Search

Fault diagnosis plays an essential role in reducing the maintenance costs of rotating machinery manufacturing systems. In many real applications of fault detection and diagnosis, data tend to be imbalanced, meaning that the number of samples for some fault classes is much less than the normal data samples. At the same time, in an industrial condition, accelerometers encounter high levels of disruptive signals and the collected samples turn out to be heavily noisy. As a consequence, many traditional Fault Detection and Diagnosis (FDD) frameworks get poor classification performances when dealing with real-world circumstances. Three main solutions have been proposed in the literature to cope with this problem: (1) the implementation of generative algorithms to increase the amount of under-represented input samples, (2) the employment of a classifier being powerful to learn from imbalanced and noisy data, (3) the development of an efficient data pre-processing including feature extraction and data augmentation. This paper proposes a hybrid framework which uses the three aforementioned components to achieve an effective signal-based FDD system for imbalanced conditions. Specifically, it first extracts the fault features, using Fourier and wavelet transforms to make full use of the signals. Then, it employs Wasserstein Generative Adversarial Networks (WGAN) to generate synthetic samples to populate the rare fault class and enhance the training set. Moreover, to achieve a higher performance a novel combination of Convolutional Long Short-term Memory (CLSTM) and Weighted Extreme Learning Machine (WELM) is proposed. To verify the effectiveness of the developed framework, different datasets settings on different imbalance severities and noise degrees were used. The comparative results demonstrate that in different scenarios GAN-CLSTM-ELM outperforms the other state-of-the-art FDD frameworks., Comment: 23 pages, 11 figures

A current trend in industries such as semiconductors and foundry is to shift their visual inspection processes to Automatic Visual Inspection (AVI) systems, to reduce their costs, mistakes, and dependency on human experts. This paper proposes a two-staged fault diagnosis framework for AVI systems. In the first stage, a generation model is designed to synthesize new samples based on real samples. The proposed augmentation algorithm extracts objects from the real samples and blends them randomly, to generate new samples and enhance the performance of the image processor. In the second stage, an improved deep learning architecture based on Faster R-CNN, Feature Pyramid Network (FPN), and a Residual Network is proposed to perform object detection on the enhanced dataset. The performance of the algorithm is validated and evaluated on two multi-class datasets. The experimental results performed over a range of imbalance severities demonstrate the superiority of the proposed framework compared to other solutions., Comment: 13 pages, submitted for THE IEEE INTERNATIONAL CONFERENCE ON INDUSTRY 4.0, ARTIFICIAL INTELLIGENCE, AND COMMUNICATIONS TECHNOLOGY (IAICT2021)

The paper develops a stochastic Agent-Based Model (ABM) mimicking the spread of infectious diseases in geographical domains. The model is designed to simulate the spatiotemporal spread of SARS-CoV2 disease, known as COVID-19. Our SARS-CoV2-based ABM framework (CoV-ABM) simulates the spread at any geographical scale, ranging from a village to a country and considers unique characteristics of SARS-CoV2 viruses such as its persistence in the environment. Therefore, unlike other simulators, CoV-ABM computes the density of active viruses inside each location space to get the virus transmission probability for each agent. It also uses the local census and health data to create health and risk factor profiles for each individual. The proposed model relies on a flexible timestamp scale to optimize the computational speed and the level of detail. In our framework each agent represents a person interacting with the surrounding space and other adjacent agents inside the same space. Moreover, families stochastic daily tasks are formulated to get tracked by the corresponding family members. The model also formulates the possibility of meetings for each subset of friendships and relatives. The main aim of the proposed framework is threefold: to illustrate the dynamics of SARS-CoV diseases, to identify places which have a higher probability to become infection hubs and to provide a decision-support system to design efficient interventions in order to fight against pandemics. The framework employs SEIHRD dynamics of viral diseases with different intervention scenarios. The paper simulates the spread of COVID-19 in the State of Delaware, United States, with near one million stochastic agents. The results achieved over a period of 15 weeks with a timestamp of 1 hour show which places become the hubs of infection. The paper also illustrates how hospitals get overwhelmed as the outbreak reaches its pick., Comment: 25 pages, 16 figures

Along with the advance of opinion mining techniques, public mood has been found to be a key element for stock market prediction. However, how market participants' behavior is affected by public mood has been rarely discussed. Consequently, there has been little progress in leveraging public mood for the asset allocation problem, which is preferred in a trusted and interpretable way. In order to address the issue of incorporating public mood analyzed from social media, we propose to formalize public mood into market views, because market views can be integrated into the modern portfolio theory. In our framework, the optimal market views will maximize returns in each period with a Bayesian asset allocation model. We train two neural models to generate the market views, and benchmark the model performance on other popular asset allocation strategies. Our experimental results suggest that the formalization of market views significantly increases the profitability (5% to 10% annually) of the simulated portfolio at a given risk level., Comment: 16 pages