Search

Motion intention detection is fundamental in the implementation of human-machine interfaces applied to assistive robots. In this paper, multiple machine learning techniques have been explored for creating upper limb motion prediction models, which generally depend on three factors: the signals collected from the user (such as kinematic or physiological), the extracted features and the selected algorithm. We explore the use of different features extracted from various signals when used to train multiple algorithms for the prediction of elbow flexion angle trajectories. The accuracy of the prediction was evaluated based on the mean velocity and peak amplitude of the trajectory, which are sufficient to fully define it. Results show that prediction accuracy when using solely physiological signals is low, however, when kinematic signals are included, it is largely improved. This suggests kinematic signals provide a reliable source of information for predicting elbow trajectories. Different models were trained using 10 algorithms. Regularization algorithms performed well in all conditions, whereas neural networks performed better when the most important features are selected. The extensive analysis provided in this study can be consulted to aid in the development of accurate upper limb motion intention detection models. Agency for Science, Technology and Research (A*STAR) Published version This work was partially supported by the grant “Intelligent Human-Robot interface for upper limb wearable robots” (Award Number SERC1922500046, A*STAR, Singapore).

Manufacturing of aerospace components consists of combination of different types of machining, finishing, and measuring processes. One of the finishing processes is deburring, i.e. a finishing process to remove burrs from work coupons after a boring hole process. Deburring is conducted to achieve required surface finish quality prior to further processes in assembly line. This paper introduces sensor data analysis as a tool to quantify and correlate the deburring stage with the features extracted from sensors data. This study covers signal processing, feature extraction and analytical method to determine its relevancy to the surface finish quality from deburring process. Wavelet decomposition and Welch’s spectrum estimate is used as a signal processing and feature extraction method. Consequently, the features are used as the basis for analysis by adaptive neuro-fuzzy inference system (ANFIS). The ANFIS yields the output corresponding to the predicted surface finish quality in terms of boss hole chamfer length and the stage classification of deburring process. The results show a decreasing trend in measured vibration signal, which is qualitatively well correlated to the deburring stage and the development of chamfer length during deburring process.

The deburring process in aerospace industry involves significant amount of manual work such as surface roughness measurement and quality verification. This manual works hinder the implementation of industry 4.0. This paper discusses on the implementation of machine learning and cloud computing to improve the conventional deburring process in aerospace manufacturing industry to be ready for industry 4.0 upgrade. The paper starts with the introduction of deburring, machine learning, and cloud computing in relevant to aerospace industry. The paper then discusses on the analytical approach of determining chamfer length of deburring through machine learning analysis from sensors data collected in the deburring process. Machine learning is one example of analysis tools to replace the manual work which often involves subjective judgement, with data-based judgement. The paper also shows the offline machine learning result and the advantages that can be brought by online machine learning implementation. After all this, the paper details on the advantages of implementing machine learning into the deburring process for aerospace industry. Moreover, the effort to scale up the deburring process using cloud services for long sustainability will be discussed. At the end of the paper, the readers can understand the implementation of machine learning and cloud computing on deburring process in aerospace industry.

The number of studies on the Internet of Things (IoT) has grown significantly in the past decade and has been applied in various fields. The IoT term sounds like it is specifically for computer science but it has actually been widely applied in the engineering field, especially in industrial applications, e.g., manufacturing processes. The number of published papers in the IoT has also increased significantly, addressing various applications. A particular application of the IoT in these industries has brought in a new term, the so-called Industrial IoT (IIoT). This paper concisely reviews the IoT from the perspective of industrial applications, in particular, the major pillars in order to build an IoT application, i.e., architectural and cloud computing. This enabled readers to understand the concept of the IIoT and to identify the starting point. A case study of the Amazon Web Services Machine Learning (AML) platform for the chamfer length prediction of deburring processes is presented. An experimental setup of the deburring process and steps that must be taken to apply AML practically are also presented. NRF (Natl Research Foundation, S’pore) Published version