Search results

With the rapid development of China’s urbanisation and market economy, municipal solid waste (MSW) generation is increasing dramatically. In response to the threat of environmental pollution and the potential value of converting waste into energy, both the government and the public are now paying more attention to MSW treatment and disposal methods. In 2014, 178.6 million tonnes of MSW was collected at a safe treatment rate of 84.8%. However, the treatment methods and the composition of MSW are influenced by the collection area, its gross domestic product, population, rainfall and living conditions. This chapter analysed the MSW composition properties of Lhasa, Tibet, compared with other cities, such as Beijing, Guangzhou and so forth. The research showed that the moisture content of MSW in Lhasa approaches 31%, which is much lower than the other cities mentioned previously. The proportion of paper and plastics (rubbers) collected was 25.67% and 19.1%, respectively. This was 1.00–3.17 times and 0.75–2.44 times more than those found in Beijing and Guangzhou, respectively. Non-combustibles can reach up to 22.5%, which was 4.03–9.11 times that of Beijing and Guangzhou, respectively. The net heating values could reach up to 6,616 kilojoule/kilogram. The food residue was only half the proportion found in other cities. Moreover, the disposal method applied in each city has also been studied and compared.

The purpose of this paper is to present a detection method based on computer vision for automatic flexible printed circuit (FPC) defect detection.

This paper proposes a new method of watershed segmentation based on morphology. A dimensional increment matrix calculation method and an image segmentation method combined with a fuzzy clustering algorithm are provided. The visibility of the segmented image and the segmentation accuracy of a defective image are guaranteed.

Compared with the traditional one, the segmentation result obtained in this study is superior in aspects of noise control and defect segmentation. It completely proves that the segmentation method proposed in this study is better matches the requirements of FPC defect extraction and can more effectively provide the segmentation result. Compared with traditional human operators, this system ensures greater accuracy and more objective detection results.

The extraction of FPC defect characteristics contains some obvious characteristics as well as many implied characteristics. These characteristics can be extracted through specific space conversion and arithmetical operation. Therefore, more images are required for analysis and foresight to establish a more widely used FPC defect detection sorting algorithm.

This paper proposes a new method of watershed segmentation based on morphology. It combines a traditional edge detection algorithm and mathematical morphology. The FPC surface defect detection system can meet the requirements of online detection through constant design and improvement. Therefore, human operators will be replaced by machine vision, which can preferably reduce the production costs and improve the efficiency of FPC production.

Rotating machineries are widely used in manufacturing, petroleum, chemical, aircraft, and other industries. To accurately identify the operating conditions of such rotating machineries, this paper aims to propose a fault diagnosis method based on sensitive dimensionless parameters and particle swarm optimization (PSO)–support vector machine (SVM) for reducing the unexpected downtime and economic losses.

A relatively new hybrid intelligent fault classification approach is proposed by integrating multiple dimensionless parameters, the Fisher criterion and PSO–SVM. In terms of data pre-processing, a method based on wavelet packet decomposition (WPD), empirical mode decomposition (EMD) and dimensionless parameters is proposed for the extraction of the vibration signal features. The Fisher criterion is applied to reduce the redundant dimensionless parameters and search for the sensitive dimensionless parameters. Then, PSO is adapted to optimize the penalty parameter and kernel parameter for SVM. Finally, the sensitive dimensionless parameters are classified with the optimized model.

As two different time–frequency analysis methods, a method based on a combination of WPD and EMD used to extract multiple dimensionless parameters is presented. More vital diagnosis information can be obtained from the vibration signals than by only using a single time–frequency analysis method. Besides, a fault classification approach combining the sensitive dimensionless parameters and PSO-SVM classifier is proposed. The comparative experiment results show that the proposed method has a high classification accuracy and efficiency.

To the best of the authors’ knowledge, very few efforts have been performed for fault classification using multiple dimensionless parameters. In this paper, eighty dimensionless parameters have been studied intensively, which provides a new strategy in fault diagnosis field.