Visual-based in-vehicle pressure data management system and method

Abstract

The application discloses a visual-based vehicle-mounted pressure data management system and method, relates to the technical field of visual pressure data analysis, and comprises the following steps: collecting display data of vehicle tire pressure in history, obtaining a first influence factor set influencing the display of vehicle tire pressure through analysis; a first deviation threshold; obtaining data records of deviation of vehicle tire pressure display in history, analyzing effective parameters having a causal relationship with the influence factors, obtaining a second effective parameter set, and calculating a second effective threshold of the display deviation; judging whether deviation occurs according to the first deviation threshold, and performing first deviation early warning on the vehicle tire pressure with deviation; calculating an effective evaluation value of the first deviation early warning according to the effective parameters, and judging whether the effective evaluation value is reliable according to the second effective threshold. The application solves the problems of poor pertinence, many interference terms and unreliable early warning in the prior art, and provides stronger technical support for driving safety.

Description

Technical Field

[0001] This invention relates to the field of visual pressure data analysis technology, specifically a visual vehicle-mounted pressure data management system and method. Background Technology

[0002] Tire Pressure Monitoring System (TPMS) is a core component of automotive active safety. Its main function is to collect tire pressure data in real time, visualize it on the vehicle terminal, and provide feedback on tire pressure status to the driver, thus avoiding safety risks such as accelerated wear, brake fade, and tire blowout caused by abnormal tire pressure. With the upgrading of automobiles to be more intelligent and connected, drivers have higher requirements for the data display accuracy and warning reliability of TPMS. They not only need real-time tire pressure feedback, but also accurate identification of display deviations and prevention of drivers misjudging vehicle conditions.

[0003] Current TPMS tire pressure monitoring systems have four major technical flaws, making them unsuitable for complex driving scenarios: One-sided consideration of influencing factors: The mainstream approach adopts a fixed threshold comparison mode, relying solely on the difference between measured values ​​and standard values ​​to judge deviations, or only introducing a single environmental factor to correct the threshold. It fails to systematically sort out multiple influencing factors such as road surface smoothness, slope, humidity, altitude, tire wear, and sensor aging, lacks quantitative screening and coupling analysis, and the deviation judgment is not targeted enough.

[0004] The threshold settings lack scientific basis: the judgment thresholds are mostly based on empirical values ​​or simple averages, without in-depth mining of historical driving data or modeling and optimization in combination with different road conditions. They cannot adapt to dynamic changes in operating conditions and are prone to deviations, misjudgments, and omissions.

[0005] The parameter verification mechanism is missing: the causal relationship verification of the influencing factors has not been carried out, and it is impossible to distinguish between core effective parameters and instantaneous interference items (such as short-term gusts), which leads to the inclusion of a large amount of redundant interference data in the early warning model, significantly reducing the accuracy of judgment.

[0006] The credibility of early warnings is not verified by a second time: the early warning is triggered directly after a single judgment deviation, without excluding sudden problems such as instantaneous sensor failure and data transmission interference. This can easily generate false alarms, which not only erode the driver's trust, but also cover up the real tire pressure abnormality and create hidden safety hazards.

[0007] In summary, existing technologies have shortcomings such as weak targeting, rigid thresholds, redundant interference, and unreliable early warnings, and cannot meet the needs of precise security management in complex scenarios. Summary of the Invention

[0008] The purpose of this invention is to provide a visualization-based vehicle pressure data management system and method to solve the problems raised in the prior art.

[0009] To achieve the above objectives, the present invention provides the following technical solution: a visualization-based method for managing vehicle pressure data, specifically comprising the following steps: Step S1: Collect historical data on vehicle tire pressure display, analyze the fluctuations of several predetermined routes to obtain candidate influencing factors, and perform correlation analysis on the candidate influencing factors to obtain a first set of influencing factors affecting vehicle tire pressure display. Step S2: Calculate the first deviation threshold for judging whether the vehicle tire pressure display has deviated, based on the influence factor values ​​of the vehicle tire pressure display in history. Step S3: Obtain historical data records of deviations in vehicle tire pressure display, analyze the correlation between all data and influencing factors, obtain effective parameters that have a causal relationship with the influencing factors, obtain a second set of effective parameters, and calculate a second effective threshold for the deviation. Step S4: For the visually displayed vehicle tire pressure, determine whether a deviation has occurred based on the first deviation threshold, and issue a first deviation warning for the vehicle tire pressure that has a deviation. Step S5: Calculate the effective evaluation value of the first deviation warning based on the effective parameters, and determine whether it is reliable based on the second effective threshold.

[0010] Furthermore, the vehicle tire pressure display data collected in the historical data is analyzed to extract the influencing factors affecting the vehicle tire pressure display, resulting in a first set of influencing factors, specifically: Step S1-1: Collect historical tire pressure data of vehicles by category; among which, normal display data is recorded as... ; where a1, a i and a I These represent the 1st, i-th, and I-th normal display data values, respectively; i represents the index of the data value; similarly, the display data with deviations is denoted as... b1, b i and b I These represent the 1st, i-th, and Ith displayed data values ​​that have deviations, respectively. Step S1-2: Perform m data collections. Using the I normal display data values ​​and I display data values ​​with deviations obtained from the m collections as a base, calculate the average fluctuation of the vehicle tire pressure display for each collection. The calculation formula is as follows: Where q represents the average fluctuation of the vehicle's tire pressure display in a single instance; M represents the number of factors influencing the deviation of the vehicle's tire pressure display. Step S1-3: Obtain the average fluctuation of vehicle tire pressure display on different predetermined routes according to the method in step S1-2, and denot it as... ;q 1 q iand q I These represent the average fluctuations in tire pressure readings of vehicles on the 1st, jth, and Jth predetermined routes, respectively. Steps S1-4: Eliminate the average fluctuation of vehicle tire pressure display in the J predetermined routes, screen several predetermined routes with average fluctuation greater than a preset threshold, count the influencing factors that cause deviation in vehicle tire pressure display, record them as candidate influencing factors, and further perform correlation analysis to obtain influencing factors.

[0011] Furthermore, in steps S1-4, correlation analysis is performed to obtain influencing factors, specifically including the following steps: Step S1-4-1: Extract the historical value sequence for each candidate influencing factor xs: X={xs1,xs2,...,xsZ}, where Z represents the length of the value sequence; xsZ represents the Zth value in the historical value sequence of the candidate influencing factor xs; the corresponding tire pressure deviation sequence is obtained synchronously: Y={y1,y2,...,yZ}, where yZ represents the Zth tire pressure display deviation value at the time of sampling; Step S1-4-2: Calculate the correlation coefficient between the candidate influencing factor xs and the tire pressure deviation using the Pearson correlation coefficient method, denoted as R(xs); Step S1-4-3: Calculate the index S(xs) that measures the responsiveness of changes in influencing factors to changes in tire pressure deviation: S(xs) = Σ t=1 t=Z |Δyt / Δxst+ξ| / Z; t represents the sequence value identifier; ξ is a minimal constant to prevent the denominator from being zero; Δyt represents the absolute difference between two consecutive tire pressure deviation values ​​in the tire pressure deviation sequence; Δxst represents the absolute difference between two consecutive candidate influencing factor values ​​in the historical value sequence; Step S1-4-4: Standardize the correlation coefficient R(xs) and the response index S(xs). The standardized correlation coefficient and response index are represented as: R(xs) * And S(xs) * A contribution model is constructed, and the contribution of candidate influencing factor xs is W(xs) = F1 × R(xs). * +F2×S(xs) * F1 and F2 are weighting factors; F1 + F2 = 1; Step S1-4-5: Select the top K influencing factors according to their contribution from largest to smallest, and construct the first set of influencing factors: ; where p 1 p k and p K These represent the 1st, kth, and Kth influencing factors, respectively, with k indicating the number of influencing factors.

[0012] Furthermore, based on the influencing factor values ​​of historical vehicle tire pressure displays, a first deviation threshold is calculated to determine whether a deviation has occurred in the vehicle tire pressure display. Specifically: Step S2-1: Obtain the influencing factor values ​​of vehicle tire pressure display in history, where the k-th influencing factor is represented as: Where p1, pM, and pm represent the influence factor values ​​of the 1st, Mth, and mth deviations in the vehicle tire pressure display, respectively; M represents the number of times the sample was collected. Step S2-2: Based on the historical influencing factor values ​​of vehicle tire pressure display, calculate the first deviation threshold G1 used to determine whether there is a deviation in the vehicle tire pressure display, characterized as: .

[0013] Furthermore, in step S3, historical data records of deviations in vehicle tire pressure displays are obtained, and the correlation between all data and influencing factors is analyzed to obtain effective parameters that have a causal relationship with the influencing factors, thus obtaining a second set of effective parameters, specifically: Step S3-1: Obtain the environmental factors that caused deviations in vehicle tire pressure displays in the past. Using the environmental factors as independent variables and the influencing factors as variables, obtain a linear regression model of the influencing factors by fitting the data values. The expression of the linear regression model is denoted as: p'=α*h env +β; where p' represents the regression predicted value of the influencing factor; h env α represents the independent variable; β and α represent the slope and intercept of the regression model, respectively. Step S3-2: Calculate the regression predicted value for each influencing factor, and obtain the difference between the measured value and the regression predicted value for each influencing factor using historical data; denoted as: ; where s1, s k and s K This represents the difference between the measured values ​​and the regression predicted values ​​of the 1st, kth, and Kth influencing factors; Step S3-3: Set a change threshold s0. Record the environmental factors corresponding to the linear regression model that exceed the change threshold s0 as effective parameters, thus obtaining the second set of effective parameters, characterized as... ; where d1, d u and d U This indicates the 1st, u, and Uth valid parameters.

[0014] Furthermore, the calculation reveals a second effective threshold for the occurrence of deviation, specifically: Obtain the effective parameter values ​​from historical data when vehicle tire pressure displays deviated; calculate the second effective threshold G2 for the displayed deviation, characterized as: Where d represents the valid parameter value when the vehicle tire pressure display deviated in history; U represents the total number of valid parameters.

[0015] Furthermore, in step S4, the displayed vehicle tire pressure is assessed based on a first deviation threshold to determine if a deviation has occurred. A first deviation warning is then issued for vehicle tire pressures showing deviations. Specifically: For the influence factor value T(p) of the real-time visualized vehicle tire pressure, according to the first deviation threshold G1 calculated in step S2-2, if T(p)≥G1, it is determined that the vehicle tire pressure display has deviated and a first deviation warning is issued; if T(p)<G1, it is determined that the vehicle tire pressure display is normal.

[0016] Furthermore, in step S5, the effective evaluation value of the first deviation warning is calculated based on the effective parameters, and its reliability is determined based on the second effective threshold, specifically as follows: Step S5-1: After the first deviation warning occurs, construct a linear regression model of the influencing factors according to the method in step S3, and obtain all effective parameters of the influencing factor value T(p) of the vehicle tire pressure displayed in real time, denoted as: [Characteristic of...] ; where d1, d v and d V The first, v, and V effective parameters represent the influence factor value T(p) of the vehicle tire pressure displayed in real time; Step S5-2: Calculate the effective evaluation value G2' of the first deviation warning based on the 1st, vth, and Vth effective parameters of the influencing factor value T(p) of the vehicle tire pressure displayed in real-time visualization, characterized as: ; Step S5-3: According to the second effective threshold G2, when G2'≥G2, the first deviation warning is determined to be effective; when G2'<G2, the first deviation warning is determined to be within the deviation range, and the first deviation warning is not issued.

[0017] A visualization-based vehicle pressure data management system includes a vehicle pressure data acquisition module, a deviation analysis module, an effective analysis module, and an early warning module. The vehicle pressure data acquisition module is used to acquire historical tire pressure data and collect real-time display data. The deviation analysis module is used to analyze the data, extract the influencing factors that affect the vehicle tire pressure display, obtain the first set of influencing factors, and calculate the first deviation threshold for judging whether the vehicle tire pressure display has deviated based on the influencing factor values ​​in the history of vehicle tire pressure display. The effective analysis module is used to acquire historical data records of deviations in vehicle tire pressure display, analyze the correlation between all data and influencing factors, obtain effective parameters that have a causal relationship with the influencing factors, obtain a second set of effective parameters, and calculate a second effective threshold for the deviation. The early warning module is used to determine whether a deviation has occurred based on the visually displayed vehicle tire pressure according to a first deviation threshold, and to issue a first deviation warning for vehicle tire pressures that have deviated; it also calculates an effective evaluation value for the first deviation warning based on effective parameters, and determines whether it is reliable based on a second effective threshold.

[0018] Furthermore, it also includes a visualization display module; the visualization display module is used to display the vehicle tire pressure and linear regression model in real time.

[0019] Compared with existing technologies, the beneficial effects of this invention are: This invention has significant comprehensive value in the field of vehicle tire pressure display deviation judgment and early warning. Its core advantage lies in the performance improvement brought about by multi-dimensional technological innovation: by classifying and collecting historical tire pressure display data and combining it with the average fluctuation pattern of tire pressure on different predetermined routes, high-frequency key influencing factors affecting tire pressure display deviation are screened out. The combined effect of multiple dimensions such as driving route characteristics, environmental conditions, and sensor status is quantitatively analyzed, effectively solving the problem of one-sided judgment caused by existing technologies considering only a single factor or empirical factors, and significantly improving the pertinence and comprehensiveness of deviation identification; based on Historical influencing factor data is used to calculate the first deviation threshold through statistical modeling. Simultaneously, a second effective threshold is obtained by normalizing the effective parameters. This overcomes the limitations of fixed or empirical thresholds in existing technologies, allowing the threshold to fully incorporate historical driving data, route fluctuation patterns, and effective parameter characteristics. It adapts to the dynamic changes in different driving scenarios and operating conditions, avoiding misjudgments and omissions caused by a "one-size-fits-all" threshold. This achieves scientific dynamic optimization and precise adaptation of the deviation threshold. A linear regression model is used to construct the causal relationship between environmental factors and influencing factors, quantifying the difference between measured values ​​and regression predictions, and screening out deviations related to tire pressure display. By eliminating the influence of irrelevant factors such as instantaneous environmental interference and data transmission noise in the effective parameters of direct causality, the deviation judgment model focuses on core variables, further improving the accuracy and stability of the judgment results. A secondary evaluation mechanism for warning credibility is added. This mechanism calculates the effective evaluation value of the warning through real-time effective parameters and compares it with a second effective threshold for verification. This effectively identifies false deviation signals caused by instantaneous sensor malfunctions and data transmission interference, solving the problem of false alarms caused by the existing technology's "one-judgment-one-warning" approach. This increases the driver's trust in warning information and prevents the driver from ignoring real tire pressure abnormalities due to false alarms, thus enhancing driving safety. It provides reliable assurance; the entire solution, through a full-process design of historical data mining, multi-factor quantitative analysis, causal relationship verification, and dual threshold verification, enables TPMS to achieve an intelligent closed-loop capability of "deviation identification - threshold adaptation - effective verification - reliable early warning" through software algorithm optimization alone, without increasing hardware costs. It has strong compatibility and high practical value, and can be adapted to different types of vehicle TPMS systems, significantly enhancing the system's intelligence level and market application prospects. It comprehensively solves the problems of poor targeting, unscientific thresholds, multiple interference factors, and unreliable early warning in existing technologies, providing stronger technical support for driving safety. Attached Figure Description

[0020] Figure 1 This is a flowchart illustrating a visualization-based vehicle pressure data management method according to the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] Example: Figure 1 As shown, the present invention provides a technical solution, a method for managing vehicle pressure data based on visualization, which specifically includes the following steps: Step S1: Collect historical data on vehicle tire pressure display, analyze the fluctuations of several predetermined routes to obtain candidate influencing factors, and perform correlation analysis on the candidate influencing factors to obtain a first set of influencing factors affecting vehicle tire pressure display. Step S2: Calculate the first deviation threshold for judging whether the vehicle tire pressure display has deviated, based on the influence factor values ​​of the vehicle tire pressure display in history. Step S3: Obtain historical data records of deviations in vehicle tire pressure display, analyze the correlation between all data and influencing factors, obtain effective parameters that have a causal relationship with the influencing factors, obtain a second set of effective parameters, and calculate a second effective threshold for the deviation. Step S4: For the visually displayed vehicle tire pressure, determine whether a deviation has occurred based on the first deviation threshold, and issue a first deviation warning for the vehicle tire pressure that has a deviation. Step S5: Calculate the effective evaluation value of the first deviation warning based on the effective parameters, and determine whether it is reliable based on the second effective threshold.

[0023] Furthermore, the vehicle tire pressure display data collected in the historical data is analyzed to extract the influencing factors affecting the vehicle tire pressure display, resulting in a first set of influencing factors, specifically: Step S1-1: Collect historical tire pressure data of vehicles by category; among which, normal display data is recorded as... ; where a1, a i and a I These represent the 1st, i-th, and I-th normal display data values, respectively; i represents the index of the data value; similarly, the display data with deviations is denoted as... b1, b i and b I These represent the 1st, i-th, and Ith displayed data values ​​that have deviations, respectively. Step S1-2: Perform m data collections. Using the I normal display data values ​​and I display data values ​​with deviations obtained from the m collections as a base, calculate the average fluctuation of the vehicle tire pressure display for each collection. The calculation formula is as follows: Where q represents the average fluctuation of the vehicle's tire pressure display in a single instance; M represents the number of factors influencing the deviation of the vehicle's tire pressure display. Step S1-3: Obtain the average fluctuation of vehicle tire pressure display on different predetermined routes according to the method in step S1-2, and denot it as... ;q 1 q i and q I These represent the average fluctuations in tire pressure readings of vehicles on the 1st, jth, and Jth predetermined routes, respectively. Steps S1-4: Eliminate the average fluctuation of vehicle tire pressure display in the J predetermined routes, screen several predetermined routes with average fluctuation greater than a preset threshold, count the influencing factors that cause deviation in vehicle tire pressure display, record them as candidate influencing factors, and further perform correlation analysis to obtain influencing factors.

[0024] Furthermore, in steps S1-4, correlation analysis is performed to obtain influencing factors, specifically including the following steps: Step S1-4-1: Extract the historical value sequence for each candidate influencing factor xs: X={xs1,xs2,...,xsZ}, where Z represents the length of the value sequence; xsZ represents the Zth value in the historical value sequence of the candidate influencing factor xs; the corresponding tire pressure deviation sequence is obtained synchronously: Y={y1,y2,...,yZ}, where yZ represents the Zth tire pressure display deviation value at the time of sampling; Step S1-4-2: Calculate the correlation coefficient between the candidate influencing factor xs and the tire pressure deviation using the Pearson correlation coefficient method, denoted as R(xs); Step S1-4-3: Calculate the index S(xs) that measures the responsiveness of changes in influencing factors to changes in tire pressure deviation: S(xs) = Σ t=1 t=Z |Δyt / Δxst+ξ| / Z; t represents the sequence value identifier; ξ is a minimal constant to prevent the denominator from being zero; Δyt represents the absolute difference between two consecutive tire pressure deviation values ​​in the tire pressure deviation sequence; Δxst represents the absolute difference between two consecutive candidate influencing factor values ​​in the historical value sequence; Step S1-4-4: Standardize the correlation coefficient R(xs) and the response index S(xs). The standardized correlation coefficient and response index are represented as: R(xs) * And S(xs) *A contribution model is constructed, and the contribution of candidate influencing factor xs is W(xs) = F1 × R(xs). * +F2×S(xs) * F1 and F2 are weighting factors; F1 + F2 = 1; Step S1-4-5: Select the top K influencing factors according to their contribution from largest to smallest, and construct the first set of influencing factors: ; where p 1 p k and p K These represent the 1st, kth, and Kth influencing factors, respectively, with k indicating the number of influencing factors.

[0025] Furthermore, based on the influencing factor values ​​of historical vehicle tire pressure displays, a first deviation threshold is calculated to determine whether a deviation has occurred in the vehicle tire pressure display. Specifically: Step S2-1: Obtain the influencing factor values ​​of vehicle tire pressure display in history, where the k-th influencing factor is represented as: Where p1, pM, and pm represent the influence factor values ​​of the 1st, Mth, and mth deviations in the vehicle tire pressure display, respectively; M represents the number of times the sample was collected. Step S2-2: Based on the historical influencing factor values ​​of vehicle tire pressure display, calculate the first deviation threshold G1 used to determine whether there is a deviation in the vehicle tire pressure display, characterized as: .

[0026] Furthermore, in step S3, historical data records of deviations in vehicle tire pressure displays are obtained, and the correlation between all data and influencing factors is analyzed to obtain effective parameters that have a causal relationship with the influencing factors, thus obtaining a second set of effective parameters, specifically: Step S3-1: Obtain the environmental factors that caused deviations in vehicle tire pressure displays in the past. Using the environmental factors as independent variables and the influencing factors as variables, obtain a linear regression model of the influencing factors by fitting the data values. The expression of the linear regression model is denoted as: p'=α*h env +β; where p' represents the regression predicted value of the influencing factor; h env α represents the independent variable; β and α represent the slope and intercept of the regression model, respectively. Step S3-2: Calculate the regression predicted value for each influencing factor, and obtain the difference between the measured value and the regression predicted value for each influencing factor using historical data; denoted as: ; where s1, s k and s K This represents the difference between the measured values ​​and the regression predicted values ​​of the 1st, kth, and Kth influencing factors; Step S3-3: Set a change threshold s0. Record the environmental factors corresponding to the linear regression model that exceed the change threshold s0 as effective parameters, thus obtaining the second set of effective parameters, characterized as... ; where d1, d u and d U This indicates the 1st, u, and Uth valid parameters.

[0027] In this embodiment, the parameters of the linear regression model are calculated using the least squares method, specifically as follows: Where, e represents the number of environmental factors that caused deviations in the vehicle's tire pressure display during historical data collection; h env The independent variable is an environmental factor in this embodiment, including temperature, humidity, air pressure, etc. This indicates the collected impact factor values; This represents the average value of the influence factors; It represents the average value of the independent variable; ; It should be noted that this model is a single-fit model, and several environmental factors need to be modeled separately. In an embodiment of the present invention, the displayed tire pressure data of vehicles in the historical data is collected in categories; normal displayed data is recorded as follows: ; where a1, a i and a I These represent the 1st, i-th, and I-th normal display data values, respectively; i represents the index of the data value; similarly, the display data with deviations is denoted as... b1, b i and b I Let represent the 1st, i-th, and I-th displayed data values ​​with deviations, respectively. m data collections are performed. Using the I normal displayed data values ​​and I deviated displayed data values ​​obtained from the m collections as a base, the average fluctuation of the vehicle tire pressure display for each collection is calculated. The calculation formula is as follows: Where q represents the average fluctuation of the vehicle's tire pressure display in a single instance; M represents the number of factors influencing the deviation of the vehicle's tire pressure display. The reason for conducting m data collections is to prevent the influence of accidental factors. Analysis shows that the influencing factors include temperature, air pressure, and vehicle speed. Furthermore, the calculation reveals a second effective threshold for the occurrence of deviation, specifically: Obtain the effective parameter values ​​from historical data when vehicle tire pressure displays deviated; calculate the second effective threshold G2 for the displayed deviation, characterized as: Where d represents the valid parameter value when the vehicle tire pressure display deviated in history; U represents the total number of valid parameters.

[0028] It should be noted that when calculating the second effective threshold where the deviation occurs, the historical average value of each effective parameter needs to be calculated separately, then normalized, and then the second effective threshold is calculated using the method described above. The normalization method can be the Max-Min method or the Z-score method, or other methods that can achieve normalization, and there are no restrictions here.

[0029] Furthermore, in step S4, the displayed vehicle tire pressure is assessed based on a first deviation threshold to determine if a deviation has occurred. A first deviation warning is then issued for vehicle tire pressures showing deviations. Specifically: For the influence factor value T(p) of the real-time visualized vehicle tire pressure, according to the first deviation threshold G1 calculated in step S2-2, if T(p)≥G1, it is determined that the vehicle tire pressure display has deviated and a first deviation warning is issued; if T(p)<G1, it is determined that the vehicle tire pressure display is normal.

[0030] Furthermore, in step S5, the effective evaluation value of the first deviation warning is calculated based on the effective parameters, and its reliability is determined based on the second effective threshold, specifically as follows: Step S5-1: After the first deviation warning occurs, construct a linear regression model of the influencing factors according to the method in step S3, and obtain all effective parameters of the influencing factor value T(p) of the vehicle tire pressure displayed in real time, denoted as: [Characteristic of...] ; where d1, d v and d V The first, v, and V effective parameters represent the influence factor value T(p) of the vehicle tire pressure displayed in real time; Step S5-2: Calculate the effective evaluation value G2' of the first deviation warning based on the 1st, vth, and Vth effective parameters of the influencing factor value T(p) of the vehicle tire pressure displayed in real-time visualization, characterized as: ; Step S5-3: According to the second effective threshold G2, when G2'≥G2, the first deviation warning is determined to be effective; when G2'<G2, the first deviation warning is determined to be within the deviation range, and the first deviation warning is not issued.

[0031] A visualization-based vehicle pressure data management system includes a vehicle pressure data acquisition module, a deviation analysis module, an effective analysis module, and an early warning module. The vehicle pressure data acquisition module is used to acquire historical tire pressure data and collect real-time display data. The deviation analysis module is used to analyze the data, extract the influencing factors that affect the vehicle tire pressure display, obtain the first set of influencing factors, and calculate the first deviation threshold for judging whether the vehicle tire pressure display has deviated based on the influencing factor values ​​in the history of vehicle tire pressure display. The effective analysis module is used to acquire historical data records of deviations in vehicle tire pressure display, analyze the correlation between all data and influencing factors, obtain effective parameters that have a causal relationship with the influencing factors, obtain a second set of effective parameters, and calculate a second effective threshold for the deviation. The warning module is used to determine whether a deviation has occurred based on the visually displayed vehicle tire pressure according to a first deviation threshold, and to issue a first deviation warning for vehicle tire pressures that have deviated; it also calculates the effective evaluation value of the first deviation warning based on effective parameters, and determines whether it is reliable based on a second effective threshold.

[0032] Furthermore, it also includes a visualization display module; the visualization display module is used to display the vehicle tire pressure and linear regression model in real time.

[0033] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A visualization-based method for managing vehicle-mounted pressure data, characterized in that: Specifically, the steps include the following: Step S1: Collect historical data on vehicle tire pressure display, analyze the fluctuations of several predetermined routes to obtain candidate influencing factors, and perform correlation analysis on the candidate influencing factors to obtain a first set of influencing factors affecting vehicle tire pressure display. Step S2: Calculate the first deviation threshold for judging whether the vehicle tire pressure display has deviated, based on the influence factor values ​​of the vehicle tire pressure display in history. Step S3: Obtain historical data records of deviations in vehicle tire pressure display, analyze the correlation between all data and influencing factors, obtain effective parameters that have a causal relationship with the influencing factors, obtain a second set of effective parameters, and calculate a second effective threshold for the deviation. Step S4: For the visually displayed vehicle tire pressure, determine whether a deviation has occurred based on the first deviation threshold, and issue a first deviation warning for the vehicle tire pressure that has a deviation. Step S5: Calculate the effective evaluation value of the first deviation warning based on the effective parameters, and determine whether it is reliable based on the second effective threshold.

2. The method for managing vehicle pressure data based on visualization according to claim 1, characterized in that: The data on vehicle tire pressure display collected in the historical data is analyzed to extract the influencing factors affecting the display of vehicle tire pressure, resulting in a first set of influencing factors, specifically: Step S1-1: Collect historical tire pressure data of vehicles by category; among which, normal display data is recorded as... ; where a1, a i and a I These represent the 1st, i-th, and I-th normal display data values, respectively; i represents the index of the data value; similarly, the display data with deviations is denoted as... b1, b i and b I These represent the 1st, i-th, and Ith displayed data values ​​that have deviations, respectively. Step S1-2: Perform m data collections. Using the I normal display data values ​​and I display data values ​​with deviations obtained from the m collections as a base, calculate the average fluctuation of the vehicle tire pressure display for each collection. The calculation formula is as follows: Where q represents the average fluctuation of the vehicle's tire pressure display in a single instance; M represents the number of factors influencing the deviation of the vehicle's tire pressure display. Step S1-3: Obtain the average fluctuation of vehicle tire pressure display on different predetermined routes according to the method in step S1-2, and denot it as... ;q 1 q i and q I These represent the average fluctuations in tire pressure readings of vehicles on the 1st, jth, and Jth predetermined routes, respectively. Steps S1-4: Eliminate the average fluctuation of vehicle tire pressure display in the J predetermined routes, screen several predetermined routes with average fluctuation greater than a preset threshold, count the influencing factors that cause deviation in vehicle tire pressure display, record them as candidate influencing factors, and further perform correlation analysis to obtain influencing factors.

3. The method for managing vehicle pressure data based on visualization according to claim 2, characterized in that: In steps S1-4, correlation analysis is performed to obtain influencing factors, specifically including the following steps: Step S1-4-1: Extract the historical value sequence for each candidate influencing factor xs: X={xs1,xs2,...,xsZ}, where Z represents the length of the value sequence; xsZ represents the Zth value in the historical value sequence of the candidate influencing factor xs; the corresponding tire pressure deviation sequence is obtained synchronously: Y={y1,y2,...,yZ}, where yZ represents the Zth tire pressure display deviation value at the time of sampling; Step S1-4-2: Calculate the correlation coefficient between the candidate influencing factor xs and the tire pressure deviation using the Pearson correlation coefficient method, denoted as R(xs); Step S1-4-3: Calculate the index S(xs) that measures the responsiveness of changes in influencing factors to changes in tire pressure deviation: S(xs) = Σ t=1 t=Z |Δyt / Δxst+ξ| / Z; t represents the sequence value identifier; ξ is a minimal constant to prevent the denominator from being zero; Δyt represents the absolute difference between two consecutive tire pressure deviation values ​​in the tire pressure deviation sequence; Δxst represents the absolute difference between two consecutive candidate influencing factor values ​​in the historical value sequence; Step S1-4-4: Standardize the correlation coefficient R(xs) and the response index S(xs). The standardized correlation coefficient and response index are represented as: R(xs) * And S(xs) * A contribution model is constructed, and the contribution of candidate influencing factor xs is W(xs) = F1 × R(xs). * +F2×S(xs) * F1 and F2 are weighting factors; F1 + F2 = 1; Step S1-4-5: Select the top K influencing factors according to their contribution from largest to smallest, and construct the first set of influencing factors: ; where p 1 p k and p K These represent the 1st, kth, and Kth influencing factors, respectively, with k indicating the number of influencing factors.

4. The method for managing vehicle pressure data based on visualization according to claim 3, characterized in that: The first deviation threshold for determining whether a deviation has occurred in the vehicle tire pressure display is calculated based on the influencing factor values ​​from historical vehicle tire pressure displays. Specifically: Step S2-1: Obtain the influencing factor values ​​of vehicle tire pressure display in history, where the k-th influencing factor is represented as: Where p1, pM, and pm represent the influence factor values ​​of the 1st, Mth, and mth deviations in the vehicle tire pressure display, respectively; M represents the number of times the sample was collected. Step S2-2: Based on the historical influencing factor values ​​of vehicle tire pressure display, calculate the first deviation threshold G1 used to determine whether there is a deviation in the vehicle tire pressure display, characterized as: .

5. The method for managing vehicle pressure data based on visualization according to claim 4, characterized in that: In step S3, historical data records of deviations in vehicle tire pressure displays are obtained, and the correlation between all data and influencing factors is analyzed to obtain effective parameters that have a causal relationship with the influencing factors, thus obtaining a second set of effective parameters, specifically: Step S3-1: Obtain the environmental factors that caused deviations in vehicle tire pressure displays in the past. Using the environmental factors as independent variables and the influencing factors as variables, obtain a linear regression model of the influencing factors by fitting the data values. The expression of the linear regression model is denoted as: p'=α*h env +β; where p' represents the regression predicted value of the influencing factor; h env α represents the independent variable; β and α represent the slope and intercept of the regression model, respectively. Step S3-2: Calculate the regression predicted value for each influencing factor, and obtain the difference between the measured value and the regression predicted value for each influencing factor using historical data; denoted as: ; where s1, s k and s K This represents the difference between the measured values ​​and the regression predicted values ​​of the 1st, kth, and Kth influencing factors; Step S3-3: Set a change threshold s0. Record the environmental factors corresponding to the linear regression model that exceed the change threshold s0 as effective parameters, thus obtaining the second set of effective parameters, characterized as... ; where d1, d u and d U This indicates the 1st, u, and Uth valid parameters.

6. The method for managing vehicle pressure data based on visualization according to claim 5, characterized in that: The calculation shows that the second effective threshold for the deviation is specifically: Obtain the effective parameter values ​​from historical data when vehicle tire pressure displays deviated; calculate the second effective threshold G2 for the displayed deviation, characterized as: Where d represents the valid parameter value when the vehicle tire pressure display deviated in history; U represents the total number of valid parameters.

7. The method for managing vehicle pressure data based on visualization according to claim 6, characterized in that: In step S4, the vehicle tire pressure displayed visually is assessed for deviation based on a first deviation threshold. A first deviation warning is issued for vehicle tire pressures showing deviation, specifically as follows: For the influence factor value T(p) of the real-time visualized vehicle tire pressure, according to the first deviation threshold G1 calculated in step S2-2, if T(p)≥G1, it is determined that the vehicle tire pressure display has deviated and a first deviation warning is issued. When T(p) < G1, the tire pressure display of the vehicle is considered normal.

8. The method for managing vehicle pressure data based on visualization according to claim 7, characterized in that: In step S5, the effective evaluation value of the first deviation warning is calculated based on the effective parameters, and its reliability is determined based on the second effective threshold. Specifically: Step S5-1: After the first deviation warning occurs, construct a linear regression model of the influencing factors according to the method in step S3, and obtain all effective parameters of the influencing factor value T(p) of the vehicle tire pressure displayed in real time, denoted as: [Characteristic of...] ; where d1, d v and d V The first, v, and V effective parameters represent the influence factor value T(p) of the vehicle tire pressure displayed in real time; Step S5-2: Calculate the effective evaluation value G2' of the first deviation warning based on the 1st, vth, and Vth effective parameters of the influencing factor value T(p) of the vehicle tire pressure displayed in real-time visualization, which is characterized as: ; Step S5-3: According to the second effective threshold G2, when G2'≥G2, the first deviation warning is determined to be effective; when G2'<G2, the first deviation warning is determined to be within the deviation range, and the first deviation warning is not issued.

9. A visualization-based vehicle pressure data management system, characterized in that: It includes an on-board pressure data acquisition module, a deviation analysis module, an effective analysis module, and an early warning module; The vehicle pressure data acquisition module is used to acquire historical tire pressure data and collect real-time display data. The deviation analysis module is used to analyze the data, extract the influencing factors that affect the vehicle tire pressure display, obtain the first set of influencing factors, and calculate the first deviation threshold for judging whether the vehicle tire pressure display has deviated based on the influencing factor values ​​in the history of vehicle tire pressure display. The effective analysis module is used to acquire historical data records of deviations in vehicle tire pressure display, analyze the correlation between all data and influencing factors, obtain effective parameters that have a causal relationship with the influencing factors, obtain a second set of effective parameters, and calculate a second effective threshold for the deviation. The early warning module is used to determine whether a deviation has occurred based on the visually displayed vehicle tire pressure according to a first deviation threshold, and to issue a first deviation warning for vehicle tire pressures that have deviated; it also calculates an effective evaluation value for the first deviation warning based on effective parameters, and determines whether it is reliable based on a second effective threshold.

10. A vehicle-mounted pressure data management system based on visualization according to claim 9, characterized in that: It also includes a visualization module; the visualization module is used to display vehicle tire pressure and linear regression model in real time.

Images