Research Grants/Fellowships/SBIR

Final Report: Intelligent Decision Making and System Development for Comprehensive Waste Minimization in the Electroplating Industry

EPA Grant Number: R824732
Title: Intelligent Decision Making and System Development for Comprehensive Waste Minimization in the Electroplating Industry
Investigators: Huang, Yinlun
Institution: Wayne State University
EPA Project Officer: Karn, Barbara
Project Period: September 1, 1995 through September 30, 1997
Project Amount: $100,000
RFA: Technology for a Sustainable Environment (1995) Recipients Lists
Research Category: Sustainability , Pollution Prevention/Sustainable Development



Virtually all manufacturing of precious metal products involves electroplating. In the United States, there are more than 3,000 electroplating plants that utilize more than 100 chemicals to electroplate parts with any one or a combination of more than 100 different metallic coatings. This has given rise to the generation of a huge volume of waste streams. Although a variety of methodologies and techniques for waste minimization (WM) in this industry have been developed during the past decade, they have not fully permeated the plants. Part of the reason for this is that they have not been well classified and compared in terms of cost and efficiency. More importantly, the implementation of these methodologies and techniques requires various kinds of experience to achieve not only WM efficiency, but also the lowest cost and the highest productivity. However, to reach this goal requires a multidisciplinary effort involving experts from a multitude of fields. Decisions on WM through process analysis, modification, control, and optimization are usually made based only on imprecise, incomplete, and uncertain information. Clearly, standard mathematical approaches may be inapplicable in this task.

In this project, we proposed to use a wide spectrum of artificial intelligence (AI) techniques to realize comprehensive WM and to develop a sophisticated knowledge base for source reduction, in-process recycling, and source waste (pre)treatment. Two decisionmaking algorithms were proposed for optimizing the use of both first-principles and heuristic knowledge in the knowledge base. The ultimate goal of this project was to develop an intelligent decision support system for deep WM in the plating plants of any size. To the best of the Principal Investigator's knowledge, this system would be the first of its kind in the Nation, perform at an expert level, and be a dependable tool with which the plating industry can significantly improve WM practice with the lowest possible cost. It was expected that the source reduction part of the system will truly help electroplaters evaluate current WM levels and identify new opportunities for further waste reduction in various types of plating processes. The source wastewater treatment with the in-process recycling part of the system will provide decisions on selecting the most efficient and cost-effective (pre)treatment processes. Reductions of about 10 percent of wastewater and sludges were targeted. This system was expected to be tested initially by selected plants over the project period and be introduced eventually into the entire plating industry, with arrangements by the American Electroplaters and Surface Finishers (AESF) Society and technical help from Hughes Research Laboratories.

Summary/Accomplishments (Outputs/Outcomes):

This project has generated many exiting theoretical and technical findings and results:
  1. AI techniques are extremely useful in decision analysis and decisionmaking for pollution prevention (P2) in the manufacturing industries. Particularly effective techniques include fuzzy logic and fuzzy modeling, and symbolic knowledge representation and manipulation. It is found that most engineering heuristics practiced in industries are not well organized, analyzed, or appropriately used. Appropriate applications of AI techniques will greatly improve the quality of knowledge exploration and manipulation.

  2. The effectiveness of P2 relies on the use of knowledge at the different levels. Knowledge- and model-based approaches must be integrated. In this regard, process characterization using fundamental knowledge must be performed. The first principles-based process dynamic models serve the purpose of precise process characterization. This greatly helps the identification of opportunities for reducing wastes.

  3. It is very possible that environmental and economical goals can be simultaneously realized. We have introduced a new theory?the profitable pollution prevention (P3) theory. This theory proves that waste can be truly minimized only when a plating process is optimized in design and operation. Our investigation shows that nearly 95 percent of plating processes can be improved; many of them are far from optimum.

  4. The P3 theory has generated four P3 technologies for chemical solvent and wastewater reduction. Industrial testing/applications have shown very significant reduction of both (at least 15 percent of chemical reduction and 15 percent of wastewater reduction).

  5. Computer-aided tools for P2 are highly desirable by platers, local governments, and professional society. P2 is not only a technical issue, but also a societal activity that needs peoples' active involvement.

Journal Articles on this Report : 9 Displayed | Download in RIS Format

Other project views: All 11 publications 9 publications in selected types All 9 journal articles
Type Citation Project Document Sources
Journal Article Gong JP, Luo KQ, Huang YL. Dynamic modeling & simulation for environmentally benign cleaning & rinsing. Plating and Surface Finishing 1997;84(11):63-70 R824732 (Final)
not available
Journal Article Liu ZP, Huang YL. Fuzzy model-based optimal dispatching for NOx reduction in power plants. International Journal of Electrical Power & Energy Systems 1998;20(3):169-176 R824732 (Final)
not available
Journal Article Lou HR, Huang YL. Profitable pollution prevention: Concept, fundamental & development. Plating and Surface Finishing 2000;87(11):59-66 R824732 (Final)
not available
Journal Article Luo KQ, Huang YL. Intelligent Decision Support for Waste Minimization in Electroplating Plants. Engineering Applications of Artificial Intelligence, Volume 10, Issue 4, August 1997, Pages 321-333. R824732 (Final)
not available
Journal Article Luo KQ, Gong JP, Huang YL. Modeling for sludge estimation & reduction. Plating and Surface Finishing 1998;85(10):59-63 R824732 (Final)
not available
Journal Article Xu Q, Huang YL. Design of an optimal reversed drag-out network for maximum chemical recovery in electroplating systems. Plating and Surface Finishing 2005;92(6):44-48 R824732 (Final)
not available
Journal Article Yang YH, Lou HR, Huang YL. Optimal design of a water reuse system in an electroplating plant. Plating and Surface Finishing 1999;86(4):80-84. R824732 (Final)
not available
Journal Article Yang YH, Lou HR, Huang YL. Synthesis of an optimal wastewater reuse network. International Journal of Waste Management 2000;20(4):311-319. R824732 (Final)
not available
Journal Article Zhou Q, Huang YL. Dynamic model-based optimal design of a waste use and reuse network for an electroplating plant. Plating and Surface Finishing. R824732 (Final)
not available
Supplemental Keywords:

computer-aided management decision support system, electroplating/metal finishing, pollution prevention management system, reverse-drag-out sludge modeling., RFA, Scientific Discipline, Water, Sustainable Industry/Business, cleaner production/pollution prevention, Wastewater, Environmental Chemistry, Sustainable Environment, Technology for Sustainable Environment, Economics and Business, in-process changes, cleaner production, waste minimization, waste reduction, chemical waste, wastewater reuse, decision making, in process recycling, electroplating, integrated process design, metal plating industry, hazardous waste, green process systems, electrochemical techniques, SIC = electroplating, pollution prevention, source reduction, artificial intelligence techniques

Progress and Final Reports:
Original Abstract