심층 학습 기반 리튬 이온 배터리 상태 진단 시스템

다국어 초록 (Multilingual Abstract)

LIB (Lithium Ion Battery) is an energy source characterized by high energy density and low self-discharge rate. It is used in various fields due to its high-output discharge and long usage cycle, and is especially actively applied as a power source for unmanned vehicles. As LIB continues to be used, a aging phenomenon occurs in which internal resistance increases. An aged LIBs have a reduced maximum charging capacity, which affects the maximum discharge current that can be output and the maximum operating time. Therefore, in order for a mobile vehicle to smoothly perform its mission, it is necessary to use a LIB with a guaranteed maximum charging capacity, and for this, a technology that can identify the maximum charging capacity of the LIB is required. Therefore, in this paper, we propose a deep learning-based LIB state diagnosis system to effectively identify the maximum charging capacity of the LIB. The proposed system is constructed using a deep neural network-based binary classification model, and extracts and synthesizes features from the input diagnostic data to output LIB status diagnosis results. Data for diagnosing the state is derived from time series data recorded during battery use, and vector-type diagnostic data using statistical variables was generated to effectively reflect the discharge and deterioration characteristics of the LIB. In addition, three states of LIB are defined considering the difficulty of the mission performed by the vehicles and the maximum charging capacity of LIB. To evaluate the performance of the proposed system, the model's diagnostic results were visualized using a confusion matrix, and the diagnostic performance for each state was analyzed in detail using recall and precision. Additionally, the feasibility of the proposed system was verified using random discharge experiment data that was not used for learning.

목차 (Table of Contents)

• Ⅰ. 서 론 1
• 1. 연구 배경 1
• 2. 연구 필요성 2
• 2.1. 무인 이동체 탑재 부품 고장 현황 분석 2
• 2.2. 고장 발생에 따른 위험도 분석 3
• 2.3. 배터리 고장 분석 4
• 2.4. 무인 이동체 BMS 현황 6
• 3. 연구 동향 8
• 3.1. 회로 모델 기반 접근법 9
• 3.2. 데이터 기반 접근법 9
• 4. 연구 목적 11
• Ⅱ. 이론적 배경 12
• 1. 데이터 형태 12
• 1.1. 시계열 데이터 12
• 1.2. 이미지 데이터 13
• 1.3. 벡터 데이터 13
• 2. 신경망 14
• 2.1. 심층 신경망 14
• 2.2. 합성곱 신경망 15
• 2.3. 순환 신경망 16
• 3. 학습 관련 기술 18
• 3.1. 하이퍼 파라미터 18
• 3.2. 활성화 함수 19
• 3.3. 잔차 연결 23
• 3.4. 손실 함수 24
• 3.5. 매개변수 최적화 25
• 3.6. 일반화 27
• 3.7. 성능 개선을 위한 학습 기술 28
• 4. 혼동 행렬 30
• Ⅲ. LIB 열화 데이터 셋 32
• 1. 배터리 수명 측정을 위한 충/방전 실험 방법 32
• 2. 열화 실험 34
• 2.1. 전력 특성 분석 34
• 2.2. 실험 조건 및 환경 36
• 2.3. 실험 데이터 분석 43
• 3. 공개 데이터 셋 45
• Ⅳ. 심층 학습 기반 LIB 상태 진단 시스템 49
• 1. 개요 49
• 2. 진단 데이터 셋 49
• 2.1 상태 검진 데이터 49
• 2.2 상태 진단 데이터 52
• 2.3 진단 데이터 셋 생성 53
• 3. 진단 모델 생성 54
• 3.1 모델 구성 54
• 3.2 모델 학습 및 평가 56
• 4. 모델 검증 및 분석 60
• 4.1 검증 및 분석 60
• 4.2 모델 비교 분석 63
• Ⅴ. 결론 67
• 참고문헌 또는 인용문헌 69