The state-of-charge (SOC) is a crucial parameter of a battery management system (BMS) for Li-ion batteries. The SOC indicates the amount of charge left in the battery of electric vehicles - akin to the fuel gauge in combustion vehicles. An accurate SOC knowledge contributes largely to the longevity, performance, reliability of the battery. However, the SOC of Li-ion batteries cannot be easily measured by any apparatus. Furthermore, the SOC also can be influenced by numerous incalculable factors such as battery chemistry, ambient environment, aging factor, etc. In this study, we propose a SOC estimation model for a Li-ion battery using an improved deep neural network (DNN) approach for electric vehicle applications. We found that a DNN with a sufficient number of hidden layers is capable of predicting the SOC of the unseen drive cycles during training. We developed a series of DNN models with a varying number of hidden layers, its training algorithm was to investigate their respective performance when evaluated on different drive cycles. We observe that increasing hidden layers in DNN (up to 4 hidden layers) decreases the error rate and improves the SOC estimation. An additional increase of hidden layer beyond that increases the error rate. In this study we show that a 4 hidden layer DNN trained on dynamic stress test (DST) drive cycle is capable of predicting SOC values unexpectedly well of other unseen drive cycles such as federal urban driving schedule (FUDS), Beijing dynamic stress test (BJDST), and supplemental federal test procedure (US06), respectively.
7 June 2022 in IEEE Transactions on Industry Applications
State-of-charge (SOC) is a crucial battery quantity that needs constant monitoring to ensure cell longevity and safe operation. However, SOC is not an observable quantity and cannot be practically measured outside of laboratory environments. Hence, machine learning (ML) has been employed to map correlated observable signals such as voltage, current, and temperature to SOC values. In recent studies, deep learning (DL) has been a prominent ML approach outperforming many existing methods for SOC estimation. However, yielding optimal performance from DL models relies heavily on an appropriate selection of hyperparameters. At present, researchers relied on established heuristics to select hyperparameters through manual tuning or exhaustive search methods such as grid search and random search. This results in lengthy development time in addition to less accurate and inefficient models. This study proposes a systematic and automated approach to hyperparameter selection with a Bayesian optimization strategy known as tree Parzen estimator (TPE) in combination with the Hyperband pruning algorithm. The TPE optimization is run on various DL models such as BGRU, GRU, LSTM, CNN, FCN, and DNN to optimize for the best hyperparameter combination for each architecture. The Hyperband pruning algorithm is used to prune unpromising trials during the TPE run which results in time and computational resource savings. Experiment results show that the best performing model, BGRU-TPE incurs a low computation cost with no compromise in model accuracy, maintaining the best balance of both. The proposed model BGRU-TPE achieves the lowest RMSE and MAE error at 0.8% and 0.56%, respectively on various electric vehicle drive cycles at varying ambient temperatures and maintains a low computational cost at 15 600 FLOPS with the model size of only 193.3 KB.
1 July 2022 in International Journal of Advanced Robotic Systems
In nuclear and radiation-related industries, it is crucial to ensure that the radiation dose exposure to the radiation worker is maintained below the permissible dose limit. A radiation map is a useful tool for visualizing the radiation distribution across the work area and for coordinating activities involving the hotspots (high radiation areas). The goal of this work was to design and implement a coverage path planning approach for autonomous radiation mapping carried out by a mobile robot. Given a 2D occupancy map, a method to generate uniformly distributed sampling points was proposed. The geometry of the region of interest, the radiation detector module, and the radiation measurement parameters were considered in formulating the sampling positions. Next, the coverage path planning planner integrates the nearest neighbor and depth-first search algorithms to create a continuous path that enables the robot to visit all the sampling points. The K-means clustering algorithm is added for systematic coverage of a large number of sampling points. The clustering provides options to partition the region of interest into smaller spaces, where the robot would perform the mapping cluster by cluster. Finally, the method of building the radiation map from the acquired data was also presented. The approach was implemented in ROS using a commercial mobile robot equipped with a Geiger–Muller detector. The performance and reliability of the proposed approach were evaluated with a series of simulations and real-world experiments. The results showed that the robot is able to perform autonomous radiation mapping at various target areas. The accuracy of the generated radiation map and the hotspots classifications were also compared and evaluated with conventional manual measurements. Overall, the theoretical frameworks and experiments have provided convincing results in the automation of hazardous work and subsequently toward improving the occupational safety of radiation workers.
This thesis reports the process of design and development of a low cost small sized in-pipe inspection robot. Problem of a pipe inspection operation surfaces when the robot only has a limited coverage of the inner surfaces of the pipe. Moreover, current solutions are largely sized and are not appropriate for smaller sized pipelines. Feasibility study completed produced a set of design requirements to be met for the final design to be able to operate inside a pipeline with inner diameter ranging from 80 mm to 180 mm. The use of magnets was decided as an adhesion system to allow the robot a full range of motion inside the pipe. Technical analyses were completed in parallel with the design work to ensure the design remains up-to-date in case there are changes in the off-the-shelf components used. A prototype of the final design was fabricated. Tests completed successfully demonstrated the robot traversing vertically and upside down on ferromagnetic surfaces, further proving the feasibility of the motor selection analysis. Moreover, the final design prototype managed to successfully satisfy the main objective of the project by being able to fit in a pipe environment with inner diameter ranging from 80 mm to 180 mm.
This article presents a collision avoidance system for multiple robots based on the current autonomous car collision avoidance system. The purpose of the system is to improve the current autonomous car collision avoidance system by including data input of other vehicles’ velocity and positioning via vehicle-to-vehicle communication into the current autonomous car collision avoidance system. There are two TurtleBots used in experimental testing. TurtleBot is used as the robot agent while Google Lightweight Communication and Marshalling is used for inter-robot communication. Additionally, Gazebo software is used to run the simulation. There are two types of collision avoidance system algorithm (collision avoidance system without inter-robot communication and collision avoidance system with inter-robot communication) that are developed and tested in two main road crash scenarios, rear end collision scenario and junction crossing intersection collision scenario. Both algorithms are tested and run both in simulation and experiment setup, each with 10 repetitions for Lead TurtleBot sudden stop, Lead TurtleBot decelerate, Lead TurtleBot slower speed, and straight crossing path conditions. Simulation and experimental results data for each algorithm are recorded and tabulated. A comprehensive comparison of performance between the proposed algorithms is analyzed. The results showed that the proposed system is able to prevent collision between vehicles with an acceptable success rate.