Sensor fault diagnosis method and device, electronic equipment and storage medium

Abstract

The invention discloses a fault diagnosis method and device of a sensor, electronic equipment and a storage medium. According to the application, the air pressure and temperature measurement values in a smart battery can be synchronously obtained, a physical model is established by means of an ideal gas state equation, and correlation calculation is performed on two parameters; by comparing the deviation between the actually measured air pressure value and the theoretical air pressure value, the abnormality caused by the air pressure sensor or the temperature sensor is accurately distinguished; the technical effects of accurately positioning a specific fault sensor, reducing the fault false alarm rate and response delay, improving the reliability of intelligent battery state monitoring and strengthening the safety risk early warning capability of a battery management system are achieved.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and in particular to a method and apparatus for diagnosing sensor faults, electronic equipment, and storage medium. Background Technology

[0002] Intelligent battery management systems, as a core technology for safe battery operation, are widely used in high-reliability scenarios such as new energy vehicles and energy storage systems. Among related technologies, a battery state monitoring system is constructed through the collaborative operation of pressure and temperature sensors and physical models.

[0003] Existing sensor diagnostic methods employ independent verification logic, but they have limitations in distinguishing between pressure sensor and temperature sensor faults. They can only determine that at least one sensor is abnormal, but cannot pinpoint the specific fault source, leading to delayed fault response or increased false alarm rate, thereby affecting the battery management system's ability to warn of safety risks such as thermal runaway. Summary of the Invention

[0004] This disclosure provides a method, apparatus, electronic device, and storage medium for diagnosing sensor faults.

[0005] According to a first aspect of this disclosure, a fault diagnosis method for a sensor is provided, comprising: The air pressure and temperature measurements inside the smart battery are acquired synchronously via wireless communication. A physical model of the gas inside the battery is established based on the ideal gas law, and the theoretical gas pressure at the current temperature is calculated based on the temperature measurement value. Calculate the deviation between the measured air pressure value and the theoretical air pressure value, and compare the deviation with a preset diagnostic threshold; The sensor is determined to be faulty based on the comparison results.

[0006] Optionally, the physical model of the internal gas of the battery based on the ideal gas law includes: Calibrate the proportionality constants in the ideal gas law; The theoretical air pressure value is calculated based on the calibrated proportional coefficient and the current temperature measurement.

[0007] Optionally, calculating the deviation between the measured air pressure value and the theoretical air pressure value, and comparing the deviation with a preset diagnostic threshold, includes: Calculate the absolute deviation; wherein, the absolute deviation is the absolute value of the difference between the measured air pressure value and the theoretical air pressure value; Calculate the relative deviation; wherein the relative deviation is the absolute value of the difference between the measured air pressure value and the theoretical air pressure value, divided by the theoretical air pressure value and then multiplied by 100%.

[0008] Optionally, determining whether the pressure sensor and / or temperature sensor is faulty based on the comparison result further includes: When the absolute or relative deviation continues to exceed the corresponding preset diagnostic threshold, it is determined to be a permanent fault; When the absolute or relative deviation fluctuates irregularly within a preset time window and exceeds the corresponding preset diagnostic threshold, it is determined to be an intermittent fault.

[0009] Optionally, the method further includes: Monitor the dynamic trends of air pressure and temperature measurements under battery charging and discharging conditions; If the changes in air pressure and temperature show an inverse relationship or no obvious correlation, it is determined to be a sensor non-correlation fault.

[0010] Optionally, determining whether the sensor is faulty based on the comparison result includes: When the deviation exceeds the diagnostic threshold and the barometric pressure sensor itself diagnoses no abnormality, the temperature sensor is determined to be faulty; wherein, the barometric pressure sensor itself diagnoses no abnormality including barometric pressure measurement values ​​within a first preset range.

[0011] Optionally, determining whether the sensor is faulty based on the comparison result includes: When the deviation exceeds the diagnostic threshold and the temperature sensor itself diagnoses no abnormality, the pressure sensor is determined to be faulty; wherein, the temperature sensor itself diagnoses no abnormality including the temperature measurement value being within a second preset range.

[0012] According to a second aspect of this disclosure, a fault diagnosis device for a sensor is provided, comprising: The acquisition unit is used to synchronously acquire the air pressure and temperature measurements inside the smart battery via wireless communication. The construction unit is used to establish a physical model of the gas inside the battery based on the ideal gas law, and to calculate the theoretical gas pressure value at the current temperature based on the temperature measurement value. The calculation unit is used to calculate the deviation between the measured air pressure value and the theoretical air pressure value, and compare the deviation with a preset diagnostic threshold. The judgment unit is used to determine whether the sensor is faulty based on the comparison result.

[0013] Optionally, the building unit is further configured to: Calibrate the proportionality constants in the ideal gas law; The theoretical air pressure value is calculated based on the calibrated proportional coefficient and the current temperature measurement.

[0014] Optionally, the computing unit is further configured to: Calculate the absolute deviation; wherein, the absolute deviation is the absolute value of the difference between the measured air pressure value and the theoretical air pressure value; Calculate the relative deviation; wherein the relative deviation is the absolute value of the difference between the measured air pressure value and the theoretical air pressure value, divided by the theoretical air pressure value and then multiplied by 100%.

[0015] Optionally, the determining unit is further configured to: When the absolute or relative deviation continues to exceed the corresponding preset diagnostic threshold, it is determined to be a permanent fault; When the absolute or relative deviation fluctuates irregularly within a preset time window and exceeds the corresponding preset diagnostic threshold, it is determined to be an intermittent fault.

[0016] Optionally, the device further includes: The monitoring unit is used to monitor the dynamic changes in air pressure and temperature measurements under battery charging and discharging conditions. The judgment unit is also used to determine that if the change in air pressure and the change in temperature show opposite characteristics or no obvious correlation, it is a sensor non-correlation fault.

[0017] Optionally, the determining unit is further configured to: When the deviation exceeds the diagnostic threshold and the barometric pressure sensor itself diagnoses no abnormality, the temperature sensor is determined to be faulty; wherein, the barometric pressure sensor itself diagnoses no abnormality including barometric pressure measurement values ​​within a first preset range.

[0018] Optionally, the determining unit is further configured to: When the deviation exceeds the diagnostic threshold and the temperature sensor itself diagnoses no abnormality, the pressure sensor is determined to be faulty; wherein, the temperature sensor itself diagnoses no abnormality including the temperature measurement value being within a second preset range.

[0019] According to a third aspect of this disclosure, an electronic device is provided, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect above.

[0020] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method described in the first aspect above.

[0021] According to a fifth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0022] The sensor fault diagnosis method, apparatus, electronic device, and storage medium disclosed herein, through which the pressure and temperature measurements inside the smart battery can be acquired simultaneously, a physical model is established using the ideal gas law, and the two parameters are correlated and calculated. By comparing the deviation between the measured pressure value and the theoretical pressure value, the abnormality can be accurately distinguished between the pressure sensor and the temperature sensor. Therefore, it can solve the technical problems of existing sensor diagnosis methods that use independent verification logic, cannot distinguish between pressure sensor and temperature sensor faults, cannot locate specific fault sources, resulting in fault response delays or increased false alarm rates, and affecting the battery management system's ability to warn of safety risks such as thermal runaway. It achieves the technical effects of accurately locating specific faulty sensors, reducing false alarm rates and response delays, improving the reliability of smart battery state monitoring, and strengthening the battery management system's ability to warn of safety risks.

[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0024] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein: Figure 1 This is a schematic flowchart of a sensor fault diagnosis method provided in an embodiment of the present disclosure; Figure 2 A schematic diagram of the structure of a sensor fault diagnosis device provided in an embodiment of this disclosure; Figure 3 A schematic diagram of the structure of another sensor fault diagnosis device provided in an embodiment of this disclosure; Figure 4 A schematic block diagram of an example electronic device provided for embodiments of this disclosure. Detailed Implementation

[0025] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0026] The following description, with reference to the accompanying drawings, describes a sensor fault diagnosis method, apparatus, electronic device, and storage medium according to embodiments of the present disclosure.

[0027] Figure 1 This is a schematic flowchart illustrating a sensor fault diagnosis method provided in an embodiment of the present disclosure.

[0028] like Figure 1 As shown, the method includes the following steps: Step 101: Simultaneously acquire the air pressure and temperature measurements inside the smart battery via wireless communication. To obtain the basic correlation data required for subsequent fault diagnosis, this step initiates a data request to the smart battery via wireless communication. The core objective is to ensure the synchronous acquisition of air pressure measurements from the battery's internal air pressure sensor and temperature measurements from the temperature sensor, ensuring temporal correspondence between the two types of data. This provides a prerequisite for subsequent analysis based on the physical coupling relationship between air pressure and temperature. As one implementation method, a data request command can be sent via a preset communication protocol, and a timestamp calibration mechanism can further ensure the synchronization accuracy of the two types of measurements. The wireless communication method is adaptable to conventional wireless transmission methods in smart battery monitoring scenarios.

[0029] Data can be obtained without disassembling the battery or physically connecting the wires, thus avoiding damage to the battery's sealing and structural integrity. At the same time, the synchronously collected air pressure and temperature measurements ensure the time correlation between the two, providing accurate data support for subsequent theoretical value calculations and deviation comparisons based on physical models, and ensuring the effectiveness of fault diagnosis logic.

[0030] Step 102: Establish a physical model of the gas inside the battery based on the ideal gas law, and calculate the theoretical gas pressure at the current temperature based on the temperature measurement value. Based on the physical laws governing gas state changes, a suitable physical model is constructed for the relatively enclosed gas environment inside a battery. The core of this model lies in converting measured temperature values ​​into theoretical values ​​of the internal gas pressure under current operating conditions, thereby establishing a quantitative coupling relationship between temperature and pressure. The physical laws governing gas state changes can be classical physical equations reflecting the correlation between gas pressure and temperature within a confined space. During model construction, inherent properties such as the battery's internal volume and total gas volume can be incorporated to optimize model parameters, ensuring the theoretical pressure value matches the actual battery operating conditions. As one implementation method, this physical model can be constructed based on the ideal gas law, integrating parameters such as the battery's internal enclosed volume and the number of gas moles into constant coefficients relevant to battery design and pre-calibrating them. The calculation is then performed using the simplified form: "Theoretical pressure = constant coefficient × measured temperature value".

[0031] By building a model based on physical principles, the calculation of theoretical air pressure values ​​can be ensured to have a scientific basis, avoiding errors caused by the subjective setting of theoretical values. At the same time, by quantitatively linking temperature measurement values ​​with theoretical air pressure values, accurate benchmark data is provided for subsequent deviation comparison between measured air pressure values ​​and theoretical values, directly ensuring the reliability of the core comparison link in the fault diagnosis logic.

[0032] Step 103: Calculate the deviation between the measured air pressure value and the theoretical air pressure value, and compare the deviation with a preset diagnostic threshold; The deviation between the measured air pressure value and the theoretical air pressure value is quantified to accurately reflect the degree of deviation between the measured data and the theoretical data derived from physical laws. This quantified deviation is then compared with a pre-set diagnostic threshold. This objective numerical comparison determines whether the current air pressure measurement value conforms to the expected physical coupling relationship, providing direct numerical evidence for subsequent fault diagnosis. The deviation quantification can employ conventional calculation methods that reflect the degree of difference between the two values. The pre-set diagnostic threshold is determined based on the battery's structural characteristics, sensor accuracy, and safety requirements in the actual application scenario, ensuring the threshold's rationality and applicability in identifying abnormal deviations. As one implementation method, the deviation can be calculated as the absolute or relative deviation between the measured air pressure value and the theoretical air pressure value, and the diagnostic threshold is correspondingly set as an absolute or relative deviation threshold.

[0033] By comparing the quantified deviation with the threshold, the abstract physical coupling relationship is transformed into an objective numerical judgment standard, avoiding the uncertainty of subjective experience judgment. At the same time, the preset threshold can be adapted to different types of smart batteries, ensuring the pertinence and reliability of deviation judgment, laying the foundation for accurate identification of sensor faults in the future.

[0034] Step 104: Determine whether the sensor is faulty based on the comparison results.

[0035] Based on the comparison between the deviation and a preset diagnostic threshold, the working status of the pressure sensor and temperature sensor is inferred by verifying the matching between the measured air pressure value and the theoretical air pressure value. If the deviation meets the threshold requirement, it indicates that the data collected by both types of sensors is consistent with the physical coupling relationship between air pressure and temperature, and the sensors are judged to be normal. If the deviation exceeds the threshold range, it indicates that the data collected by at least one type of sensor deviates from the physical law, and there is a risk of failure. The essence of this judgment logic is to indirectly judge the health status of the sensors through the consistency verification between the data and the physical model, without directly testing the sensor hardware itself. As one implementation method, when the absolute deviation is less than or equal to the absolute deviation threshold or the relative deviation is less than or equal to the relative deviation threshold, the sensor is judged to be working normally; otherwise, a fault is judged.

[0036] The determination is made by comparing the theoretical values ​​derived from physical laws with the measured values, avoiding the risk of misjudgment based on subjective experience or single data, and ensuring the objectivity of fault diagnosis. At the same time, it can directly locate whether the sensor is faulty, providing a clear basis for subsequent possible fault isolation or safety measures, and ensuring the practicality and effectiveness of the diagnostic process.

[0037] In some embodiments, the physical model of the gas inside the battery based on the ideal gas law includes: Calibrate the proportionality constants in the ideal gas law; The theoretical air pressure value is calculated based on the calibrated proportional coefficient and the current temperature measurement.

[0038] When establishing a physical model of the internal gas of a battery based on the ideal gas law, the first step is to calibrate the proportionality coefficient. Since the battery's interior is a sealed, rigid space after packaging, its volume V and the number of moles of gas n remain constant. The ideal gas law can be integrated into a fixed proportionality coefficient K. The calibration process must be performed before the battery leaves the factory or when it is confirmed to be in normal condition. Specifically, several typical operating points within the battery's normal operating temperature range (e.g., -20℃, 0℃, 25℃, 50℃, 80℃) are selected. At each operating point, the battery is left to stand for at least 30 minutes until the internal temperature and pressure stabilize. Temperature measurements (converted to Kelvin thermodynamic temperature units) and pressure measurements are simultaneously collected under this stable state. A temporary proportionality coefficient is calculated for each operating point. The arithmetic mean of the temporary proportionality coefficients for all operating points is then applied to obtain the battery-specific calibrated proportionality coefficient, which is stored in the non-volatile memory of the battery management system. When calculating the theoretical pressure value subsequently, the calibrated proportionality coefficient is used, and the currently acquired temperature measurement value is substituted into the formula to quickly calculate the theoretical expected value of the battery's internal pressure at the current temperature.

[0039] By calibrating a dedicated proportional coefficient for each individual battery, the interference of individual differences in volume and initial gas quantity during the manufacturing process on the theoretical pressure calculation is effectively avoided, making the theoretical pressure value more consistent with the actual physical state of the battery. At the same time, the calculation process of subsequent theoretical values ​​is simplified, eliminating the need to process complex multi-parameter equations in real time, and improving the real-time performance of fault diagnosis while ensuring calculation accuracy.

[0040] In some embodiments, calculating the deviation between the measured air pressure value and the theoretical air pressure value, and comparing the deviation with a preset diagnostic threshold, includes: Calculate the absolute deviation; wherein, the absolute deviation is the absolute value of the difference between the measured air pressure value and the theoretical air pressure value; Calculate the relative deviation; wherein the relative deviation is the absolute value of the difference between the measured air pressure value and the theoretical air pressure value, divided by the theoretical air pressure value and then multiplied by 100%.

[0041] When calculating the deviation between the measured air pressure value and the theoretical air pressure value and comparing it with the threshold, the absolute deviation is first calculated based on the measured air pressure value inside the battery and the theoretical air pressure value calculated through the physical model. After the absolute deviation is calculated, the relative deviation is calculated. Specifically, the absolute deviation is used as the numerator, divided by the theoretical air pressure value, and the quotient is multiplied by 100% to obtain the relative deviation in percentage form. During the calculation, the numerical result needs to be retained to two decimal places to balance the calculation accuracy and the convenience of subsequent threshold comparison, ensuring that the deviation data can accurately reflect the degree of deviation between the measured value and the theoretical value.

[0042] By simultaneously calculating absolute and relative deviations, the actual difference between measured and theoretical air pressure values ​​can be intuitively reflected. Furthermore, the influence of differences in theoretical air pressure values ​​under different operating conditions on deviation judgment can be eliminated by using percentages, thus avoiding the bias caused by a single type of deviation. At the same time, the clear calculation formulas and numerical processing requirements ensure the standardization and consistency of deviation calculations, providing a reliable quantitative basis for subsequent accurate comparison with preset diagnostic thresholds.

[0043] In some embodiments, determining whether the pressure sensor and / or temperature sensor is faulty based on the comparison result further includes: When the absolute or relative deviation continues to exceed the corresponding preset diagnostic threshold, it is determined to be a permanent fault; When the absolute or relative deviation fluctuates irregularly within a preset time window and exceeds the corresponding preset diagnostic threshold, it is determined to be an intermittent fault.

[0044] When the absolute deviation first exceeds the absolute deviation threshold, or the relative deviation first exceeds the relative deviation threshold, the battery management system (BMS) starts the built-in timer. If the deviation continues to exceed the corresponding threshold during the timing process (for example, the timer accumulates to a preset 30 seconds) and there is no return to the threshold, it is determined that the pressure sensor and / or temperature sensor has a permanent fault. At this time, the timer stops and the fault state is locked. If the deviation fluctuates irregularly multiple times within a preset time window (for example, 10 seconds), that is, the deviation exceeds the threshold multiple times and then quickly returns to the threshold, and the duration of each time the deviation exceeds the threshold is less than 5 seconds and the fluctuation has no fixed period (such as 3 threshold jumps within 10 seconds), it is determined that the sensor has an intermittent fault. At the same time, the timer is reset each time the deviation falls back until the irregular jump characteristics are detected and the intermittent fault state is locked.

[0045] This specific implementation method can accurately distinguish between permanent and intermittent faults by using time monitoring and fluctuation characteristic judgment, avoiding misjudging transient interference as permanent faults and preventing the omission of potential intermittent faults. At the same time, the clear time parameters and fluctuation judgment criteria make fault type judgment operable, providing an accurate basis for subsequent targeted handling (such as permanent faults requiring shutdown for maintenance and intermittent faults requiring enhanced monitoring), and improving the precision of fault diagnosis.

[0046] In some embodiments, the method further includes: Monitor the dynamic trends of air pressure and temperature measurements under battery charging and discharging conditions; If the changes in air pressure and temperature show an inverse relationship or no obvious correlation, it is determined to be a sensor non-correlation fault.

[0047] Synchronous monitoring of the dynamic trends of air pressure and temperature measurements under charging and discharging conditions: First, set the operating condition trigger conditions. When the battery management system (BMS) detects that the charging current is ≥0.5C or the discharging current is ≤-0.5C (C is the rated capacity of the battery), the dynamic trend monitoring module is automatically started. The air pressure and temperature measurements are collected synchronously at a sampling frequency of 2 seconds / time. The direction (rise / fall) and rate of change (such as the change in temperature and air pressure per unit time) of the two types of data are continuously recorded throughout the entire charging and discharging cycle. Subsequently, a trend correlation analysis was performed on the collected dynamic data: if the temperature change direction is completely opposite to the air pressure change direction (for example, during the charging process, the temperature measurement value rises from 25°C to 32°C within 5 minutes, showing a continuous upward trend, while the air pressure measurement value drops from 95kPa to 92kPa during the same period, showing a continuous downward trend), or if the two types of data changes have no obvious logical correlation (for example, during the discharging process, the temperature measurement value rises steadily by 3°C every 10 minutes, but the air pressure measurement value fluctuates irregularly within the range of 90kPa±0.3kPa, without showing the expected slight upward trend with the temperature rise), then it is determined that the air pressure sensor and / or temperature sensor have an uncorrelated fault.

[0048] By focusing on the typical dynamic operating condition of battery charging and discharging, and utilizing the inherent physical correlation between air pressure and temperature (a slight increase in air pressure is usually accompanied by a rise in temperature) for trend verification, it can accurately identify unrelated faults that are difficult to detect by static data comparison. At the same time, the clear operating condition triggering conditions and sampling standards ensure the consistency and repeatability of fault judgment, effectively avoiding misjudgment of the internal state of the battery management system due to unrelated data output by sensors, and further improving the reliability of diagnosis.

[0049] In some embodiments, determining whether the sensor is faulty based on the comparison result includes: When the deviation exceeds the diagnostic threshold and the barometric pressure sensor itself diagnoses no abnormality, the temperature sensor is determined to be faulty; wherein, the barometric pressure sensor itself diagnoses no abnormality including barometric pressure measurement values ​​within a first preset range.

[0050] The temperature sensor value T_measured is read in real time. T_measured is then substituted into the baseline model to calculate a desired air pressure value P_expected. Simultaneously, the measured air pressure value P_measured is read in real time from the air pressure sensor.

[0051] Calculate the deviation: ΔP = |P_measured - P_expected| Set a reasonable deviation threshold ε. Fault determination criteria: If ΔP consistently exceeds the threshold ε, and the barometer's initial diagnostics show no abnormalities (e.g., readings outside the range), then the temperature sensor is highly suspected of being inaccurate. The barometer is giving a "reasonable" reading, but this reading does not match the temperature level reported by the temperature sensor. Since barometer pressure is a response to temperature, it is more likely that the temperature measurement is inaccurate.

[0052] In some embodiments, determining whether the sensor is faulty based on the comparison result includes: When the deviation exceeds the diagnostic threshold and the temperature sensor itself diagnoses no abnormality, the pressure sensor is determined to be faulty; wherein, the temperature sensor itself diagnoses no abnormality including the temperature measurement value being within a second preset range.

[0053] The temperature sensor value T_measured is read in real time. T_measured is then substituted into the model to calculate the expected air pressure value P_expected. The actual measured value P_measured from the air pressure sensor is then read in real time.

[0054] Calculate the deviation: ΔP = |P_measured - P_expected| Fault determination criteria: If ΔP consistently exceeds the threshold ε, and the temperature sensor itself shows no abnormalities in its initial diagnosis (e.g., reasonable changes in reading), then the barometric pressure sensor is highly suspected of being inaccurate. The temperature sensor provides a "reasonable" reading, and battery conditions (e.g., charge / discharge current) indicate that the temperature change is credible, but the barometric pressure reading does not respond in a physically plausible manner.

[0055] The following example illustrates the fault diagnosis method for the sensor disclosed in this application. Assuming the battery is functioning normally, a standard pressure-temperature coupling model (PT curve) is established. Distinguishing between transient disturbances and permanent faults typically requires the fault state to persist for a certain period before final confirmation. Step S1: Data synchronization acquisition. The system sends a data request command to the smart battery via wireless communication, and simultaneously obtains the battery's internal air pressure measurement value P_meas and temperature measurement value T_meas at the same timestamp.

[0056] Step S2: Calculate the theoretical air pressure value using a physical model. A physical model of the gas inside the battery is established based on the ideal gas law (PV = nRT). The theoretical expected value of the gas pressure inside the battery, P_calc, is calculated based on the measured temperature T_meas at the current temperature.

[0057] Its core calculation formula is: P_calc = (nR / V) * T_meas (assuming that the inside of the battery is a closed rigid volume V, and the number of gas moles n remains unchanged).

[0058] Note: In practical applications, (nR / V) can be considered as a constant coefficient K related to battery design, which can be pre-calibrated experimentally. Therefore, the formula simplifies to: P_calc = K * T_meas.

[0059] Step S3: Deviation calculation and comparison. Calculate the absolute deviation ΔP or relative deviation δP between the measured barometric pressure P_meas and the theoretically calculated value P_calc.

[0060] ΔP = |P_meas - P_calc| δP = |P_meas - P_calc| / P_calc * 100% Step S4: Fault diagnosis and location. The deviation ΔP or δP is compared with a preset diagnostic threshold (ΔP_threshold or δP_threshold), and the sensor status is determined based on the comparison result. Case A: If ΔP ≤ ΔP_threshold (or δP ≤ δP_threshold), then the air pressure and temperature sensors are considered to be working normally.

[0061] Case B: If ΔP > ΔP_threshold (or δP > δP_threshold), then at least one of the pressure sensor and / or temperature sensor is determined to be faulty.

[0062] Example: Logic: The internal air pressure and temperature of the battery are within a reasonable physical range. Under normal circumstances, they fluctuate within a very small range.

[0063] Judgment criteria: Whether the read air pressure or temperature value is within a reasonable range.

[0064] For example, readings below 80 kPa or above 120 kPa can be directly identified as sensor malfunctions.

[0065] For example, -20°C to +80°C. Readings outside this range (such as 200°C or -100°C) can be immediately identified as sensor open circuit, short circuit, or circuit failure.

[0066] Reference judgment: 1) When the battery is well sealed, the pressure difference between the inside and outside should be within a very small range. If there is a large difference (such as the internal pressure being a vacuum or extremely high pressure), the sensor is faulty.

[0067] 2) The temperature values ​​measured by multiple sensors differ, but the difference is within a reasonable range (e.g., ΔT < 3°C), which may be due to uneven heat distribution inside the battery.

[0068] 3) Excessive deviation: The reading of a certain sensor consistently deviates from the average reading of all other sensors by more than a threshold (e.g., >5°C).

[0069] Unique fault: When the battery is in stable condition, one sensor reading continuously drifts in one direction, while other sensor readings remain stable.

[0070] Dynamic response consistency verification logic: When the battery begins to charge or discharge, the readings of all temperature sensors should show a similar trend (rising simultaneously at similar rates). If the temperature change response of a certain sensor lags significantly behind that of other sensors, or if the rate of change is abnormal, it may indicate that the sensor's performance has deteriorated (e.g., increased thermal resistance).

[0071] Correlation check Logic: Changes in the internal gas pressure of a battery are strongly correlated with the battery's temperature and charging / discharging current. High-current charging / discharging or high temperatures will cause the battery's internal temperature to rise, which, according to the ideal gas law, will cause a slight increase in gas pressure.

[0072] Judgment criteria: When the battery temperature rises significantly or the current is very high, the air pressure reading should show a slight, reasonable increase.

[0073] Fault symptoms: 1) No correlation fault: The temperature changes drastically, but the air pressure reading remains unchanged or changes in the opposite direction. 2) Over-correlated fault: A small temperature change causes a drastic and unreasonable jump in air pressure.

[0074] Phase stability check (runout verification) Logic: When the battery is in a static state (no charging or discharging, stable temperature), the air pressure reading is very stable.

[0075] Judgment criteria: Continuously monitor the air pressure value while it is stationary. If the reading shows high-frequency, irregular, and violent fluctuations (far exceeding the sensor's nominal noise level), it can be determined that the sensor signal is unstable or there is a hardware malfunction.

[0076] Continuity check (viscosity value verification) Logic: The sensor's output value should change continuously as conditions change.

[0077] Judgment criteria: If the air pressure reading remains unchanged for a long time, becoming a "viscous value", especially when the battery conditions change significantly (such as switching from charging to discharging), the reading still does not change, then the sensor can be judged to be faulty (for example, the ADC circuit is stuck).

[0078] Corresponding to the aforementioned sensor fault diagnosis method, this invention also proposes a sensor fault diagnosis device. Since the device embodiments of this invention correspond to the aforementioned method embodiments, details not disclosed in the device embodiments can be referred to the aforementioned method embodiments, and will not be repeated here.

[0079] Figure 2 This is a schematic diagram of the structure of a sensor fault diagnosis device provided in an embodiment of the present disclosure, as shown below. Figure 2 As shown, it includes: The acquisition unit 21 is used to synchronously acquire the air pressure measurement value and temperature measurement value inside the smart battery via wireless communication. The construction unit 22 is used to establish a physical model of the gas inside the battery based on the ideal gas law, and to calculate the theoretical gas pressure value at the current temperature based on the temperature measurement value. The calculation unit 23 is used to calculate the deviation between the measured air pressure value and the theoretical air pressure value, and compare the deviation with a preset diagnostic threshold. The judgment unit 24 is used to determine whether the sensor is faulty based on the comparison result.

[0080] Furthermore, in one possible implementation of this disclosure embodiment, the construction unit 22 is further configured to: Calibrate the proportionality constants in the ideal gas law; The theoretical air pressure value is calculated based on the calibrated proportional coefficient and the current temperature measurement.

[0081] Furthermore, in one possible implementation of this disclosure, the computing unit 23 is further configured to: Calculate the absolute deviation; wherein, the absolute deviation is the absolute value of the difference between the measured air pressure value and the theoretical air pressure value; Calculate the relative deviation; wherein the relative deviation is the absolute value of the difference between the measured air pressure value and the theoretical air pressure value, divided by the theoretical air pressure value and then multiplied by 100%.

[0082] Furthermore, in one possible implementation of this disclosure, the determining unit 24 is further configured to: When the absolute or relative deviation continues to exceed the corresponding preset diagnostic threshold, it is determined to be a permanent fault; When the absolute or relative deviation fluctuates irregularly within a preset time window and exceeds the corresponding preset diagnostic threshold, it is determined to be an intermittent fault.

[0083] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 3 As shown, the device further includes: Monitoring unit 25 is used to monitor the dynamic change trend of air pressure and temperature measurement values ​​under battery charging and discharging conditions; The judgment unit 24 is also used to determine that if the change in air pressure and the change in temperature show opposite characteristics or no obvious correlation, the sensor is uncorrelated.

[0084] Furthermore, in one possible implementation of this disclosure, the determining unit 24 is further configured to: When the deviation exceeds the diagnostic threshold and the barometric pressure sensor itself diagnoses no abnormality, the temperature sensor is determined to be faulty; wherein, the barometric pressure sensor itself diagnoses no abnormality including barometric pressure measurement values ​​within a first preset range.

[0085] Furthermore, in one possible implementation of this disclosure, the determining unit 24 is further configured to: When the deviation exceeds the diagnostic threshold and the temperature sensor itself diagnoses no abnormality, the pressure sensor is determined to be faulty; wherein, the temperature sensor itself diagnoses no abnormality including the temperature measurement value being within a second preset range.

[0086] It should be noted that the foregoing explanation of the method embodiments also applies to the apparatus of the embodiments of this disclosure, and the principle is the same. Therefore, the embodiments of this disclosure are not limited thereto.

[0087] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0088] Figure 4A schematic block diagram of an example electronic device 400 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0089] like Figure 4 As shown, device 400 includes a computing unit 401, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 402 or a computer program loaded from storage unit 408 into RAM (Random Access Memory) 403. RAM 403 may also store various programs and data required for the operation of device 400. The computing unit 401, ROM 402, and RAM 403 are interconnected via bus 404. I / O (Input / Output) interface 405 is also connected to bus 404.

[0090] Multiple components in device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of monitors, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0091] The computing unit 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as a sensor fault diagnosis method. For example, in some embodiments, the sensor fault diagnosis method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the methods described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the aforementioned sensor fault diagnosis method by any other suitable means (e.g., by means of firmware).

[0092] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0093] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0094] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0095] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0096] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.

[0097] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0098] It's important to note that artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0099] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0100] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A fault diagnosis method for a sensor, characterized in that, include: The air pressure and temperature measurements inside the smart battery are acquired synchronously via wireless communication. A physical model of the gas inside the battery is established based on the ideal gas law, and the theoretical gas pressure at the current temperature is calculated based on the temperature measurement value. Calculate the deviation between the measured air pressure value and the theoretical air pressure value, and compare the deviation with a preset diagnostic threshold; The sensor is determined to be faulty based on the comparison results.

2. The method according to claim 1, characterized in that, The physical model of the gas inside the battery based on the ideal gas law includes: Calibrate the proportionality constants in the ideal gas law; The theoretical air pressure value is calculated based on the calibrated proportional coefficient and the current temperature measurement.

3. The method according to claim 1, characterized in that, The step of calculating the deviation between the measured air pressure value and the theoretical air pressure value, and comparing the deviation with a preset diagnostic threshold, includes: Calculate the absolute deviation; wherein, the absolute deviation is the absolute value of the difference between the measured air pressure value and the theoretical air pressure value; Calculate the relative deviation; wherein the relative deviation is the absolute value of the difference between the measured air pressure value and the theoretical air pressure value, divided by the theoretical air pressure value and then multiplied by 100%.

4. The method according to claim 1, characterized in that, The step of determining whether the pressure sensor and / or temperature sensor is faulty based on the comparison result also includes: When the absolute or relative deviation continues to exceed the corresponding preset diagnostic threshold, it is determined to be a permanent fault; When the absolute or relative deviation fluctuates irregularly within a preset time window and exceeds the corresponding preset diagnostic threshold, it is determined to be an intermittent fault.

5. The method according to any one of claims 1-4, characterized in that, The method further includes: Monitor the dynamic trends of air pressure and temperature measurements under battery charging and discharging conditions; If the changes in air pressure and temperature show an inverse relationship or no obvious correlation, it is determined to be a sensor non-correlation fault.

6. The method according to claim 1, characterized in that, The step of determining whether the sensor is faulty based on the comparison result includes: When the deviation exceeds the diagnostic threshold and the barometric pressure sensor itself diagnoses no abnormality, the temperature sensor is determined to be faulty; wherein, the barometric pressure sensor itself diagnoses no abnormality including barometric pressure measurement values ​​within a first preset range.

7. The method according to claim 1, characterized in that, The step of determining whether the sensor is faulty based on the comparison result includes: When the deviation exceeds the diagnostic threshold and the temperature sensor itself diagnoses no abnormality, the pressure sensor is determined to be faulty; wherein, the temperature sensor itself diagnoses no abnormality including the temperature measurement value being within a second preset range.

8. A fault diagnosis device for a sensor, characterized in that, include: The acquisition unit is used to synchronously acquire the air pressure and temperature measurements inside the smart battery via wireless communication. The construction unit is used to establish a physical model of the gas inside the battery based on the ideal gas law, and to calculate the theoretical gas pressure value at the current temperature based on the temperature measurement value. The calculation unit is used to calculate the deviation between the measured air pressure value and the theoretical air pressure value, and compare the deviation with a preset diagnostic threshold. The judgment unit is used to determine whether the sensor is faulty based on the comparison result.

9. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-7.

Images