Paper aims: Due to increasing energy prices, manufacturers have to pay more attention to the energy efficiency of their production processes. This paper aims to support manufacturers in increasing processes’ energy efficiency by using production data and applying machine learning approaches. Originality: Systematic guidelines or standards for minimising the energy consumption of manufacturing processes through machine learning approaches are still lacking. This gap is addressed in this paper. Research method: The paper follows a qualitative research method to understand the manufacturing processes and their challenges in improving energy efficiency. The raw data for a 5-step approach were collected in research projects with manufacturing SMEs, and information about the processes through interviews and workshops with them. Then, an analysis of currently available machine learning frameworks and their selection and implementation is conducted. Main findings: The main result is a 5-step approach for increasing the energy efficiency of manufacturing processes through machine learning. Essential applications and technical challenges for data mapping, integrating, modelling, implementing, and deploying machine learning algorithms in manufacturing processes for increasing energy efficiency are presented. Implications for theory and practice: The findings can guide manufacturers, researchers, and data scientists to use machine learning in practice when they intend to increase the energy efficiency of manufacturing processes.

Improvement in current manufacturing settings for enabling energy efficiency is a challenge for many manufacturers. Although virtual reality has been so far applied in manufacturing for training, visualization and product development, the use of this technology in manufacturing for increasing energy efficiency has been less addressed. This paper investigates the potential of virtual reality for a better analysis of energy demands in manufacturing. By envisioning and illustrating energy flows and consumption, virtual reality can support energy efficiency. The paper provides a systematic review of the literature. The findings are analysed from the perspective of research gaps in making virtual-based technologies to enable energy-efficient manufacturing. Particularly, the elements and factors (opportunities) and methods that can be transmitted from current research to energy-efficient manufacturing, are identified and discussed.

High tidal ranges pose a significant challenge for affected ports. Waterway locks ensure sufficient water levels but their use often coincides with a loss of water in the harbour basins. As an alternative to energy-intensive pumping stations, it is desirable to fill the port naturally, e.g., by opening the lock gates at high tides. Unfortunately, this is a complex and dynamic scheduling problem due to manifold contributing factors. This paper outlines a novel architecture towards intelligent control for waterway lock operations. The concept employs a multi-agent system to cope with the problem complexity and dynamics. Its software agents represent relevant stakeholders, thereby integrating prediction models derived from machine learning.

Currently, manufacturing industries are faced by ever-growing complexities. On the one hand, sustainability in economic and ecological domains should be considered in manufacturing. With respect to energy, many manufacturing companies still lack energy-efficient processes. On the other hand, Industry 4.0 provides large manufacturing datasets, which can potentially enhance energy efficiency. Here, traditional methods of data analytics reach their limits due to the increasing complexity, high dimensionality and variability in raw data of industrial processes. This paper outlines the potential of deep learning as an enabler for energy efficiency in manufacturing. We believe that enough consideration has not been given to make manufacturing efficient in terms of energy. In this paper, we present three manufacturing environments where available DL approaches are identified as opportunities for the realization of energy-efficient manufacturing.

The processing of natural resources involves many variations of uncertainties as the natural resources themselves vary in their composition. Since the weather influences harvest quality, natural products are strongly affected by weather conditions. Excessive rainfall increases the water content of products, while a lack of rain may cause the whole harvest to dry out. Due to the varying soil conditions also the quality of wheat, measured, for example, by its protein or starch content, varies from region to region. During the processing of natural products, as presented in this case study for animal feed, the produced compound feed can change its composition as well, for example by raising the starch content through the addition of hot steam to wheat grains. As the processing of natural raw materials as compound feed consumes a lot of energy, producers aim to decrease costs related to energy consumption without decreasing the product's quality. In addition, energy efficient production also leads to lower CO2 emissions. This paper highlights the energy efficiency challenges during the processing of natural resources in feed processing and gives advice on how to cope with uncertainties by reaching the goal of achieving a constant product quality.

Our planet has limited resources, and due to our increasing demands on a variety of products, we rely on the availability of primary and secondary resources. This paper will give an overview on the required information received from processing secondary resources. It is possible to assess the quality of the generated material fl ows with this information. By describing the material characteristics and the material fl ow uncertainties, a forecast of the material’s future potential to replace primary resources may be possible. Future prospects of the quality of secondary resources, including their input and output properties may be helpful to assess their potential to substitute primary resource for example. It is the contribution of the paper to point out the necessity of knowing the whole life cycle of a product to gain the best available end-of-life option. The case study of scrap tire recycling gives an example of assessing the material’s properties. Modeling recycling processes offers the potential of identifying the processing steps with regard to the main material fl ows and emissions to reduce the environmental impact and improve the economics. Material fl ow analysis and life cycle assessment can support the determination of the future potential of waste streams entering the recycling process. Some material fl ows are appropriate to replace primary resources without loss of quality. But other materials are only useful for products with minor quality. Some materials are made to never separate by itself, and therefore pure material fl ows are impossible to achieve. A model that considers different material properties of material fl ows helps to evaluate the global recycling potential. Therefore, material qualities have to be defi ned to make an assessment of sustainable management of secondary resources possible. A concept of developing a model that addresses this issue is presented in this paper. The aim of the model is to predict secondary material fl ows that are of equal quality of primary material fl ows. These material fl ows are then suitable to substitute primary resources which results in global savings in resources, both material and energy.

This paper presents an approach aiming to reduce the energy consumption during the processing of natural raw materials. Natural raw materials are processed with more energy than they actually need. This is due to uncertainties on material and energy flows and to a lack of process flexibility and inappropriate machine configuration. The proposed approach combines techniques like artificial intelligence (expert systems) with technologies for data processing in order to create real-time “action plans” containing energy reduction suggestions for compound feed manufacturers. These suggestions are based on the correlation between energy consumption, product quality and process control by influencing the grain size, the steam amount and machine parameters. Through the application of expert systems the energy consumption in energy-intensive processes could be reduced and seen as an efficient way leading to lower CO2 emissions. At the end of the paper current results are detailed and future work is presented.

Dumping secondary raw materials is already forbidden by legislation in Europe. Due to limited resources, especially in high-tech products or the dependency on other countries who provide specific minerals or metals, efficient recycling processes are improving to guarantee a sustainable management of secondary resources with replacing primary resources. We can save our raw materials by either reducing the consumption of primary raw materials or the increased use of secondary raw materials. Processing waste materials ensures the availability of secondary resources. To evaluate the potential of the reusability of materials the knowledge of material flows of recycling processes and their characteristics is essential. For example, the knowledge of the quantity and quality of material flows gives an indication for the assessment of the environmental process performance. The combination of Material Flow Assessment (MFA) and Life Cycle Assessment (LCA) may help to improve sustainable resource management and makes environmental decision making easier. This paper will give an overview on the required information received from recycling processes to build up an environmental management system to serve as a tool for sustainable material management. The main focus lies on the material characteristics, uncertainties and the material’s future potential to replace primary resources.

Material Flow Assessment (MFA) is a method of analyzing the material flow of a process in a well-defined system. Referring to the life cycle of a product the Material Flow Assessment is part of a Life Cycle Assessment (LCA) and provides the possibility of assessing the environmental impact of a process and product respectively. Applying these methods to recycling processes the potential of saving primary and secondary resources may be measurable. The presented paper will give an overview on the strategy how MFA can contribute to Environmental Management Information Systems (EMIS).