Abstract
Deep belief network (DBN) is now being recognized as a powerful and eminently practical tool for large scale data processing. The main characteristics of DBN are the feature extension from low-level content to high-level data association and the representation of joint distribution between original data and matched labels. For a wheeled robot with no other available location reference supports, the internally integrated inertial measurement units (IMUs) essentially requires the robot to be able to implement efficient fault diagnosis to locate and identify the faults, especially for the accumulated error caused by large drifts of gyroscopes. An optimized DBN based fault diagnosis design is proposed to deal with such faults with complexity and diversity. The highlights of the proposed DBN model lies in its combination of weight value optimization via an inexact LSA-GA (abbreviates `inexact linear searching algorithm- genetic algorithm') and dynamic adjustment for hidden-layer neurons of constituent RBMs (abbreviates `restricted Boltzmann machines'). The problems associated with DBN anatomy, bat algorithm (BA) description and fault diagnosis modeling are discussed in detail. The real robot platform experiments and dataset tests are conducted. The results indicate that, the optimized DBN design leads to a better fault classification with excellent generalization ability on given datasets, and the adjustable `DBN structure' contributes to the data association extraction between multiples of fault categories. The proposed scheme may therefore be considered to provide preferred reference models for a class of data based fault diagnosis problems.
Highlights
With the development and maturation of intelligent robot technology, robot and robotics appear to be not constrained to manufacturing domain, whereas, they show superior applicability to a wider range of areas involving resource exploration, disaster relief, medical services, military, aerospace, etc., [1]
With algorithmically constructing the modules in which the numbers of hidden-layer neuron of 3 constituent RBMs dynamically changes with respect to the given datasets, which was experimentally assessed with a MPU6050 module and further applied to practical wheeled robot fault diagnosis
It demonstrated that, corresponding to the uniform motions of robot bodies, the established datasets function as training, test and validation sets appear to have their applicabilities to classification problems, and the simulated deviation and drift faults of inertial measurement units (IMUs) can be used for deep level data association extraction between data and fault categories
Summary
With the development and maturation of intelligent robot technology, robot and robotics appear to be not constrained to manufacturing domain, whereas, they show superior applicability to a wider range of areas involving resource exploration, disaster relief, medical services, military, aerospace, etc., [1]. The typical neural networks, like BP (abbreviates ‘back prorogation’), RBF (abbreviates ‘radial basis function’), adaptive probabilistic neural network, etc., enhance their own generalization abilities and classification performances by fusing some other computational means (including genetic algorithm, fuzzy logic control, SVM, etc.). They essentially reflect a low level I-O data association.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
