No abstract

No abstract

Over several decades, control theory has developed its own set of more or less formal modelling techniques designed to automatically control the dynamic behaviour of complicated manufacturing systems and processes. The emerging Internet society is addressing new enterprise control and management integration (ECMI) challenges for agile business to manufacturing (B2M) purposes which enlarge the traditional setting of Automation Engineering to the systems engineering (SE) approach. In order to cope with the increasing complexity of integrating intelligence/information-intensive manufacturing automation within the networked manufacturing enterprise, Automation Engineering should be integrated into the systems engineering approach to achieve a holistic approach that treats in fine the technical operational manufacturing system emerging from the deployment of an ad hoc combination of formal and informal partial models. This paper emphasises that a Holonic Manufacturing Execution System Engineering (HMESE) approach should be a relevant B2M SE approach along with other relevant scientific, industrial and educational areas dealing with information and intelligence control and management issues in agile automation.

Abstract-This paper deals with robust iterative learning control design for uncertain single-input-single-output linear time-invariant systems. The design procedure is based upon solving the robust performance condition using the Youla parameterization and the µ-synthesis approachto obtain a feedback controller. Thereafter, a convergent iterative learning law is obtained by using the performance weighting function involved in the robust performance condition. Experimental results, on a CRS465 robot manipulator, are provided to illustrate the effectiveness of the proposed design method.

No abstract

The design of multiple human activity recognition applications in areas such as healthcare, sports and safety relies on wearable sensor technologies. However, when making decisions based on the data acquired by such sensors in practical situations, several factors related to sensor data alignment, data losses, and noise, among other experimental constraints, deteriorate data quality and model accuracy. To tackle these issues, this paper presents a data-driven iterative learning framework to classify human locomotion activities such as walk, stand, lie, and sit, extracted from the Opportunity dataset. Data acquired by twelve 3-axial acceleration sensors and seven inertial measurement units are initially de-noised using a two-stage consecutive filtering approach combining a band-pass Finite Impulse Response (FIR) and a wavelet filter. A series of statistical parameters are extracted from the kinematical features, including the principal components and singular value decomposition of roll, pitch, yaw and the norm of the axial components. The novel interactive learning procedure is then applied in order to minimize the number of samples required to classify human locomotion activities. Only those samples that are most distant from the centroids of data clusters, according to a measure presented in the paper, are selected as candidates for the training dataset. The newly built dataset is then used to train an SVM multi-class classifier. The latter will produce the lowest prediction error. The proposed learning framework ensures a high level of robustness to variations in the quality of input data, while only using a much lower number of training samples and therefore a much shorter training time, which is an important consideration given the large size of the dataset.

No abstract

No abstract