Deep Learning-Driven Particle Swarm Optimisation for Additive Manufacturing Energy Optimisation
بهینه سازی ازدحام ذرات با محوریت یادگیری عمیق برای بهینه سازی انرژی تولید افزودنی-2019
The additive manufacturing (AM) process is characterised as a high energy-consuming process, which has a significant impact on the environment and sustainability. The topic of AM energy consumption modelling, prediction, and optimisation has then become a research focus in both industry and academia. This issue involves many relevant features, such as material condition, process operation, part and process design, working environment, and so on. While existing studies reveal that AM energy consumption modelling largely depends on the design-relevant features in practice, it has not been given sufficient attention. Therefore, in this study, design-relevant features are firstly examined with respect to energy modelling. These features are typically determined by part designers and process operators before production. The AM energy consumption knowledge, hidden in the design-relevant features, is exploited for prediction modelling through a design-relevant data analytics approach. Based on the new modelling approach, a novel deep learning-driven particle swarm optimisation (DLD-PSO) method is proposed to optimise the energy utility. Deep learning is introduced to address several issues, in terms of increasing the search speed and enhancing the global best of PSO. Finally, using the design-relevant data collected from a real-world AM system in production, a case study is presented to validate the proposed modelling approach, and the results reveal its merits. Meanwhile, optimisation has also been carried out to guide part designers and process operators to revise their designs and decisions in order to reduce the energy consumption of the designated AM system under study.
Keywords: Additive Manufacturing | Energy Consumption Modelling | Prediction and Optimisation | Deep Learning | Particle Swarm Optimisation
Physical metallurgy-guided machine learning and artificial intelligent design of ultrahigh-strength stainless steel
یادگیری ماشین با هدایت متالورژی فیزیکی و طراحی هوشمند مصنوعی از فولاد ضد زنگ قوی-2019
With the development of the materials genome philosophy and data mining methodologies, machine learning (ML) has been widely applied for discovering new materials in various systems including highend steels with improved performance. Although recently, some attempts have been made to incorporate physical features in the ML process, its effects have not been demonstrated and systematically analysed nor experimentally validated with prototype alloys. To address this issue, a physical metallurgy (PM) -guided ML model was developed, wherein intermediate parameters were generated based on original inputs and PM principles, e.g., equilibrium volume fraction (Vf) and driving force (Df) for precipitation, and these were added to the original dataset vectors as extra dimensions to participate in and guide the ML process. As a result, the ML process becomes more robust when dealing with small datasets by improving the data quality and enriching data information. Therefore, a new material design method is proposed combining PM-guided ML regression, ML classifier and a genetic algorithm (GA). The model was successfully applied to the design of advanced ultrahigh-strength stainless steels using only a small database extracted from the literature. The proposed prototype alloy with a leaner chemistry but better mechanical properties has been produced experimentally and an excellent agreement was obtained for the predicted optimal parameter settings and the final properties. In addition, the present work also clearly demonstrated that implementation of PM parameters can improve the design accuracy and efficiency by eliminating intermediate solutions not obeying PM principles in the ML process. Furthermore, various important factors influencing the generalizability of the ML model are discussed in detail.
Keywords: Alloy design | Machine learning | Physical metallurgy | Small sample problem | Stainless steel
Inclusiveness by design? Reviewing sustainable electricity access and entrepreneurship from a gender perspective
شمول طراحی شده توسط؟ بررسی دسترسی پایدار به برق و کارآفرینی از منظر جنسیت-2019
There is a substantial literature analysing the role of electricity as a catalyst for economic development. However, there are significant knowledge gaps in whether such systems are or can indeed be designed in a gender sensitive way to promote equal opportunity for socially inclusive entrepreneurship at the local level. We make three main contributions with this paper. First, we carry out a literature review to unpack the genderelectricity- entrepreneurship nexus by identifying the agenda of the gender-energy and gender-entrepreneurship literature respectively and how they intersect and understand gender over time. Second, we synthesise key factors identified as hindering and driving empowerment in relation to electricity and entrepreneurship and identify the weaknesses of the respective literature. Third, we outline the contours of the conceptual intersection and develop a framework which shows how electricity systems can be designed to become favourable and economically empowering for both men and women. Furthermore, we demonstrate how local value chains can benefit from this electric inclusiveness. Finally, with our framework, we develop recommendations for strategic action and identify points of intervention in policy, planning, design and operation of electricity systems.
Keywords: Gender and energy | Gender and entrepreneurship | Electricity access | Women’s empowerment
Problems of engineering entrepreneurship in Africa: A design optimization example in solar thermal engineering
مشکلات کارآفرینی مهندسی در آفریقا: یک نمونه بهینه سازی طراحی در مهندسی حرارتی خورشیدی-2019
This paper addresses Africa’s challenges and opportunities to engineering entrepreneurs. A business environmental scan is done in line with the standard PESTLE analysis, identifying at least twenty generic problems across the continent. Focus is directed to an opportunity in solar water heating, where inadequate electricity supply combines with a plentiful solar resource amidst environmental protection awareness, to make investments potentially worthwhile. Three home level market segments are identified. Key issues in the PESTLE scan are linked with available materials to formulate and solve a design optimization model for these segments. A competition-less product emerges for rural homes. Another – for small urban homes – can be retailed at 50% of current equivalent system prices, and yet, still make profits for the entrepreneur. Both these systems attain average temperatures in excess of 57 C, the fatal level for most pathogenic bacteria. The 3rd and larger system for rich urban homes incorporates a supplementary electric heater that is programmable to kick in half an hour before water withdrawal if solar energy has failed to maintain water temperature above 60 C. The entrepreneur can still make profit if the product retails at 52% of the equivalent competition price.
Keywords: Africa | Design optimization | Engineering entrepreneurship | PESTLE analysis | Solar water heating
2DToonShade: A stroke based toon shading system
2DToonShade: ضربه بر اساس سیستم سایه toon-2019
We present 2DToonShade: a semi-automatic method for creating shades and self-shadows in cel animation. Besides producing attractive images, shades and shadows provide important visual cues about depth, shapes, movement and lighting of the scene. In conventional cel animation, shades and shadows are drawn by hand. As opposed to previous approaches, this method does not rely on a complex 3D reconstruction of the scene: its key advantages are simplicity and ease of use. The tool was designed to stay as close as possible to the natural 2D creative environment and therefore provides an intuitive and user-friendly interface. Our system creates shading based on hand-drawn objects or characters, given very limited guidance from the user. The method employs simple yet very efficient algorithms to create shading directly out of drawn strokes. We evaluate our system through a subjective user study and provide qualitative comparison of our method versus existing professional tools and recent state of the art.
Keywords: Toon shading | Cel shading | Hand-drawn animation | Image-based rendering | Non-photorealistic-rendering
Researching Pure Digital Entrepreneurship – A Multimethod Insider Action Research approach
تحقیق در مورد کارآفرینی دیجیتالی خالص - یک رویکرد تحقیقات خود عملی چند منظوره -2019
Knowledge production in Pure Digital Entrepreneurship (PDE) needs to reflect the non-linear nature of a journey defined by digital artifact and platform creation. Accordingly, this paper proposes and offers practical guidance on the use of Multimethod Insider Action Research (MIAR) as a suitable research design for studying the entrepreneurial journey in this context. It argues for integrating first-person Reflective Practice, second-person Collaborative Inquiry and Design Research for third-person knowledge production that balances rigour and relevance. While calls for such forms of longitudinal process inquiry have largely gone unanswered due to identified challenges, this paper uses a case narrative to illustrate the feasibility of conducting them in a PDE context.
Keywords: Digital entrepreneurship | Multimethod | Insider Action Research | Design research
Mining patient-specific and contextual data with machine learning technologies to predict cancellation of children’s surgery
استخراج داده های خاص و اختصاصی بیمار با فناوری های یادگیری ماشین برای پیش بینی لغو جراحی کودکان-2019
Background: Last-minute surgery cancellation represents a major wastage of resources and can cause significant inconvenience to patients. Our objectives in this study were: 1) To develop predictive models of last-minute surgery cancellation, utilizing machine learning technologies, from patient-specific and contextual data from two distinct pediatric surgical sites of a single institution; and 2) to identify specific key predictors that impact children’s risk of day-of-surgery cancellation. Methods and findings: We extracted five-year datasets (2012–2017) from the Electronic Health Record at Cincinnati Children’s Hospital Medical Center. By leveraging patient-specific information and contextual data, machine learning classifiers were developed to predict all patient-related cancellations and the most frequent four cancellation causes individually (patient illness, “no show,” NPO violation and refusal to undergo surgery by either patient or family). Model performance was evaluated by the area under the receiver operating characteristic curve (AUC) using ten-fold cross-validation. The best performance for predicting all-cause surgery cancellation was generated by gradient-boosted logistic regression models, with AUC 0.781 (95% CI: [0.764,0.797]) and 0.740 (95% CI: [0.726,0.771]) for the two campuses. Of the four most frequent individual causes of cancellation, “no show” and NPO violation were predicted better than patient illness or patient/family refusal. Models showed good cross-campus generalizability (AUC: 0.725/0.735, when training on one site and testing on the other). To synthesize a human-oriented conceptualization of pediatric surgery cancellation, an iterative step-forward approach was applied to identify key predictors which may inform the design of future preventive interventions. Conclusions: Our study demonstrated the capacity of machine learning models for predicting pediatric patients at risk of last-minute surgery cancellation and providing useful insight into root causes of cancellation. The approach offers the promise of targeted interventions to significantly decrease both healthcare costs and also families’ negative experiences.
Keywords: Pediatric surgery cancellation | Quality improvement | Predictive modeling | Machine learning
Analytical games for knowledge engineering of expert systems in support to Situational Awareness: The Reliability Game case study
بازی های تحلیلی برای مهندسی دانش سیستم های خبره در حمایت از آگاهی وضعیتی: مطالعه موردی بازی اطمینان-2019
Knowledge Acquisition (KA) methods are of paramount importance in the design of intelligent systems. Research is ongoing to improve their effectiveness and efficiency. Analytical games appear to be a promis- ing tool to support KA. In fact, in this paper we describe how analytical games could be used for Knowl- edge Engineering of Bayesian networks, through the presentation of the case study of the Reliability Game. This game has been developed with the aim of collecting data on the impact of meta-knowledge about sources of information upon human Situational Assessment in a maritime context. In this paper we describe the computational model obtained from the dataset and how the card positions, which reflect a player belief, can be easily converted in subjective probabilities and used to learn latent constructs, such as the source reliability, by applying the Expectation-Maximisation algorithm.
Keywords: Source reliability | Expert knowledge | Knowledge acquisition | Bayesian networks | Parameter learning | Analytical game
An efficient simulation optimization methodology to solve a multi-objective problem in unreliable unbalanced production lines
یک روش بهینه سازی شبیه سازی کارآمد برای حل یک مشکل چند هدف در خطوط تولید نامتوازن غیرقابل اعتماد-2019
This research develops an expert system to addresses a novel problem in the literature of buffer allo- cation and production lines. We investigate real-world unreliable unbalanced production lines where all time-based parameters are probabilistic including time between parts arrivals, processing times, time be- tween failures, repairing times, and setup times. The main contributions of the paper are a twofold. First and foremost, the mean processing times of workstations and buffer capacities, unlike the existing litera- ture, are considered as decision variables in a multi-objective optimization problem which maximizes the throughput rate and minimizes the total buffer capacities as well as the total cost of the mean process time reductions. Secondly, an efficient methodology is developed that can precisely reflect a real-world system without any unrealistic and/or restrictive assumptions on the probabilistic nature of the system, which are commonly assumed in the existing literature. One of the greatest challenges in this research is to estimate the throughput rate function since it highly depends on the random behavior of the sys- tem. Thus, a simulation optimization approach is developed based on the Design of Experiments and Re- sponse Surface Methodology to fit a regression model for throughput rate. Finally, Non-dominated Sorting Genetic Algorithm (NSGA-II) and Non-dominated Ranked Genetic Algorithm (NRGA) are used to gener- ate high-quality solutions for the aforementioned problem. This methodology is run on a real numerical case. The experimental results confirm the advantages of the proposed methodology. This methodology is an innovative expert system with a knowledge-base developed through this simulation optimization approach. This expert system can be applied to complex production line problems in large or small scale with different types of decision variables and objective functions. The application of this expert system is transformative to other manufacturing systems.
Keywords: Unreliable unbalanced production lines | Buffer allocation problem | Simulation optimization | Design of experiments | Response surface methodology | Meta-heuristics
The tacit knowledge of entrepreneurial design: Interrelating theory, practice and prescription in entrepreneurship research
دانش ضمنی در مورد طراحی کارآفرینی: نظریه ، عمل و تجویز در تحقیقات کارآفرینی-2019
An important challenge facing entrepreneurship researchers is the “three-body” knowledge problem of how to use “theoretical knowledge” to produce “prescriptive knowledge” that communicates the “practical knowledge” of situated practice to students and practitioners of entrepreneurship. We argue that a contribution can be made to solving this problem by theorizing practical knowledge as the “know-how” to do a situated entrepreneurial practice. “Know-how” is a cognitive “capacity to act” that prescribes for a practitioner how to produce a type of outcome in a range of circumstances. This “know-how” can potentially, therefore, be reconstructed theoretically as explicit micro-prescriptive guidelines for third-party practice. To exploit this connection between practical knowledge and prescriptive knowledge, however, we first need to overcome the problem that “know-how” is largely tacit in the moment of real-time forward-looking practice. In other words, the practitioner is not directly aware of their tacit “know-how”, or “tacit knowledge”, at the time of practice. In this article, we explore the contribution design theory can make to empirically eliciting, and conceptually inferring, the real-time “tacit knowledge” of entrepreneurial practice as a precursor to producing micro-prescriptive knowledge.
Keywords: Artifact | Design | Prescriptive knowledge | Tacit knowledge | Entrepreneurial practice | Problem space