Real-time fault detection method for pressure sensors based on dynamic environment adaptation

Abstract

The present invention provides a real-time fault detection method for pressure sensors based on dynamic environmental adaptation, which belongs to the field of sensor fault detection technology. The method establishes a time-domain correlation data set of noise-sensor signals by synchronously collecting environmental noise signals and pressure sensor output signals in real time; performs spectrum analysis on environmental noise signals, dynamically divides frequency bands, and calculates the energy distribution of each frequency band; dynamically generates an operation delay threshold based on the energy distribution and weight factor of each frequency band; calculates the sensor operation status credibility coefficient by combining the time domain characteristics of the pressure sensor output signal with the current noise energy distribution; when an abnormality is detected in the pressure sensor output signal, the abnormality duration is corrected based on the operation status credibility coefficient, and the corrected duration is compared with the dynamic operation delay threshold to determine whether it is a real fault. The present invention can effectively suppress environmental noise interference and improve the accuracy and reliability of pressure sensor fault detection.

Description

Technical Field

[0001] The present invention relates to the technical field of sensor fault detection, and in particular to a real-time fault detection method for a pressure sensor based on dynamic environment adaptation. Background Art

[0002] As core sensing components in industrial automation systems, pressure sensors' measurement accuracy and reliability directly impact the stability and safety of production processes. In complex industrial environments, pressure sensors are constantly exposed to dynamic environmental factors, such as high-frequency noise interference and temperature and humidity fluctuations. These interferences can not only mask the sensor's true output signal but also lead to accumulated measurement errors and even false alarms. Traditional fault detection methods often struggle to distinguish between environmental noise interference and actual sensor failures, posing a significant challenge to the accuracy and timeliness of fault diagnosis.

[0003] The pressure sensor fault detection system disclosed in patent CN116878728B represents a typical current technical solution, which uses a fixed noise threshold to determine environmental interference. Although this system is the first to incorporate environmental noise monitoring into a sensor fault detection system, its core mechanism is a static threshold comparison mechanism: when the noise value collected by the environmental noise detection module exceeds a preset fixed threshold, the sensor is determined to be potentially interfered with. This rigid judgment method is effective under simple working conditions, but it cannot cope with the complex dynamic noise characteristics of industrial sites.

[0004] Because this technology uses a static noise threshold as its sole judgment criterion, the system suffers from fundamental flaws: First, the fixed threshold cannot adapt to the dynamic changes in noise intensity under different operating conditions, inevitably resulting in numerous false positives in scenarios with severe noise fluctuations. Second, relying solely on noise amplitude comparison while ignoring noise spectrum analysis makes it impossible for the system to distinguish the essential differences between high-frequency abnormal noise and normal operating noise. This flaw directly leads to two serious consequences: 1) the system frequently falsely reports faults when ambient noise naturally fluctuates; 2) the system may miss faults when actual sensor faults are accompanied by noise in a specific frequency band. Summary of the Invention

[0005] In order to solve the problems of fault detection lag caused by environmental noise interference and static analysis in the prior art, and the separation of environmental noise and sensor operating status analysis, effectively distinguish the interference of high-frequency abnormal noise and normal operating noise, and improve the timeliness and accuracy of fault detection, the present invention provides a real-time fault detection method for pressure sensors based on dynamic environmental adaptation.

[0006] To this end, the present invention adopts the following technical solutions:

[0007] In one aspect, the present invention discloses a real-time fault detection method for a pressure sensor based on dynamic environment adaptation, comprising the following steps:

[0008] Real-time synchronous acquisition of environmental noise signals and pressure sensor output signals to establish a time-domain correlation dataset of noise-sensor signals;

[0009] Performing spectrum analysis on the environmental noise signal, dynamically dividing the noise spectrum into a low-frequency band, a mid-frequency band, and a high-frequency band, and calculating the energy distribution of each frequency band;

[0010] Dynamically generate the operating delay threshold based on the energy distribution and weight factors of each frequency band, where the energy of the high frequency band has a higher weight on the threshold adjustment than the low frequency band and the mid frequency band;

[0011] Calculating the reliability coefficient of the sensor operation state by combining the time domain characteristics of the pressure sensor output signal with the current noise energy distribution;

[0012] When an abnormality in the output signal of the pressure sensor is detected, the abnormality duration is corrected based on the operating state credibility coefficient, and the corrected duration is compared with the dynamic operating delay threshold to determine whether it is a real fault.

[0013] Furthermore, real-time synchronous acquisition of the environmental noise signal and the pressure sensor output signal includes:

[0014] Use hardware trigger signals to synchronously start data acquisition of noise sensor and pressure sensor;

[0015] The sampling time window length is dynamically adjusted according to the operating frequency of the pressure sensor, and the adjustment range is 10ms-200ms.

[0016] Furthermore, the dynamic division of the noise spectrum includes:

[0017] Obtain the spectrum distribution of the noise signal through fast Fourier transform;

[0018] An adaptive clustering algorithm is used to divide the spectrum into low-frequency band, mid-frequency band and high-frequency band, and the division boundaries are dynamically adjusted according to the characteristics of the environmental noise.

[0019] Furthermore, the low frequency band is 0-500 Hz, the medium frequency band is 500 Hz-2000 Hz, and the high frequency band is above 2000 Hz.

[0020] Furthermore, based on the energy distribution and weight factors of each frequency band, an operating delay threshold is dynamically generated, including:

[0021] Adjust the weight coefficient of each frequency band according to the current working stage of the sensor;

[0022] Generate a dynamic delay threshold based on the following formula : ;in: is the preset benchmark threshold; Activate the threshold for high-frequency energy; is the slope coefficient; is the total noise energy; 、 、 is the ratio of low-frequency, medium-frequency and high-frequency noise energy; 、 、 Represent the dynamic weight coefficients of low frequency band, medium frequency band and high frequency band respectively.

[0023] Furthermore, the dynamic weight coefficient 、 、 satisfy: ;

[0024] Adjust the weight coefficient of each frequency band according to the current working stage of the sensor, including:

[0025] Startup phase: high-frequency weighting Increase by 20%-30%;

[0026] Stable phase: mid-frequency weighting Increased to 1.2 times the baseline value;

[0027] Downtime: Low-frequency weighting Decay exponentially.

[0028] Furthermore, the calculation of the operating status credibility coefficient includes: ; Among them, the time domain credibility factor The calculation formula is: ; Frequency domain credibility factor The calculation formula is: Where, 、 、 is the ratio of low-frequency, medium-frequency and high-frequency noise energy; is the total noise energy; is the abnormality duration, reflecting the time window for fault detection; Represents the current moment, i.e., the time point at which the credibility is calculated; is an integral variable, representing a time point within the sliding time window, ranging from to ; For pressure sensors Detection signal at the moment; 、 is the signal statistic within the sliding time window; 、 is the steepness coefficient of the sigmoid function; 、 is the energy proportion threshold; is the time decay factor, is the credible weight coefficient of the high frequency band.

[0029] Furthermore, correcting the abnormality duration based on the operating state credibility coefficient includes:

[0030] Establish the credibility-time correction mapping function: ;in: is the corrected abnormal duration; The initial abnormal duration; is the baseline credibility threshold; is the modified strength coefficient;

[0031] Obtaining a corrected abnormality duration based on the operating state credibility coefficient;

[0032] The exponential smoothing algorithm is used to optimize the corrected anomaly duration: ;in: is the optimized abnormal duration, is the smoothing factor; The duration of the anomaly after the previous correction.

[0033] On the other hand, the present invention further provides a pressure sensor system, comprising: a pressure sensing unit; an environmental noise monitoring unit; a fault detection module for performing fault detection using the above-mentioned fault detection method; and an alarm output interface.

[0034] Compared with the existing technology, the present invention has the following beneficial effects: The present invention uses dynamic spectrum analysis and adaptive frequency band division technology to monitor the spectrum characteristics of environmental noise in real time and dynamically adjust the detection frequency band boundaries, so as to achieve the technical effect of accurately identifying the noise interference characteristics of different frequency bands; uses noise-sensor signal joint acquisition and time domain correlation analysis technology to establish a dynamic correspondence between noise and sensor signals, so as to achieve the technical effect of eliminating signal acquisition delay errors and improving signal correlation; uses adaptive threshold generation technology based on multi-band energy distribution to dynamically adjust the fault judgment threshold according to the noise spectrum characteristics, so as to achieve the technical effect of maintaining stable detection performance in complex noise environments; uses credibility coefficient calculation and abnormality duration correction technology to comprehensively evaluate time domain signal characteristics and frequency domain noise distribution, so as to achieve the technical effect of accurately distinguishing real faults from environmental interference; uses multi-dimensional signal fusion and secondary verification technology, combined with historical data comparison and comparative analysis of sensors from the same batch, so as to achieve the technical effect of improving the reliability of fault judgment. The systematic application of these technical means enables the pressure sensor fault detection system to adapt to changes in noise interference in complex industrial environments, significantly improving the accuracy and reliability of fault detection, while effectively reducing false alarm and missed alarm rates, providing more stable and reliable sensor monitoring guarantees for industrial automation systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0036] Figure 1 This is a flow chart of a real-time fault detection method for a pressure sensor based on dynamic environment adaptation and multi-dimensional fusion according to the present invention;

[0037] Figure 2 This is a structural block diagram of a pressure sensor system of the present invention. DETAILED DESCRIPTION

[0038] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0039] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0040] like Figure 1 As shown, a real-time fault detection method for a pressure sensor based on dynamic environment adaptation includes the following steps:

[0041] S1: Real-time synchronous acquisition of environmental noise signals and pressure sensor output signals to establish a time-domain correlation dataset of noise-sensor signals;

[0042] Specifically, a hardware trigger signal is used to synchronize data acquisition between the noise and pressure sensors. The system uses a unified hardware trigger signal source, which is connected to the acquisition channels of both the noise and pressure sensors via a splitter. This ensures that the acquisition start times of the two signals are completely synchronized, eliminating correlation analysis errors caused by time deviations.

[0043] The sampling time window length is dynamically adjusted based on the operating frequency of the pressure sensor, within a range of 10ms-200ms. For high-frequency pressure sensors, the system automatically sets a shorter sampling window, such as 10ms-50ms, to capture rapidly changing signal characteristics. For medium-frequency pressure sensors, the sampling window is set to 50ms-100ms; for low-frequency pressure sensors, the sampling window is set to 100ms-200ms to ensure that the entire signal cycle is captured.

[0044] During the acquisition process, the system pairs the noise signal and the pressure sensor output signal according to the timestamp, forming a time-domain correlation dataset of the noise and sensor signals. This dataset contains information such as the amplitude and frequency characteristics of the noise signal, as well as the pressure sensor output value and rate of change at the corresponding moment, providing a data foundation for subsequent analysis.

[0045] S2: Perform spectrum analysis on the ambient noise signal, dynamically divide the noise spectrum into low-frequency band, mid-frequency band and high-frequency band, and calculate the energy distribution of each frequency band;

[0046] Specifically, the system uses a fast Fourier transform (FFT) algorithm to obtain the spectral distribution of the noise signal. The system applies the FFT algorithm to the collected ambient noise signal, converting the time-domain signal into a frequency-domain representation, thereby determining the energy distribution of the noise signal at different frequencies. To improve the accuracy of the spectral analysis, the system preprocesses the original signal using a Hanning window function to reduce spectral leakage.

[0047] An adaptive clustering algorithm is used to divide the spectrum into low, mid, and high frequency bands, with the boundaries dynamically adjusted based on the ambient noise characteristics. The system first calculates the energy distribution curve of the noise spectrum. Then, using the K-means clustering algorithm, it automatically identifies the main areas of energy concentration and determines the frequency band boundaries based on the energy density variation. Under standard operating conditions, the low frequency band is 0-500Hz, the mid frequency band is 500Hz-2000Hz, and the high frequency band is above 2000Hz. However, under special environmental conditions, the system dynamically adjusts these boundaries based on the actual noise characteristics.

[0048] The system calculates the energy distribution of each frequency band, including the total energy value, energy percentage, peak frequency, and amplitude of each frequency band. For low frequencies, the system focuses on the energy distribution in the 0-100Hz range, which is often associated with mechanical vibration. For mid-frequency bands, the system analyzes energy changes in the 500Hz-1000Hz range, which often reflect the operating status of machinery in the environment. For high frequencies, the system monitors energy fluctuations in the 2000Hz-5000Hz range, which may indicate electrical interference or other high-frequency noise sources.

[0049] S3: Dynamically generates an operating delay threshold based on the energy distribution and weight factors of each frequency band, where the energy of the high frequency band has a higher weight on the threshold adjustment than the low frequency band and the mid frequency band;

[0050] Specifically, the weight coefficients of each frequency band are adjusted according to the current working stage of the sensor. The system identifies the working stage of the pressure sensor, including the startup stage, the stable stage and the shutdown stage, and sets different frequency band weight coefficients for different stages.

[0051] Dynamic weight coefficients for low, mid, and high frequency bands 、 、 satisfy: ; Under standard operating conditions, the baseline weight is set to =0.2, =0.3, =0.5, which reflects the importance of high-frequency noise to sensor interference.

[0052] In the startup phase, high frequency weights Increase by 20%-30%, that is, from the base value of 0.5 to 0.6-0.65, and reduce the low frequency and medium frequency weights accordingly to adapt to the high frequency electrical interference that may occur during the startup process. Increase to 1.2 times of the baseline value, that is, from 0.3 to 0.36, and appropriately reduce the high-frequency weight to focus on the impact of mechanical vibration during stable operation. According to exponential decay, the initial value is 0.2 and gradually decreases to 0.1 over time to reduce the impact of low-frequency vibration on judgment during shutdown.

[0053] The dynamic operation delay threshold is the fault judgment time threshold that the pressure sensor system adaptively adjusts according to the real-time working conditions. When the abnormal signal duration of the pressure sensor exceeds this threshold, it is judged as a real fault.

[0054] Generate a dynamic delay threshold based on the following formula : ;in: The preset benchmark threshold is in milliseconds and is set according to the sensor model and application scenario, usually 50ms-200ms; The high-frequency energy activation threshold is set to 1.5 times the high-frequency energy of the ambient baseline noise; is the slope coefficient, with a value range of 0.01-0.05, which is used to control the influence of noise energy on the threshold; is the total noise energy, which is calculated by the RMS value of the acquired signal; 、 、 is the proportion of low-frequency, medium-frequency and high-frequency noise energy, which respectively indicates the proportion of each frequency band energy to the total energy.

[0055] When high-frequency noise energy Exceeding the activation threshold When the low-frequency noise energy is When the ratio is high, the threshold adjustment is relatively small to maintain sensitivity to low-frequency anomalies.

[0056] S4: Calculate the reliability coefficient of the sensor's operating status by combining the time domain characteristics of the pressure sensor's output signal with the current noise energy distribution;

[0057] Among them, the operating status credibility coefficient is a dynamic weight value (usually ranging from 0 to 1) that is used to quantify the credibility of the current operating status of the pressure sensor; it integrates factors such as historical data consistency, environmental conditions, and equipment health status to reflect the reliability of sensor signal anomalies.

[0058] Specifically, the calculation of the operating status credibility coefficient includes:

[0059] ;

[0060] The time domain credibility factor The calculation formula is:

[0061] ;

[0062] Frequency domain credibility factor The calculation formula is:

[0063] ;

[0064] Where, 、 、 is the ratio of low-frequency, medium-frequency and high-frequency noise energy; is the total noise energy; The duration of the anomaly is in milliseconds, reflecting the time window for fault detection; Represents the current moment, i.e., the time point at which the credibility is calculated; is an integral variable, representing a time point within the sliding time window, ranging from to ; For pressure sensors Detection signal at the moment; 、 are the signal statistics within the sliding time window, representing the standard deviation and coefficient of variation of the signal respectively; 、 is the steepness coefficient of the sigmoid function, which are set to 0.05 and 0.1 respectively; 、 are the energy proportion thresholds, which are set to 0.4 and 100ms respectively; is the time decay factor, set to 0.01; is the high frequency band credible weight coefficient, which is set to 0.6.

[0065] When the high-frequency noise energy ratio exceeds the preset threshold, the sensitivity to short-term signal anomalies is reduced. > When the frequency domain credibility factor The value decreases, resulting in an overall credibility coefficient The system adopts a more conservative judgment strategy for signal anomalies that occur in a short period of time, requiring the anomaly to last longer before triggering a fault alarm.

[0066] When low-frequency noise energy dominates, the detection weight of continuous abnormal signals is increased. The specific implementation method is: When >0.5, the system automatically adjusts the time decay factor in the time domain credibility calculation , reducing it from the baseline value of 0.01 to 0.005, so that the continuous abnormal signal obtains a higher weight in the credibility assessment and effectively identifies the slow fault development process in the low-frequency noise environment.

[0067] S5: When an abnormality in the output signal of the pressure sensor is detected, the abnormality duration is corrected based on the operating status credibility coefficient, and the corrected duration is compared with the dynamic operating delay threshold to determine whether it is a real fault.

[0068] Specifically, the abnormality duration is corrected based on the operating status credibility coefficient, including:

[0069] Establish the credibility-time correction mapping function:

[0070] ;in: is the corrected abnormal duration; The initial abnormal duration; is the baseline credibility threshold, set to 0.7; is the correction strength coefficient, set to 2.0, which is used to control the influence of credibility on time correction.

[0071] The corrected abnormal duration is obtained based on the operating status credibility coefficient. Below the baseline threshold When the reliability coefficient is Above the baseline threshold When the system is in operation, it shortens the abnormality duration and speeds up the fault determination process.

[0072] The exponential smoothing algorithm is used to optimize the corrected anomaly duration: ;in: is the optimized abnormal duration, is the smoothing factor, set to 0.7; is the abnormal duration after the previous correction; this smoothing process can reduce the sudden change of correction time and improve the stability of fault judgment.

[0073] The system will optimize the abnormal duration With dynamic operation delay threshold Compare: When > When it is determined to be a fault signal, the fault alarm process can be triggered directly, or a secondary verification can be performed to confirm that it is a real fault signal before triggering the fault alarm process; when ≤ When an error occurs, it is determined to be a temporary anomaly or a false anomaly caused by environmental interference, and monitoring continues without triggering a fault alarm.

[0074] For signals that are judged to be faulty, secondary verification is performed using at least one of the following methods:

[0075] Check the frequency of recurrence of similar abnormal patterns in the historical data of the same sensor. The system extracts the sensor's operating data from the past 30 days from the database and analyzes the frequency and duration of similar abnormal patterns. If a similar abnormality has occurred more than three times in the past and each duration exceeds 80% of the threshold, it is confirmed as a real fault.

[0076] Compare the output differences of other sensors in the same batch during the same period. The system automatically selects 3-5 sensors of the same model in the same working environment as a reference group and compares their output signal characteristics during the same period. If the abnormal characteristics of the target sensor are not present in the reference group or the degree of presence is significantly lower than that of the target sensor, it is confirmed to be a real fault.

[0077] Injecting a test signal to verify sensor response characteristics. The system inputs a standard test signal into a suspected faulty sensor and analyzes the sensor's response curve characteristics, including parameters such as response time, amplitude accuracy, and signal stability. If the response characteristics deviate from the normal range by more than 20%, it is confirmed to be a true fault.

[0078] Secondary verification is used to verify the fault signal determined by the above-mentioned pressure sensor fault detection method to avoid false alarms. However, since secondary verification is time-consuming, in actual applications, secondary verification is mainly used in the testing phase and the initial implementation stage.

[0079] In another embodiment, Figure 2 As shown, a pressure sensor system includes:

[0080] The pressure sensing unit 100 is used to measure pressure changes in the working environment and convert them into electrical signals for output. This unit includes a pressure-sensitive element, a signal conditioning circuit, and a data conversion module, enabling the acquisition, conversion, and output of pressure signals. The pressure-sensitive element utilizes a silicon piezoresistive sensor with a measurement range of 0-10 MPa, an accuracy of ±0.1% FS, and a response time of less than 5 ms. The signal conditioning circuit utilizes a low-noise operational amplifier with a signal-to-noise ratio greater than 60 dB. The data conversion module utilizes a 16-bit ADC with a sampling rate of up to 10 kHz.

[0081] The environmental noise monitoring unit 200 is used to collect noise signals in the working environment in real time. This unit comprises a wideband microphone array, a preamplifier, and a spectrum analysis processor. It can capture ambient noise in the 0-10kHz range with a sensitivity of -40dB and a dynamic range of 100dB. The microphone array consists of four omnidirectional microphones arranged in a square with a side length of 10cm, enabling noise source location and noise feature extraction.

[0082] The fault detection unit 300 applies the fault detection method described in Example 1 to perform fault detection. The fault detection unit 300 is respectively connected to the pressure sensing unit 100 and the environmental noise monitoring unit 200, and includes a signal processing subunit, a feature extraction subunit and a decision subunit, which can realize the correlation analysis of noise signals and pressure signals, anomaly detection and fault judgment functions. The signal processing subunit adopts a DSP chip to realize real-time signal processing, and the operation speed reaches 1GFLOPS. The feature extraction subunit realizes spectrum analysis and time domain feature extraction, and supports 512-point FFT operation. The decision subunit realizes fault judgment based on the credibility assessment algorithm, and the judgment delay is less than 200ms. The specific fault detection method refers to Example 1 and will not be repeated here.

[0083] Alarm output interface 400 is used to provide fault alarm information to higher-level systems or users. This interface supports multiple output modes, including relay output, 4-20mA analog output, RS485 digital communication output, and wireless communication output. Relay output supports both normally open and normally closed modes, with a maximum switching current of 2A. Analog output accuracy is 0.1%FS. RS485 communication supports the Modbus protocol with a communication rate of up to 115200bps. Wireless communication supports WiFi and Bluetooth 4.0 protocols, with communication ranges of 100m and 30m, respectively.

[0084] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0085] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0086] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0087] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), a mobile hard drive, a magnetic disk, or an optical disk.

[0088] 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 above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A real-time fault detection method for pressure sensors based on dynamic environment adaptation, characterized in that: The following steps are involved: Real-time synchronous acquisition of environmental noise signals and pressure sensor output signals to establish a time-domain correlation dataset of noise-sensor signals; Performing spectrum analysis on the environmental noise signal, dynamically dividing the noise spectrum into a low-frequency band, a mid-frequency band, and a high-frequency band, and calculating the energy distribution of each frequency band; Dynamically generate the operating delay threshold based on the energy distribution and weight factors of each frequency band, where the energy of the high frequency band has a higher weight on the threshold adjustment than the low frequency band and the mid frequency band; Calculating the reliability coefficient of the sensor operation state by combining the time domain characteristics of the pressure sensor output signal with the current noise energy distribution; When an abnormality in the output signal of the pressure sensor is detected, the abnormality duration is corrected based on the operating state credibility coefficient, and the corrected duration is compared with the dynamic operating delay threshold to determine whether it is a real fault.

2. The method according to claim 1, characterized in that Real-time synchronous acquisition of environmental noise signals and pressure sensor output signals, including: Use hardware trigger signals to synchronously start data acquisition of noise sensor and pressure sensor; The sampling time window length is dynamically adjusted according to the operating frequency of the pressure sensor, and the adjustment range is 10ms-200ms.

3. The method according to claim 1, characterized in that The dynamic division of the noise spectrum comprises: Obtain the spectrum distribution of the noise signal through fast Fourier transform; An adaptive clustering algorithm is used to divide the spectrum into low-frequency band, mid-frequency band and high-frequency band, and the division boundaries are dynamically adjusted according to the characteristics of the environmental noise.

4. The method according to claim 3, characterized in that The low frequency band is 0-500 Hz, the middle frequency band is 500 Hz-2000 Hz, and the high frequency band is above 2000 Hz.

5. The method according to claim 1, wherein Dynamically generate operating delay thresholds based on the energy distribution and weight factors of each frequency band, including: Adjust the weight coefficient of each frequency band according to the current working stage of the sensor; Generate a dynamic delay threshold based on the following formula : ； in: is the preset benchmark threshold; Activate the threshold for high-frequency energy; is the slope coefficient; is the total noise energy; 、 、 is the ratio of low-frequency, medium-frequency and high-frequency noise energy; 、 、 Represent the dynamic weight coefficients of low frequency band, medium frequency band and high frequency band respectively.

6. The method according to claim 5, characterized in that Dynamic weight coefficients for low, mid, and high frequency bands 、 、 satisfy: ; Adjust the weight coefficient of each frequency band according to the current working stage of the sensor, including: Startup phase: high-frequency weighting Increase by 20%-30%; Stable phase: mid-frequency weighting Increased to 1.2 times the baseline value; Downtime: Low-frequency weighting Decay exponentially.

7. The method according to claim 1, characterized in that The calculation of the operating state credibility coefficient includes: ； The time domain credibility factor The calculation formula is: ； Frequency domain credibility factor The calculation formula is: ； Where, 、 、 is the ratio of low-frequency, medium-frequency and high-frequency noise energy; is the total noise energy; is the abnormality duration, reflecting the time window for fault detection; Represents the current moment, i.e., the time point at which the credibility is calculated; is an integral variable, representing a time point within the sliding time window, ranging from to ; For pressure sensors Detection signal at the moment; 、 is the signal statistic within the sliding time window; 、 is the steepness coefficient of the sigmoid function; 、 is the energy proportion threshold; is the time decay factor, is the credible weight coefficient of the high frequency band.

8. The method according to claim 7, characterized in that Correcting the abnormality duration based on the operating state credibility coefficient includes: Establish the credibility-time correction mapping function: ； in: is the corrected abnormal duration; The initial abnormal duration; is the baseline credibility threshold; is the modified strength coefficient; Obtaining a corrected abnormality duration based on the operating state credibility coefficient; The exponential smoothing algorithm is used to optimize the corrected anomaly duration: ;in: is the optimized abnormal duration, is the smoothing factor; The duration of the anomaly after the previous correction.

9. A pressure sensor system, characterized in that: include: pressure sensing unit; Environmental noise monitoring unit; A fault detection module for performing fault detection using the fault detection method according to any one of claims 1 to 8; Alarm output interface.

Images