Artificial Intelligence Applications for Increasing Resource Efficiency in Manufacturing Companies—A Comprehensive Review
12 Jun 2021-Sustainability (Multidisciplinary Digital Publishing Institute)-Vol. 13, Iss: 12, pp 6689
TL;DR: An overview of the current AI applications and how they affect resource efficiency is provided, with a focus on predictive maintenance, production planning, fault detection and predictive quality, as well as the increase in energy efficiency.
Abstract: Sustainability improvements in industrial production are essential for tackling climate change and the resulting ecological crisis. In this context, resource efficiency can directly lead to significant advancements in the ecological performance of manufacturing companies. The application of Artificial Intelligence (AI) also plays an increasingly important role. However, the potential influence of AI applications on resource efficiency has not been investigated. Against this background, this article provides an overview of the current AI applications and how they affect resource efficiency. In line with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, this paper identifies, categorizes, and analyzes seventy papers with a focus on AI tasks, AI methods, business units, and their influence on resource efficiency. Only a minority of papers was found to address resource efficiency as an explicit objective. Subsequently, typical use cases of the identified AI applications are described with a focus on predictive maintenance, production planning, fault detection and predictive quality, as well as the increase in energy efficiency. In general, more research is needed that explicitly considers sustainability in the development and use phase of AI solutions, including Green AI. This paper contributes to research in this field by systematically examining papers and revealing research deficits. Additionally, practitioners are offered the first indications of AI applications increasing resource efficiency.
Citations
More filters
DOI•
01 Dec 2021
TL;DR: In this article, the basic principle of systemic life cycle thinking in cellular units is introduced as the foundation of a management framework for bio-intelligent production systems (BIS) and a coherent theoretical model of a future decentralized production system is developed.
Abstract: A sustainable design of production systems is essential for the future viability of the economy. In this context, biointelligent production systems (BIS) are currently considered one of the most innovative paths for a comprehensive reorientation of existing industrial patterns. BIS are intended to enable a highly localized on-demand production of personalized goods via stand-alone non-expert systems. Recent studies in this field have primarily adopted a technical perspective; this paper addresses the larger picture by discussing the essential issues of integrated production system design. Following a normative logic, we introduce the basic principle of systemic life cycle thinking in cellular units as the foundation of a management framework for BIS. Thereupon, we develop a coherent theoretical model of a future decentralized production system and derive perspectives for future research and development in key areas of management.
8 citations
TL;DR: In this article, the authors analyzed the relationships between the technologies of Industry 4.0, continuous improvement, and the business results through the Partial Least Squares (PLS) methodology.
Abstract: This study analyses the relationships between the technologies of Industry 4.0, continuous improvement, and the business results. To carry out this study, 109 questionnaires to companies of different sectors were collected, but an indispensable condition to take into account was the fact that these companies develop themselves their logistics management. The analysis of the results obtained through the Partial Least Squares (PLS) methodology argues that there is a positive relationship between 4.0 Industry and continuous improvement processes, as well as between continuous improvement processes and organizational results, although it cannot be concluded that a direct relationship between 4.0 Industry and organizational results exists, which means that there are other variables, such as continuous improvement, mediating between them. With this work, there is already an accredited reference of the relationship, which has been verified to exist, between the Industry 4.0, the continuous improvement, and the business results.
8 citations
TL;DR: In this article , the authors reviewed the recent literature on energy-efficient scheduling in job shop manufacturing systems, with a particular focus on metaheuristics, and pointed out potential directions for future research, namely developing integrated scheduling approaches for interconnected problems, fast metaheuristic methods to respond to dynamic scheduling problems, and hybrid meta-heuristic and big data methods for cyber-physical production systems.
Abstract: Energy efficiency has become a major concern for manufacturing companies not only due to environmental concerns and stringent regulations, but also due to large and incremental energy costs. Energy-efficient scheduling can be effective at improving energy efficiency and thus reducing energy consumption and associated costs, as well as pollutant emissions. This work reviews recent literature on energy-efficient scheduling in job shop manufacturing systems, with a particular focus on metaheuristics. We review 172 papers published between 2013 and 2022, by analyzing the shop floor type, the energy efficiency strategy, the objective function(s), the newly added problem feature(s), and the solution approach(es). We also report on the existing data sets and make them available to the research community. The paper is concluded by pointing out potential directions for future research, namely developing integrated scheduling approaches for interconnected problems, fast metaheuristic methods to respond to dynamic scheduling problems, and hybrid metaheuristic and big data methods for cyber-physical production systems.
8 citations
TL;DR: In this paper , the authors investigated the relationship between AI capabilities, servitization, and the role of absorptive capacity, and found that the positive impact of AI capabilities was positively moderated by absorptive capacities.
Abstract: The advent of artificial intelligence (AI)-based technologies has opened new opportunities for manufacturers to maintain their technological edge and address pressing societal challenges. This research investigates the nature of the relationships between AI capabilities, servitization, and the role of absorptive capacity. Building on dynamic capabilities literature, we developed and empirically tested a model using structural equation modeling (SEM) and further applied a fuzzy-set qualitative comparative analysis (fsQCA). Through the construct of AI capabilities and its four sub-dimensions, we find supportive evidence from our model estimates employing data from 185 manufacturing firms in the US and EU. The study findings highlight the positive impact of AI capabilities on servitization; this relationship is positively moderated by absorptive capacity. Furthermore, the road to servitization is through advancing AI capabilities related to internal process and resource optimization coupled with AI for social innovation services. The study’s theoretical and pragmatic implications are discussed.
8 citations
TL;DR: Wang et al. as mentioned in this paper explored the impact of industrial intelligence on carbon intensity and how this impact fluctuates when industrial structure upgrading is included as a mediator, based on the spatial Durbin model (SDM) and the mediating effect model.
7 citations
References
More filters
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Abstract: Learning to store information over extended time intervals by recurrent backpropagation takes a very long time, mostly because of insufficient, decaying error backflow. We briefly review Hochreiter's (1991) analysis of this problem, then address it by introducing a novel, efficient, gradient based method called long short-term memory (LSTM). Truncating the gradient where this does not do harm, LSTM can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units. Multiplicative gate units learn to open and close access to the constant error flow. LSTM is local in space and time; its computational complexity per time step and weight is O. 1. Our experiments with artificial data involve local, distributed, real-valued, and noisy pattern representations. In comparisons with real-time recurrent learning, back propagation through time, recurrent cascade correlation, Elman nets, and neural sequence chunking, LSTM leads to many more successful runs, and learns much faster. LSTM also solves complex, artificial long-time-lag tasks that have never been solved by previous recurrent network algorithms.
72,897 citations
TL;DR: It is shown how the proposed bidirectional structure can be easily modified to allow efficient estimation of the conditional posterior probability of complete symbol sequences without making any explicit assumption about the shape of the distribution.
Abstract: In the first part of this paper, a regular recurrent neural network (RNN) is extended to a bidirectional recurrent neural network (BRNN). The BRNN can be trained without the limitation of using input information just up to a preset future frame. This is accomplished by training it simultaneously in positive and negative time direction. Structure and training procedure of the proposed network are explained. In regression and classification experiments on artificial data, the proposed structure gives better results than other approaches. For real data, classification experiments for phonemes from the TIMIT database show the same tendency. In the second part of this paper, it is shown how the proposed bidirectional structure can be easily modified to allow efficient estimation of the conditional posterior probability of complete symbol sequences without making any explicit assumption about the shape of the distribution. For this part, experiments on real data are reported.
7,290 citations
Posted Content•
TL;DR: A new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely is proposed, which generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.
Abstract: The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.
7,019 citations
TL;DR: Central issues of reinforcement learning are discussed, including trading off exploration and exploitation, establishing the foundations of the field via Markov decision theory, learning from delayed reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state.
Abstract: This paper surveys the field of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of the field and a broad selection of current work are summarized. Reinforcement learning is the problem faced by an agent that learns behavior through trial-and-error interactions with a dynamic environment. The work described here has a resemblance to work in psychology, but differs considerably in the details and in the use of the word "reinforcement." The paper discusses central issues of reinforcement learning, including trading off exploration and exploitation, establishing the foundations of the field via Markov decision theory, learning from delayed reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state. It concludes with a survey of some implemented systems and an assessment of the practical utility of current methods for reinforcement learning.
6,895 citations
Posted Content•
TL;DR: A survey of reinforcement learning from a computer science perspective can be found in this article, where the authors discuss the central issues of RL, including trading off exploration and exploitation, establishing the foundations of RL via Markov decision theory, learning from delayed reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state.
Abstract: This paper surveys the field of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of the field and a broad selection of current work are summarized. Reinforcement learning is the problem faced by an agent that learns behavior through trial-and-error interactions with a dynamic environment. The work described here has a resemblance to work in psychology, but differs considerably in the details and in the use of the word ``reinforcement.'' The paper discusses central issues of reinforcement learning, including trading off exploration and exploitation, establishing the foundations of the field via Markov decision theory, learning from delayed reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state. It concludes with a survey of some implemented systems and an assessment of the practical utility of current methods for reinforcement learning.
5,970 citations