Figure - uploaded by Alexandra Melike Brintrup
Content may be subject to copyright.
Source publication
Consideration of qualitative factors is an integral and necessary part of design optimization. In this paper, we consider qualitative factors as design objectives to be optimized and attempt to optimize qualitative and quantitative criteria together. Interactive evolutionary computation (IEC) provides an ideal platform to include qualitative perspe...
Context in source publication
Context 1
... area 2's width is overall width minus the sum of assembly area 1 width and stores area width while its length is overall length minus the sum of paint room and spares area widths. The problem is thereby reduced to eight parameters as shown in Table 2. The cost of each facility is proportional to its area, except the press area and the warehouse area, whose cost is doubled. ...Citations
... This work demonstrated viable solutions for part and component integration to meet customer expectations. In another work, Brintrup et al. (2007) presented the Multi-Objective Interactive Genetic Algorithm framework that addresses quantitative and qualitative criteria together. The validity and applicability of the method were tested in the factory layout problem. ...
Having passed the primitive phases and starting to revolutionize many different fields in some way, artificial intelligence is on its way to becoming a disruptive technology. It is also foreseen to totally change human-centred traditional engineering design approaches. Although still in the early phases, AI-powered engineering applications enable them to work with ambiguous design parameters and solve complex engineering problems, not otherwise possible with traditional design methods. This work attempts to shine a light on current progress and future research trends in AI applications in design/engineering design concepts, covering the last 15 years which is the ramp-up period for AI. Methods such as machine learning, genetic algorithm, and fuzzy logic have been carefully examined from an engineering design perspective. AI-powered design studies have been categorized and critically reviewed for various design stages such as inspiration, idea and concept generation, evaluation, optimization, decision-making, and modelling. As an overview result of this review, we can confidently say that the interest in data-based design methods and Explainable Artificial Intelligence (XAI) has increased in recent years. Furthermore, the use of AI methods in engineering design applications helps to obtain efficient, fast, accurate, and comprehensive results. Especially with deep learning methods and combinations, situations where human capacity is insufficient can be addressed efficiently. However, choosing the right AI method for a design problem under consideration is significantly important for such successful results. Hence, we have given an outline perspective on choosing the right AI method based on the literature outcomes for design problems.
... On the one hand, the framework can help algorithm researchers to study and compare different improved IGAs; and on the other hand, it is convenient to apply these algorithms in specific fields. Although some IGA design systems [22][23][24] have been proposed, they are found difficult to exploit due to their closed code and the lack of their universality. ...
In order to prompt the theoretical research and application of interactive genetic algorithm (IGA), the framework for IGAOD (Interactive Genetic Algorithm Online Design) is developed from the perspective of software reuse and the commonness and individuality of IGA. This framework encapsulates the basic commonality of IGA, integrates some classic evolution operators of IGA, and provides visual application scenarios and data analysis charts to help users quickly build their own IGA systems. In addition, the template design pattern can be used to construct the genetic algorithm library, which encapsulates the commonness of a series of selection, crossover and mutation operators into different abstract base classes. These classes inherit the identical abstract base class, making it easier for the algorithm to maintain and expand. In this article, the use of the frame is introduced with the example of 3D vase shape design and plate pattern design. Therefore, the framework is more suitable for the theoretical and application research of IGA.
... e paper examines the consequences of the development of the forest health-care industry and makes recommendations for promoting the integrated development of the forest health-care industry. Its goal is to serve as a model for the development of a forest health-care product system based on industrial integration and the promotion of the long-term viability of the forest health-care sector [35,36]. ...
This paper proposes a high-satisfaction evaluation method for health-care product design based on the genetic optimization algorithm in order to deeply understand consumers' satisfaction with forest health-care products. This article builds a consumer demand index system for the service content of forest health-care bases from the four levels of environmental conditions, service items, supporting facilities, and service levels. According to the questionnaire survey results of 1000 randomly selected forest health-care consumers, based on the genetic optimization algorithm, the overall design takes the four levels of satisfaction evaluation into account, resulting in a more reasonable evaluation of health-care products. Experiments show that the method proposed in this paper outperforms the traditional method for evaluating health-care products.
... Minimization of total manufacturing cost and total weighted completion time were two objectives considered in [5,6]. In some studies, such as [7], a list of qualitative and quantitative objectives was targeted. Again in [8], manufacturing cost and total weighted tardiness as objectives were minimized for a flexible manufacturing system. ...
... e best allocation of operations to the machines according to Table 5 was revealed on the basis of the machines' generated degradation level. Consequently, the operations numbers 9, 10, and 18 with processing times 10, 10, and 10, respectively, are allocated to the third machine; the operations numbers 1, 2, 4, 5, 8,11,12,13,14,15,17,24,27,33, and 34 with their processing times 10,7,8,5,4,8,7,4,3,7,8,3,7,10, and 3, respectively, are allocated to the second machine; and the rest of the operations are allocated to the first machine. ...
... e best allocation of operations to the machines according to Table 5 was revealed on the basis of the machines' generated degradation level. Consequently, the operations numbers 9, 10, and 18 with processing times 10, 10, and 10, respectively, are allocated to the third machine; the operations numbers 1, 2, 4, 5, 8,11,12,13,14,15,17,24,27,33, and 34 with their processing times 10,7,8,5,4,8,7,4,3,7,8,3,7,10, and 3, respectively, are allocated to the second machine; and the rest of the operations are allocated to the first machine. ...
The purpose of this paper is to model two problems comprising schedule-allocate (in case of producing identical parts) and sequencing of parts (in case of producing different parts). The first model is used for minimizing the cycle time and operational cost, and the second one for minimizing both the mean and standard deviation of the total production cost as well the cycle time, in an unreliable three-machine robotic cell which confronted with many uncertainty factors. In the current article, mathematical modelling and simulation-based optimization method have been presented to schedule-allocate similar parts and trace the optimal sequence of different parts. Several solution procedures, including epsilon-constraint method and multiobjective particle swarm optimization algorithm, for identical parts case and response surface methodology for different parts case are applied. The results derived from solving numerical examples revealed some advantages in terms of time to attain the optimal solution.
... 9. Perform asexual reproduction as in basic CRO (Section 3.1). 10. Predate worst solutions as described in Section 3.1. ...
The Unequal Area Facility Layout Problem (UA-FLP) has been widely analyzed in the literature using several heuristics and meta-heuristics to optimize some qualitative criteria, taking into account different restrictions and constraints. Nevertheless, the subjective opinion of the designer (Decision Maker, DM) has never been considered along with the quantitative criteria and restrictions. This work proposes a novel approach for the UA-FLP based on an Interactive Coral Reefs Optimization (ICRO) algorithm, which combines the simultaneous consideration of both quantitative and qualitative (DM opinion) features. The algorithm implementation is explained in detail, including the way of jointly considering quantitative and qualitative aspects in the fitness function of the problem. The experimental part of the paper illustrates the effect of including qualitative aspects in UA-FLP problems, considering three different hard UA-FLP instances. Empirical results show that the proposed approach is able to incorporate the DM preferences in the obtained layouts, without affecting much to the quantitative part of the solutions.
... The complexity and poor decision practices of construction projects often lie in the inconsistencies occurred during the early design stages when engineers, clients, architects, and contractors formalise multiple priorities and preferences [1]. In structural engineering problems where the project team can significantly influence the final design decisions, it is important to consider both quantitative (analysis) and qualitative (preferences) aspects when outlining a decision-making framework [2]. Group decision-making processes are suitable for the selection of engineering design priorities when there is a need to satisfy several conflicting opinions. ...
... The reason the component [0-9] × 20% is added into the model is because the initial belief structure is incomplete (80% < 100%). In that case the remaining belief degree represents the probability that has not been assigned to any of the other ratings [0][1][2][3][4][5][6][7][8][9]. This means that the rating would be interval ranging from 3.6 (lower bound) to 7.8 (upper bound). ...
... Larger column spacing help architects plan the internal layout of the building. However, at the same time the decision of a structural grid could make the whole structure more inefficient due to larger spans DR 2 ...
The design and optimisation of building structures is a complex undertaking that requires the effective collaboration of various stakeholders and involves technical and non-technical expertise. The paper investigated an integrated decision-support framework using Quality Function Deployment (QFD) in structural design optimisation. The aim of the study was to develop and test a systematic participatory model that utilises Building Information Modelling (BIM)-enabled technologies for data collection and group decision-making theory. The uncertainties associated with the decision-makers’ preferences were computed using Evidential Reasoning (ER) algorithms in the QFD house of quality. An actual decision scenario was used to test the proposed framework and investigate its capabilities in the context of reinforced concrete buildings. The study demonstrated how the proposed QFD model could effectively enhance decision-making by managing the diversity of stakeholders’ preferences via design integration, enhanced communication and shared domain knowledge.
... They proposed ε-constraint to solve the model and could find the complete Pareto front [3]. The reader is referred to [4], [5], [6], [7], [8], [9], [10] for studying other papers concerning bi objective problems in the field of robotic manufacturing cell scheduling. In most previous researches conducted in the field of robotic manufacturing cells, scheduling is done based on single criteria. ...
This paper focused on scheduling problems arising in a two-machine, identical parts robotic cell configured in a flow shop. Through current research, a mathematical programming model on minimizing cycle time as well operational cost, considering availability of robotic cell as a constraint, is proposed to search for the optimum allocation and schedule of operations to these two machines. Two solution procedures, including weighted sum method and ∊-constraint method are provided. Based on the weighted sum method, like some previous studies, sensitivity analysis on model parameters were done and the optimum solutions were compared with previous results, while the ∊-constraint method can find the Pareto optimal solutions for problems with up to 18 operations in a reasonable time.
... In this respect, qualitative features should be taken into consideration [7], for instance, preferences about the location of specific facilities, distribution of the remaining space, relative placement of the facilities, or any other subjective consideration that can be important for the Decision Maker (DM). Such qualitative features are complicated to include with a classical heuristic or meta-heuristic optimization [8]. Besides, these qualitative features can be: subjective, not known at the beginning or changed during the process. ...
... Among these, the Genetic Algorithms (GAs) [16] are commonly used [17]. Brintup et al. [18] have highlighted the fact that Interactive Evolutionary Computation (IEC) can greatly contribute to improve optimized design by involving users in searching for a satisfactory solution [8]. Interactivity allows more qualitative considerations, which can be more subjective, to be taken into account. ...
The unequal area facility layout problem (UA-FLP) has been addressed by many approaches. Most of them only consider quantitative aspects into the approach. In this work, we will solve UA-FLPs using a novel hybrid model that joins multi-criteria decision making method and interactive evolutionary optimization. Particularly, a combination of the analytic hierarchy process (AHP) and an interactive genetic algorithm, is suggested. By means of this new model, it is possible to take into account both qualitative (using the expert knowledge) criteria and quantitative in order to achieve an acceptable design solution. Our algorithm is able to interact with the decision maker (DM), directing the search process by means of the DM preferences and arranging the criteria that are more important in each design solution.
Thus, the system is adapted to the DM's preferences by means of his/her subjective evaluations of the designs that are consider as representative of the population (reached by a clustering method), and also, to the quantitative criteria. In order to test the proposed approach, an interesting real-world data set has been probed and analysed. Important results are achieved, and relevant conclusions are drawn from the application of this novel intelligent framework.
... The complexity and deficient designs in construction projects often lies in poor decision practises during the early design stages when engineers, clients, architects, and contractors formalise their diverse priorities and preferences (Huang, et al., 2006). In structural engineering problems where the project team can significantly influence the final design decisions, it is important to consider both quantitative (analysis) and qualitative (preferences) aspects when outlining a decisionmaking framework (Brintup, et al., 2007). Group decision-making processes are suitable approaches for the selection of engineering design priorities when there is a need to satisfy several conflicting opinions. ...
... Currently, there is not a mature method to determine the optimal parameters of a deep neural network [46]. Genetic algorithm (GA) is an important intelligent optimization method, which has been widely used in function optimization, automatic control and machine learning [47][48][49][50][51]. In this paper, GA is used to optimize the key parameters of the constructed CDBN model due to its strong global search capability. ...
Rolling bearing fault detection is of crucial significance to enhance the availability, the reliability and the security of rotating machinery. In this paper, a novel method called continuous deep belief network with locally linear embedding is proposed for rolling bearing fault detection. Firstly, a new comprehensive feature index is defined based on locally linear embedding to quantify rolling bearing performance degradation. Secondly, a continuous deep belief network (CDBN) is constructed based on a series of trained continuous restricted Boltzmann machines (CRBMs) to model vibration signals. Finally, the key parameters of the continuous deep belief network are optimized with genetic algorithm (GA) to adapt to the signal characteristics. The proposed method is applied to analyze the experimental bearing signals. The results demonstrate that the proposed method is more superior in stability and accuracy to the traditional methods.
