Figure - available from: Neural Computing and Applications
This content is subject to copyright. Terms and conditions apply.
Schematic of construction site of waste recycling plant and C&DW treatment path for non-inferior solution 2
Source publication
With regard to the site selection of construction and demolition of waste recycling plants in China, an optimization model for the site selection of a recycling plant was constructed using a genetic algorithm, and an empirical study was conducted with Panyu and Nansha Districts of Guangzhou City as examples. The study shows that the optimal solutio...
Similar publications
Since the outbreak of COVID-19, the rapid construction and operation of Wuhan Vulcan Mountain Hospital and Raytheon Hospital have attracted positive responses from local and international observers. At the same time, it has also highlighted the urgency for the construction of emergency medical facilities for public health emergencies. Before constr...
Citations
... Current systems suffer from logistical inefficiencies, such as disjointed operations across multiple locations and communication gaps between stakeholders. For instance, recycling companies typically receive construction and demolition waste from demolition sites and transport it to consumers after recycling, involving multiple intermediate steps [38][39][40][41]. This fragmented approach results in high transportation costs and environmental impacts due to repeated material handling and long-distance transportation. ...
Using recycled aggregates has many positive environmental impacts because of the conservation of natural resources and minimization of waste. The use of recycled aggregates in downcycling processes is already common in Germany, whereas utilizing them to produce high-quality recycled concrete is rarely applied in practice. The reasons behind this lag have been investigated based on surveys and interviews with stakeholders. Miscommunication and missing information were identified in all stakeholder groups. Therefore, establishing a robust network and facilitating knowledge transfer by specifying the demand for recycled aggregates in the case study region have been considered as prerequisites. Therefore, the paper presents a novel concept of a stakeholder network for an integrated construction and demolition waste center. The conceptualization integrates the recycling companies and construction product manufacturers in one venue with research, service, and educational divisions. The design of the facilities is based on calculations regarding future construction activities and the demand for concrete production. The proposed concept aims to supply the region in the west of Germany with high-quality recycled products while also establishing a robust network that offers benefits in terms of logistical optimization and knowledge transfer.
... Many scholars research construction waste, such as Dosal et al. [15] proposed improved multi-standard analysis to analyze the location of recycling facilities. Liu et al. [42] proposed a multi-objective recycling station location model and proposed a genetic algorithm to solve it. Shi et al. [56] proposed a site selection model for recycling plants considering uncertain environments. ...
... Aydemir-Karadag (2018) proposed a profit-oriented mixed integer mathematical model, which takes into account both environmental impacts and economic benefits, for the site routing problem of hazardous wastes. Liu et al. (2019) constructed an optimization model of recycling plant location using genetic algorithm, and conducted an empirical study with Panyu and Nansha districts in Guangzhou as examples. Toutouh, Rossit & Nesmachnow (2020) proposed a series of applications for single-objective and multi-objective heuristic algorithms based on PageRank method and two multi-objective evolutionary algorithms to resolve urban garbage dump sites location problem. ...
... Some scholars used multi-criteria approaches such as Analytic Hierarchy Process (AHP) (Aragones-Beltran et al., 2010), comprehensive network analysis and data envelopment analysis (Khadivi & Ghomi, 2012) to conduct site selection research. Some scholars also use meta-heuristic algorithms in the site selection research, such as genetic algorithm (Liu et al., 2019), simulated annealing algorithm (Santosa & Kresna, 2015) and other metaheuristic algorithms based on evolutionary strategies. In fact, metaheuristic algorithms are designed to address a broad spectrum of challenging optimization problems, including NP-hard problems like site selection problem, without the need for extensive problemspecific adaptations. ...
With the development of the express delivery industry, how to increase the recycling rate of waste cartons has become a problem that needs to be solved. Recycling enterprises began to provide the new recycling mode, door-to-door recycling services, to residents with waste cartons. In this article, we constructed a site selection model for a carton recycling site with the aim of maximizing total profits. Considering the residents’ recycling willingness and the government subsidy earned through the contribution to carbon emission reduction, this model achieves the task of site selection and unit price fixation for carton recycling. We used the particle swarm optimization (PSO) algorithm to solve the model and compared it with the genetic algorithm (GA) for validity testing. PSO algorithm was also used to carry out sensitivity analysis in this model. The proposed model and the results of the sensitivity analysis can be used for decision-making in recycling enterprises as well as for further research on waste recycling and reverse logistics.
... Therefore, the intelligent optimization algorithm is superior to the traditional optimization method in solving COPs. It has been widely used in robot path optimization (Lamini, Benhlima, & Elbekri, 2018), AGV vehicle scheduling (Han, Wang, Liu, & Zhao, 2017;Qiuyun, Hongyan, Hengwei, & Ping, 2021), location problem (Liu, Xiao, Wang, & Pang, 2018;MirarabRazi, Hassanzad Navrodi, Ghajar, & Salahi, 2020), image threshold segmentation (Huo, Liu, Wang, & Sun, 2017;Houssein, Helmy, Oliva, Elngar, & Shaban, 2021;Li, et al., 2017), production line balancing (Zhu, Zhang, & Wang, 2018;Fathi, Nourmohammadi, HC Ng, Syberfeldt, & Eskandari, 2019;Jiayi Liu, et al., 2018), aerospace (Jafari & Nikolaidis, 2019;Mekki, Langer, & Lynch, 2021), network security (Ali & Ahmed, 2019) and environmental protection(Z. Wang & Cai, 2018). ...
... As the BCDW recycling plant is the primary facility for urban BCDW management, site selection and route optimization for the wastecollecting and effective management are very important for systemic circularity implementation in BCI. Using GA, Liu et al. (2019b) determined the layouts of waste transfer stations and recycling plants scientifically and reasonably. This showed that the process can not only reduce their fixed cost investments and operating costs, but it can also improve overall environmental hygiene conditions, promote CE, and waste to wealth, and reduce pollution in a landfill. ...
Data-driven technology such as Artificial Intelligence is considered an essential enabler of circular economy (CE) in the building construction industry (BCI). As both AI and CE applications are emerging areas in the BCI, there exists little systematic guidance on how AI can be applied to capture the full potential of systemic circularity along the building product lifecycle. To fill this gap, this study provides an extensive systematic review of scientific research advancement in AI and CE in the BCI. AI algorithms for enabling systemic circularity in the BCI were discussed alongside their respective Strengths, Weaknesses, Threats, and Opportunities (SWOT) analysis concerning CE solutions. Further, thirteen application areas of the AI models were illustrated and summarised using a tree diagram. Among the application areas include circular materials selection, design for disassembly, pre-demolition auditing, demolition waste sorting, materials strength prediction, technical and economic circularity of materials, operation of circular business model, onsite waste recycling, and reverse logistics. In addition, the profound challenges of applying AI in enabling CE implementation in BCI were identified and their potential solutions were highlighted. A holistic framework integrating the AI models and their application domains along the building product lifecycle was developed. Future research directions including a deep reinforcement learning (DRL) adaptive control system for circularity, AI in 3D printing of circular materials, optimisation of management infrastructure for circular products, optimisation of circular business model and reverse logistics are highlighted. The findings have delineated the core application domains of AI in enabling CE adoption along the building lifecycle and provided insightful future research needs that could promote digital systemic circularity in BCI.
... It was shown that the hybrid method has good performance for large-scale problems concerning solution time and quality. In addition to the CPMP, the genetic algorithms have been used for other facility location problems, such as bus terminal location [41], e-commerce distribution center location [42,43], and waste recycling plant location problems [44] The efficient use of GA is investigated in some studies. Osaba et al. [8] studied the influence of using heuristic initialization functions in GA and implied the efficiency of using heuristic initialization functions. ...
The capacitated p-median problem is a well-known location-allocation problem that is NP-hard. We proposed an advanced Genetic Algorithm (GA) integrated with an Initial Solution Procedure for this problem to solve the medium and large-size instances. A 3^3 Full Factorial Design was performed where three levels were selected for the probability of mutation, population size, and the number of iterations. Parameter tuning was performed to reach better performance at each instance. MANOVA and Post-Hoc tests were performed to identify significant parameter levels, considering both computational time and optimality gap percentage. Real data of Lorena and Senne (2003) and the data set presented by Stefanello et al. (2015) were used to test the proposed algorithm, and the results were compared with those of the other heuristics existing in the literature. The proposed GA was able to reach the optimal solution for some of the instances in
contrast to other metaheuristics and the Mat-heuristic, and it reached a solution better than the best known for the largest instance and found near-optimal solutions for the other cases. The results show that the proposed GA has the potential to enhance the solutions for large-scale instances. Besides, it was also shown that the parameter tuning process might improve the solution quality in terms of the objective function and the CPU time of the proposed GA, but the magnitude of improvement may vary among different instances.
... Over the years, GA has been extensively and successfully used as a search and optimization technique in various problem domains (Cao 2020;Guo, Yang, and Zhu 2020;Liu et al. 2019;Majumdar et al. 2016). GAs have found their way in textile engineering for addressing various objectives, like detection of source of yarn faults in spinning line by analysis of spectrograms, establishing the effect of woven fabric construction parameters on its macroporosity, optimization of weave and other structural parameters to enable creative fabric designing, etc. (Amin et al. 2007;Lin 2013). ...
Yarn engineering is a long-standing problem for the cotton spinning industry as the functional relationship between fiber and yarn properties is quite complex. The objective of this research is to develop a hybrid machine learning-based prescriptive yarn engineering system that can foretell the properties of cotton fiber for achieving desired yarn properties. Artificial neural network (ANN) and genetic algorithm (GA) were used to develop the predictive model for cotton yarn properties and optimization of cotton fiber properties, respectively. Two separate ANN models were developed for predicting yarn tenacity and yarn unevenness. The functional relationships approximated by the ANN models were used to formulate the fitness function for GA. The validation of the ANN-GA system demonstrated good accuracy as cotton fiber strength, length and length uniformity were predicted with very good accuracy (mean error < 5%). The developed machine learning system can supplant the intuition-based decision making in textile spinning industry and pave the way for yarn engineering.
... The total cost of construction waste disposal can be affected by many unpredictable factors, whether in the early consideration stage of the location for constructing the waste disposal facility or later in the plant's day-to-day operations. The site location and maximum processing capacity are key strategic decisions and are made at different levels of uncertainty (Liu et al., 2019), such as in unit transport costs, construction waste generation level, and adverse environmental effects (Jin et al., 2017;Xu et al., 2019). As key strategic decisions, If these uncertainty factors are ignored during the location selection stage, the inadequate location of waste disposal facility will poses a significant risk to governments and residents and can even lead to serious conflicts (Chatzouridis and Komilis, 2012). ...
The location of a construction waste disposal facility is a vital part of recycling construction waste strategy. Many factors affect the location especially, ignoring uncertain factors can lead to inaccurate results, resulting in an inappropriate location. Therefore, waste supply and transportation cost, as two uncertain factors, were highlighted in current study. Based on the traditional nominal facility location model approach and considered the uncertainty of two parameter intervals. Thus, a novel robust facility location model is established in the hybrid programming of CPLEX and MATLAB. Results show that: (1) the supply uncertainty costs of construction waste transfer stations and transportation significantly affected the total costs of waste disposal, the total costs of location and site allocation scheme of construction waste disposal facilities were more sensitive to changes in waste supply. (2) As the combination value of the uncertainty level parameter increases (2%, 7%, 10%), the optimal total cost sum and α also increases, and its changing trend is from obvious to slow. (3) The optimal cost of the distribution and disposal facility layout of the construction waste transit station was determined taking Guangzhou for example. This study provided a scientific and effective method for the location of construction waste disposal facilities by considering multiple uncertain factors. This can also help stakeholders reduce the costs of the distribution net and choose appropriate interval value according to preference for risk.
... Yet another group of researchers have inclined towards the application of MA for solving site selection problems. Liu et al. (2018) employed GA for performing site selection for construction and demolition waste recycling plants. Alhaffa and Abdulal (2011) studied the optimal ATM deployment strategy using GA. ...
Education is one of the most vital sectors of any nation’s development. Site selection for Education Centers (EC) like schools, colleges, and coaching centers can be a very complex process. Various parameters like population, literacy rate, property cost, etc. have to be considered while selecting a site. Though deterministic approaches employed for site selection have been proven to give the best possible solution, they fail to work on large datasets. Recently metaheuristics have become very popular for solving optimization problems. This paper presents two integrated approaches, Fuzzy Genetic Algorithm for EC site selection (FGA-ECSS) and Fuzzy Binary Particle Swarm Optimization for EC site selection (FBPSO-ECSS) for choosing sites optimally. To evaluate the effectiveness of the two approaches, FGA-ECSS and FBPSO-ECSS have been compared with each other as well as with Genetic Algorithm and Binary Particle Swarm Optimization. The results obtained from the proposed solutions are promising and indicate that they can be used for solving such optimization problems.
... Genetic algorithms (GA) is applied in this research to obtain the near-optimal fleet combinations. This algorithm has proven its efficiency in optimizing site selection for CDW recycling plants and vehicle routing for waste collection and transportation (Liu et al., 2019;Wu et al., 2020). GA, proposed by Holland (1975), is a random algorithm that imitates natural selection based on genetics. ...
Purpose
There have been numerous efforts to tackle the problem of accumulated construction and demolition wastes worldwide. In this regard, this study develops a model for identifying the optimum fleet required for waste transportation. The proposed model is validated through a case study from the construction sector in New Cairo, Egypt.
Design/methodology/approach
Various fleet combinations are assessed against the time, cost, energy and emissions generated from waste transportation. Genetic algorithm optimization is performed to select the near-optimum solutions. Complex proportional assessment and operational competitiveness rating analysis decision-making techniques are applied to rank Pareto frontier solutions. These rankings are aggregated using an ensemble approach based on the half-quadratic theory. Finally, a sensitivity analysis is implemented to determine the most sensitive attribute.
Findings
The results reveal that the optimum fleet required for construction and demolition wastes (CDW) transportation consists of one wheel loader of bucket capacity 2.5 cubic meters and nine trucks of capacity 22 cubic meters. Furthermore, consensus index and trust level of 0.999 are obtained for the final ranking. This indicates that there is a high level of agreement between the rankings. Moreover, the most sensitive criterion (i.e. energy) is identified using a sensitivity analysis.
Originality/value
This study proposes an efficient and effective construction and demolition waste transportation strategy that will lead to economic gains and protect the environment. It aims to select the optimum fleet required for waste transportation based on economic, social and environmental aspects. The usefulness of this study is establishing a consensual decision through the aggregation of conflicting decision makers' preferences in waste transportation and management.
