A safety assessment and early warning method for electric bicycle batteries based on vehicle-cloud collaboration

Abstract

The present invention relates to electric bicycle safety early warning technology, and specifically to an electric bicycle battery safety assessment early warning method based on vehicle-cloud collaboration, including: high-frequency data collection on the vehicle side of the electric bicycle, battery parameter collection of the electric bicycle through multiple sensors, and aggregation of the collected data to the cloud; through the data on the cloud, determining the mapping relationship between the battery health-fault-safe failure evolution and characteristic parameters, establishing a characterization parameter library reflecting battery fault information and a risk assessment model for the electric bicycle side; based on cloud big data fault diagnosis records, establishing a battery safety risk cloud assessment model, building a cloud system, integrating the battery safety risk cloud assessment model into the system, and realizing vehicle-cloud collaborative electric bicycle safety early warning. This method can realize the advanced and accurate perception of the battery safety failure risk under complex working conditions with multiple factors coupled, and solves the problem of limited early warning capability and short early warning lead time on the vehicle side alone.

Description

Technical Field

[0001] The present invention belongs to the technical field of electric bicycle safety warning, and in particular relates to an electric bicycle battery safety assessment and warning method based on vehicle-cloud collaboration. Background Art

[0002] Electric bicycles, which are convenient, economical and environmentally friendly, have gradually become the main means of transportation for people to travel short distances. However, with the investment of a large number of electric bicycles, the safety of electric bicycles has gradually become a concern. Due to the uneven quality of electric bicycle batteries, and the lack of guarantee of the battery's use environment, protection and maintenance, the safety risk of electric bicycles has been further increased. Charging without supervision can easily lead to fires. Therefore, it is extremely important to conduct a safety assessment of the battery status of electric bicycles through the vehicle-cloud management of electric bicycles and to provide users with timely battery safety warnings. Therefore, it is urgent to upgrade the electric bicycle safety supervision technology system to digital supervision, establish electric bicycle safety data monitoring, battery safety and batch failure rapid warning technology methods, and realize timely and efficient safety supervision of electric bicycle products. Summary of the invention

[0003] In view of the problems existing in the background technology, the present invention provides an electric bicycle battery safety assessment and early warning method based on vehicle-cloud collaboration.

[0004] In order to solve the above technical problems, the present invention adopts the following technical solution: an electric bicycle battery safety assessment and early warning method based on vehicle-cloud collaboration, comprising the following steps:

[0005] Step 1: Collect high-frequency data from the electric bicycle, use multiple sensors to collect battery parameters of the electric bicycle, and aggregate the collected data to the cloud;

[0006] Step 2: Determine the mapping relationship between battery health-failure-safety failure evolution and characteristic parameters by aggregating the data in the cloud, and establish a parameter library reflecting battery failure information and a risk assessment model for electric bicycles;

[0007] Step 3: Based on the cloud big data fault diagnosis records, a cloud-based battery safety risk assessment model is established, with the main indicators being the characteristic changes of various internal short circuit evolutions, health status and aging abnormal evolution processes of the faulty battery;

[0008] Step 4: Build a cloud system and integrate the battery safety risk cloud assessment model into the system to achieve vehicle-cloud collaborative electric bicycle safety warning.

[0009] In the above-mentioned vehicle-cloud collaborative electric bicycle battery safety assessment and early warning method, the implementation of step 1 includes the following steps:

[0010] Step 1.1, collect battery parameters through the sensor on the electric bicycle or the battery BMS monitoring chip of the electric car;

[0011] Step 1.2: Store the collected battery parameters in the embedded system of the vehicle, and transmit the collected battery parameters wirelessly via Bluetooth through the BMS expansion system;

[0012] Step 1.3: Summarize and store the collected battery parameter data in the cloud database.

[0013] In the above-mentioned vehicle-cloud collaborative electric bicycle battery safety assessment and early warning method, the implementation of step 2 includes the following steps:

[0014] Step 2.1, considering the damage mechanism and evolution law of the battery, build different fault risk assessment models F(X) for the battery's slight short circuit, severe short circuit, inconsistency anomaly, aging anomaly, leakage, and lithium deposition problems, where X represents the overall sampling data set;

[0015] Step 2.2, determine the mapping relationship between battery health-failure-safety failure evolution and characteristic parameters; the failure risk function F(X) is composed of i independent failure functions f i (X n ), each fault function is composed of n independent collection data sets X according to different fault conditions. n To determine, the failure risk function f i (x) is:

[0016]

[0017] In the formula, a0 is a constant, a i is the weight coefficient of each feature parameter.

[0018] In the above-mentioned vehicle-cloud collaborative electric bicycle battery safety assessment and early warning method, the implementation of step 3 includes the following steps:

[0019] Step 3.1: Based on the battery database of cloud big data, track the changing rules of the battery throughout its life cycle, identify the abnormal evolution of battery trends, analyze the evolution of short circuits in the battery, abnormal evolution of health status and aging, and changes in various battery parameters under the process of consistency deterioration;

[0020] Step 3.2: Based on the battery problem described in step 2, establish the failure risk function G(X) of the battery life cycle in the cloud, where X represents the overall sampling data set;

[0021] Step 3.3: Conduct cloud-side risk assessment of battery safety; the fault risk function G(X) is composed of i independent fault assessment functions g i (X n ), according to the data set of the battery's full cycle, the failure risk function of the battery's full cycle is g i (x):

[0022]

[0023] Among them, b0 is a constant, b i is the weight coefficient of each feature parameter.

[0024] In the above-mentioned vehicle-cloud collaborative electric bicycle battery safety assessment and early warning method, the implementation of step 4 includes the following steps:

[0025] Step 4.1: Based on the risk assessment models on both the vehicle side and the cloud side, the risk assessment of the electric bicycle is performed. The risk assessment model function H(X) is: H(X) = λF(X) + μG(X), where λ and μ are the risk assessment weights on both sides, and λ+μ=1;

[0026] Step 4.2: Considering the data volume, data transmission rate, and data input requirements of the vehicle-side and cloud-side security assessment models, adaptively adjust the risk assessment weights on both sides;

[0027] Step 4.3: According to the risk assessment model, the risk level is divided by setting the safety risk threshold and the user is fed back. When the risk reaches the risk threshold that requires replacement or repair of the battery, a warning message is given.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] (1) Comprehensively consider battery data quality, model accuracy, computational complexity, and data transmission and storage costs to achieve advanced and accurate perception of battery safety failure risks under complex working conditions with multiple coupled factors, and solve the current problem of high safety accident rate and short warning lead time due to limited vehicle-side warning capabilities.

[0030] (2) The present invention configures different battery safety risk assessment algorithms for the cloud and vehicle-mounted ends, respectively, to build a "vehicle-cloud" collaborative battery safety assessment system.

[0031] (3) With the advantages of big data storage and computing in the cloud, the technical foundation of digital supervision has been established, which can provide early warnings to electric bicycle users in a timely manner. It provides a data-based early warning solution for the compilation of battery data collection and data reporting standards in the electric bicycle field. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1This is a flow chart of an electric bicycle battery safety assessment and early warning method based on vehicle-cloud collaboration according to an embodiment of the present invention;

[0033] Figure 2 This is a schematic diagram of an algorithm for an electric bicycle battery safety assessment and early warning method based on vehicle-cloud collaboration according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The technical solutions in the embodiments of the present invention will be described clearly and completely below in combination with the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0036] The present invention will be further described below in conjunction with specific embodiments, but the present invention is not limited thereto.

[0037] This embodiment comprehensively considers battery data quality, model accuracy, computational complexity, and data transmission and storage costs, etc., to achieve advanced and accurate perception of battery safety failure risks under complex working conditions with multiple factors coupled, and to solve the current problem of high safety accident rate and short warning lead time due to limited warning capabilities on the vehicle side. At the same time, this embodiment configures different battery safety risk assessment algorithms for the cloud and vehicle side, respectively, to build a "vehicle-cloud" collaborative battery safety assessment system. Through the advantages of big data storage and computing in the cloud, a technical foundation for digital supervision has been established, and battery warnings for electric bicycles have been carried out, providing a data-based warning solution for the compilation of battery data collection and data reporting standards in the electric bicycle field.

[0038] This embodiment is implemented by the following technical solutions: Figure 1 As shown, a safety assessment and early warning method for an electric bicycle battery based on vehicle-cloud collaboration includes the following steps:

[0039] S1: Collect high-frequency data from the electric bicycle, collect battery parameters of the electric bicycle through multiple sensors, and aggregate the collected data to the cloud;

[0040] S11: Collecting battery parameters through sensors on the electric bicycle or battery BMS monitoring chips on electric vehicles;

[0041] S12: storing the collected parameter information in the embedded system of the vehicle, and wirelessly transmitting the collected battery parameter data via Bluetooth through the BMS expansion system;

[0042] S13: Summarize and store the collected data in a cloud database.

[0043] S2: By collecting data from the cloud, determine the mapping relationship between battery health-failure-safety failure evolution and characteristic parameters, establish a characterization parameter library reflecting battery failure information and a risk assessment model for electric bicycles;

[0044] S21: Considering the damage mechanism and evolution law of the battery, different fault risk assessment models F(X) are built for the battery's slight short circuit, severe short circuit, inconsistency anomaly, aging anomaly, leakage, lithium deposition and other problems. X represents the overall sampling data set.

[0045] S22: Failure risk function F(X), composed of i independent failure functions f i (X n ), each fault function is composed of n independent collection data sets X according to different fault conditions. n To determine, therefore

[0046]

[0047] In the formula, f i (x) is the failure risk function, a0 is a constant, a i is the weight coefficient of each characteristic parameter, which can be used to determine the mapping relationship between the battery health-fault-safe failure evolution and the characteristic parameters.

[0048] S23: Establish a characterization parameter library that reflects battery failure information and make necessary preparations for the subsequent battery safety cloud-based evaluation model.

[0049] S3: A cloud-based battery safety risk assessment model is established based on cloud-based big data fault diagnosis records. The main indicators are the characteristic changes of various internal short-circuit evolutions, health status, and aging abnormal evolution processes of faulty batteries;

[0050] S31: Based on the battery database of cloud big data, the battery life cycle change pattern is tracked, and the abnormal evolution of battery trends is identified. The battery short circuit evolution, abnormal evolution of health status and aging, and changes in various battery parameters under the process of consistency deterioration are analyzed;

[0051] S32: Based on the various battery problems described in S2, a failure risk model G(X) of the battery life cycle in the cloud is established, where X represents the overall sampling data set;

[0052] S33: Fault assessment function G(X), which is also composed of i independent fault assessment functions g i (X n), according to the data set of the battery full cycle, there are also

[0053]

[0054] where g i (x) is the failure risk function of the battery throughout its entire cycle, b0 is a constant, b i It is the weight coefficient of each characteristic parameter, which is used to conduct cloud-side risk assessment of battery safety.

[0055] S4: Build a cloud system and integrate the battery safety risk cloud assessment model into the system to achieve vehicle-cloud collaborative electric bicycle safety warning.

[0056] S41: Integrate the risk assessment models on both the vehicle side and the cloud side, and consider the characteristics of electric bicycles, comprehensively conduct safety considerations and risk assessments of electric bicycles, and propose a risk assessment model function H(X), where H(X) = λF(X) + μG(X), where λ and μ are the risk assessment weights on both sides, and λ+μ=1;

[0057] S42: Considering the data volume, data transmission rate, vehicle-side and cloud-side security assessment model data input requirements, adaptively adjust the risk assessment weights on both sides;

[0058] S43: Based on the risk assessment model, the risk level is divided by setting the safety risk threshold, and timely feedback is given to the user. When the risk reaches the risk threshold that requires replacement or repair of the battery, a warning message is given.

[0059] like Figure 2 As shown, it is a schematic diagram of the algorithm technology of the electric bicycle battery safety assessment and early warning method based on vehicle-cloud collaboration in this embodiment:

[0060] (1) Vehicle side: Through high-frequency data collection, vehicle-side edge computing is performed to extract evaluation feature values, build a risk assessment function model, and perform risk perception and early warning.

[0061] (2) Cloud: Through the data collected from the vehicle side, data collection is carried out throughout the entire life cycle, the battery life cycle is tracked, evaluation features are extracted, a cloud-based risk assessment model is built, and mechanism-risk assessment and early warning are carried out.

[0062] (3) Integrate the function models of the vehicle and the cloud, conduct comprehensive risk assessment, and issue early warnings.

[0063] This embodiment can accurately evaluate the safety and performance of the battery under the coupling conditions of multiple influencing factors and provide timely warnings, build a real-time perception and data transmission model for the safety status of electric bicycle batteries, and solve problems such as technical and intelligent supervision of electric bicycle safety supervision.

[0064] The above are only preferred embodiments of the present invention, and are not intended to limit the implementation methods and protection scope of the present invention. Those skilled in the art should be aware that all solutions obtained by equivalent substitutions and obvious changes made using the contents of the specification of the present invention should be included in the protection scope of the present invention.

Claims

1. A vehicle-cloud collaboration-based electric bicycle battery safety assessment and early warning method, characterized in that: The following steps are involved: Step 1: Collect high-frequency data from the electric bicycle, use multiple sensors to collect battery parameters of the electric bicycle, and aggregate the collected data to the cloud; Step 2: Determine the mapping relationship between battery health-failure-safety failure evolution and characteristic parameters by aggregating the data in the cloud, establish a parameter library reflecting battery failure information and a risk assessment model for electric bicycles; the specific steps are as follows: Step 2.1, considering the damage mechanism and evolution law of the battery, build different fault risk assessment models F(X) for the battery's slight short circuit, severe short circuit, inconsistency anomaly, aging anomaly, leakage, and lithium deposition problems, where X represents the overall sampling data set; Step 2.2, determine the mapping relationship between battery health-failure-safety failure evolution and characteristic parameters; the failure risk function F(X) is composed of i independent failure functions f i (X n ), each fault function is composed of n independent collection data sets X according to different fault conditions. n To determine, the failure risk function f i (x) is: In the formula, a0 is a constant, a i is the weight coefficient of each characteristic parameter; Step 3: Based on the cloud big data fault diagnosis records, a cloud-based battery safety risk assessment model is established. The main indicators are the characteristic changes of various internal short circuit evolutions, health status and aging abnormal evolution processes of the faulty battery. The specific steps are as follows: Step 3.1: Based on the battery database of cloud big data, track the changing rules of the battery throughout its life cycle, identify the abnormal evolution of battery trends, analyze the evolution of short circuits in the battery, abnormal evolution of health status and aging, and changes in various battery parameters under the process of consistency deterioration; Step 3.2: Based on the battery problem described in step 2.1, establish the failure risk function G(X) of the battery life cycle in the cloud, where X represents the overall sampling data set; Step 3.3: Conduct cloud-side risk assessment of battery safety; the fault risk function G(X) is composed of i independent fault assessment functions g i (X n ), according to the data set of the battery's full cycle, the failure risk function of the battery's full cycle is g i (x): Among them, b0 is a constant, b i is the weight coefficient of each characteristic parameter; Step 4: Build a cloud system and integrate the battery safety risk cloud assessment model into the system to achieve vehicle-cloud collaborative electric bicycle safety warning. The specific steps are as follows: Step 4.1: Based on the risk assessment models on both the vehicle side and the cloud side, the risk assessment of the electric bicycle is performed. The risk assessment model function H(X) is: H(X)=λF(X)+μG(X), where λ and μ are the risk assessment weights on both sides, and λ+μ=1; Step 4.2: Considering the data volume, data transmission rate, and data input requirements of the vehicle-side and cloud-side security assessment models, adaptively adjust the risk assessment weights on both sides; Step 4.3: According to the risk assessment model, the risk level is divided by setting the safety risk threshold and the user is fed back. When the risk reaches the risk threshold that requires replacement or repair of the battery, a warning message is given.

2. The vehicle-cloud collaborative electric bicycle battery safety assessment and early warning method according to claim 1 is characterized by: The implementation of step 1 includes the following steps: Step 1.1, collect battery parameters through the sensor on the electric bicycle or the battery BMS monitoring chip of the electric car; Step 1.2: Store the collected battery parameters in the vehicle-side embedded system, and transmit the collected battery parameters wirelessly via Bluetooth through the BMS expansion system; Step 1.3: Summarize and store the collected battery parameter data in the cloud database.

Images