In this paper, we take a water quality testing Unmanned Surface Vessel (USV) as the research object. We propose a heading keeping strategy based on Human Simulated Intelligent Control (HSIC) algorithm and a trajectory tracking strategy under line-of-sight (LOS) algorithm. The practicality of the proposed control strategies was verified by combining simulations and experiments. The main contents were constructed with three parts: Firstly, we designed a complete control system of a water quality inspection unmanned boat with Arduino microcontroller as the core processor. Secondly, we derived the mathematical model of motion after reasonable simplification. Combined with the cycle experiment, the mapping relation between virtual rudder angle and motor speed was established. Then, the USV heading direction control strategy of HSIC was presented and the reliability of the proposed strategy was verified by the course control experiment of USV. Finally, aiming at the defects and shortcomings of the upper-level trajectory tracking LOS algorithm in practical application, we propose the trajectory correction and precise steering control strategies, and the practicality of the improved algorithm was verified by multi-point trajectory tracking experiments. The autonomous fixed-point water quality testing experiment was designed and verified the effectiveness of the proposed strategies.

The central air conditioning system provides city dwellers with an efficient and comfortable environment. Meanwhile, coinciding with their use, the building electricity load is increased, as central air conditioners consume a lot of electricity. It has become necessary to control central air conditioners for storage and to analyze the energy saving optimization of central air conditioner operation. This study investigates the energy consumption background of central air conditioning systems, and proposes an intelligent load prediction method. With a back propagation (BP) neural network, we use the data collected in the actual project to build the cooling load prediction model for central air conditioning. The network model is also trained using the Levenberg–Marquardt (LM) algorithm, and the established model is trained, tested, and predicted by importing a portion of the sample data, which is filtered by preprocessing. The experimental results show that most of the data errors for training, testing, and prediction are within 10%, indicating that the accuracy achievable by the model can meet the practical requirements, and can be used in real engineering projects.