A vehicle maintenance state intelligent prediction method based on user big data analysis

Abstract

This invention relates to the field of vehicle maintenance technology and discloses an intelligent prediction method for vehicle maintenance status based on user big data analysis. The invention compares the current maintenance status coefficient with a preset maintenance status coefficient threshold. If the current maintenance status coefficient is greater than the preset threshold, maintenance is required immediately. If the current maintenance status coefficient is not greater than the preset threshold, the invention compares the vehicle's predicted maintenance status coefficient with a preset vehicle maintenance status prediction coefficient threshold. If the predicted vehicle maintenance status coefficient is greater than the preset threshold, the invention predicts that the vehicle is at a critical point in its maintenance status. The invention also obtains the vehicle's daily driving parameters and, based on the predicted vehicle maintenance status coefficient and the preset threshold, predicts and calculates the vehicle's maintenance timeframe, allowing for advance vehicle maintenance and thus reducing potential safety hazards.

Description

Technical Field

[0001] This invention relates to the field of vehicle maintenance technology, and specifically to an intelligent prediction method for vehicle maintenance status based on user big data analysis. Background Technology

[0002] Vehicle maintenance refers to the preventative work of regularly inspecting, cleaning, replenishing, lubricating, adjusting, or replacing certain parts of a car. The vehicle braking system refers to a series of specialized devices that apply a certain force to certain parts of the car (mainly the wheels) to force braking them to a certain extent. Its main purpose is to ensure driving safety. Therefore, the braking system is crucial during regular vehicle maintenance.

[0003] In existing vehicle braking system maintenance processes, real-time parameter data of the braking system is used to determine if maintenance is needed. If the real-time parameter data exceeds a critical value, it indicates that the vehicle needs maintenance. However, since vehicles are constantly in use and each owner's driving habits and the driving environment in which each vehicle is frequently driven are different, there is a lack of prediction and feedback on the overall maintenance status of the vehicle's braking system, which poses a safety hazard to the vehicle. Therefore, this invention provides an intelligent prediction method for vehicle maintenance status based on user big data analysis. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent prediction method for vehicle maintenance status based on user big data analysis, thereby solving the above-mentioned technical problems.

[0005] The objective of this invention can be achieved through the following technical solutions:

[0006] A method for intelligent prediction of vehicle maintenance status based on user big data analysis, the method comprising the following steps:

[0007] Step S1: Monitor the real-time status parameters of the vehicle braking system at regular intervals t.

[0008] Step S2: Calculate the current maintenance status coefficient of the vehicle based on the real-time status parameters of the vehicle braking system;

[0009] Step S3: Determine the current maintenance status of the vehicle braking system based on the current maintenance status coefficient. Compare the current maintenance status coefficient with the preset maintenance status coefficient threshold. If the current maintenance status coefficient is greater than the preset maintenance status coefficient threshold, maintenance needs to be performed immediately. Otherwise, proceed to step S4.

[0010] Step S4: Obtain the historical changes of vehicle braking system parameters based on the real-time status parameters of the vehicle braking system obtained periodically;

[0011] Step S5: Calculate the vehicle's maintenance status prediction coefficient based on the historical changes in the vehicle's braking system parameters.

[0012] Step S6: Predict the vehicle's maintenance status based on the vehicle's maintenance status prediction coefficient. Compare the vehicle's maintenance status prediction coefficient with a preset vehicle maintenance status prediction coefficient threshold. If the vehicle's maintenance status prediction coefficient is greater than the preset vehicle maintenance status prediction coefficient threshold, then predict that the vehicle is at the maintenance status critical point and proceed to step S7. Otherwise, predict that the vehicle does not need maintenance at present.

[0013] Step S7: Obtain the vehicle's daily driving parameters, and predict and calculate the vehicle maintenance time limit based on the vehicle's maintenance status prediction coefficient and the preset vehicle maintenance status prediction coefficient threshold.

[0014] As a further description of the present invention, the real-time status parameters of the vehicle braking system periodically acquired in step S1 include: brake pad wear D, brake fluid level H, and brake pedal travel L.

[0015] The vehicle's daily driving parameters in step S7 include: daily driving mileage M and daily driving fuel consumption V.

[0016] As a further description of the present invention, the specific process of step S2 includes:

[0017] Obtain the current wear amount D of each brake pad in the vehicle's braking system. i Brake fluid level H and brake pedal travel L;

[0018] The current maintenance condition coefficient σ of the vehicle is calculated using the following formula:

[0019]

[0020] In the formula, α, β, and γ are preset weighting coefficients, where α > β > γ > 0, n is the total number of brake pads, n > i > 0, and i belongs to [1, n]. i D represents the wear amount of the i-th brake pad. i0 The wear amount is preset for the i-th brake pad, H is the preset brake fluid level, and L0 is the preset brake pedal travel.

[0021] As a further description of the present invention, the specific process of step S3 includes:

[0022] Compare the vehicle's current maintenance status coefficient σ with the preset maintenance status coefficient threshold σ. th In comparison, when the vehicle's current maintenance status coefficient σ is greater than the preset maintenance status coefficient threshold σ... thIf necessary, the vehicle should be maintained immediately; otherwise, the vehicle's maintenance status should be predicted.

[0023] As a further description of the present invention, the specific process of step S4 includes:

[0024] Obtain the monitored vehicle braking system state parameters for each period t, and fit the wear amount D of each brake pad in the vehicle braking system. i Function D that varies with time t i (t), brake fluid level change function H(t) and brake pedal travel change function L(t) over time;

[0025] Construct a rectangular coordinate system xoy, where the x-axis represents t. Generate the wear amount D of each brake pad in the vehicle's braking system within this rectangular coordinate system. i Function D that varies with time t i (t) curve Brake fluid level height as a function of time H(t) curve C H And the curve C of the function L(t) of brake pedal travel over time. L ;

[0026] The curve is calculated using the following formula. The area S enclosed by the x-axis 1i Curve C H The area S2 enclosed by the x-axis and the curve C L The area S3 enclosed by the x-axis:

[0027]

[0028] S 1i Substituting S2 and S3 into the following formula, the vehicle maintenance condition prediction coefficient ρ is calculated:

[0029]

[0030] In the formula, max{D i {H(t)}, max{H(t)}, and max{L(t)} are functions D, respectively. i (t), the maximum value of functions H(t) and L(t), min{D i The minimum values ​​of {H(t)}, {L(t)}, and {H(t)}.

[0031] As a further description of the present invention, the specific process of step S6 is as follows:

[0032] The vehicle maintenance condition prediction coefficient ρ is compared with the vehicle maintenance condition prediction coefficient threshold ρ. thIn comparison, when the vehicle's maintenance condition prediction coefficient ρ is greater than the preset vehicle maintenance condition prediction coefficient threshold ρ th If the forecast is positive, the vehicle maintenance timeframe is calculated; otherwise, the vehicle is predicted not to require maintenance at present.

[0033] As a further description of the present invention, the specific process of step S7 is as follows:

[0034] The vehicle maintenance time limit indicator value is calculated using a formula.

[0035]

[0036] In the formula, M0 is the preset daily standard driving mileage of the vehicle, V0 is the preset daily standard driving fuel consumption of the vehicle, and θ is the conversion coefficient.

[0037] Will The data is input into the neural network model, and the output is a suggested vehicle maintenance timeframe.

[0038] As a further description of the present invention, the neural network model is a BP selection network model trained based on historical data.

[0039] The beneficial effects of this invention are:

[0040] This invention monitors the real-time status parameters of the vehicle's braking system at regular intervals t. Then, it calculates the vehicle's current maintenance status coefficient based on these parameters and compares it with a preset maintenance status coefficient threshold. If the current maintenance status coefficient is greater than the threshold, immediate maintenance is required. If the current maintenance status coefficient is not greater than the threshold, a vehicle maintenance status prediction coefficient is calculated based on historical changes in the vehicle's braking system parameters. This prediction coefficient is then compared with a preset vehicle maintenance status prediction coefficient threshold. If the predicted coefficient is greater than the threshold, the vehicle is predicted to be at a critical maintenance point. The invention also obtains the vehicle's daily driving parameters and, based on the predicted and threshold values, predicts the vehicle's maintenance timeframe, allowing for early maintenance and reducing potential safety hazards. Attached Figure Description

[0041] The invention will now be further described with reference to the accompanying drawings.

[0042] Figure 1 This is a partial flowchart of the intelligent prediction method for vehicle maintenance status based on user big data analysis provided by the present invention. Detailed Implementation

[0043] 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.

[0044] Please see Figure 1 This invention relates to an intelligent prediction method for vehicle maintenance status based on user big data analysis, the method comprising the following steps:

[0045] Step S1: Monitor the real-time status parameters of the vehicle braking system at regular intervals t.

[0046] Step S2: Calculate the current maintenance status coefficient of the vehicle based on the real-time status parameters of the vehicle braking system;

[0047] Step S3: Determine the current maintenance status of the vehicle braking system based on the current maintenance status coefficient. Compare the current maintenance status coefficient with the preset maintenance status coefficient threshold. If the current maintenance status coefficient is greater than the preset maintenance status coefficient threshold, maintenance needs to be performed immediately. Otherwise, proceed to step S4.

[0048] Step S4: Obtain the historical changes of vehicle braking system parameters based on the real-time status parameters of the vehicle braking system obtained periodically;

[0049] Step S5: Calculate the vehicle's maintenance status prediction coefficient based on the historical changes in the vehicle's braking system parameters.

[0050] Step S6: Predict the vehicle's maintenance status based on the vehicle's maintenance status prediction coefficient. Compare the vehicle's maintenance status prediction coefficient with a preset vehicle maintenance status prediction coefficient threshold. If the vehicle's maintenance status prediction coefficient is greater than the preset vehicle maintenance status prediction coefficient threshold, then predict that the vehicle is at the maintenance status critical point and proceed to step S7. Otherwise, predict that the vehicle does not need maintenance at present.

[0051] Step S7: Obtain the vehicle's daily driving parameters, and predict and calculate the vehicle maintenance time limit based on the vehicle's maintenance status prediction coefficient and the preset vehicle maintenance status prediction coefficient threshold.

[0052] Through the above technical solution, this invention monitors the real-time status parameters of the vehicle's braking system at regular intervals t, then calculates the vehicle's current maintenance status coefficient based on the real-time status parameters of the vehicle's braking system. The current maintenance status coefficient is compared with a preset maintenance status coefficient threshold. If the current maintenance status coefficient is greater than the preset maintenance status coefficient threshold, maintenance needs to be performed immediately. If the current maintenance status coefficient is not greater than the preset maintenance status coefficient threshold, a vehicle maintenance status prediction coefficient is calculated based on the historical changes of the vehicle's braking system parameters. This prediction coefficient is compared with a preset vehicle maintenance status prediction coefficient threshold. If the vehicle maintenance status prediction coefficient is greater than the preset vehicle maintenance status prediction coefficient threshold, the vehicle is predicted to be at a critical point in its maintenance status. Daily driving parameters of the vehicle are obtained, and the vehicle maintenance timeframe is predicted and calculated based on the vehicle maintenance status prediction coefficient and the preset vehicle maintenance status prediction coefficient threshold, allowing for advance vehicle maintenance and thus reducing vehicle safety hazards.

[0053] As a further description of the present invention, the real-time status parameters of the vehicle braking system obtained periodically in step S1 include: brake pad wear amount D: the wear degree of the brake pads directly affects the braking performance, and the thickness of the brake pads needs to be checked periodically, and repaired or replaced when necessary.

[0054] Brake fluid level H: The brake fluid should reach the baseline of the reservoir. If the brake fluid level is significantly lower than the previous check, there is a high probability of a malfunction, such as leakage. The brake fluid level needs to be checked regularly. If the level drops significantly or the quality deteriorates, it should be added or replaced in time.

[0055] Brake pedal travel L: The travel and feel of the brake pedal directly affect the sensitivity and braking effect of the braking system. Regularly check whether the brake pedal travel is normal and make necessary adjustments.

[0056] The vehicle's daily driving parameters in step S7 include: daily driving mileage M: this refers to the average speed of the car over a specific period of time. This helps the driver understand driving efficiency and fuel consumption. Generally, the average speed is lower in urban areas and higher on highways.

[0057] Vehicle fuel consumption (V) during daily driving describes the amount of fuel a car consumes over a certain distance. Fuel consumption is affected by various factors, including driving habits, road conditions, vehicle load, and the vehicle's performance.

[0058] As a further description of the present invention, the specific process of step S2 includes:

[0059] Obtain the current wear amount D of each brake pad in the vehicle's braking system. i Brake fluid level H and brake pedal travel L;

[0060] The current maintenance condition coefficient σ of the vehicle is calculated using the following formula:

[0061]

[0062] In the formula, α, β, and γ are preset weighting coefficients, where α > β > γ > 0, n is the total number of brake pads, n > i > 0, and i belongs to [1, n]. i D represents the wear amount of the i-th brake pad. i0 The wear amount is preset for the i-th brake pad, H is the preset brake fluid level, and L0 is the preset brake pedal travel.

[0063] As a further description of the present invention, the specific process of step S3 includes:

[0064] Compare the vehicle's current maintenance status coefficient σ with the preset maintenance status coefficient threshold σ. th In comparison, when the vehicle's current maintenance status coefficient σ is greater than the preset maintenance status coefficient threshold σ... th If necessary, the vehicle should be maintained immediately; otherwise, the vehicle's maintenance status should be predicted.

[0065] Through the above technical solution, this embodiment obtains the current wear amount D of each brake pad in the vehicle braking system. i The brake fluid level H and brake pedal travel L are then determined using the formula. Calculate the vehicle's current maintenance condition coefficient σ, where the current maintenance condition coefficient σ is related to D. i It is directly proportional to L and inversely proportional to H. The current maintenance state coefficient σ of the vehicle is compared with the preset maintenance state coefficient threshold σ. th In comparison, when the vehicle's current maintenance status coefficient σ is greater than the preset maintenance status coefficient threshold σ... th If necessary, the vehicle should be maintained immediately; otherwise, the vehicle's maintenance status should be predicted.

[0066] As a further description of the present invention, the specific process of step S4 includes:

[0067] Obtain the monitored vehicle braking system state parameters for each period t, and fit the wear amount D of each brake pad in the vehicle braking system. i Function D that varies with time t i (t), brake fluid level change function H(t) and brake pedal travel change function L(t) over time;

[0068] Construct a rectangular coordinate system xoy, where the x-axis represents t. Generate the wear amount D of each brake pad in the vehicle's braking system within this rectangular coordinate system. iFunction D that varies with time t i (t) curve Brake fluid level height as a function of time H(t) curve C H And the curve C of the function L(t) of brake pedal travel over time. L ;

[0069] The curve is calculated using the following formula. The area S enclosed by the x-axis 1i Curve C H The area S2 enclosed by the x-axis and the curve C L The area S3 enclosed by the x-axis:

[0070]

[0071] S 1i Substituting S2 and S3 into the following formula, the vehicle maintenance condition prediction coefficient ρ is calculated:

[0072]

[0073] In the formula, max{D i {H(t)}, max{H(t)}, and max{L(t)} are functions D, respectively. i (t), the maximum value of functions H(t) and L(t), min{D i The minimum values ​​of {H(t)}, {L(t)}, and {H(t)}.

[0074] As a further description of the present invention, the specific process of step S6 is as follows:

[0075] The vehicle maintenance condition prediction coefficient ρ is compared with the vehicle maintenance condition prediction coefficient threshold ρ. th In comparison, when the vehicle's maintenance condition prediction coefficient ρ is greater than the preset vehicle maintenance condition prediction coefficient threshold ρ th If the forecast is positive, the vehicle maintenance timeframe is calculated; otherwise, the vehicle is predicted not to require maintenance at present.

[0076] Using the above technical solution, this embodiment obtains the monitored vehicle braking system state parameters for each period t, and then fits the wear amount D of each brake pad in the vehicle braking system. i Function D that varies with time t i The curves for calculating the brake fluid level height as a function of time (H(t)) and the brake pedal travel as a function of time (L(t)) are given. The area S enclosed by the x-axis 1i Curve C H The area S2 enclosed by the x-axis and the curve C L The area S3 enclosed by the x-axis is then calculated using the formula. Calculate the vehicle maintenance condition prediction coefficient ρ, where Know This represents the rate of change of the three curves, all of which are proportional to the vehicle's maintenance condition prediction coefficient ρ. The vehicle's maintenance condition prediction coefficient ρ is then compared with the vehicle's maintenance condition prediction coefficient threshold ρ. th In comparison, when the vehicle's maintenance condition prediction coefficient ρ is greater than the preset vehicle maintenance condition prediction coefficient threshold ρ th If the forecast is positive, the vehicle maintenance timeframe is calculated; otherwise, the vehicle is predicted not to require maintenance at present.

[0077] As a further description of the present invention, the specific process of step S7 is as follows:

[0078] The vehicle maintenance time limit indicator value is calculated using a formula.

[0079]

[0080] In the formula, M0 is the preset daily standard driving mileage of the vehicle, V0 is the preset daily standard driving fuel consumption of the vehicle, and θ is the conversion coefficient.

[0081] Will The data is input into the neural network model, and the output is a suggested vehicle maintenance timeframe.

[0082] As a further description of the present invention, the neural network model is a BP selection network model trained based on historical data.

[0083] Through the above technical solution, based on the maintenance status prediction coefficient ρ and the maintenance status prediction coefficient threshold ρ th The difference between these values, combined with the vehicle's daily driving conditions, is used to calculate the vehicle maintenance interval indication value. Will The data is input into the neural network model, and the output is a suggested vehicle maintenance timeframe.

[0084] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the patent coverage of this invention.

Claims

1. A method for intelligent prediction of vehicle maintenance status based on user big data analysis, characterized in that, The method includes the following steps: Step S1: Monitor the real-time status parameters of the vehicle braking system at regular intervals t. Step S2: Calculate the current maintenance status coefficient of the vehicle based on the real-time status parameters of the vehicle braking system; Step S3: Determine the current maintenance status of the vehicle's braking system based on the current maintenance status coefficient, and set the vehicle's current maintenance status coefficient accordingly. Compared with the preset maintenance state coefficient threshold Comparison, when the vehicle's current maintenance status coefficient Greater than the preset maintenance status coefficient threshold If the condition is not met, maintenance must be carried out immediately; otherwise, proceed to step S4. Step S4: Obtain the historical changes of vehicle braking system parameters based on the real-time status parameters of the vehicle braking system obtained periodically; Step S5: Calculate the vehicle's maintenance status prediction coefficient based on the historical changes in the vehicle's braking system parameters. Step S6: Predict the vehicle's maintenance condition based on the vehicle's maintenance condition prediction coefficient, and then calculate the vehicle's maintenance condition prediction coefficient. Vehicle maintenance status prediction coefficient threshold Comparison, when the vehicle's maintenance condition prediction coefficient The vehicle's maintenance status prediction coefficient is greater than the preset threshold. If the vehicle is predicted to be at the critical point of maintenance, proceed to step S7; otherwise, it is predicted that the vehicle does not need maintenance at present. Step S7: Obtain the vehicle's daily driving parameters, and predict and calculate the vehicle maintenance time limit based on the vehicle's maintenance status prediction coefficient and the preset vehicle maintenance status prediction coefficient threshold. The real-time status parameters of the vehicle braking system periodically acquired in step S1 include: brake pad wear D, brake fluid level H, and brake pedal travel L. The vehicle's daily driving parameters in step S7 include: daily driving mileage M and daily driving fuel consumption V. The specific process of step S2 includes: Obtain the current wear of each brake pad in the vehicle's braking system. Brake fluid level H and brake pedal travel L; The current maintenance status coefficient of the vehicle is calculated according to the following formula. : In the formula, , and These are preset weighting coefficients, where, > > >0, where n is the total number of brake pads, n>i>0, and i belongs to [1,n]. This represents the wear amount of the i-th brake pad. Preset the wear measurement amount for the i-th brake pad. To preset the measurement of brake fluid level, To preset the measurement of brake pedal travel; The specific process of step S5 includes: The vehicle braking system state parameters are obtained at each period t, and the wear amount of each brake pad in the vehicle braking system is fitted. Function of change with time t The function H(t) for the change of brake fluid level over time and the function L(t) for the change of brake pedal travel over time; Construct a Cartesian coordinate system xoy, where the x-axis represents t. Generate the wear amount of each brake pad in the vehicle's braking system within this Cartesian coordinate system. Function of change with time t curve Brake fluid level height as a function of time, H(t) curve And the curve of the function L(t) of brake pedal travel over time ; The curve is calculated using the following formula. Area enclosed by the x-axis ,curve Area enclosed by the x-axis and curve Area enclosed by the x-axis : Will , and Substitute into the following formula to calculate the vehicle's maintenance condition prediction coefficient. : In the formula, , and functions respectively The maximum values ​​of functions H(t) and L(t). , and functions respectively Find the minimum values ​​of functions H(t) and L(t); The specific process of step S7 is as follows: The vehicle maintenance time limit indicator value is calculated using a formula. : In the formula, This is the preset standard daily mileage for the vehicle. The preset fuel consumption for daily standard driving of the vehicle. These are the conversion factors; Will The data is input into the neural network model, and the output is a suggested vehicle maintenance timeframe.

2. The intelligent prediction method for vehicle maintenance status based on user big data analysis according to claim 1, characterized in that, The neural network model is a backpropagation (BP) selection network model trained based on historical data.

Images