Search Results (3)

Improving the decoding accuracy of biological signals has been a research focus for decades to advance health, automation, and robotic industries. However, challenges like inter-subject variability, data scarcity, and multifunctional variability cause low decoding accuracy, thus hindering the practical deployment of biological signal paradigms. This paper proposes a multifunctional biological signals network (Multi-BioSig-Net) that addresses the aforementioned issues by devising a novel blind few-shot learning (FSL) technique to quickly adapt to multiple target domains without needing a pre-trained model. Specifically, our proposed multimodal similarity extractor (MMSE) and self-multiple domain adaptation (SMDA) modules address data scarcity and inter-subject variability issues by exploiting and enhancing the similarity between multimodal samples and quickly adapting the target domains by adaptively adjusting the parameters’ weights and position, respectively. For multifunctional learning, we proposed inter-function discriminator (IFD) that discriminates the classes by extracting inter-class common features and then subtracts them from both classes to avoid false prediction of the proposed model due to overfitting on the common features. Furthermore, we proposed a holistic-local fusion (HLF) module that exploits contextual-detailed features to adapt the scale-varying features across multiple functions. In addition, fractal dimension estimation (FDE) was employed for the classification of left-hand motor imagery (LMI) and right-hand motor imagery (RMI), confirming that proposed method can effectively extract the discriminative features for this task. The effectiveness of our proposed algorithm was assessed quantitatively and statistically against competent state-of-the-art (SOTA) algorithms utilizing three public datasets, demonstrating that our proposed algorithm outperformed SOTA algorithms. Full article

In the present article, the solution for choosing the optimal structural variant of an industrial robot for extracting castings from die casting machines is considered. For this purpose, the process of extracting the castings from the mold is analyzed. On this basis, functions are defined, and a functional structure of the robot is built. Alternative variants of devices for each function are developed. The set of possible structural variants are constructed, considering the compatibility between devices and the possibility of performing more than one function with one device. The problem of choosing an optimal structural variant is formulated, and its characteristic features are determined. The main stages of a methodology and application software for the problem’s solution are presented. After an analysis of requirements for the extractor, the set of criteria for evaluating the structural variants are determined. The set includes criteria that minimize the production costs, production floor space, as well as the energy costs in the operation process, which is of particular importance in the conditions of global energy crisis. A mathematical model of the problem is built. The formulated multi-criteria optimization problem is solved, both with equal objective functions and with different priority. Full article

The oil industry is facing a major problem with the large amount of oil residue generated in the tanks that store and process crude oil or its products. Research has shown that the residues of petroleum sludge, which according to a sample from the Azzawiya oil refinery in Libya mainly consist of oil, water and solid residues in 42.8%, 2.9% and 55.2% respectively, result in the alteration of the product quality and reduced capacity of the tanks. The solution for this problem as well as the need for inspection and maintenance requires the removal of this oil sludge and the internal cleaning of the tanks. This report aims to review the applied clean-up methods available in the world market and to identify the most efficient, safest, most economical and most environmentally friendly cleaning process. It must be noted that until now, there is not any published work which presents the applied techniques. To accomplish this goal, a total of five manual, automatic and robotic cleaning systems were analyzed and evaluated according to their advantages and disadvantages. The results show that the MEGAMACS with sludge extractor automatic cleaning system with an output of 14.8 m³/h is the fastest cleaning system, while the MARTin where the presence of people inside the tank is not necessary at any stage is the safest. In terms of cleaning costs and environmental impact, the automated BLABO, COW and MEGAMACS systems as well as the MARTin robotic system are the most economical and environmentally friendly due to the closed cleaning circuit and the ability to recover up to 95% of the oil from the sludge, which is returned to the customer and the earnings cover the costs of cleaning. The conclusion drawn is that the current need in the oil industry, in the field of tank cleaning, is the use of high-efficiency automatic or robotic cleaning methods, which aim to reduce the tank downtime, without the need for staff entrance into a permit-required confined space and with the ability to recover up to 100% of the hydrocarbons present in the composition of the sludge. Full article