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.

One of the key components in real-time monitoring and control on machining and surface finishing processes are sensors. The advances of such system have triggered interesting questions on sensor selection that act as the fundamental before starting a project. This paper is made to review and answer the questions surrounding sensor selection. The paper first explains on the type of sensors commonly used in practice for real-time monitoring and control systems. After which, the paper discusses on how often the sensors are used on several machining and surface finishing processes and what are the reasons for the sensor selection. Thereafter, a review on the type features commonly analysed through these sensors is discussed. The paper expects reader would decide better upon selecting sensors and has a better direction in their project. Thus the paper works to guide reader to improve based on what has been completed before. Published version

The monitoring of surface finishing processes in aerospace manufacturing industry becomes one of key issues to maintain the overall quality of product or part. To date, the surface quality monitoring post machining processes such as deburring, use visual inspection, surface roughness test or laser gap gun. The whole manufacturing process then requires a considerable amount of time as the production line must be halted due to these measurements taking place. This study presents an online monitoring system to measure the chamfer quality of replica boss hole post-deburring process. Vibration signal was measured during the deburring process and the features that correlate to the deburring stages (passes) were extracted. This paper focuses on the validation of actual vibration signal with the modal analysis of work coupon (replica boss hole) to obtain the correlation between the vibration amplitude level on particular region and the mode shape of work coupon during the deburring process. Published version

The industrial revolution has reached a new development cycle which uses the advantages of cyber world into the physical world of manufacturing, and called Industry 4.0. Cyber world offers Internet of Things which allows transmission and reception of data from and to anywhere on earth through Internet. In the current aerospace industry, the production of components has significant manual work involved. Meanwhile, the demand in quantity and quality of these components are increasing. In order to enhance manufacturing capability and solve this, this paper introduced a universal platform for real time sensors monitoring and analysis for Industry 4.0 implementation in aerospace industry. Our objective was to develop a universal platform that is reliable to be used in various analytical applications and investigate the supporting factors that has to be considered in applying such platform. To achieve this objective, the paper used easily available hardware which consists of ABB Robot, Wi-Fi Data Acquisition Systems (Wi-Fi DAQs), FPGA equipped CompactRIO, Wireless Access Point (WAP), sensors, and monitor. The system mentioned is made to trial for aerospace component manufacturing processes. The data acquired from the sensors is collected and transmitted by the Wi-Fi DAQs to the WAP. Consequently, the CompactRIO will collect the sensors data from the WAP and analyze them. The result will then be sent to the internet and also used to trigger necessary action for the ABB Robot based on predetermined decision making tables or resources. Ultimately, this application enables aerospace component manufacturers to enhance their capability to increase the product quality and manufacturing process safety while also reduce the manufacturing time required.

Process monitoring using indirect methods relies on the usage of sensors. Using sensors to acquire vital process related information also presents itself with the problem of big data management and analysis. Due to uncertainty in the frequency of events occurring, a higher sampling rate is often used in real-time monitoring applications to increase the chances of capturing and understanding all possible events related to the process. Advanced signal processing methods are used to further decipher meaningful information from the acquired data. In this research work, power spectrum density (PSD) of sensor data acquired at sampling rates between 40-51.2 kHz was calculated and the corelation between PSD and completed number of cycles/passes is presented. Here, the progress in number of cycles/passes is the event this research work intends to classify and the algorithm used to compute PSD is Welch's estimate method. A comparison between Welch's estimate method and statistical methods is also discussed. A clear co-relation was observed using Welch's estimate to classify the number of cycles/passes. The paper also succeeds in classifying vibration signal generated by the spindle from the vibration signal acquired during finishing process. ispartof: SENSORS vol:17 issue:6 ispartof: location:Switzerland status: published

Measurement of surface roughness of any machining process is crucial for obtaining a component or part of the correct size and surface finish in the first instance, in order to minimize the manufacturing cost. In-process monitoring of machining processes based on an estimation of the surface roughness using the cutting parameters is inaccurate. In this investigation, a fuzzy inference system based on an intelligent sensor fusion model has been developed for the purpose of in-process indirect measurement of surface roughness for a machining process. In the proposed technique, measurement of the Speed Force component, Radial Force component, Feed Force component, Vibration, and Acoustic Emission sensor inputs from a turning process have been considered as the inputs. The results have been compared with the surface roughness estimated with a second order regression model using cutting parameters as inputs. The proposed method has shown considerable improvement in the surface roughness estimation in a simulation environment.