Various kinds of sensing data can be acquired for smart fault detection. Each signal source has spatial attributes and strong correlations exist between different data sources. However, most of the existing fault detection models are established in the vector domain, which would destroy the structure information embedded within multisource data. Besides, the nonideal data, especially strong-noise data and mislabeled data, will seriously affect the fault detection performance. Therefore, a matrix-form one-class model called robustness one-class support matrix machine (ROCSMM) is proposed for industrial gearbox fault detection under multisource nonideal data. ROCSMM extends the traditional one-class support vector machine to the matrix domain, which can retain the topological structure information of multisource data while improving the fault detection performance. Besides, an adaptive weight generation strategy is designed for ROCSMM according to the prior distribution of matrix samples. This strategy can eliminate the negative impact of nonideal data on ROCSMM to the greatest extent and improve the model's robustness. The experimental results indicate that the proposed model is superior to other cutting-edge models in the fault detection of industrial gearboxes.

The increasing number of residential buildings that are installing distributed energy resources enforces the need for schemes to facilitate a local energy balance. With the continuing evolution of Internet of Things (IoT) technology, Peer-to-Peer (P2P) energy trading is becoming a viable solution to incentivize prosumers and promote efficient energy sharing in a community. This paper develops a model to quantitatively analyze the potential benefits of P2P energy trading for residential buildings that have installed photovoltaic battery systems. The integration of the bidding strategy into a residential energy-management system is feasible to realize cost savings for prosumers. However, the coordination between the bidding strategy and the optimal scheduling of energy has received far too little attention. To better participate in the P2P market, we propose a novel separate bidding energy-management system (SBEMS) that can realize rolling optimal energy scheduling while determining energy bids. The model’s effectiveness is verified via case studies of 75 participants in a community. The results indicate that the prosumers can reduce their costs by up to 24% by employing the proposed SBEMS in the P2P market. In addition, the proposed method is found to offer better performance in terms of economic and technical indices.