Kerf width is one of the most important quality items in cutting of thin metallic sheets. The aim of this study was to develop a convolutional neural network (CNN) model for analysis and prediction of kerf width in laser cutting of thin non-oriented electrical steel sheets. Three input process parameters were considered, namely, laser power, cutting speed, and pulse frequency, while one output parameter, kerf width, was evaluated. In total, 40 sets of experimental data were obtained for development of the CNN model, including 36 sets for training with k-fold cross-validation and four sets for testing. Compared with a deep neural network (DNN) model and an extreme learning machine (ELM) model, the developed CNN model had the lowest mean absolute percentage error (MAPE) of 4.76% for the final test dataset in predicting kerf width. This indicates that the proposed CNN model is an appropriate model for kerf width prediction in laser cutting of thin non-oriented electrical steel sheets.

This paper presents a versatile solution in an effort of improving the accuracy in monitoring the environmental conditions and reducing manpower for industrial households shrimp farming. A ZigBee-based wireless sensor network (WSN) was used to monitor the critical environmental conditions and all the control processes are done with the help of a series of low-power embedded MSP430 microcontrollers from Texas Instruments. This system is capable of collecting, analyzing and presenting data on a Graphical User Interface (GUI), programmed with LabVIEW. It also allows the user to get the updated sensor information online based on Google Spreadsheets application, via Internet connectivity, or at any time through the SMS gateway service and sends alert message promptly enabling user interventions when needed. Thereby the system minimizes the effects of environmental fluctuations caused by sudden changes and reduces the expended labor power of farms. Because of that, the proposed system saves the cost of hiring labor as well as the electricity usage. The design promotes a versatile, low-cost, and commercial version which will function best for small to medium sized farming operations as it does not require any refitting or reconstruction of the pond.

This paper proposes a method to optimize the structure of the radial basis function neural network (RBFNN) by using particle swarm optimization (PSO) algorithm. The combination of PSO and RBFNN can overcome the disadvantages of RBF neural network. The PSO algorithm is used to determine the number of hidden neurons, initial weights, center and base widths in RBF neural network. After being optimised, the RBF neural network-based controller is applied in trajectory tracking to control an Omnidirectional Mobile Robot. This is a holonomic robot that can be operated easily in small and narrow spaces, due to flexible rotational and translational movementing, simultaneously and independently. The simulation results in MATLAB Simulink show that PSO-RBF-PD Supervisory controller was better than RBF-PD Supervisory controller.