Search for: All records

Electric vehicles (EVs) are considered an environmentally friendly option to conventional vehicles. As the most critical module in EVs, batteries are complex electrochemical components with nonlinear behavior. On-board battery system performance is also affected by complicated operating environments. Real-time EV battery in-service status prediction is tricky but vital to enable fault diagnosis and aid in the prevention of dangerous occurrences. Data-driven models with advantages in time series analysis can be used to capture the degradation pattern from data about certain performance indicators and predict the battery states. The Transformer model is capable of capturing long-range dependencies efficiently using a multi-head attention block mechanism. This paper presents the implementation of a standard Transformer and an encoder-only Transformer neural network to predict EV battery state of health (SOH). Based on the analysis of the lithium-ion battery from NASA Prognostics Center of Excellence website's publicly accessible dataset, 28 features related to the charge and discharge measurement data are extracted. The features are screened using Pearson correlation coefficients. The results show that the filtered features can effectively improve the accuracy of the model as well as the computational efficiency. The proposed standard Transformer shows good performance in SOH prediction. 

Activity recognition is a crucial aspect in smart manufacturing and human-robot collaboration, as robots play a vital role in improving efficiency and safety by accurately recognizing human intentions and proactively assisting with tasks. Current human intention recognition applications only consider the accuracy of recognition but ignore the importance of predicting it in advance. Given human reaching movements, we want to equip the robot with the ability to predict human intent not only with precise recognition but also at an early stage. In this paper, we propose a framework to apply Transformer-based and LSTM-based models to learn motion intentions. Second, based on the observation of distances of human joints along the motion trajectory, we explore how we can use the hidden Markov model to find intent state transitions, i.e., intent uncertainty and intent certainty. Finally, two data types are generated, one for the full data and the other for the length of data before state transitions; both data are evaluated on models to assess the robustness of intention prediction. We conducted experiments in a manufacturing workspace where the experimenter reaches multiple scattered targets and further this experimental scenario was designed to examine how intents differ, but motions are only slightly different. The proposed models were then evaluated with experimental data, and further performance comparisons were made between models and between different intents. Finally, early predictions were validated to be better than using full-length data. 

Large volumes of used electronics are often collected in remanufacturing plants, which requires disassembly before harvesting parts for reuse. Disassembly is mainly conducted manually with low productivity. Recently, human-robot collaboration is considered as a solution. For robots to assist effectively, they should observe work environments and recognize human actions accurately. Rich activity video recording and supervised learning can be used to extract insights; however, supervised learning does not allow robots to self-accomplish the learning process. This study proposes an unsupervised learning framework for achieving video-based human activity recognition. The framework consists of two main elements: a variational autoencoder-based architecture for unlabeled data representation learning, and a hidden Markov model for activity state division. The complete explicit activity classification is validated against ground truth labels; here, we use a case study of disassembling a hard disk drive. The framework shows an average recognition accuracy of 91.52% , higher than competing methods. 

Abstract Disassembly is an essential process for the recovery of end-of-life (EOL) electronics in remanufacturing sites. Nevertheless, the process remains labor-intensive due to EOL electronics’ high degree of uncertainty and complexity. The robotic technology can assist in improving disassembly efficiency; however, the characteristics of EOL electronics pose difficulties for robot operation, such as removing small components. For such tasks, detecting small objects is critical for robotic disassembly systems. Screws are widely used as fasteners in ordinary electronic products while having small sizes and varying shapes in a scene. To enable robotic systems to disassemble screws, the location information and the required tools need to be predicted. This paper proposes a computer vision framework for detecting screws and recommending related tools for disassembly. First, a YOLOv4 algorithm is used to detect screw targets in EOL electronic devices and a screw image extraction mechanism is executed based on the position coordinates predicted by YOLOv4. Second, after obtaining the screw images, the EfficientNetv2 algorithm is applied for screw shape classification. In addition to proposing a framework for automatic small-object detection, we explore how to modify the object detection algorithm to improve its performance and discuss the sensitivity of tool recommendations to the detection predictions. A case study of three different types of screws in EOL electronics is used to evaluate the performance of the proposed framework. 

Abstract Disassembly is an essential step for remanufacturing end-of-life (EOL) products. Optimization of disassembly sequences and the utilization of robotic technology could alleviate the labor-intensive nature of dismantling operations. This study proposes an optimization framework for disassembly sequence planning under uncertainty considering human–robot collaboration. The proposed framework combines three attributes: disassembly cost, safety, and complexity of disassembly, namely disassembleability, to identify the optimal disassembly path and allocate operations between human and robot. A multi-attribute utility function is used to address uncertainty and make a tradeoff among multiple attributes. The disassembly time reflects the cost of disassembly which is assumed to be an uncertain parameter with a Beta distribution; the disassembleability evaluates the feasibility of conducting operations by robot; finally, the safety index ensures the protection of human workers in the work environment. An example of dismantling a desktop computer is used to show the application. The model identifies the optimal disassembly sequence with less disassembly cost, high disassembleability, and increased safety index while allocating disassembly operations among human and robot. A sensitivity analysis is conducted to show the model's performance when changing the disassembly cost for the robot. 

A rapid rise in the recycling and remanufacturing of end-of-use electronic waste (e-waste) has been observed due to multiple factors including our increased dependence on electronic products and the lack of resources to meet the demand. E-waste disassembly, which is the operation of extracting valuable components for recycling purposes, has received ever increasing attention as it can serve both the economy and the environment. Traditionally, e-waste disassembly is labor intensive with significant occupational hazards. To reduce labor costs and enhance working efficiency, collaborative robots (cobots) might be a viable option and the feasibility of deploying cobots in high-risk or low value-added e-waste disassembly operations is of tremendous significance to be investigated. Therefore, the major objective of this study was to evaluate the effects of working with a cobot during e-waste disassembly processes on human workload and ergonomics through a human subject experiment. Statistical results revealed that using a cobot to assist participants with the desktop disassembly task reduced the sum of the NASA-TLX scores significantly compared to disassembling by themselves (p = 0.001). With regard to ergonomics, a significant reduction was observed in participants’ mean L5/S1 flexion angle as well as mean shoulder flexion angle on both sides when working with the cobot (p < 0.001). However, participants took a significantly longer time to accomplish the disassembly task when working with the cobot (p < 0.001), indicating a trade-off of deploying cobot in the e-waste disassembly process. Results from this study could advance the knowledge of how human workers would behave and react during human-robot collaborative e-waste disassembly tasks and shed light on the design of better HRC for this specific context. 

This paper presents a comprehensive disassembly sequence planning (DSP) algorithm in the human–robot collaboration (HRC) setting with consideration of several important factors including limited resources and human workers’ safety. The proposed DSP algorithm is capable of planning and distributing disassembly tasks among the human operator, the robot, and HRC, aiming to minimize the total disassembly time without violating resources and safety constraints. Regarding the resource constraints, we consider one human operator and one robot, and a limited quantity of disassembly tools. Regarding the safety constraints, we consider avoiding potential human injuries from to-be-disassembled components and possible collisions between the human operator and the robot due to the short distance between disassembly tasks. In addition, the transitions for tool changing, the moving between disassembly modules, and the precedence constraint of components to be disassembled are also considered and formulated as constraints in the problem formulation. Both numerical and experimental studies on the disassembly of a used hard disk drive (HDD) have been conducted to validate the proposed algorithm.