Compensation of Measurement Errors for a Magnetoresistive Angular Sensor Array Using Artificial Neuronal Networks

Abstract

Sensing setups based on the magnetic field possess many benefits that make such sensors an important class in many application fields. Especially in industrial or automotive applications, such sensing concepts are very important parts in many essential system components. Magnetic field sensors are typically used to measure angular positions and rotational velocity as well as linear positions. Due to their high robustness and accuracy, MR-based sensors have a dominant role in the angular sensing domain. Nevertheless, novel vehicle concepts such as electrical driven or hybrid cars as well as increasing quality and reliability requirements demand improvements. However, those sensors face challenges due to new technologies, which are accompanied by new regulations. From this follows that manufactures can either adapt existing technologies or develop new sensing concepts. The goal of the following work is the evaluation of the capability of neuronal networks to enhance the measurement results of magnetic field sensors if these are disturbed by magnetic stray fields. Therefore, the system setup and possible error sources are analyzed before different neural networks are designed, tried and tested, whereby special attention is given to the network configuration in order to enable a deployment close to the individual sensors. Finally, the results are verified with an adapted measurement setup.

Construction of an efficient evaluation model for athletic athletes' competitive ability based on deep neural network algorithm

“…Artificial neuronal network is a theorized mathematical model of the neural network of the human brain, an information processing system based on imitating the structure and function of the neural network of the brain [25,26]. It is an artificially constructed neural network capable of achieving certain functions based on the existing human understanding of the neural network of the brain, which absorbs many advantages of biological neural networks and thus has its special characteristics: (1) highly parallel computing and distributed storage functions: artificial neural networks are composed of many identical basic processing units grouped in parallel, and although the function of each unit is simple, both each Although the function of each unit is simple, both the small unit and the whole neural network have the dual capability of processing and storing information, and these two functions are naturally integrated in the same network, which makes its processing capability and effect on information amazing [27,28]. (2) Highly nonlinear global action: An artificial neural network is a large-scale nonlinear dynamical system in which each neuron can receive inputs from a large number of other neurons and produce outputs that affect other neurons through parallel networks.…”