Differences

This shows you the differences between two versions of the page.

--- knowledge_base:professional:battery [2025/05/03 22:07] – [Dual Battery System] Normal User
+++ knowledge_base:professional:battery [2025/07/08 15:40] (current) – [Modeling from Advanced BMS Work Shop AAC 2025] Normal User
@@ Line 19: / Line 19: @@
     * Easy translation to what-if DoU
     * User oriented (vs engineering oriented) DoU communications
+===== Modeling from Advanced BMS Work Shop AAC 2025 =====
+  * Battery swells (some reversable, some permanent). It is found to be very beneficial to reduce aging by applying 5 psi pressure to physically limiting the swelling. Too much pressure can also be problematic. This information was provided by professor Anna G. Stefanopoulou from U. Michigan.
+  * P2D physical model
+  * PCA correlation analysis
+  * Parallel R*C benefits
+  * SOC physical model not temperature, c-rate dependent
+  * Symbolic regression.
+  * DFN (doyle fuller newman) model
+  * Single particle model (simple model has limitations)
+  * POD - reduced order model ROM
+  * ESPM
+  * Adaptive Ensemble Sparse Identification (AESI)
+  * SPCI method
+  * SYNDy approach
+  * SPM -> ESPM
+  * {{ :knowledge_base:professional:acc-plett-advanced_battery_management-perspectives_on_the_role_of_machine_learning.zip |}}
+==== Raw Notes ====
+  * PCA - Principal Component Analysis (PCA) and neural networks are powerful tools in data analysis, and they can be used together in various ways. PCA is often used as a preprocessing step for neural networks, particularly with high-dimensional data, to reduce dimensionality and improve model performance. Additionally, neural networks can be designed to perform PCA-like operations, effectively learning the principal components during training
+  * Sys ID - surrogate AI model types and how to choose - simple feedforward, long-short (LSTM) memory model. Delayed input...
+  * Model Conversion, Training methods - PyTorch, TensorFlow, MATLA
+  * RNN vs LSTM vs GRU vs Transformers - https://www.geeksforgeeks.org/deep-learning/rnn-vs-lstm-vs-gru-vs-transformers/
+  * Virtual sensor - How to identify if the import has correlation to output to reduce the order of the system - perturbation sensitivity analysis.
+  * Imitation learning
+  * NLP/QP solving for MPC is expensive
+  * Neural state space model
+  * Reinforcement learning (RL)
+  * Pruning and projection (structure compression), quantization (data compression) to deploy for low memory low computing power applications.