No abstract

To realize real-time and accurate performance monitoring of large- and medium-sized seed metering devices, a performance monitoring system was designed for seed metering devices based on LED visible photoelectric sensing technology and a pulse width recognition algorithm. Through an analysis of the of sensing component pointing characteristics and seed motion characteristics, the layout of the sensing components and critical photoelectric sensing system components was optimized. Single-grain seed metering devices were employed as monitoring objects, and the pulse width thresholds for Ekangmian-10 cotton seeds and Zhengdan-958 corn seeds were determined through pulse width threshold calibration experiments employed at different seed metering plate rotational speeds. According to the seeding quantity monitoring experiments, when the seed metering plate rotational speed ranged from 28.31~35.71 rev/min, the accuracy reached 98.41% for Ekangmian-10 cotton seeds. When the seed metering plate rotational speed ranged from 13.78~19.39 rev/min, the seeding quantity monitoring accuracy reached 98.19% for Zhengdan-958 corn seeds. Performance monitoring experiments revealed that the qualified seeding quantity monitoring accuracy of cotton precision seed metering devices, missed seeding quantity monitoring accuracy, and reseeding quantity monitoring accuracy could reach 98.75%, 94.06%, and 91.30%, respectively, within a seeding speed range of 8~9 km/h. This system meets the requirements of real-time performance monitoring of large- and medium-sized precision seed metering devices, which helps to improve the operational performance of seeding machines.

Active magnetic bearing (AMB) supported flywheel energy system, also called flywheel battery, is a mechanical battery storing kinetic energy in a rotating flywheel disk and has appealing features such as high specific power and energy, short time of charging/discharging, no pollution and long life span. In this paper, we apply AMB-supported flywheel battery as a new type of power battery to electric tractors, which absorbs wasted energy when the electric tractor brakes frequently and provide additional driving energy supplement when the electric tractor face an overload start, a sudden load mutations or field work resistance mutations. The structure design of the AMB-supported flywheel battery is introduced, including the axial/radial magnetic bearing, flywheel disk, the rotor and the motor. The driving method of the whole system is also analyzed. This design provides the reliability guarantee for the innovative application of the AMB-supported energy storage flywheel battery in electric tractors.

Anomaly detection for non-linear dynamical system plays an important role in ensuring the system stability. However, it is usually complex and has to be solved by large-scale simulation which requires extensive computing resources. In this paper, we propose a novel anomaly detection scheme in non-linear dynamical system based on Long Short-Term Memory (LSTM) to capture complex temporal changes of the time sequence and make multi-step predictions. Specifically, we first present the framework of LSTM-based anomaly detection in non-linear dynamical system, including data preprocessing, multi-step prediction and anomaly detection. According to the prediction requirement, two types of training modes are explored in multi-step prediction, where samples in a wall shear stress dataset are collected by an adaptive sliding window. On the basis of the multi-step prediction result, a Local Average with Adaptive Parameters (LAAP) algorithm is proposed to extract local numerical features of the time sequence and estimate the upcoming anomaly. The experimental results show that our proposed multi-step prediction method can achieve a higher prediction accuracy than traditional method in wall shear stress dataset, and the LAAP algorithm performs better than the absolute value-based method in anomaly detection task.