally, the maximum pooling or average pooling operation is used to reduce the amount of data and speed up the calculation. The feature map output by the pooling layer will contain simplified feature information, which is convenient for subsequent classification operations.

[0074] Here, the feature map output by the pooling layer is passed to the fully connected layer, which is used to integrate the features and map them to specific classification results. In this process, the model generates a stability criterion for the pressure sensor based on the information in the feature map to determine whether the signal is stable or has abnormal fluctuations.

[0075] Optionally, the pressure sensor stability evaluation module based on the convolutional neural network and the data curve can also classify the input signal through the CNN model and judge the modulation result of the signal to ensure that the identified pressure signal is real and valid, rather than fluctuation caused by noise or error.

[0076] In this way, the accuracy and reliability of the signal can be improved, thereby further enhancing the stability evaluation effect of the pressure sensor.

[0077] Furthermore, in order to ensure that the CNN model can accurately evaluate the stability of the pressure sensor, it needs to be fully trained. The training dataset is generated by the generator function to ensure that all signals have the same length and structure.

[0078] The signals in the dataset contain various pressure values ​​and possible anomalies so that the model can learn and identify different types of signal features.

[0079] Here, in signal processing, measuring the horizontal distance between signal features (such as peaks) and the true pressure value can help identify abnormal fluctuations in the pressure sensor data curve and use them for subsequent stability criterion evaluation.

[0080] S102: Determine a data confidence criterion and a data weight of the pressure sensor according to the data curve.

[0081] In a specific implementation, the data curve collected by the pressure sensor is input into a preset pressure sensor data confidence evaluation module, and the pressure sensor data confidence evaluation module outputs the data confidence criterion and data weight of the pressure sensor.

[0082] Here, the model structure of the pressure sensor data confidence evaluation module can be found in Figure 2 As shown in FIG. 1 , a schematic diagram of the structure of a pressure sensor data confidence evaluation module provided by an embodiment of the present disclosure is shown. Figure 2 As shown in , the pressure sensor data confidence evaluation module is provided with a minimum value calculation unit, an integration and filtering unit, a three-dimensional data processing unit, a search unit, a data comparison unit, an integration unit and a nonlinear transformation unit.

[0083] Among them, the minimum value calculation unit is used to select the minimum value from the input signal. The integration and filtering unit smoothes the signal to make the fluctuations on the data curve more stable. This module can eliminate high-frequency noise in the signal, so as to better capture the long-term trend in the data. The three-dimensional data processing unit is used to process the input data and organize it into a three-dimensional data structure for subsequent analysis, which helps to more comprehensively evaluate the overall trend and characteristics of the pressure sensor data. The search module is used to locate specific values ​​or states in the data curve, such as the location of peaks, valleys or outliers, which can help quickly locate key points in the data. The data comparison unit calculates the absolute difference of the input signals. By comparing the differences between the signals, the degree of deviation of the sensor data can be more accurately evaluated. This comparison helps to identify inconsistencies in the data and provides a basis for the calculation of confidence.

[0084] It should be noted that the identifiers of all the above-mentioned computing units in the figure all adopt the conventional identifiers of the computing units, and those skilled in the art can determine the corresponding identifiers.

[0085] It can be understood by those skilled in the art that Figure 2 The related computing units not mentioned in the above description belong to conventional computing modules, that is, they realize their own conventional computing functions and have no special meaning, so they will not be described in detail here.

[0086] As a possible implementation, the data confidence criterion and data weight of the pressure sensor are determined by following steps 1 to 5:

[0087] Step 1: extracting data statistics from the data curve, wherein the data statistics at least include an average value or a median value of the pressure data in the data curve;

[0088] Step 2: Determine the standard error between the pressure data in the data curve and the data statistic.

[0089] Step 3: According to the preset confidence level, find the corresponding standard score value in the preset normal distribution table.

[0090] Step 4: Determine a target confidence interval corresponding to the pressure data according to the standard score value and the standard error, and use the target confidence interval as the data confidence criterion.

[0091] Step 5: assigning the corresponding data weight to the pressure data according to the width of the target confidence interval.

[0092] In the specific implementation, first, after the data curve of the pressure sensor is collected, it will be statistically analyzed for preliminary processing. These data may contain various types of noise and errors, so data cleaning and preprocessing are required.

[0093] Here, after data preprocessing, the system will calculate the mean, median and other appropriate statistics of the data sample. These statistics help describe the central trend and distribution of the data curve and provide a basis for subsequent standard error analysis.

[0094] Among them, the standard error is used to measure the difference between the data sample statistic and the overall parameter. When calculating the standard error, you first need to determine the variance of the sample, and then calculate the standard error based on the variance and sample size. The smaller the standard error, the higher the data confidence, indicating that the data is more reliable.

[0095] Furthermore, according to the required confidence level, the corresponding standard score value (z value) is found from the normal distribution table. The z value represents the degree to which the data point deviates from the mean after standardization. Generally, a larger confidence level corresponds to a larger z value, which is used to judge the probability that the data is within the normal range.

[0096] Here, using the calculated z-value and standard error, the confidence interval of the data can be determined. The confidence interval represents the range within which the data value will fall under a certain probability. After determining the confidence interval, the data weight can be calculated. The data weight is assigned based on the width of the confidence interval and the reliability of the data. The higher the confidence, the greater the weight. In this way, when multi-sensor data is fused, data with larger weights can be given priority, improving the reliability and accuracy of the overall system.

[0097] S103 . Determine the sensitivity weight, temperature weight, and offset weight of the pressure sensor according to the sensitivity parameter of the pressure sensor, the ambient temperature curve, and the offset error parameter.

[0098] In a specific implementation, the sensitivity parameter of the pressure sensor is input into a preset pressure sensor sensitivity confidence judgment module, and the sensitivity weight of the pressure sensor is output; the temperature data curve around the pressure sensor is input into a preset pressure sensor temperature confidence judgment module, and the temperature weight of the pressure sensor is output; the offset error parameter of the pressure sensor is input into an offset confidence judgment module based on the pressure sensor offset error, and the offset weight of the pressure sensor is output.

[0099] Specifically, the model structure of the pressure sensor sensitivity confidence evaluation module can be found in Figure 3 As shown in FIG. 1 , a schematic diagram of the structure of a pressure sensor sensitivity confidence evaluation module provided by an embodiment of the present disclosure is shown. Figure 3 As shown in , the pressure sensor sensitivity confidence evaluation module includes a sensitivity function unit, a data compression unit, a multi-input merging unit and a minimum value calculation unit.

[0100] Here, the sensitivity function unit is used to define the sensitivity function of the pressure sensor. P(u) represents the pressure response characteristics of the sensor, and O(P)=5 is the setting value or threshold condition of the sensitivity, which is used to control and evaluate the response strength of the sensor. The sensitivity function unit quantifies the output response of the sensor under a specific pressure through a formula expression. The data compression unit (Squeeze) is used to compress or simplify the sensitivity data, compressing the multi-dimensional data into one or several key characteristic values, which can remove redundant information and make data processing more efficient. The compressed data can more directly reflect the sensitivity characteristics of the sensor. The multi-input merging unit combines multiple input signals together so that they can be considered together in subsequent processing. The purpose of merging signals is to comprehensively analyze the data of different sensors or measurement points to obtain more accurate and reliable sensitivity evaluation results. The minimum value calculation unit is used to calculate the minimum value in the input signal, which can help screen out the lowest point in the pressure sensor response to evaluate its responsiveness to the minimum pressure change. It helps to determine the lower limit of the sensitivity of the sensor, that is, its response characteristics under a small pressure signal.

[0101] It should be noted that the identifiers of all the above-mentioned computing units in the figure all adopt the conventional identifiers of the computing units, and those skilled in the art can determine the corresponding identifiers.

[0102] It can be understood by those skilled in the art that Figure 3 The related computing units not mentioned in the above description belong to conventional computing modules, that is, they realize their own conventional computing functions and have no special meaning, so they will not be described in detail here.

[0103] Specifically, the model structure of the pressure sensor temperature confidence evaluation module can be found in Figure 4 As shown in FIG. 1 , it is a schematic diagram of the structure of a pressure sensor temperature confidence evaluation module provided by an embodiment of the present disclosure. Figure 4 As shown in , the judgment module of the temperature confidence of the pressure sensor includes an integration unit, a minimum value calculation unit and a nonlinear transformation unit.

[0104] Here, the integration unit is used to integrate the input signal and process the temperature drift compensation of the sensor. Since the temperature drift effect is often accumulated over time, the impact of temperature change on the sensor signal can be estimated through integration, and provide a basis for subsequent compensation processing. The minimum value calculation unit is used to calculate the minimum value of the input signal and selectively filter out the lowest output of the sensor under different temperature conditions, which helps to identify the minimum impact of temperature drift on the sensor output, so as to perform more accurate compensation. The nonlinear transformation unit performs a nonlinear transformation operation, that is, performs a square root inverse processing on the signal, which can smoothly adjust the signal response to make it more linear under temperature changes. Through the processing of the square root inverse, the impact of temperature on the sensor output can be reduced, and the stability and accuracy of the data can be improved.

[0105] It should be noted that the identifiers of all the above-mentioned computing units in the figure all adopt the conventional identifiers of the computing units, and those skilled in the art can determine the corresponding identifiers.

[0106] It can be understood by those skilled in the art that Figure 4 The related computing units not mentioned in the above description belong to conventional computing modules, that is, they realize their own conventional computing functions and have no special meaning, so they will not be described in detail here.

[0107] Specifically, the model structure of the offset confidence evaluation module can be found in Figure 5 , which is a schematic diagram of the structure of an offset confidence evaluation module provided by an embodiment of the present disclosure. The functions corresponding to the components of the offset confidence evaluation module are the same as the functions corresponding to the same components in the above modules, which will not be described in detail.

[0108] It should be noted that the identifiers of all the above-mentioned computing units in the figure all adopt the conventional identifiers of the computing units, and those skilled in the art can determine the corresponding identifiers.

[0109] It can be understood by those skilled in the art that Figure 5 The related computing units not mentioned in the above description belong to conventional computing modules, that is, they realize their own conventional computing functions and have no special meaning, so they will not be described in detail here.

[0110] As a possible implementation, sensitivity is the degree of response of the pressure sensor to changes in the input signal, which is used to measure the proportional relationship between the output signal and the input pressure. When calculating the sensitivity weight, the current sensitivity parameter of the pressure sensor is obtained. If the output and input of the sensor are linearly related, the sensitivity value is a constant; if it is nonlinear, the sensitivity changes with the change of the input amount. The confidence of the sensitivity is calculated using a logarithmic function formula. Based on the calculated sensitivity confidence value, the sensitivity confidence is converted into a sensitivity weight using normalization processing. The higher the confidence, the larger the sensitivity weight, which means that the sensor's response under different input conditions is more stable.

[0111] As another possible implementation, temperature changes have a significant impact on the pressure sensor, and temperature drift may cause errors in the measurement results. The temperature weight can be calculated by the following steps: Record the temperature change curve in the working environment of the pressure sensor and obtain temperature data. Evaluate the impact of temperature changes on sensor performance, that is, the temperature drift effect. Calculate the temperature drift confidence to measure the degree of influence of temperature changes on measurement accuracy. According to the temperature drift confidence, the confidence value is normalized and converted into a temperature weight. The higher the confidence, the larger the temperature weight, which means that the performance of the sensor is more stable under temperature fluctuations.

[0112] As another possible implementation, the offset error refers to the output deviation of the sensor in the zero state, which affects the measurement accuracy of the sensor. The steps for calculating the offset weight are as follows: record the offset error of the sensor under different conditions and generate an offset data curve. According to the size of the offset error, use statistical analysis methods (such as standard error) to calculate the confidence of the offset. Smaller offset errors correspond to higher confidence. Normalize the offset confidence to obtain the offset weight. The higher the confidence, the larger the offset weight, which means that the smaller the zero offset of the sensor is, the more reliable the measurement result is.

[0113] Furthermore, after determining the sensitivity weight, temperature weight, and offset weight, all weight values ​​are adjusted to the same scale range through normalization processing so that their sum is 1. This ensures that in the comprehensive evaluation of multiple factors, each weight can reasonably reflect its importance in the performance evaluation of the pressure sensor.

[0114] Among them, in the final weight output, sensitivity weight: reflects the response ability of the pressure sensor to input changes. Temperature weight: reflects the stability of the pressure sensor under different temperature conditions. Offset weight: reflects the accuracy of the sensor in the zero state.

[0115] In this way, through this multi-dimensional weight calculation method, the overall performance of the pressure sensor can be comprehensively evaluated, and then more accurate data fusion and decision-making can be performed in the system.

[0116] S104, integrating the data weight, the sensitivity weight, the temperature weight, and the offset weight into the evidence weight of the pressure sensor.

[0117] In a specific implementation, the data weight, sensitivity weight, temperature weight and offset weight are input into a preset judgment weight integration module, and the judgment weight integration module outputs the evidence weight of a single pressure sensor.

[0118] Here, the model structure of the pressure sensor temperature confidence evaluation module can be found in Figure 6 As shown, it is a schematic diagram of the structure of a judgment weight integration module provided by an embodiment of the present disclosure. The functions corresponding to the components are the same as the functions corresponding to the same components in the above modules, which will not be described in detail. It should be noted that the identification of all the above-mentioned computing units in the figure adopts the conventional identification of the computing unit, and those skilled in the art can determine the corresponding.

[0119] It can be understood by those skilled in the art that Figure 6 The related computing units not mentioned in the above description belong to conventional computing modules, that is, they realize their own conventional computing functions and have no special meaning, so they will not be described in detail here.

[0120] Specifically, the weight of evidence can be determined through the following steps 1-3:

[0121] Step 1: Normalize the data weight, the sensitivity weight, the temperature weight, and the offset weight respectively, and determine the corresponding credibility function and likelihood function.

[0122] Step 2: Determine the degree of conflict among the data weight, the sensitivity weight, the temperature weight, and the offset weight according to the credibility function and the likelihood function.

[0123] Step 3: Adopt the Dempster synthesis rule, fuse the data weight, the sensitivity weight, the temperature weight and the offset weight as evidence sources, and determine the evidence weight.

[0124] In the specific implementation, data weight, sensitivity weight, temperature weight and offset weight are used as evidence sources, and these weights are initialized as independent evaluation values ​​of sensor data reliability by each module. The support of each piece of evidence is described by belief function and likelihood function.

[0125] Here, the credibility function represents the minimum credibility of evidence supporting a hypothesis, which is the cumulative probability of all evidence supporting the hypothesis. The likelihood function represents the maximum credibility of evidence that does not negate a hypothesis, and includes all possible evidence supporting the hypothesis. The purpose of these function calculations is to determine the degree of mutual support and conflict between different weights.

[0126] Furthermore, the Dempster synthesis rule is used to integrate the weights from different modules. For the weights from different sources, the degree of conflict between them, that is, the conflict degree of evidence, is calculated. If the conflict degree between two sources of evidence is large, it means that there are large differences in their judgments on the same situation. Through the synthesis rule, each source of evidence is integrated to calculate the comprehensive support of each hypothesis.

[0127] Here, during the synthesis process, the conflicting information is normalized to ensure that the sum of all evidence weights is 1, which can avoid the invalidation of evidence due to conflicts.

[0128] Furthermore, after completing Dempster synthesis, the pressure sensor temperature confidence evaluation module obtains a comprehensive evidence weight, which represents the credibility assessment of the pressure sensor state after comprehensive judgment by all modules. These weights reflect the consistency judgment of multiple independent modules on sensor performance, and improve the accuracy of the weights through conflict handling and normalization.

[0129] It should be noted that the stability criterion is used to evaluate the stability index of the pressure sensor; the data confidence criterion is used to evaluate the credibility level of the pressure sensor data; the weight of evidence is used to describe the credibility assessment of the pressure sensor under the influence of sensitivity, ambient temperature and offset.

[0130] S105 . Determine the normal or abnormal state of the pressure sensors according to the stability criterion, the data confidence criterion, and the weight of evidence corresponding to the two pressure sensors.

[0131] In the specific implementation, the data curves collected by the two pressure sensors are processed by the pressure sensor data confidence judgment module, the pressure sensor sensitivity confidence judgment module, the pressure sensor temperature confidence judgment module, the offset confidence judgment module and the judgment weight integration module, and then input into the preset dual redundant self-diagnosis decision tree to obtain the pressure sensor status judgment criteria.

[0132] Here, the model structure of the double redundant self-diagnosis decision tree can be seen in Figure 7As shown, it is a schematic diagram of the structure of a dual redundant self-diagnosis decision tree provided by an embodiment of the present disclosure. The functions corresponding to the components are the same as the functions corresponding to the same components in the above modules, which will not be described in detail. It should be noted that the identification of all the above computing units in the figure adopts the conventional identification of the computing unit, and those skilled in the art can determine the corresponding.

[0133] It can be understood by those skilled in the art that Figure 7 The related computing units not mentioned in the above description belong to conventional computing modules, that is, they realize their own conventional computing functions and have no special meaning, so they will not be described in detail here.

[0134] Specifically, respectively obtain the stability criteria, data confidence criteria and evidence weight corresponding to the two pressure sensors; determine the hardware stability status corresponding to the two pressure sensors according to the stability criteria and the evidence weight; determine the data confidence status corresponding to the two pressure sensors according to the data confidence criteria and the evidence weight; determine the normal or abnormal status of the pressure sensor according to the hardware stability status and the data confidence status.

[0135] Here, if the hardware stability states corresponding to the two pressure sensors are both normal, it is determined that the hardware state of the pressure sensor is normal; if at least one of the hardware stability states corresponding to the two pressure sensors is abnormal, it is determined that the hardware state of the pressure sensor is abnormal; when the hardware state of the pressure sensor is normal, if the difference in the data confidence states corresponding to the two pressure sensors is greater than the preset difference threshold, it is determined that the pressure sensor is in a data abnormal state.

[0136] In the specific implementation, the dual-redundant self-diagnosis decision tree judges and classifies the status of the dual-channel sensors according to the input pressure sensor stability criteria, data confidence criteria and evidence weight. If the hardware stability criteria of the two-channel sensors are normal, it means that the sensor hardware is in good condition, and the dual warning system maintains a normally closed signal. If the hardware stability criteria of one or both sensors are abnormal, the hardware abnormality warning signal is triggered, indicating that the sensor needs to be repaired or replaced.

[0137] Furthermore, when the hardware of both sensors is normal but the data curves show a large difference, the sensor data abnormality warning system is activated, prompting the need to check the data. If there is a large difference in the data confidence criteria of the two sensors, the system will reduce or eliminate the erroneous signal input by the abnormal sensor through weight adjustment to improve the accuracy of the overall data.

[0138] Here, when the hardware stability of the dual-channel sensors is normal, the dual-redundant self-diagnosis decision tree integrates and normalizes the weights of the evidence to ensure that the sum of the weights is 1, so as to achieve variable weight fusion of the dual-channel signals and further improve the accuracy of pressure detection. In the case of abnormal sensor data, the signal is adjusted or shielded using dynamically adjusted weights to ensure accurate data detection when one sensor fails.

[0139] Among them, normal state: all sensors and data criteria are normal, the system continues to operate in normal mode, and outputs high-precision pressure values ​​based on multi-module information fusion. Data abnormal state: data confidence is low but the hardware is normal, the system adjusts the weight to shield abnormal data and maintain temporary pressure detection capabilities. Hardware abnormal state: hardware is abnormal but data confidence is normal, the system issues a maintenance warning and monitors data fluctuations to ensure detection capabilities during fault repair. Double abnormal state: both hardware and data are abnormal, the system forces a maintenance warning and requires rapid repair to avoid further affecting the detection accuracy.

[0140] The self-diagnosis method of a dual redundant pressure sensor provided by the embodiment of the present disclosure determines the stability criterion of the pressure sensor according to the data curve collected by the pressure sensor and the corresponding standard input data set; determines the data confidence criterion and data weight of the pressure sensor according to the data curve; determines the sensitivity weight, temperature weight and offset weight of the pressure sensor according to the sensitivity parameter, ambient temperature curve and offset error parameter of the pressure sensor; integrates the data weight, the sensitivity weight, the temperature weight and the offset weight into the evidence weight of the pressure sensor; determines the normal or abnormal state of the pressure sensor according to the stability criterion, the data confidence criterion and the evidence weight corresponding to the two pressure sensors. The weight distribution can be dynamically adjusted by integrating multiple data evaluation indicators to improve the detection accuracy and stability of the pressure sensor system.

[0141] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0142] Based on the same inventive concept, the embodiment of the present disclosure also provides a self-diagnosis device for a dual redundant pressure sensor corresponding to the self-diagnosis method for a dual redundant pressure sensor. Since the principle of solving the problem by the device in the embodiment of the present disclosure is similar to the self-diagnosis method for the dual redundant pressure sensor in the embodiment of the present disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0143] See also Figure 8 , Figure 8 Schematic diagram of a self-diagnosis device for a dual redundant pressure sensor provided by an embodiment of the present disclosure. Figure 8 As shown in , the self-diagnosis device 800 of the dual redundant pressure sensor provided by the embodiment of the present disclosure includes:

[0144] The stability criterion determination module 810 is used to determine the stability criterion of the pressure sensor according to the data curve collected by the pressure sensor and the corresponding standard input data set.

[0145] The confidence criterion module 820 is used to determine the data confidence criterion and data weight of the pressure sensor according to the data curve.

[0146] The evidence source acquisition module 830 is used to determine the sensitivity weight, temperature weight and offset weight of the pressure sensor according to the sensitivity parameter of the pressure sensor, the ambient temperature curve and the offset error parameter.

[0147] The evidence integration module 840 is used to integrate the data weight, the sensitivity weight, the temperature weight and the offset weight into the evidence weight of the pressure sensor.

[0148] The diagnosis module 850 is used to determine the normal or abnormal state of the pressure sensor according to the stability criterion, the data confidence criterion and the evidence weight corresponding to the two pressure sensors.

[0149] For descriptions of the processing flow of each module in the device and the interaction flow between each module, reference may be made to the relevant descriptions in the above method embodiment, which will not be described in detail here.

[0150] The self-diagnosis device of a dual redundant pressure sensor provided by the embodiment of the present disclosure determines the stability criterion of the pressure sensor according to the data curve collected by the pressure sensor and the corresponding standard input data set; determines the data confidence criterion and data weight of the pressure sensor according to the data curve; determines the sensitivity weight, temperature weight and offset weight of the pressure sensor according to the sensitivity parameter, ambient temperature curve and offset error parameter of the pressure sensor; integrates the data weight, the sensitivity weight, the temperature weight and the offset weight into the evidence weight of the pressure sensor; determines the normal or abnormal state of the pressure sensor according to the stability criterion, the data confidence criterion and the evidence weight corresponding to the two pressure sensors. The weight distribution can be dynamically adjusted by integrating multiple data evaluation indicators to improve the detection accuracy and stability of the pressure sensor system.

[0151] Corresponds to Figure 1 The self-diagnosis method of the dual redundant pressure sensor in the present disclosure also provides an electronic device 900, such as Fig. 9 FIG. 1 is a schematic diagram of the structure of an electronic device 900 provided in an embodiment of the present disclosure, including:

[0152] Processor 91, memory 92, and bus 93; memory 92 is used to store execution instructions, including memory 921 and external memory 922; memory 921 here is also called internal memory, which is used to temporarily store the operation data in processor 91 and the data exchanged with external memory 922 such as hard disk. Processor 91 exchanges data with external memory 922 through memory 921. When the electronic device 900 is running, the processor 91 communicates with the memory 92 through bus 93, so that the processor 91 executes Figure 1 Steps of a self-diagnosis method for a dual redundant pressure sensor.

[0153] The embodiment of the present disclosure also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the self-diagnosis method of the dual redundant pressure sensor described in the above method embodiment are executed. The storage medium can be a volatile or non-volatile computer-readable storage medium.

[0154] The embodiments of the present disclosure also provide a computer program product, which includes computer instructions. When the computer instructions are executed by a processor, the steps of the self-diagnosis method of the dual redundant pressure sensor described in the above method embodiment can be executed. For details, please refer to the above method embodiment, which will not be repeated here.

[0155] The computer program product may be implemented in hardware, software or a combination thereof. In one optional embodiment, the computer program product is implemented as a computer storage medium. In another optional embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0156] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0157] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0158] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0159] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0160] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The protection scope of the present disclosure is not limited thereto. Although the present disclosure is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed in the present disclosure, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A self-diagnosis method for a dual redundant pressure sensor, characterized in that: include: Determine the stability criterion of the pressure sensor according to the data curve collected by the pressure sensor and the corresponding standard input data set; Determining the data confidence criterion and data weight of the pressure sensor according to the data curve; According to the sensitivity parameter of the pressure sensor, the ambient temperature curve and the offset error parameter, the sensitivity weight, the temperature weight and the offset weight of the pressure sensor are determined respectively; integrating the data weight, the sensitivity weight, the temperature weight, and the offset weight into an evidence weight of a pressure sensor; The normal or abnormal state of the pressure sensor is determined according to the stability criterion, the data confidence criterion and the weight of evidence corresponding to the two pressure sensors.

2. The method according to claim 1, characterized in that According to the data curve collected by the pressure sensor and the corresponding standard input data set, the stability criterion of the pressure sensor is determined, including: Acquire the data curve collected by the pressure sensor and the standard input data set corresponding to the pressure sensor; Inputting the data curve into a preset convolutional neural network, extracting a data curve feature graph and mapping the data curve features reflected in the data curve features to corresponding classification results; The stability criterion is determined according to the data curve characteristics and the standard input data set.

3. The method according to claim 1, characterized in that According to the data curve, the data confidence criterion and data weight of the pressure sensor are determined, specifically including: Extracting data statistics from the data curve, wherein the data statistics at least include an average value and a median value of the pressure data in the data curve; determining a standard error between pressure data in the data curve and the data statistic; According to the preset confidence level, find the corresponding standard score value in the preset normal distribution table; Determining a target confidence interval corresponding to the pressure data according to the standard score value and the standard error, and using the target confidence interval as a criterion for the data confidence; The corresponding data weight is allocated to the pressure data according to the width of the target confidence interval.

4. The method according to claim 1, characterized in that Integrating the data weight, the sensitivity weight, the temperature weight, and the offset weight into the evidence weight of the pressure sensor specifically includes: Normalizing the data weight, the sensitivity weight, the temperature weight, and the offset weight respectively, and determining corresponding credibility functions and likelihood functions; Determining the degree of conflict among the data weight, the sensitivity weight, the temperature weight, and the offset weight according to the belief function and the likelihood function; The Dempster synthesis rule is adopted to fuse the data weight, the sensitivity weight, the temperature weight and the offset weight as evidence sources to determine the evidence weight.

5. The method according to claim 1, characterized in that: The stability criterion is used to evaluate the stability index of the pressure sensor; The data confidence criterion is used to evaluate the credibility level of the pressure sensor data; The weight of evidence is used to describe the credibility assessment of the pressure sensor under the influence of sensitivity, ambient temperature and offset.

6. The method according to claim 1, characterized in that Determining the normal or abnormal state of the pressure sensor according to the stability criterion, the data confidence criterion and the weight of evidence corresponding to the two pressure sensors specifically includes: Respectively obtaining the stability criterion, the data confidence criterion and the evidence weight corresponding to the two pressure sensors; Determining hardware stability states corresponding to the two pressure sensors according to the stability criterion and the weight of evidence; Determining the data confidence states corresponding to the two pressure sensors according to the data confidence criterion and the evidence weight; A normal or abnormal state of the pressure sensor is determined according to the hardware stability state and the data confidence state.

7. The method according to claim 6, characterized in that Determining a normal or abnormal state of the pressure sensor according to the hardware stability state and the data confidence state specifically includes: If the hardware stability states corresponding to the two pressure sensors are both normal, it is determined that the hardware state of the pressure sensor is normal; If at least one of the hardware stability states corresponding to the two pressure sensors is in an abnormal state, it is determined that the hardware state of the pressure sensor is abnormal; When the hardware status of the pressure sensor is normal, if the difference between the data confidence states corresponding to the two pressure sensors is greater than a preset difference threshold, it is determined that the pressure sensor is in a data abnormal state.

8. A self-diagnostic device for a dual redundant pressure sensor, characterized in that: include: A stability criterion determination module, used to determine the stability criterion of the pressure sensor according to the data curve collected by the pressure sensor and the corresponding standard input data set; A confidence criterion module, used to determine the data confidence criterion and data weight of the pressure sensor according to the data curve; An evidence source acquisition module, used to determine the sensitivity weight, temperature weight and offset weight of the pressure sensor according to the sensitivity parameter of the pressure sensor, the ambient temperature curve and the offset error parameter; an evidence integration module, configured to integrate the data weight, the sensitivity weight, the temperature weight, and the offset weight into an evidence weight of a pressure sensor; The diagnosis module is used to determine the normal or abnormal state of the pressure sensor according to the stability criterion, the data confidence criterion and the evidence weight corresponding to the two pressure sensors.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the self-diagnosis method of the dual redundant pressure sensor as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the self-diagnosis method of the dual redundant pressure sensor according to any one of claims 1 to 7 are executed.

Images