Haitian Pan
Zhejiang University of Technology
6 Papers
10 Citations
Haitian Pan is an academic researcher from Zhejiang University of Technology. The author has contributed to research in topics: Process design & Deep learning. The author has an hindex of 3, co-authored 6 publications.
Chat about Author
Papers
Leak Detection and Location Based on ISLMD and CNN in a Pipeline
TL;DR: An improved spline-local mean decomposition (ISLMD) is proposed to eliminate noise interference and an image recognition method using a convolutional neural network for leak detection is proposed, which can better address the problem that the features of different leak apertures or locations are highly similar to each other.
A Pipeline Leak Detection and Localization Approach Based on Ensemble TL1DCNN
TL;DR: Wang et al. as mentioned in this paper proposed an ensemble transfer learning one-dimension convolutional neural network (TL1DCNN) for pipeline leak detection and localization, which plays the role of base learner.
Preparation of Papers for IFAC Conferences & Symposia: Integration of Process Design and Control Using Hierarchical Control Structure
TL;DR: In this article, the two-level hierarchical control structure is taken into account within the IPDC framework for the first time, which separates the design decisions from the APC decisions and then keeps the problem size manageable.
7
•Proceedings Article
Performance assessment of PID controller with time-variant disturbance dynamics
Mengfei Zhou,Lei Xie,Haitian Pan,Shuqing Wang +3 more
- 23 May 2011
TL;DR: In this article, a method for performance assessment of PID control loops subject to time-varying disturbance dynamics, which is often observed in industrial processes, is proposed, optimizes overall performance of the processes and presents a PID tradeoff curve which provides a useful lower bound on the achievable performance of a PID controller in terms of both the most significant disturbance rejection and the representative disturbance rejection.
3