Abstract
Improvements in energy efficiency in Industry 4.0 is the main imperative in manufacturing. An important challenge in many fields of complex industrial processes is energy-efficient optimization. The basic idea of the energy efficiency optimization algorithm is to find the optimal assigned value of process parameters to achieve the lowest energy cost and the best working conditions. Applying the multi-objective approach for solving real industry optimization problems is a challenging task. Therefore, this chapter provides an overview of the most significant issues in multi-objective optimization problem. Improving energy efficiency with the multi-objective optimization has opened new opportunities for technological progress in Industry 4.0.
TopIntroduction
In industries such as chemical and metallurgical industries, like cement, steal, paper, aluminum, etc. which are extremely energy intensive in nature, heating and cooling of solid materials often cause major energy losses. Industry is responsible for around 38% of global total final energy use (Data source: International Energy Agency (IEA), 2019). To reduce the increasing demand, either more industrial energy has to be generated or the existing consumption of energy has to be brought down without any compromise on either product quality or quantity (Kini & Bansa, 2011).
Energy efficiency presents the ratio between achieved performance or the profits from services, goods or energy, and the energy used to achieve this (Definition according to DIN EN 16001 or ISO 50001). Improvement of energy efficiency has become one of the most challenging tasks and a core component of Industry 4.0 for the following reasons (Jaiswal, Gupta & Kanojiya, 2016):
- •
Improve the profitability and competitiveness of companies through the lower heating, electricity and transportation costs.
- •
Reducing local air pollutants; energy efficiency can reduce the amount of local air pollutants.
Consequently, the current transition in energy mix, wind and photovoltaic power are pushing fossil fuel generation out of the base-load market. Most cogeneration plants are still being operated to meet base-load demand in phases when heat is needed. Owing to the growing power from renewable energy sources, in the future cogeneration plants will also be pushed from continuous full load operation into low partial-load segments. (Slad, Pickard & Strobelt, 2018).
To capture the potential of the cognitive manufacturing transformation in the scope of Industry 4.0, the three key pillars of manufacturing that drive the highest improvement are (IBM, 2019):
- •
Intelligent asset and equipment.
- •
Cognitive process and operations.
- •
Smarter resources and optimization.
Intelligent asset and equipment optimize their performance, reduce unnecessary downtime and increase process efficiency with industry models. Some of commonly used equipment in energy intensive processes are boiler systems, steam systems, motor driven systems, compressed air systems, heating, ventilation and air conditioning systems, fans, pumping systems, cooling towers, etc. 70% of the electrical energy demand in industrial plants is required for drives. Variable-speed drives for fans and pumps save up to 50% of the drive energy (Kini & Bansa, 2011).
Energy savings of 15% can be achieved in industrial plants by means of intelligent process automation (Siemens, 2011). Cognitive process and operations analyze much information from workflows and environment in order to drive quality decision-making in form of advanced process control methods using a fuzzy control or a model predictive controller.
Despite the increasing use of renewable energy which became the leading global source of electricity, the main contribution and challenge in the scope of Industry 4.0 is exploring how optimization could assist in improving accessibility and efficiency of energy technology (Sennaar, 2019). Multi-objective optimization is an area of multiple-criteria decision making, where optimal decisions need to be taken in the presence of trade-offs between two or more objectives that may be in conflict, such as maximizing performance while minimizing energy consumption.
Key Terms in this Chapter
Search Space: Set of all possible solutions for any given optimization problem. Almost always, a neighborhood around each solution can also be defined in the search space.
Fitness: A measure that is used to determine the goodness of a solution for an optimization problem.
Energy Efficiency: The ratio between achieved performance or the profits from services, goods or energy, and the energy used to achieve this.
Multi-Objective Optimization: An optimization problem involving more than a single objective function.
Objective Function: The function that is to be optimized. In a minimization problem, the fitness varies inversely as the objective function.
Evolutionary Algorithm: A class of probabilistic algorithms that are based upon biological metaphors such as Darwinian evolution, and widely used in optimization.
Artificial Intelligence: Algorithms which make machines learn from experience, adjust to new inputs and perform human-like tasks.
Population-Based Algorithm: An algorithm that maintains an entire set of candidate solutions, each solution corresponding to a unique point in the search space of the problem.