Analysis and Visualization of New Energy Vehicle Battery Data
Abstract
:1. Introduction
2. Related Work
3. Data
Data Analysis
- New Energy Vehicle Battery Dataset 1
- New Energy Vehicle Battery Dataset 2
4. Methods
4.1. GB/T32960 Standard Introduction and Data Format Analysis
4.1.1. Introduction to GB/T32960 Standard
4.1.2. Data Format Analysis
4.1.3. Analytical Thinking
- 1.
- The entire message is structured according to the structure and definition of the packet, and the message is divided into starters, command units, unique vehicle identifiers, data encryption methods, data unit lengths, data unit, and check code.
- 2.
- Judge the vehicle status (vehicle login, real-time information reporting, vehicle logout) contained in this message by the command ID in the command unit.
- 3.
- Further analyze the vehicle status in detail according to different modules defined in the data unit format. Details can be seen in Figure 4.
4.1.4. Codification
4.2. Visual Analysis
Data Preprocessing
- 1.
- Since the missing values account for less than 10% of the total data, they can be deleted directly.
- 2.
- If the missing values account for a larger proportion of the total data, the missing data need to be filled in. The common ways of filling in are mean interpolation and regression replacement methods.
- 3.
- Outliers are missing.
4.3. K-Nearest Neighbor Algorithm
- 1.
- Randomly select K tuples from the training tuples as the initial nearest neighbor tuples, and calculate the distance from the test tuples to the K tuples, respectively;
- 2.
- Sort according to the increasing relationship of distance;
- 3.
- Select the K points with the minimum distance;
- 4.
- Determine the occurrence frequency of the category of the first K points;
- 5.
- The category with the highest frequency among the first K points is returned as the prediction classification of test data [32].
5. Results and Discussion
5.1. Visualization
5.2. KNN Prediction
6. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Conflicts of Interest
Abbreviations
SOC | State of Charge |
VIN | Vehicle Identification Number |
BMS | Battery Management System |
KNN | K Nearest Neighbors |
SSE | The Sum Of Squares Due To Erro |
MSE | Mean square error |
References
- Hu, Z.; Song, Y.; Xu, Z.; Luo, Z.; Zhan, K.; Jia, L. lmpacts and Uilization of Electric Vehicles Integration into Power Systems. Chin. Soc. Electr. Eng. 2012, 32, 1–10. [Google Scholar]
- Nicholas, L.; Daniel, S. Regulatory adaptation: Accommodating electric vehicles in a petroleum world. Energy Policy 2012, 45, 308–316. [Google Scholar]
- Yabe, K.; Shinoda, Y.; Seki, T.; Tanaka, H.; Akisawa, A. Market penetration speed and effects on CO2 reduction of electric vehicles and plug-in hybrid electric vehicles in Japan. Energy Policy 2012, 45, 529–540. [Google Scholar] [CrossRef]
- Shao, C.; Wang, X.; Shahidehpour, M. Partial decomposition for distributed electric vehicle charging controlconsidering electric power grid congestion. IEEE Trans. Smart Grid 2016, 8, 75–83. [Google Scholar] [CrossRef]
- Xiangning, X.; Jianfeng, W.; Shun, T.; Qiushuo, L. Study and Recommendations of the Key Isues in Planning of Electric Vehicles’Charging Facilities. China Electrotech. 2014, 29, 1–10. [Google Scholar]
- Al-Ogaili, A.S.; Aris, I.B.; Sabry, A.H.; Othman, M.L.B.; Azis, N.B.; Isa, D.; Hoon, Y. Design and development of three levels universal electric vehicle charger based on integration of VOC and SPWM techniques. J. Comput. Theor. Nanosci. 2017, 14, 4674–4685. [Google Scholar] [CrossRef]
- Mehigan, L.; Deane, J.P. A review of the role ofdistributed generation (DC) in future electricitysystems. Energy 2018, 163, 822–836. [Google Scholar] [CrossRef]
- Wang, Q.; Li, S.; Li, R. China’s dependency onforeign oil will exceed 0.8 by 2030: Developing anovel NMGM-ARIMA to forecast China’s foreign oildependence from two dimensions. Energy 2018, 163, 151–167. [Google Scholar] [CrossRef]
- Li, M.; Xu, H.; Li, W. The structure andcontrol method of hybrid power source for electricvehicle. Energy 2016, 112, 1273–1285. [Google Scholar] [CrossRef]
- Smiley, A.; Plettg, L. An adaptive physics-based reduced-order model of an aged lithium-ioncell, selected using an interacting multiple-modelKalman filter. J. Energy Storage 2018, 19, 120–134. [Google Scholar] [CrossRef]
- Uddin, K.; Jackson, T.; Widanage, W.D. On the possibility of extending the lifetime of lithium-ion batteries through optimal V2G facilitated by an integrated vehicle and smart-grid system. Energy 2017, 133, 710–722. [Google Scholar] [CrossRef]
- Hu, X. Power Battery Technology and Application; Chemical Industry Press: Beijing, China, 2012; pp. 125–258. [Google Scholar]
- Cheng, K.W.E.; Divakar, B.P.; Wu, H. Battery-Management System (BMS) and SOC Development for Electrical Vehicles. EEE Trans. Ions Veh. 2011, 1, 76–88. [Google Scholar] [CrossRef]
- Zhan, D.; Huang, L.; Lu, X. BMS-based control of electric vehicle battery management system. Spec. Purp. Veh. 2022, 2, 18–21. [Google Scholar]
- Battery Management System BMS Knowledge and Functions. Available online: https://zhuanlan.zhihu.com/p/403671105 (accessed on 12 July 2022).
- Williamson, S.S.; Rathore, A.K.; Musavi, F. Industrial Electronics for Electric Transportation: Current State-of-the-Art and Future Challenges. IEEE Trans. Ind. Electron. 2015, 62, 3021–3032. [Google Scholar] [CrossRef]
- Zhang, R.; Xia, B.; Li, B.; Cao, L.; Lai, Y.; Zheng, W.; Wang, H.; Wang, W. State of the art of lithium-ion battery soc estimation for electrical vehicles. Energies 2018, 11, 1820. [Google Scholar] [CrossRef]
- Rui, Z.; Qiang, L.; Sanfu, W. Research on battery data analysis of pure electric vehicles. Autom. Instrum. 2017, 11, 106–108. [Google Scholar]
- Hongyang, L.; Lin, Y.; Jilin, L. Fault diagnosis of electric vehicle battery based on long short-term memory network. Mechatronics 2020, 26, 17–23. [Google Scholar]
- Jaidi, J.; Chitta, S.D.; Akkaldevi, C.; Panchal, S.; Fowler, M.; Fraser, R. Performance Study on the Effect of Coolant Inlet Conditions for a 20 Ah LiFePO4 Prismatic Battery with Commercial Mini Channel Cold Plates. Electrochem 2022, 3, 259–275. [Google Scholar] [CrossRef]
- Ma, D.; Gao, K.; Mu, Y.; Wei, Z.; Du, R. An Adaptive Tracking-Extended Kalman Filter for SOC Estimation of Batteries with Model Uncertainty and Sensor Error. Energies 2022, 15, 3499. [Google Scholar] [CrossRef]
- Hasan, A.S.M.J.; Yusuf, J.; Faruque, R.B. Performance comparison of machine learning methods with distinct features to estimate battery SOC. In Proceedings of the 2019 IEEE Green Energy and Smart Systems Conference (IGESSC), Long Beach, CA, USA, 4–5 November 2019; pp. 1–5. [Google Scholar]
- National Automotive Standardization Technical Committee. GB/T 32960-2016 Technical Specification for Electric Vehicle Remote Service and Management System; China Standard Press: Beijing, China, 2019; pp. 1–5. [Google Scholar]
- Dou, H.; Xul, B.; Shen, F. V-SOINN: A topology preserving visualization method for multidimensional data. Neurocomputing 2021, 449, 280–289. [Google Scholar] [CrossRef]
- Paspatis, I.; Tsohou, A.; Kokolakis, S. AppAware: A policy visualization model for Mobile applications. Inf. Comput. Secur. 2020, 28, 116–132. [Google Scholar] [CrossRef]
- Huang, Q. Data visualization method and system implementation based on Python. Inf. Comput. 2019, 14, 137–140. [Google Scholar]
- Dasu, T.; Johnson, T. Exploratory Data Mining and Data Cleaning; Wiley-InterScience: Hoboken, NJ, USA, 2003. [Google Scholar]
- Mavridis, D.; White, I.R. Dealing with missing outcome data in meta-analysis. Res. Synth. Methods 2020, 11, 2–13. [Google Scholar] [CrossRef]
- Golden, R.M.; Henley, S.S.; White, H.; Kashner, T.M. Consequences of Model Misspecification for Maximum Likelihood Estimation with Missing Data. Econometrics 2019, 7, 37. [Google Scholar] [CrossRef]
- Chandola, V.; Banerjee, A.; Kumar, V. Anomaly detection: A survey. ACM Comput. Surv. 2009, 41, 58. [Google Scholar] [CrossRef]
- Min, J. Analysis and Prediction of Flight Delay Based on Data Minings. Ph.D. Thesis, Nanjing University of Aeronautics and Astronautics, Nanjing, China, 2018. [Google Scholar]
- Liu, J.; Yang, G. Short-term delay risk prediction of airport flights based on KNN. J. Chongqing Jiaotong Univ. 2021, 40, 12–18. [Google Scholar]
- Wu, D.; Wang, Y.; Wu, X.; Jin, A. Research and application of K-mean-square clustering algorithm based on Euclidean distance. Digit. Technol. Appl. 2017, 4, 148–150. [Google Scholar]
- Machine Learning Based SOC Prediction. Available online: https://blog.csdn.net/abc1234598/article/details/120027974 (accessed on 12 May 2022).
Start Byte | Definition | Type of Data | Describe |
---|---|---|---|
0 | Starter | STRING | Fixed to ASCII characters ‘#’ i.e., 0 × 23, 0 × 23 |
2 | Command ID | BYTE | See Table 2 |
3 | Response ID | BYTE | 0 × FE: command packet, received Party does not answer |
4 | VIN | STRING | Vehicle Unique VIN Car |
21 | Data encryption method | BYTE | 0 × 01: Data is not encrypted 0 × 02: RSA encryption 0 × 03: AES128 encryption |
22 | Data unit length | WORD | Data Unit Length Total Words |
24 | Data unit | COMPOUND | Divided into information type flag and information body |
Penultimate | Check code | BYTE | BCC XOR check |
Coding | Definition | Directions |
---|---|---|
0 × 01 | Vehicle login | Go up |
0 × 02 | Real-time information reporting | Up |
0 × 03 | Real-time information reporting | Up |
0 × 04 | Vehicle logout | Go up |
0 × 07 | Heartbeat | Go up |
0 × 08 | Terminal time | Up |
0 × 80 | Query command | Down |
0 × 81 | Set command | Down |
Type Code | Illustrate |
---|---|
0 × 01 | Vehicle data |
0 × 02 | Drive motor data |
0 × 03 | Fuel cell data |
0 × 04 | Engine data |
0 × 05 | Vehicle location |
0 × 06 | Extreme data |
0 × 07 | Alarm data |
0 × 08 | Rechargeable energy-storage device voltage Data |
0 × 09 | Rechargeable energy-storage device temperature data |
Algorithm Structure | Parsing Algorithm |
---|---|
(1) Public fun | Base conversion |
(2) Global Var | Define global variables |
(3) Fun_01to06 | Overall division analysis (Table 1) |
(4) Self.nextMark | Expand with the first token of the remaining message |
(5) Fun_07 | Command bit parsing |
(6) Self.ol | Display in columns |
(7) Self. next | Identify remaining messages |
Index | Illustrate |
---|---|
Vehicle status | 01: Vehicle start; 02: Turn off; 03: Other; 254: Abnormal; 255: Invalid |
Charge status | 01: Parking and charging; 02: Driving and charging; 03: Not charging; 04: Charging completed; 254: Abnormal; 255: Invalid |
Speed | Valid value range: 0∼220 km/h, 65,534 means abnormal, 65,535 means invalid |
Sum mileage | Valid value range: 0∼99,999.9 km, 4,294,967,294 means abnormal. 4,294,967,295 means invalid |
Sum voltage | Valid value range: 0∼1000 V, FFFE means abnormal, FFF means invalid |
Sum current | Valid value range: −1000∼+1000 A, 65,534 means abnormal, 65,535 means abnormal |
Soc | Valid value range: 0∼100%, 254 means abnormal, 255 means invalid |
Gearnum | Binary bits, 0–6 binary bits represent neutral gear–sixth gear, 1101 reverse gear, 1110 D gear, 1111 parking P gear |
Maxbatterysinglevoltageval | Valid value range: 0∼15 V, minimum measurement unit: 0.001 V, 65,534 means abnormal, 65,535 means invalid |
Minbatterysinglevoltageval | Valid value range: 0∼15 V, minimum measurement unit: 0.001 V, 65,534 means abnormal, 65,535 means invalid |
Maxtmpval | Valid value range: −40∼+210 °C, minimum measurement unit: 1 °C, 254 means abnormal, 255 means invalid |
Mintmpval | Valid value range: −40∼+210 °C, minimum measurement unit: 1 °C, 254 means abnormal, 255 means invalid |
Vehiclestatus | Chargestatus | Speed | Summileage | Sumcurrent | Sumvoltage | Soc | Maxtmpval | Mintmpval | |
---|---|---|---|---|---|---|---|---|---|
Count | 5111.0000 | 5111.0000 | 5111.0000 | 5111.0000 | 5111.0000 | 5111.0000 | 5111.0000 | 5111.0000 | 5111.0000 |
Mean | 1.1545 | 2.6497 | 23.8796 | 43,048.9649 | −0.7088 | 377.0951 | 73.1655 | 25.5437 | 23.8385 |
Std | 0.5004 | 0.6657 | 25.1968 | 101.3028 | 42.3631 | 16.3452 | 17.7004 | 3.7593 | 1.9647 |
Min | 1.0000 | 1.0000 | 0.0000 | 42,886.0000 | −233.700 | 347.5000 | 40.0000 | 23.0000 | 22.0000 |
Max | 3.0000 | 4.0000 | 85.8000 | 59,776.0000 | 107.0000 | 405.0000 | 100.0000 | 255.0000 | 34.0000 |
Hyperparameter Range | K, P Value Selected | MSE | Test Score |
---|---|---|---|
(3, 18), (2, 8) | K = 3, P = 2 | 0.6257625297381677 | 0.9987738423863558 |
(5, 18), (1, 8) | K = 5, P = 1 | 0.5864392223608215 | 0.9989231053759856 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Ren, W.; Bian, X.; Gong, J.; Chen, A.; Li, M.; Xia, Z.; Wang, J. Analysis and Visualization of New Energy Vehicle Battery Data. Future Internet 2022, 14, 225. https://doi.org/10.3390/fi14080225
Ren W, Bian X, Gong J, Chen A, Li M, Xia Z, Wang J. Analysis and Visualization of New Energy Vehicle Battery Data. Future Internet. 2022; 14(8):225. https://doi.org/10.3390/fi14080225
Chicago/Turabian StyleRen, Wenbo, Xinran Bian, Jiayuan Gong, Anqing Chen, Ming Li, Zhuofei Xia, and Jingnan Wang. 2022. "Analysis and Visualization of New Energy Vehicle Battery Data" Future Internet 14, no. 8: 225. https://doi.org/10.3390/fi14080225
APA StyleRen, W., Bian, X., Gong, J., Chen, A., Li, M., Xia, Z., & Wang, J. (2022). Analysis and Visualization of New Energy Vehicle Battery Data. Future Internet, 14(8), 225. https://doi.org/10.3390/fi14080225