Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
HEAVY METAL WASTEWATER TREATMENT PROCESS ABNORMAL WORKING CONDITION INTELLIGENT MONITORING METHOD AND APPARATUS BASED ON TRANSFER LEARNING, AND STORAGE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2021/185044
Kind Code:
A1
Abstract:
A heavy metal wastewater treatment process abnormal working condition intelligent monitoring method and apparatus based on transfer learning, and a storage medium. In the intelligent monitoring, based on transfer learning, of a heavy metal wastewater treatment process abnormal working condition, data fusion is performed during the treatment process of heavy metal wastewater of different sources, such that intelligent identification of abnormal working conditions during the treatment process of the heavy metal wastewater of different sources can be automatically realized. The method specifically comprises: using a normal sample YSD of the treatment process of heavy metal wastewater of a fixed source and a normal sample YTD of the treatment process of a small amount of heavy metal wastewater of an unknown source; firstly, learning YSD to obtain a data representation dictionary DSD thereof; and then considering that YSD and YTD are different in terms of distribution, fusing features of YTD into a dictionary learning process by using a transfer learning method, so as to obtain a dictionary DTD of a stronger generalization ability. By means of the heavy metal wastewater treatment process abnormal working condition intelligent monitoring method based on transfer learning, uncertain factors in a wastewater treatment system can be adapted to in a self-adaptive manner, without the need for a priori knowledge of a process, changes in related indexes during the process can be detected more accurately, and detection and early warning are achieved in a timely manner.

Inventors:
HUANG KEKE (CN)
WEN HAOFEI (CN)
YANG CHUNHUA (CN)
ZHU HONGQIU (CN)
LI YONGGANG (CN)
Application Number:
PCT/CN2021/077910
Publication Date:
September 23, 2021
Filing Date:
February 25, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
UNIV CENTRAL SOUTH (CN)
International Classes:
G05B13/04; C02F1/00
Foreign References:
CN111427265A2020-07-17
CN104199441A2014-12-10
CN110579967A2019-12-17
CN110580488A2019-12-17
CN104182642A2014-12-03
US20160358075A12016-12-08
Other References:
NING C ET AL.: "Sparse contribution plot for fault diagnosis of multimodal chemical processes", IFAC-PAPERSONLINE, vol. 48, no. 21, 15 October 2015 (2015-10-15), pages 619 - 626, XP055851670, DOI: 10.1016/j.ifacol.2015.09.595
GUO, XIAOPING ET AL.: "Fault Detection of Multi-mode Processes Employing Sparse Residual Distance", ACTA AUTOMATICA SINICA, vol. 45, no. 3, 31 March 2019 (2019-03-31), pages 617 - 625, XP055851611, DOI: 10.16383/j.aas.c170389
Attorney, Agent or Firm:
CHANGSHA RONG ZHI PATENT AGENCY (CN)
Download PDF: