Short communicationA niched genetic algorithm to solve a pollutant emission reduction problem in the manufacturing industry: A case study
Introduction
In the last few decades, environmental problems have received much attention from society and governments. In this context, the European Union has introduced the concept of est vailable echnologies (, for short) as a new integrated approach to deal with environmental problems caused by pollution produced by manufacturing/production industries.
This approach highlights the requirement that the development of new manufacturing/production processes must be balanced by the implementation of best available technical options, that eliminate or at least reduce the amount of pollutants released into the environment.
The are all the methods, tools and technologies that can be applied in the design and production phase, in order to achieve a good reduction of emission level with an acceptable additional cost.
Often, different types of technical options can control a given source. In this context, mathematical programming techniques can be used to select the best combination of removal and control technologies from different alternatives available.
Depending on the specific goal to be achieved, different optimization problems can be formulated [1], [2]. Generally, the main objective is to minimize the total cost of policy decisions (i.e., mainly the costs involved in implementation and maintenance of removal and control technologies), whereas, environmental considerations are addressed through integrating emission constraints. Other modelling approaches handle the minimization of the emission as another objective function in addition to the cost. The resulting multiobjective optimization problem is then converted to a single objective problem by a linear combination of the different objectives as a weighted sum.
In this paper, we consider a multiobjective combinatorial linear programming model that handles pollution emissions and control costs simultaneously as competing objectives. The main aim is to determine the Pareto set of combinations of that allow both to maximize emission reductions and to minimize the total control cost.
For the solution of the problem under investigation, a niched Pareto genetic algorithm based approach is defined and implemented. The effectiveness of the developed algorithm is evaluated by using an illustrative case study, that is, industrial painting of wood.
The remainder of the paper is organized as follows. Section 2 gives the general mathematical formulation of the problem we are dealing with. Section 3 presents some basic concepts used in multiobjective evolutionary approaches and gives a general description of the niched Pareto genetic algorithm. Section 4 describes the considered manufacturing process. Section 5 introduces the niched Pareto genetic algorithm specifically designed for the industrial painting of wood. Section 6 reports the experimental results obtained on a real case study. Finally, Section 7 presents the conclusions of this work.
Section snippets
Problem statement
In order to describe the problem under investigation, we focus our attention on generic manufacturing plants that can be viewed as decomposed in different production phases, consuming some inputs in order to produce some outputs.
The scheme of a generic manufacturing plan is outlined in Fig. 1, where the production phases are modelled as black boxes, whereas the raw materials represent the inputs for the entire process.
During the execution of successive production phases, additional materials
Evolutionary approaches to multiobjective optimization
Evolutionary algorithms are search procedures that imitate the process of natural evolution in order to solve complex optimization problems. Since the 1960s, several evolutionary methodologies have been proposed that can be broadly grouped in: genetic algorithms [7], [8], [9] evolutionary programming [10] and evolution strategies [11], [12].
The main idea of the mentioned approaches is to process a set of candidate solutions, called population, simultaneously. Population is modified by two basic
The manufacturing process
We have focused our attention on the industrial painting of wood. Our choice has been motivated by the fact that the directive 1999/13/CE of the European Commission [31], [32] applies to the companies working in this productive sector. Such a directive focuses on the emissions of volatile organic compounds (i.e., ) into the environment by manufacturing industries and, in order to prevent or reduce the direct and indirect effects of such emissions, the directive has established limit values
Design of NPGA for industrial painting of wood
The first step in designing a genetic algorithm for a particular problem is to devise a suitable scheme to represent the individuals. In the , proposed for solving the problem under investigation, the set of technical options available for each phase is viewed as an individual or member of the population. Consequently, a binary representation is an obvious choice for the problem since it represents the underlying integer variables. Hence, in our representation, we use a -bit binary
Numerical results and discussion
In this section, we present the results obtained from the application of the on the problem described in Section 4, by considering as case study the manufacturing process of an Italian company specialized in the industrial painting of wood.
The main activity of the company in question is the manufacturing of chairs. In this case, the threshold value for the consumption of solvents, established by the 1999/13/CE norm, is fixed at 15 tons per year. The consumptions are determined by
Concluding remarks
In this paper, a based approach has been applied to the pollutant emission reduction problem in the manufacturing industry. The problem under investigation has been formulated as a bicriteria optimization problem with competing cost and environmental impact objectives. The sensitivity of the proposed solution approach to the parameters that control the behaviour of the algorithm itself have been assessed, namely population size, tournament size and niche radius.
The computational results,
References (35)
- et al.
An optimization model for air pollution control decision making
Environmental modelling and software with environment data news
(1997) - et al.
Survey of mathematical programming models in air pollution management
European Journal of Operational Research
(1996) - Roth B, German BJ, Mavris DN, Macsotai N. Adaptive selection of engine technology solution sets from a large...
A comprehensive survey of evolutionary-based multiobjective optimization techniques
Knowledge and Information Systems
(1999)- et al.
Evolutionary algorithms for solving multi-objective problems
(2002) Evolutionary multiobjective optimization: current and future challenges
Genetic algorithms in search, optimisation and machine learning
(1989)- Davis L, editor. Handbook of genetic algorithms. New York: Van Nostrand Reinhold;...
Adaptation in natural and artificial systems
(1992)- et al.
Artificial intelligence through simulated evolution
(1966)
Evolutionsstrategie: Optimierung technischer Systeme nach Prinzipien der biologischen Evolution
Numerical optimization of computer models
Multi-objective optimization using evolutionary algorithms
Multiple objective optimization with vector evaluated genetic algorithms
Genetic algorithms for multiobjective optimization: formulation, discussion and generalization
Cited by (13)
Optimization of global and local pollution control in electricity production from coal burning
2012, Applied EnergyCitation Excerpt :Ren et al. [12] introduced a multi-objective approach based on linear programming (LP) for the design of a distributed energy system that minimizes simultaneously an economic objective function (the annual energy cost) and an environmental one (the annual CO2 emissions). Grandinetti et al. [13] presented a multi-objective linear programming model to identify the optimal set of Best Available Technologies (BATs) in an industrial facility for painting wood that accounts for the simultaneous minimization of the emissions and total cost. In the same line, Mavrotas et al. [14], proposed a methodology that offers the decision-maker combinations of BATs to be implemented.
Optimization of heat pipe with axial "Ω"-shaped micro grooves based on a niched Pareto genetic algorithm (NPGA)
2009, Applied Thermal EngineeringA dynamic chain-like agent genetic algorithm for global numerical optimization and feature selection
2009, NeurocomputingCitation Excerpt :The algorithms for global optimization problems are very important in modern engineering design and system operation in many areas. Among the existing optimization algorithms, the genetic algorithm (GA) has received considerable attention regarding its potential as a novel optimization technique for complex problems and has been applied in various areas successfully [2,4,5,7,9,11]. The main specific feature of the GA as an optimization method is its implicit parallelism, which is a result of the evolution and the hereditary-like process.
An integrated optimization and simulation approach for air pollution control under uncertainty in open-pit metal mine
2019, Frontiers of Environmental Science and Engineering