System and method for monitoring the coordinated state of a vehicle and a charging station in an electric vehicle charging / discharging process

Abstract

The present invention relates to the technical field of electrical variable measurement, and more particularly to a system and method for monitoring the coordinated state of a vehicle and a charging station in an electric vehicle charging and discharging process. The present invention includes a vehicle battery monitoring module for collecting vehicle battery state parameters in real time, a charging station monitoring module for monitoring charging station state parameters in real time, a monitoring module for processing the vehicle battery state parameters and the charging station state parameters and judging the charging / discharging state of the vehicle battery based on a preset formula, and a processing module for predicting the life of the vehicle battery based on the charging / discharging state of the vehicle battery, the vehicle battery state parameters and the charging station state parameters. The present invention rationally predicts the battery life through the parameters of the coordinated state of the vehicle and the charging station, and combines multiple influencing parameters to correct the prediction of the battery life, thereby accurately and effectively evaluating the battery life.

Description

[Technical field]

[0001] The present invention relates to the technical field of electrical variable measurement, and more particularly to a system and method for monitoring the coordinated state of a vehicle and a charging station in an electric vehicle charging and discharging process. [Background technology]

[0002] Electric vehicles are becoming more and more popular as battery performance improves. It is believed that the future mainstream of vehicle development will be an increase in electric vehicles year by year, replacing some internal combustion engine vehicles. At the same time, as electric vehicle technology becomes more and more mature, the management and service of electric vehicles are also becoming more standardized. Electric vehicle standards will also emerge as series and standardized latest models, and electric vehicles will bring about changes in the era of automobiles.

[0003] However, in the existing technology, it is difficult to evaluate the health state of the battery in the charging and discharging process of the electric vehicle, and the main influencing factors include the nonlinear change of the battery parameters, the change of the battery performance with the passage of time and the use environment, which makes it difficult to build an accurate mathematical model, and the randomness and unpredictability of the battery deterioration process, which means that there is currently no clear deterioration rule, and there is also the difficulty of how to effectively integrate various monitoring data and perform a rational analysis to evaluate the health state of the battery. Therefore, a system and method for monitoring the coordinated state of the vehicle and the charging station in the charging and discharging process of the electric vehicle is an urgent technical problem that needs to be solved by those skilled in the art. Summary of the Invention [Problem to be solved by the invention]

[0004] The present invention aims to provide a system and method for monitoring the coordinated state of a vehicle and a charging station in an electric vehicle charging and discharging process, which rationally predicts battery life through parameters of the coordinated state of the vehicle and the charging station, and corrects the battery life prediction by combining multiple influencing parameters, so as to accurately and effectively evaluate the battery life. [Means for solving the problem]

[0005] To achieve the above objectives, the present invention provides the following technical solutions: A system for monitoring a cooperative state between a vehicle and a charging station in an electric vehicle charging / discharging process, comprising: A vehicle battery monitoring module is used for collecting vehicle battery status parameters in real time, the vehicle battery status parameters including a battery terminal voltage Vd, a battery charge / discharge current Id and a battery temperature Td; A charging station monitoring module is used for monitoring state parameters of the charging station in real time, the state parameters of the charging station including a charging station voltage Vc, a charging station current Ic and a charging station power Pc; a data communication module used for transmitting status parameters of the vehicle battery and status parameters of the charging station through wireless communication technology; A monitoring module is used to receive the state parameters of the vehicle battery and the state parameters of the charging station, process the state parameters of the vehicle battery and the state parameters of the charging station, and judge the charge / discharge state of the vehicle battery based on a preset formula; A processing module is included which is used to predict the life of the vehicle battery based on a charge / discharge state of the vehicle battery, a state parameter of the vehicle battery and a state parameter of the charging station.

[0006] In some embodiments of the present application, the monitoring module determining the charge / discharge state of the vehicle battery based on a preset formula includes: Calculate the remaining amount of the vehicle battery based on the battery terminal voltage Vd and the battery charge and discharge current Id, and determine the charge and discharge state of the vehicle battery based on the remaining amount of the vehicle battery. The preset formula is as follows.

[0007]

Number

[0008] In the formula, SOC is the remaining amount of the vehicle battery, V bat is the terminal voltage of the vehicle battery, V min is the minimum allowable voltage of the vehicle battery, V max is the maximum allowable voltage of the vehicle battery, and when the remaining amount of the vehicle battery exceeds 50%, the vehicle battery is determined to be in a charging state. when the remaining amount of the vehicle battery is less than 50%, the vehicle battery is determined to be in a discharging state. when the remaining amount of the vehicle battery is 50%, the vehicle battery is determined to be in a fully charged state.

[0009] In some embodiments of the present application, when the monitoring module further determines that the vehicle battery is in a charging state, a charging curve is generated based on the state parameters of the charging stand, and is also used to obtain the charging speed vd of the vehicle battery based on the charging curve. The processing module is further used to predict the life of the vehicle battery based on the charging speed vd of the vehicle battery. A preset charging speed matrix T0 and a preset remaining life time matrix A are preset in the processing module. For the preset remaining life time matrix A, A(A1, A2, A3, A4) is set, where A1 is the first preset remaining life time, A2 is the second preset remaining life time, A3 is the third preset remaining life time, A4 is the fourth preset remaining life time, and A1 < A2 < A3 < A4 < 5 years. For the preset charging speed matrix T0, set T0 (T01, T02, T03, T04), where T01 is the first preset charging speed, T02 is the second preset charging speed, T03 is the third preset charging speed, T04 is the fourth preset charging speed, and T01 < T02 < T03 < T04. The processing module is used to select the corresponding remaining life time based on the relationship between vd and the preset charging speed matrix T0 as the predicted life of the vehicle battery. When vd < T01, select the fourth preset remaining life time A4 as the predicted life of the vehicle battery. When T01 ≤ vd < T02, select the third preset remaining life time A3 as the predicted life of the vehicle battery. When T02 ≤ vd < T03, select the second preset remaining life time A2 as the predicted life of the vehicle battery. When T03 ≤ vd < T04, select the first preset remaining life time A1 as the predicted life of the vehicle battery.

[0010] In some embodiments of the present application, the processing module is also used to obtain the past charging times k of the vehicle battery. The processing module is also set with a preset past charging times matrix R0 and a preset remaining life time correction coefficient matrix B. For the preset remaining life time correction coefficient matrix B, set B (B1, B2, B3, B4), where B1 is the first preset remaining life time correction coefficient, B2 is the second preset remaining life time correction coefficient, B3 is the third preset remaining life time correction coefficient, B4 is the fourth preset remaining life time correction coefficient, and 0.6 < B1 < B2 < B3 < B4 < 1. For the preset past charge count matrix R0, set R0(R01, R02, R03, R04), where R01 is the first preset past charge count, R02 is the second preset past charge count, R03 is the third preset past charge count, R04 is the fourth preset past charge count, and R01 < R02 < R03 < R04. The processing module is used to select a corresponding remaining life time correction coefficient based on the relationship between k and the preset past charge count matrix R0 to correct the remaining life time. When k < R01, the fourth preset remaining life time correction coefficient B4 is selected to correct the fourth preset remaining life time A4, and the corrected remaining life time is A4 × B4. When R01 ≤ k < R02, the third preset remaining life time correction coefficient B3 is selected to correct the third preset remaining life time A3, and the corrected remaining life time is A3 × B3. When R02 ≤ k < R03, the second preset remaining life time correction coefficient B2 is selected to correct the second preset remaining life time A2, and the corrected remaining life time is A2 × B2. When R03 ≤ k < R04, the first preset remaining life time correction coefficient B1 is selected to correct the first preset remaining life time A1, and the corrected remaining life time is A1 × B1.

[0011] In some embodiments of the present application, when the monitoring module further determines that the vehicle battery is in a discharged state, it generates a discharge curve based on the state parameters of the vehicle battery and the remaining amount of the vehicle battery, and is used to obtain the discharge rate vt of the vehicle battery based on the discharge curve. The above processing module is further set with a preset discharge rate matrix W0 and a preset remaining life time quadratic correction coefficient matrix C. For the above preset remaining life time quadratic correction coefficient matrix C, C(C1, C2, C3, C4) is set. Here, C1 is the first preset remaining life time quadratic correction coefficient, C2 is the second preset remaining life time quadratic correction coefficient, C3 is the third preset remaining life time quadratic correction coefficient, C4 is the fourth preset remaining life time quadratic correction coefficient, and 0.6 < C1 < C2 < C3 < C4 < 1. For the above preset discharge rate matrix W0, W0(W01, W02, W03, W04) is set. Here, W01 is the first preset discharge rate, W02 is the second preset discharge rate, W03 is the third preset discharge rate, W04 is the fourth preset discharge rate, and W01 < W02 < W03 < W04. The above processing module is further used to select a corresponding remaining life time quadratic correction coefficient based on the relationship between vt and the above preset discharge rate matrix W0, and perform quadratic correction on each corrected preset remaining life time. When vt < W01, the fourth preset remaining life time quadratic correction coefficient C4 is selected, and quadratic correction is performed on the corrected preset fourth remaining life time A4. The corrected remaining life time is A4 × B4 × C4. When W01 ≤ vt < W02, the third preset remaining life time quadratic correction coefficient C3 is selected, and quadratic correction is performed on the corrected preset third remaining life time A3. The corrected remaining life time is A3 × B3 × C3. When W02 ≤ vt < W03, the second preset remaining life time quadratic correction coefficient C2 is selected, and quadratic correction is performed on the corrected preset second remaining life time A2. The corrected remaining life time is A2 × B2 × C2. When W03 ≤ vt < W04, the first preset remaining life time quadratic correction coefficient C1 is selected, and quadratic correction is performed on the corrected preset first remaining life time A1. The corrected remaining life time is A1 × B1 × C1.

[0012] In some embodiments of the present application, the processing module is further adapted to perform a failure prediction for the vehicle battery based on the predicted lifespan of the vehicle battery, wherein: The processing module performing a fault prediction on the vehicle battery includes: Acquiring past state parameters of the vehicle battery, the past state parameters of the vehicle battery including a past terminal voltage of the battery, a past charge / discharge current of the battery, and a past temperature of the battery; Arranging the acquired past state parameters of the vehicle battery based on a time series, and pre-processing the arranged past state parameters; Performing learning training on the data of the past state parameters based on SVR to build a failure prediction model; predicting a fault for the vehicle battery based on the fault prediction model and state parameters of the vehicle battery; The method includes performing a residual threshold test and performing a fault warning based on a fault prediction result of the vehicle battery by the fault prediction model.

[0013] In some embodiments of the present application, pre-processing the past state parameters arranged in the processing module includes: The method includes removing outlier data in the past state parameters, interval processing the data in the past state parameters, and performing non-linear decision making on the data in the past state parameters to generate a sample format used to support vector machine learning training.

[0014] In order to achieve the above object, the present invention further provides a method for monitoring the coordinated state of a vehicle and a charging station in an electric vehicle charging and discharging process, which is applied to a monitoring system for the coordinated state of a vehicle and a charging station in an electric vehicle charging and discharging process accordingly; Collecting vehicle battery condition parameters in real time, including a battery terminal voltage Vd, a battery charge / discharge current Id, and a battery temperature Td; Monitoring the state parameters of the charging station in real time, including the charging station voltage Vc, the charging station current Ic, and the charging station power Pc; transmitting status parameters of the vehicle battery and status parameters of the charging station via wireless communication techniques; receiving the state parameters of the vehicle battery and the state parameters of the charging station, processing the state parameters of the vehicle battery and the state parameters of the charging station, and judging the charging / discharging state of the vehicle battery according to a preset formula; The method includes predicting a life of the vehicle battery based on a charge / discharge state of the vehicle battery, a state parameter of the vehicle battery, and a state parameter of the charging station.

[0015] In some embodiments of the present application, determining the state of charge / discharge of the vehicle battery based on a preset formula includes: Calculating a remaining capacity of the vehicle battery based on the battery terminal voltage Vd and the battery charge / discharge current Id, and determining a charge / discharge state of the vehicle battery based on the remaining capacity of the vehicle battery; The preset formula is as follows:

[0016]

number

[0017] In the formula, SOC is the remaining charge of the vehicle battery, V bat is the terminal voltage of the vehicle battery, V min is the minimum allowable voltage of the vehicle battery, V max is the maximum allowable voltage of the vehicle battery, Here, if the remaining charge of the vehicle battery is more than 50%, the vehicle battery is determined to be in a charging state; If the vehicle battery has a remaining charge of less than 50%, the vehicle battery is determined to be in a discharged state; If the vehicle battery has 50% remaining charge, the vehicle battery is determined to be fully charged.

[0018] In some embodiments of the present application, further comprising: performing a failure prediction for the vehicle battery based on the predicted life of the vehicle battery, wherein: To perform failure prediction on the vehicle battery, Acquiring past state parameters of the vehicle battery, the past state parameters of the vehicle battery including a past terminal voltage of the battery, a past charge / discharge current of the battery, and a past temperature of the battery; Arranging the acquired past state parameters of the vehicle battery based on a time series, and pre-processing the arranged past state parameters; Performing learning training on the data of the past state parameters based on SVR to build a failure prediction model; predicting a fault for the vehicle battery based on the fault prediction model and state parameters of the vehicle battery; The method includes performing a residual threshold test and performing a fault warning based on a fault prediction result of the vehicle battery by the fault prediction model. Effect of the Invention

[0019] The present invention provides a system and method for monitoring the coordinated state of a vehicle and a charging station in an electric vehicle charging and discharging process, and compared with the prior art, its beneficial effects are as follows: The present invention calculates the charging rate and discharging rate based on the vehicle battery state parameters and the charging station state parameters, and can reasonably predict the battery life. By combining with adaptive correction of related parameters, the battery life can be accurately evaluated, and by combining with a machine learning method, a fault warning can be provided according to the battery life. [Brief description of the drawings]

[0020] [Figure 1] 1 is a functional block diagram of a system for monitoring a coordinated state between a vehicle and a charging station in an electric vehicle charging / discharging process according to an embodiment of the present invention; [Diagram 2] 2 is a flowchart of a method for monitoring the coordination state between a vehicle and a charging station in an electric vehicle charging / discharging process according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0021] Specific embodiments of the present invention are described in more detail below with reference to figures and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0022] In the description of this application, any orientations or positional relationships indicated by the terms "center," "up," "down," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inside," "outside," etc., are based on the orientations or positional relationships shown in the drawings and are intended merely to explain and simplify the description of the application, and do not indicate or imply that a specified device or element must be configured or operated in a particular orientation or manner, and therefore should not be construed as limiting the application.

[0023] The terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying a relative importance or number of the technical features indicated. Thus, features defined as "first" and "second" may explicitly or implicitly include one or more of those features. In the present description, unless otherwise specified, "plurality" means two or more than two.

[0024] In the description of this application, unless otherwise clearly stated and limited, the terms "installed", "coupled" and "connected" should be understood in a broad sense, for example, may be fixed connection, detachable connection, integral connection, etc., may be mechanical connection or electrical connection, may be direct connection, may be indirect connection via an intermediate, or may be internal communication between two components. Those skilled in the art will be able to understand the specific meaning of the above terms in this application on a case-by-case basis.

[0025] Long charging time is one of the problems in promoting new energy vehicles. The first solution is to improve charging efficiency, that is, the so-called fast charging technology, which can replenish power to 80% in 30 minutes or 15 minutes, but the requirements for the safety of the power battery are relatively high and it also affects the battery life. The second is the power exchange mode, which theoretically has the advantages of improving energy efficiency, improving the utilization efficiency of the power battery, controlling safety, and favoring the commercialization of the power battery, but there are also problems such as cost control, management system, and standardization, and not all cars are suitable for the power exchange mode.

[0026] Since the common charging method for electric vehicles is to adopt quick charging technology, it is difficult to evaluate the battery health state during the charging and discharging process of electric vehicles. Due to the nonlinear changes in battery parameters and the changes in battery performance over time and with the usage environment, it is difficult to build an accurate mathematical model. In addition, due to the randomness and unpredictability of the battery degradation process, there are currently no clear degradation rules. Another difficulty is how to effectively integrate various monitoring data to perform rational analysis to evaluate the battery health state.

[0027] Therefore, the present invention provides a system and method for monitoring the coordinated state of a vehicle and a charging station in an electric vehicle charging and discharging process, and rationally predicts battery life through parameters of the coordinated state of the vehicle and the charging station, combines multiple influencing parameters to correct the prediction of battery life, and accurately and effectively evaluates battery life.

[0028] Referring to FIG. 1, an embodiment disclosed by the present invention is a monitoring system for a coordinated state of a vehicle and a charging station in an electric vehicle charging and discharging process, comprising: A vehicle battery monitoring module is used for collecting vehicle battery state parameters in real time, the state parameters of the vehicle battery including a battery terminal voltage Vd, a battery charge / discharge current Id and a battery temperature Td; A charging station monitoring module is used for monitoring the state parameters of the charging station in real time, the state parameters of the charging station including the charging station voltage Vc, the charging station current Ic and the charging station power Pc; a data communication module used for transmitting the vehicle battery status parameters and the charging station status parameters through wireless communication technology; A monitoring module is used for receiving the state parameters of the vehicle battery and the state parameters of the charging station, processing the state parameters of the vehicle battery and the state parameters of the charging station, and judging the charging / discharging state of the vehicle battery based on a preset formula; The vehicle battery includes a processing module that is used to predict the life of the vehicle battery based on the charge / discharge state of the vehicle battery, a state parameter of the vehicle battery, and a state parameter of the charging station.

[0029] In one embodiment of the present application, the monitoring module determines the charging / discharging state of the vehicle battery based on a preset formula, Calculating a remaining capacity of the vehicle battery based on the battery terminal voltage Vd and the battery charge / discharge current Id, and determining a charge / discharge state of the vehicle battery based on the remaining capacity of the vehicle battery; The preset formula is as follows:

[0030]

number

[0031] where SOC is the remaining charge of the vehicle battery, V bat is the terminal voltage of the vehicle battery, V min is the minimum allowable voltage of the vehicle battery, V max is the maximum allowable voltage of the vehicle battery, Wherein, if the remaining charge of the vehicle battery is more than 50%, the vehicle battery is determined to be in a charging state; If the vehicle battery has less than 50% charge remaining, the vehicle battery is determined to be in a discharged state. If the vehicle battery has 50% charge remaining, the vehicle battery is determined to be fully charged.

[0032] It should be noted that the above technical solution is applied to a lithium battery, and in practical application, the parameters are acquired by combining with a battery management system (BMS) or by directly reading the electrical parameter sensor of the battery, so as to acquire parameters such as the terminal voltage and the charge / discharge current of the battery.

[0033] In one specific embodiment of the present application, the monitoring module is further used for generating a charging curve according to the state parameters of the charging station when it is determined that the vehicle battery is in a charging state, and obtaining a charging rate vd of the vehicle battery according to the charging curve; The processing module is further used to predict a lifespan of the vehicle battery based on a charging rate vd of the vehicle battery; In the processing module, a preset charging speed matrix T0 and a preset remaining life time matrix A are preset. For the preset remaining life time matrix A, A(A1, A2, A3, A4) is set. Here, A1 is the first preset remaining life time, A2 is the second preset remaining life time, A3 is the third preset remaining life time, A4 is the fourth preset remaining life time, and A1 < A2 < A3 < A4 < 5 years. For the preset charging speed matrix T0, T0(T01, T02, T03, T04) is set. Here, T01 is the first preset charging speed, T02 is the second preset charging speed, T03 is the third preset charging speed, T04 is the fourth preset charging speed, and T01 < T02 < T03 < T04. The processing module is used to select the corresponding remaining life time based on the relationship between vd and the preset charging speed matrix T0 to be the predicted life of the vehicle battery. When vd < T01, the fourth preset remaining life time A4 is selected as the predicted life of the vehicle battery. When T01 ≤ vd < T02, the third preset remaining life time A3 is selected as the predicted life of the vehicle battery. When T02 ≤ vd < T03, the second preset remaining life time A2 is selected as the predicted life of the vehicle battery. When T03 ≤ vd < T04, the first preset remaining life time A1 is selected as the predicted life of the vehicle battery.

[0034] It can be understood that the faster the charging speed, the shorter the battery life. This is because fast charging will cause the balance of chemical reactions inside the battery to be lost, leading to problems such as warping and deformation of the battery plates and increased acid concentration. Therefore, the present invention can predict the life of a vehicle battery in combination with the charging speed, and effectively evaluate the performance and reliability of the battery during use. Through the prediction, the change in battery life at different charging speeds can be confirmed, so that reasonable charging advice can be provided to users, which can extend the battery life and improve the range and performance of electric vehicles. This is also beneficial for battery manufacturers and electric vehicle manufacturers, and helps promote the development of the electric vehicle industry.

[0035] In one specific embodiment of the present application, the processing module is further used to obtain a number k of past charges of the vehicle battery; The processing module further sets a preset past charging count matrix R0 and a preset remaining life time correction coefficient matrix B, and sets B(B1, B2, B3, B4) for the preset remaining life time correction coefficient matrix B, where B1 is the first preset remaining life time correction coefficient, B2 is the second preset remaining life time correction coefficient, B3 is the third preset remaining life time correction coefficient, and B4 is the fourth preset remaining life time correction coefficient, and is 0.6 <B1<B2<B3<B4<1であり、 R0 (R01, R02, R03, R04) is set for the preset past charging count matrix R0, where R01 is the first preset past charging count, R02 is the second preset past charging count, R03 is the third preset past charging count, and R04 is the fourth preset past charging count; and R01 <R02<R03<R04であり、 The processing module selects a corresponding remaining life time correction coefficient according to the relationship between k and the preset past charging number matrix R0, and is used to correct the remaining life time; When k < R01, the fourth preset remaining life time correction coefficient B4 is selected to correct the fourth preset remaining life time A4, and the corrected remaining life time is A4 × B4. When R01 ≤ k < R02, the third preset remaining life time correction coefficient B3 is selected to correct the third preset remaining life time A3, and the corrected remaining life time is A3 × B3. When R02 ≤ k < R03, the second preset remaining life time correction coefficient B2 is selected to correct the second preset remaining life time A2, and the corrected remaining life time is A2 × B2. When R03 ≤ k < R04, the first preset remaining life time correction coefficient B1 is selected to correct the first preset remaining life time A1, and the corrected remaining life time is A1 × B1.

[0036] It can be understood that the life of a lithium-ion battery is usually 3 to 5 years under normal usage conditions, but this is also affected by the number of charge cycles. As the number of charge cycles increases, the life becomes shorter. The present invention further improves the accuracy of the prediction result by correcting the life prediction of the vehicle battery in combination with the number of charge cycles.

[0037] In one specific embodiment of the present application, when it is determined that the vehicle battery is in a discharging state, the monitoring module further generates a discharge curve based on the state parameters of the vehicle battery and the remaining amount of the vehicle battery, and is used to obtain the discharge rate vt of the vehicle battery based on the discharge curve. The processing module is further set with a preset discharge rate matrix W0 and a preset remaining life time secondary correction coefficient matrix C. For the preset remaining life time secondary correction coefficient matrix C, C(C1, C2, C3, C4) is set, where C1 is the first preset remaining life time secondary correction coefficient, C2 is the second preset remaining life time secondary correction coefficient, C3 is the third preset remaining life time secondary correction coefficient, C4 is the fourth preset remaining life time secondary correction coefficient, and 0.6 < C1 < C2 < C3 < C4 < 1. For the preset discharge rate matrix W0, set W0 (W01, W02, W03, W04), where W01 is the first preset discharge rate, W02 is the second preset discharge rate, W03 is the third preset discharge rate, W04 is the fourth preset discharge rate, and W01 < W02 < W03 < W04. The processing module is further used to select the corresponding remaining life time secondary correction coefficient based on the relationship between vt and the preset discharge rate matrix W0 and perform secondary correction on each corrected preset remaining life time. When vt < W01, select the fourth preset remaining life time secondary correction coefficient C4 and perform secondary correction on the corrected preset fourth remaining life time A4. The corrected remaining life time is A4 × B4 × C4. When W01 ≤ vt < W02, select the third preset remaining life time secondary correction coefficient C3 and perform secondary correction on the corrected preset third remaining life time A3. The corrected remaining life time is A3 × B3 × C3. When W02 ≤ vt < W03, select the second preset remaining life time secondary correction coefficient C2 and perform secondary correction on the corrected preset second remaining life time A2. The corrected remaining life time is A2 × B2 × C2. When W03 ≤ vt < W04, select the first preset remaining life time secondary correction coefficient C1 and perform secondary correction on the corrected preset first remaining life time A1. The corrected remaining life time is A1 × B1 × C1.

[0038] It can be understood that the discharge rate has a great impact on the battery life of a vehicle, and the faster the discharge rate, the shorter the battery life, because rapid discharge will unbalance the chemical reactions in the battery and accelerate the deterioration of battery performance; the slower the battery discharge rate, the longer the battery life. The present invention can predict battery life through the discharge rate and check the changes in battery life at different discharge rates, which provides a basis for battery management and maintenance, and helps optimize battery use conditions, extend battery life, improve battery performance, improve the overall performance of the vehicle, and detect potential battery problems in advance for timely repair and replacement.

[0039] In one specific embodiment of the present application, the processing module is further used to perform a failure prediction for the vehicle battery based on the predicted vehicle battery life, wherein: The processing module may include: Acquire past state parameters of the vehicle battery, the past state parameters of the vehicle battery including a past terminal voltage of the battery, a past charge / discharge current of the battery, and a past temperature of the battery; Arranging the acquired past state parameters of the vehicle battery based on the time series, and pre-processing the arranged past state parameters; Performing learning training on data of past state parameters based on SVR to build a failure prediction model; predicting a fault for the vehicle battery based on the fault prediction model and the state parameters of the vehicle battery; The method includes performing a residual threshold test and performing a fault warning based on a fault prediction result of the vehicle battery by the fault prediction model.

[0040] In one specific embodiment of the present application, performing fault prediction on a vehicle battery and constructing a fault prediction model includes: Regression analysis is performed using SVM, i.e., Support Vector Regression Machine (SVR), whose implementation is to map data X from the input space to a high-dimensional feature space G via a nonlinear mapping φ, and then perform linear regression in this space. Given a training set, T = {(x1, y1), ..., (x l , y l )}∈(R n ×γ) l , where x i ∈R n , y i ∈γ=R, i=1,...,l, and to simplify the regression problem, a less sensitive loss function is introduced, also called ε-SVR, which is the standard algorithm for support vector machine regression, and the following equation is used to estimate the function:

[0041]

number

[0042] In the formula, b is the amount of bias.

[0043] When optimizing the estimation function, an extremum of the optimization target is taken.

[0044]

number

[0045] The result is as follows:

[0046]

number

[0047] where C is the penalty coefficient used to achieve a compromise between empirical risk and reliability risk, the larger C is, the greater the ability to fit the data, and ξ i and ξ * iis the relaxation coefficient, which is used to control the linear inseparability boundary, and ε is used to control the regression approximation error and the generalization ability of the model, and is defined as follows:

[0048]

number

[0049] Introducing the Lagrangian function and utilizing the dual form of the optimization problem, we finally obtain the following regression function:

[0050]

number

[0051] In the formula, α, α * i ≧0, and γ, γ * i = ≧ 0, i = 1, ... l. According to the KKT theorem, we have the following:

[0052]

number

[0053] Therefore, for nonlinear support vector machine regression, the regression function is expressed as:

[0054]

number

[0055] The kernel function is selected as the radial basis kernel function (RBF).

[0056]

number

[0057] It can be seen that the present invention combines machine learning methods to grasp the battery status in real time, and builds a failure prediction model based on SVR to predict the health state and predict possible failures based on current and historical data.

[0058] In one embodiment of the present application, the pre-processing of the past state parameters of the processing module includes: This includes removing outlier data in the past state parameters, interval processing the data in the past state parameters, and performing non-linear decision making on the data in the past state parameters to generate a sample format used to support vector machine learning training.

[0059] Based on the similar technical concept, as shown in FIG. 2, the present invention further provides a method for monitoring the coordinated state of a vehicle and a charging station in an electric vehicle charging and discharging process, which is applied to a monitoring system for the coordinated state of a vehicle and a charging station in an electric vehicle charging and discharging process accordingly; Collecting vehicle battery condition parameters in real time, including a battery terminal voltage Vd, a battery charge / discharge current Id, and a battery temperature Td; Monitoring the state parameters of the charging station in real time, including the charging station voltage Vc, the charging station current Ic, and the charging station power Pc; Transmitting a vehicle battery status parameter and a charging station status parameter via wireless communication technology; receiving a state parameter of the vehicle battery and a state parameter of the charging station, processing the state parameter of the vehicle battery and the state parameter of the charging station, and determining a charge / discharge state of the vehicle battery based on a preset formula; The method includes predicting the life of the vehicle battery based on the charge / discharge state of the vehicle battery, the state parameters of the vehicle battery, and the state parameters of the charging station.

[0060] In one specific embodiment of the present application, determining the charge / discharge state of the vehicle battery based on the preset formula includes: Calculating a remaining capacity of the vehicle battery based on the battery terminal voltage Vd and the battery charge / discharge current Id, and determining a charge / discharge state of the vehicle battery based on the remaining capacity of the vehicle battery; The preset formula is as follows:

[0061]

number

[0062] where SOC is the remaining charge of the vehicle battery, V bat is the terminal voltage of the vehicle battery, V min is the minimum allowable voltage of the vehicle battery, V max is the maximum allowable voltage of the vehicle battery, If the vehicle battery has more than 50% charge remaining, the vehicle battery is considered to be in a charging state. If the vehicle battery has less than 50% charge remaining, the vehicle battery is determined to be in a discharged state. If the vehicle battery has 50% charge remaining, the vehicle battery is determined to be fully charged.

[0063] It should be noted that the above technical solution is applied to a lithium battery, and in practical application, the parameters are acquired by combining with a battery management system (BMS) or by directly reading the electrical parameter sensor of the battery, so as to acquire parameters such as the terminal voltage and the charge / discharge current of the battery.

[0064] In one specific embodiment of the present application, the method further includes: performing a failure prediction for the vehicle battery based on the predicted vehicle battery life, wherein: To predict failures in vehicle batteries, Obtaining past state parameters of the vehicle battery, including a past terminal voltage of the battery, a past charge / discharge current of the battery, and a past temperature of the battery; Arranging the acquired past state parameters of the vehicle battery based on the time series, and pre-processing the arranged past state parameters; Performing learning training on data of past state parameters based on SVR to build a failure prediction model; predicting a fault for the vehicle battery based on the fault prediction model and the state parameters of the vehicle battery; The method includes performing a residual threshold test and performing a fault warning based on a fault prediction result of the vehicle battery by the fault prediction model.

[0065] In summary, the present invention calculates the charging rate and discharging rate through the vehicle battery state parameters and the charging station state parameters to reasonably predict the battery life, and by combining with the adaptive correction of related parameters, the battery life can be accurately evaluated, and by combining with the machine learning method, a fault warning can be provided according to the battery life. The present invention has the advantage of being both accurate and intelligent.

[0066] The above is only one embodiment of the present invention, and does not limit the scope of the present invention. Any structural modifications made according to the present invention are considered to be within the protection scope of the present invention, and should be limited as long as the essence of the present invention is not lost.

[0067] Those skilled in the art can clearly understand that, for convenience and simplicity of explanation, the specific working process and related description of the above system can refer to the corresponding process in the above method embodiments, and will not be described again here.

[0068] It should be noted that the system provided by the above embodiment is merely illustrated by taking the division of each of the above functional modules as an example, and in actual application, the above functions can be allocated to different functional modules as required, that is, the modules or steps in the embodiments of the present invention can be further decomposed or recombined. For example, the modules in the above embodiment can be combined into one module, or further divided into multiple sub-modules to perform all or part of the above functions.

[0069] Those skilled in the art will understand that the modules and method steps of each example described in connection with the embodiments disclosed herein can be realized by electronic hardware, computer software, or a combination of both, and the programs corresponding to the software modules, method steps can be located in a random access memory (RAM), memory, read-only memory (ROM), electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or other forms of storage media known in the art. In order to clearly show the compatibility of electronic hardware and software, the above description generally describes the configurations and steps of each embodiment in terms of functions. Whether these functions are implemented as electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the functions described for each specific application, but such implementation should not be considered as going beyond the scope of the present invention.

[0070] The term "comprising" or other similar terms means that a process, method, article, or apparatus / device that includes a list of elements includes not only those elements, but also other elements that are not expressly listed or that are inherent to the process, method, article, or device / device.

[0071] Although the technical solutions of the present invention have been described above in conjunction with the preferred embodiments shown in the drawings, those skilled in the art can easily understand that the protection scope of the present invention is not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent modifications or substitutions to the relevant technical features, and the technical solutions after these modifications or substitutions will fall within the protection scope of the present invention. The above descriptions are only preferred embodiments of the present invention and are not intended to limit the scope of the present invention.

Claims

1. A vehicle battery monitoring module is used for collecting state parameters of a vehicle battery in real time, the state parameters of the vehicle battery including a battery terminal voltage Vd, a battery charge / discharge current Id and a battery temperature Td; A charging station monitoring module is used for monitoring state parameters of the charging station in real time, the state parameters of the charging station including a charging station voltage Vc, a charging station current Ic and a charging station power Pc; a data communication module used for transmitting the status parameters of the vehicle battery and the status parameters of the charging station through wireless communication technology; a monitoring module used to receive the vehicle battery status parameters and the charging station status parameters, process the vehicle battery status parameters and the charging station status parameters, and determine the charging / discharging status of the vehicle battery based on a preset formula; a processing module used to predict a life of the vehicle battery based on a charge / discharge state of the vehicle battery, a state parameter of the vehicle battery, and a state parameter of the charging station; Wherein, the monitoring module is further used for generating a charging curve based on the state parameters of the charging station when it is determined that the vehicle battery is in a charging state, and obtaining a charging rate vd of the vehicle battery based on the charging curve; The processing module is further used to predict a life of the vehicle battery based on a charging rate vd of the vehicle battery; In the processing module, a preset charging speed matrix T0 and a preset remaining life matrix A are preset, and for the preset remaining life matrix A, A(A1, A2, A3, A4) is set, where A1 is a first preset remaining life, A2 is a second preset remaining life, A3 is a third preset remaining life, A4 is a fourth preset remaining life, and A1<A2<A3<A4<5 years; Set T0(T01, T02, T03, T04) for the preset charging rate matrix T0, where T01 is a first preset charging rate, T02 is a second preset charging rate, T03 is a third preset charging rate, and T04 is a fourth preset charging rate, and T01<T02<T03<T04; The processing module is used to select a corresponding remaining life time as a predicted life time of the vehicle battery based on a relationship between vd and the preset charging rate matrix T0; If vd<T01, select the fourth preset remaining life time A4 as the predicted life of the vehicle battery; If T01≦vd<T02, select a third preset remaining life time A3 as the predicted life of the vehicle battery; If T02≦vd<T03, select a second preset remaining life time A2 as the predicted life of the vehicle battery; If T03≦vd<T04, select a first preset remaining life time A1 as the predicted life of the vehicle battery; The monitoring module determines the charge / discharge state of the vehicle battery based on a preset formula, calculating a remaining capacity of the vehicle battery based on the battery terminal voltage Vd and the battery charge / discharge current Id, and determining a charge / discharge state of the vehicle battery based on the remaining capacity of the vehicle battery; The preset formula is as follows: [0010] In the formula, SOC is the remaining charge of the vehicle battery, V bat is the terminal voltage of the vehicle battery, V min is the minimum allowable voltage of the vehicle battery, and V max is the maximum allowable voltage of the vehicle battery. If the remaining charge of the vehicle battery is more than 50%, the vehicle battery is determined to be in a charging state; If the remaining charge of the vehicle battery is less than 50%, the vehicle battery is determined to be in a discharged state; A monitoring system for monitoring the coordinated state of a vehicle and a charging station in an electric vehicle charging / discharging process, characterized in that when the remaining charge of the vehicle battery is 50%, the vehicle battery is determined to be in a fully charged state.

2. The processing module is further used to obtain a number k of past charges of the vehicle battery; The processing module also sets a preset past charging count matrix R0 and a preset remaining life time correction coefficient matrix B, and sets B(B1, B2, B3, B4) for the preset remaining life time correction coefficient matrix B, where B1 is a first preset remaining life time correction coefficient, B2 is a second preset remaining life time correction coefficient, B3 is a third preset remaining life time correction coefficient, and B4 is a fourth preset remaining life time correction coefficient, and 0.6<B1<B2<B3<B4<1; R0 (R01, R02, R03, R04) is set for the preset past charging count matrix R0, where R01 is a first preset past charging count, R02 is a second preset past charging count, R03 is a third preset past charging count, and R04 is a fourth preset past charging count, and R01<R02<R03<R04; The processing module is used to select a corresponding remaining life time correction coefficient according to the relationship between k and the preset past charging count matrix R0, and correct the remaining life time; If k<R01, the fourth preset remaining life time correction coefficient B4 is selected to correct the fourth preset remaining life time A4, and the corrected remaining life time is A4×B4; If R01≦k<R02, the third preset remaining life time correction coefficient B3 is selected to correct the third preset remaining life time A3, and the corrected remaining life time is A3×B3; If R02≦k<R03, the second preset remaining life time correction coefficient B2 is selected to correct the second preset remaining life time A2, and the corrected remaining life time is A2×B2; 2. The monitoring system for monitoring the coordinated state of a vehicle and a charging station in an electric vehicle charging / discharging process as described in claim 1, wherein when R03≦k<R04, the first preset remaining life time correction coefficient B1 is selected to correct the first preset remaining life time A1, and the corrected remaining life time is A1×B1.

3. The monitoring module is further used for generating a discharge curve based on the state parameters of the vehicle battery and the remaining capacity of the vehicle battery when it is determined that the vehicle battery is in a discharge state, and obtaining a discharge rate vt of the vehicle battery based on the discharge curve; The processing module further sets a preset discharge rate matrix W0 and a preset remaining life secondary correction coefficient matrix C, and sets C(C1, C2, C3, C4) for the preset remaining life secondary correction coefficient matrix C, where C1 is a first preset remaining life secondary correction coefficient, C2 is a second preset remaining life secondary correction coefficient, C3 is a third preset remaining life secondary correction coefficient, and C4 is a fourth preset remaining life secondary correction coefficient, and 0.6<C1<C2<C3<C4<1; For the preset discharge rate matrix W0, set W0(W01, W02, W03, W04), where W01 is a first preset discharge rate, W02 is a second preset discharge rate, W03 is a third preset discharge rate, and W04 is a fourth preset discharge rate, and W01<W02<W03<W04; The processing module is further used to select a corresponding remaining life time quadratic correction coefficient based on the relationship between vt and the preset discharge rate matrix W0, and perform quadratic correction for each corrected preset remaining life time; If vt<W01, select the fourth preset remaining life secondary correction coefficient C4 to perform secondary correction on the corrected fourth preset remaining life A4, and the corrected remaining life is A4×B4×C4; If W01≦vt<W02, select the third preset remaining life secondary correction coefficient C3 to perform secondary correction on the corrected third preset remaining life A3, and the corrected remaining life is A3×B3×C3; If W02≦vt<W03, select the second preset remaining life secondary correction coefficient C2 to perform secondary correction on the corrected preset second remaining life A2, and the corrected remaining life is A2×B2×C2; 3. The monitoring system for monitoring the coordinated state of a vehicle and a charging station in an electric vehicle charging / discharging process according to claim 2, wherein, when W03≦vt<W04, the first preset remaining life time secondary correction coefficient C1 is selected to perform secondary correction on the corrected first preset remaining life time A1, and the corrected remaining life time is A1×B1×C1.

4. The processing module is further used to perform a failure prediction for the vehicle battery based on the predicted life of the vehicle battery, wherein: The performing of fault prediction on the vehicle battery by the processing module includes: Acquiring past state parameters of the vehicle battery, the past state parameters of the vehicle battery including a past terminal voltage of the battery, a past charge / discharge current of the battery, and a past temperature of the battery; Arranging the acquired past state parameters of the vehicle battery based on a time series, and pre-processing the arranged past state parameters; Performing learning training on data of the past state parameters based on SVR to construct a failure prediction model; predicting a fault for the vehicle battery based on the fault prediction model and state parameters of the vehicle battery; 4. The monitoring system for the coordinated state of a vehicle and a charging station in an electric vehicle charging / discharging process according to claim 3, further comprising: performing a residual threshold test and issuing a fault warning based on a fault prediction result of the vehicle battery by the fault prediction model.

5. The step of pre-processing the past state parameters of the processing module includes: removing outlier data in the past state parameters, interval processing the data in the past state parameters, and performing non-linear decision making on the data in the past state parameters to generate a sample format used to support vector machine learning training. The monitoring system for the coordinated state of a vehicle and a charging station in an electric vehicle charging and discharging process according to claim 4.

6. Collecting vehicle battery status parameters in real time, including a battery terminal voltage Vd, a battery charge / discharge current Id, and a battery temperature Td; monitoring the state parameters of the charging station in real time, including the charging station voltage Vc, the charging station current Ic, and the charging station power Pc; transmitting status parameters of the vehicle battery and status parameters of the charging station via wireless communication techniques; receiving the state parameters of the vehicle battery and the state parameters of the charging station, processing the state parameters of the vehicle battery and the state parameters of the charging station, and determining a charging / discharging state of the vehicle battery based on a preset formula; When it is determined that the vehicle battery is in a charging state, a charging curve is generated based on the state parameters of the charging station, and a charging rate vd of the vehicle battery is obtained based on the charging curve; predicting a life of the vehicle battery based on a charge / discharge state of the vehicle battery, a state parameter of the vehicle battery, and a state parameter of the charging station; Specifically, predicting the life of the vehicle battery based on the charging rate vd of the vehicle battery includes: Preset the preset charging rate matrix T0 and the preset remaining life matrix A, and set A(A1, A2, A3, A4) for the preset remaining life matrix A, where A1 is the first preset remaining life, A2 is the second preset remaining life, A3 is the third preset remaining life, and A4 is the fourth preset remaining life, and A1<A2<A3<A4<5 years; Set T0(T01, T02, T03, T04) for the preset charging rate matrix T0, where T01 is a first preset charging rate, T02 is a second preset charging rate, T03 is a third preset charging rate, and T04 is a fourth preset charging rate, and T01<T02<T03<T04; Based on the relationship between vd and the preset charging rate matrix T0, select a corresponding remaining life time as a predicted life of the vehicle battery; If vd<T01, select the fourth preset remaining life time A4 as the predicted life of the vehicle battery; If T01≦vd<T02, select a third preset remaining life time A3 as the predicted life of the vehicle battery; If T02≦vd<T03, select a second preset remaining life time A2 as the predicted life of the vehicle battery; If T03≦vd<T04, select a first preset remaining life time A1 as the predicted life of the vehicle battery; Determining a charge / discharge state of the vehicle battery based on a preset equation includes: Calculating a remaining capacity of the vehicle battery based on the battery terminal voltage Vd and the battery charge / discharge current Id, and determining a charge / discharge state of the vehicle battery based on the remaining capacity of the vehicle battery; The preset formula is: [0025] and In the formula, SOC is the remaining charge of the vehicle battery, V bat is the terminal voltage of the vehicle battery, V min is the minimum allowable voltage of the vehicle battery, and V max is the maximum allowable voltage of the vehicle battery. Here, if the remaining charge of the vehicle battery is more than 50%, the vehicle battery is determined to be in a charging state; If the remaining charge of the vehicle battery is less than 50%, the vehicle battery is determined to be in a discharged state; The method for monitoring the coordinated state of a vehicle and a charging station in an electric vehicle charging / discharging process, which is applied to a monitoring system for the coordinated state of a vehicle and a charging station in an electric vehicle charging / discharging process as described in any one of claims 1 to 5, wherein the vehicle battery is determined to be in a fully charged state when the remaining charge of the vehicle battery is 50%.

7. and performing a failure prediction for the vehicle battery based on the predicted life of the vehicle battery, wherein: The method of performing a failure prediction on the vehicle battery includes: Acquiring past state parameters of the vehicle battery, the past state parameters of the vehicle battery including a past terminal voltage of the battery, a past charge / discharge current of the battery, and a past temperature of the battery; Arranging the acquired past state parameters of the vehicle battery based on a time series, and pre-processing the arranged past state parameters; Performing learning training on data of the past state parameters based on SVR to construct a failure prediction model; predicting a fault for the vehicle battery based on the fault prediction model and state parameters of the vehicle battery; 7. The method for monitoring the coordinated state of a vehicle and a charging station in an electric vehicle charging / discharging process according to claim 6, further comprising: performing a residual threshold test and issuing a fault warning based on a fault prediction result of the vehicle battery by the fault prediction model.

Images