AI for Status Monitoring of Utility Scale Batteries
2: University of Warwick, UK
3: Department of Automation, University of Science and Technology, China
4: AAU Energy, Aalborg University, Denmark
5: Robert Gordon University, Scotland
Batteries are a necessary part of a low-emission energy system, as they can store renewable electricity and assist the grid. Utility-scale batteries, with capacities of several to hundreds of MWh, are particularly important for condominiums, local grid nodes, and EV charging arrays. However, such batteries are expensive and need to be monitored and managed well to maintain capacity and reliability. Artificial intelligence offers a solution for effective monitoring and management of utility-scale batteries.
This book systematically describes AI-based technologies for battery state estimation and modeling for utility-scale Li-ion batteries. Chapters cover utility-scale lithium-ion battery system characteristics, AI-based equivalent modeling, parameter identification, state of charge estimation, battery parameter estimation, offer samples and case studies for utility-scale battery operation, and conclude with a summary and prospect for AI-based battery status monitoring. The book provides practical references for the design and application of large-scale lithium-ion battery systems.
AI for Status Monitoring of Utility-Scale Batteries is an invaluable resource for researchers in battery R&D, including battery management systems and related power electronics, battery manufacturers, and advanced students.
Inspec keywords: battery management systems; power engineering computing; artificial intelligence; secondary cells; lithium compounds
Other keywords: wind power plants; battery management systems; parameter estimation; distributed power generation; fossil fuels; utility scale batteries; power engineering computing; artificial intelligence; lithium compounds; status monitoring; secondary cells; photovoltaic power systems
Subjects: Secondary cells; General electrical engineering topics; General and management topics; Conference proceedings; Secondary cells; Knowledge based systems; Power engineering computing
- Book DOI: 10.1049/PBPO238E
- Chapter DOI: 10.1049/PBPO238E
- ISBN: 9781839537387
- e-ISBN: 9781839537394
- Page count: 495
- Format: PDF
-
Front Matter
- + Show details - Hide details
-
p.
(1)
-
1 Introduction
- + Show details - Hide details
-
p.
1
–23
(23)
Some researchers estimate that the fossil fuel reserves can support the world's demand for power for 50 years, whereas others say it will be 100-120 years [1]. Though there is no accurate number about how many years the fuel reserves will deplete, at least it shows that the current energy source is shortly facing a serious shortage [2]. The infrastructure for the current power grid is rapidly aging [3]. The radical changes in the environment show the great negative effects brought by the consumption of fossil resources. Based on these factors, the concept of "smart grids" has been advanced, requiring the modernization of the distribution and the transmission system [4]. One of the priorities of the smart grid is to deploy and integrate distributed resources, including renewable energy resources. One way in which utility-scale battery storage is particularly helpful is in being paired with renewable resources, such as solar or wind farms [5]. These resources provide a forecastable, predictable amount of generation every hour but, due to the nature of sun and wind, do not generate at their maximum capacity every hour. By pairing utility-scale batteries with solar and wind, resource developers can smoothen the output from these resources and ensure that renewable energy is injected onto the grid at the times when it is most needed [6]. Renewable resources are substantial for the long term and can be used to generate electricity with low or zero CO2 emissions. In some European countries, more than 30% of electricity comes from renewable energy including photovoltaic (PV) power, wind, and other resources.
-
2 Utility-scale lithium-ion battery system characteristics
- + Show details - Hide details
-
p.
25
–60
(36)
(1) Brief introduction of lithium-ion battery
Lithium-ion battery system is a complex system integrating chemical, electrical, and mechanical characteristics [62]. So the requirements of the various characteristics must be considered for the design of a lithium-ion battery. In particular, the safety and life attenuation characteristics contained in the chemical characteristics of the battery cell cannot be measured directly by the equipment, and it is not easy to predict in a short time. Therefore, when designing the battery system, battery technology, group technology, and BMS (battery management system) technology should be adopted to ensure the safety, reliability, and durability of the battery.
-
3 AI-based equivalent modeling and parameter identification
- + Show details - Hide details
-
p.
61
–144
(84)
The significance of battery model is to establish a clear mathematical relationship, and then we can get important input and output. Various characteristics of the battery in the work can be estimated by establishing an accurate battery model, analyzing and testing the feasibility and effectiveness of the battery model by applying specific software, and finally verifying the accuracy of the model by comparing with the experiment. Parameter identification is the process of processing the experimental data after the experiment. Most of the offline identification methods are based on offline data, such as linear fitting, LS method, and so on. Online identification algorithm is the mainstream algorithm of battery parameter identification at present, which can be divided into two categories: one is the derivative algorithm of LS method, including RLS method, deviation compensation RLS method, and LS derivative algorithm with forgetting factor. In the field of system identification, LS method is a basic estimation method. The LS method can be used in both dynamic and static systems; it can be used in both linear and nonlinear systems; it can be used for offline estimation and online estimation.
-
4 Use of artificial intelligence for utility-scale battery systems
- + Show details - Hide details
-
p.
145
–183
(39)
In the battery system, the application of artificial intelligence will have a profound impact on it. With the use of lithium-ion batteries, more and more data are accumulated, so the use of artificial intelligence methods can achieve accurate battery parameter prediction for battery systems. This chapter mainly introduces artificial intelligence that is an application in utility-scale battery systems. First, this chapter analyzes the application of commonly used artificial intelligence methods in battery systems from the selection criteria for selecting artificial intelligence technologies, which include the common artificial intelligence methods for utility-scale battery systems and the artificial intelligence technology evaluation index. Besides, this chapter describes the monitoring of utility-scale battery development with artificial intelligence, which includes the development status and prospects. Last, the basic parameters in AI-based status monitoring are analyzed in this chapter, such as voltage for input and correction, capacity for internal state parameters, internal resistance for internal state parameters, polarization resistance and capacitance internal state parameters, and energy density for correction. For the application of artificial intelligence methods in lithium-ion battery systems, the first part is the selection criteria for artificial intelligence technology. This part analyzes the application of some existing artificial intelligence methods in lithium-ion battery systems, including utility-scale applications. Common artificial intelligence methods are explained, such as some machine-learning artificial intelligence methods, data-driven methods, etc., through the introduction of these methods, the application prospects of artificial intelligence methods in lithium-ion battery systems, and the resulting benefit.
-
5 AI-based state-of-charge estimation
- + Show details - Hide details
-
p.
185
–310
(126)
Neural networks have been widely used for image recognition and result prediction based on input data. Compared with other SOC estimation methods, the neural network method does not need to accurately consider the electrochemical state inside the battery to estimate the SOC by self-learning capability. With the continuous development of artificial intelligence, neural network methods have received increasing attention from researchers in the battery field. However, few articles summarize neural network methods individually. This review examines recent articles that use neural network methods alone to estimate the SOC of lithium-ion batteries, dividing the methods into FFNN method, deep learning method, and hybrid method. Then, the neural network method is summarized and discussed from the aspects of network structure, algorithm principle, appropriate environment, advantages, disadvantages, and estimation errors. The challenges to neural network use in the EV field are discussed briefly, and the prospects and opportunities for neural networks are examined in closing.
-
6 AI-based battery parameter estimation
- + Show details - Hide details
-
p.
311
–369
(59)
With the application of lithium-ion batteries (LIBs) in aerospace, new energy vehicles, civil power generation and other fields, ensuring the safety and reliability of LIBs in complex working conditions has become a hot issue in the field of LIBs research [196]. Researchers use the state of health (SOH) of LIBs to indirectly represent the current performance of batteries, so it is very important to accurately estimate the SOH of lithium batteries and evaluate the health status of lithium batteries. To extend the life of the battery while ensuring reliability throughout its life, it is crucial to accurately diagnose the SOH of the battery in real time [197]. Battery SOH represents the capacity of the current battery to store electric energy relative to the new battery and represents the state of the battery from the beginning to the end of its life in percentage form, which is used to quantitatively describe the current battery performance state.
-
7 Examples and case studies for utility-scale battery operation
- + Show details - Hide details
-
p.
371
–397
(27)
The battery management system is closely combined with the battery to detect the battery's voltage, current, and temperature in real time [286]. Besides, it also carries out leakage detection, thermal management, battery balance management, alarm reminder, calculation of the residual capacity and discharge power. According to the voltage, current, and temperature of the battery, the maximum output power is controlled by the algorithm to obtain the maximum driving mileage, the optimal current is controlled by the charging algorithm, and real-time communication is carried out with an onboard general controller, motor controller, energy control system and onboard display system through the CAN bus interface. The basic functional block diagram of the battery management system is shown in Figure 7.1.
-
8 Summary and prospect for AI-based battery status monitoring
- + Show details - Hide details
-
p.
399
–432
(34)
As the most important material found in the industrial age, energy plays an irreplaceable supporting role in the progress and development of human society. Party and state leaders also deeply recognized the importance of energy and made important instructions: 'Throughout the historical context of social progress and development, every major progress of human civilization is also accompanied by the continuous improvement and development of energy' [339]. As the evolution of the international energy crisis and the pollution caused by fossil energy has drawn international public attention, the international energy landscape is undergoing profound changes [340]. The biggest change is that renewable energy, mainly clean energy, has an increasing proportion in the country's total energy.
-
Back Matter
- + Show details - Hide details
-
p.
(1)