Harbin Institute of Technology

About: Harbin Institute of Technology is a education organization based out in Harbin, China. It is known for research contribution in the topics: Microstructure & Control theory. The organization has 88259 authors who have published 109297 publications receiving 1603393 citations. The organization is also known as: HIT.

Industrial Cyberphysical Systems: A Backbone of the Fourth Industrial Revolution

Abstract: Cyberphysical systems (CPSs) are perceived as the pivotal enabler for a new era of real-time Internetbased communication and collaboration among value-chain participants, e.g., devices, systems, organizations, and humans. The CPS utilization in industrial settings is expected to revolutionize the way enterprises conduct their business from a holistic viewpoint, i.e., from shop-floor to business interactions, from suppliers to customers, and from design to support across the whole product and service lifecycle. Industrial CPS (ICPSs) blur the fabric of cyber (including business) and physical worlds and kickstart an era of systemwide collaboration and information-driven interactions among all stakeholders of the value chain. Therefore, ICPSs are expected to empower the transformation of industry and business at large to a digital, adaptive, networked, and knowledge-based industry with significant long-term impact on the economy, society, environment, and citizens.

FP-DNN: An Automated Framework for Mapping Deep Neural Networks onto FPGAs with RTL-HLS Hybrid Templates

Abstract: DNNs (Deep Neural Networks) have demonstrated great success in numerous applications such as image classification, speech recognition, video analysis, etc. However, DNNs are much more computation-intensive and memory-intensive than previous shallow models. Thus, it is challenging to deploy DNNs in both large-scale data centers and real-time embedded systems. Considering performance, flexibility, and energy efficiency, FPGA-based accelerator for DNNs is a promising solution. Unfortunately, conventional accelerator design flows make it difficult for FPGA developers to keep up with the fast pace of innovations in DNNs. To overcome this problem, we propose FP-DNN (Field Programmable DNN), an end-to-end framework that takes TensorFlow-described DNNs as input, and automatically generates the hardware implementations on FPGA boards with RTL-HLS hybrid templates. FP-DNN performs model inference of DNNs with our high-performance computation engine and carefully-designed communication optimization strategies. We implement CNNs, LSTM-RNNs, and Residual Nets with FPDNN, and experimental results show the great performance and flexibility provided by our proposed FP-DNN framework.

Adaptive Fuzzy Control of Strict-Feedback Nonlinear Time-Delay Systems With Unmodeled Dynamics

Abstract: In this paper, an approximated-based adaptive fuzzy control approach with only one adaptive parameter is presented for a class of single input single output strict-feedback nonlinear systems in order to deal with phenomena like nonlinear uncertainties, unmodeled dynamics, dynamic disturbances, and unknown time delays. Lyapunov–Krasovskii function approach is employed to compensate the unknown time delays in the design procedure. By combining the advances of the hyperbolic tangent function with adaptive fuzzy backstepping technique, the proposed controller guarantees the semi-globally uniformly ultimately boundedness of all the signals in the closed-loop system from the mean square point of view. Two simulation examples are finally provided to show the superior effectiveness of the proposed scheme.

Adaptive Neural Network Tracking Control for Robotic Manipulators With Dead Zone

Abstract: In this paper, the adaptive neural network (NN) tracking control problem is addressed for robot manipulators subject to dead-zone input. The control objective is to design an adaptive NN controller to guarantee the stability of the systems and obtain good performance. Different from the existing results, which used NN to approximate the nonlinearities directly, NNs are employed to identify the originally designed virtual control signals with unknown nonlinear items in this paper. Moreover, a sequence of virtual control signals and real controller are designed. The adaptive backstepping control method and Lyapunov stability theory are used to prove the proposed controller can ensure all the signals in the systems are semiglobally uniformly ultimately bounded, and the output of the systems can track the reference signal closely. Finally, the proposed adaptive control strategy is applied to the Puma 560 robot manipulator to demonstrate its effectiveness.