energy utilization, optimization of the entire manufacturing process, integration of the supply chain, new product development, product delivery speed, etc. As of now, it is quite clear that digital will have a significant impact on many areas of the chemical industry, with the gains in manufacturing performance potentially among the largest. This chapter gives an overview of how digital will affect the chemical industry and where the biggest impact can be expected. There are three major areas where applications of an advanced analytic tool can give an enormous profit increase, namely predictive maintenance; yield, energy, and throughput analytics; and value‐maximization modeling. This chapter gives insights about how to achieve a business impact using data and introduces the concept of how valuable data analytics and upstream and downstream activities can result in achieving a business impact.
Profit Maximization Project (PMP) Implementation Steps
Chapter 3 describes different steps for implementing a profit maximization project. It introduces 14 major broad ideas or steps for profit maximization in running commercial plants. These ideas are described in detail in subsequent chapters throughout the book. These generic steps are holistic and can be applied in any process industry, starting from refinery, petrochemical, chemical plants, metals, pharmaceuticals, paper and pulp industries, etc. It starts with mapping the whole plant in monetary terms (US$/h) instead of flow terms. This gives an idea of where to focus maximization of the profit and what low hanging fruits are needed that can be easily translated to increase profit without much investment. Practical guidelines to build a profit maximization framework, easily implementable solutions, numerous examples, and case studies from industries give a completely new computational approach to solve process industry problems and are the hallmark of this book.
Strategy of Profit Maximization
A strategy of profit maximization is the essence of Chapter 4. This chapter describes different ways to maximize the operating profit. The concept of process cost intensity and how to calculate it are introduced in this chapter. The procedure for mapping the whole process in monetary terms and gain insights is described by way of an ethylene glycol plant case study.
This chapter describes in detail eight key steps in mapping current process conditions against different process constraints and limits. The first three major steps are (i) define plant business and economic objectives, (ii) identify various process and safety limitations, and (iii) critically identify the profit scope. Key parameter identification steps for economics, operations, and constraints of the plant are discussed in detail. How to evaluate and exploit potential optimization opportunity is discussed with industrial case studies.
Key Performance Indicators and Targets
Knowing what key operating parameters to monitor and defining the targets and limits for these parameters is an important step for profit optimization. We also need to know the economic values of closing gaps between actual and targeted performances to create incentives for improvement. This chapter deals with how to identify the key performance parameters in running the plant and the whole process is explained with a real‐life commercial plant case study. It provides a methodology to identify qualitatively potential areas of opportunities. The system of key indicators is the cornerstone of a sustainable profit management system.
Assessment of Current Plant Status
An assessment of current plant status and know where you are is the first major step in building a profit maximization project. This chapter deals with the holistic approach to assess the current plant status. How to assess the performance of the base regulatory control layer and the advance process control layer of running a plant is discussed in detail in this chapter. A performance assessment of the major process equipment and an evaluation of the economic performance of the plant against a benchmark are two key focus areas discussed in this chapter. An assessment of profit suckers and identification of equipment for modeling and optimization and an assessment of process parameters having a high impact on profit are two takeaways in this chapter. Readers are enlightened with an assessment of various profit improvement opportunities.
Process Modeling by an Artificial Neural Network
Chapter 7 emphases the need for data‐driven black box and grey box modeling techniques where building of a first principle‐based model is infeasible or time consuming due to the complexity of the industrial equipment. How an artificial neural network (ANN) can be utilized as an effective tool of black box modeling in an industrial context is discussed in this chapter with various real‐life applications. A step‐by‐step procedure to build an ANN‐based modeling platform to utilize a large amount of process data is explained in detail with example calculations. The new horizon of modeling process performance parameters like selectivity, yield, and efficiency and how these models can be utilized to increase profit is explained here. Different examples and case studies of ANN models already applied in diverse fields of process industries are illustrated to give the reader a feel for large scope and potential of applications of the ANN in industry.
Optimization of Industrial Processes and Process Equipment
Due to cut‐throat competition in business, companies now want to reduce their operating costs by optimizing all of their available resources, be it man, machine, money, or methodology. Optimization is an important tool, which can be utilized to strike a proper balance so that profit can be maximized in the long run. Since capital cost is already incurred for a running plant, optimization essentially boils down to minimization of the operating cost for the operating plants. In running a chemical plant, there is a huge scope to optimize the operating parameters, like temperature, pressure, concentration, reflux ratio, etc., which gives either a higher profit through higher production or lower operating costs. There are many ways to optimize the operating conditions of reactors, distillation columns, absorbers, etc., to enhance their profitability. Chapter 8 lays the foundation about how parameter optimization can be utilized to increase profit in running the chemical plant. Conventional optimization techniques are initially discussed to enlighten the reader about the scope and huge potential of optimization in the process industry. This chapter introduces new advanced Meta heuristic optimization techniques that can be applied where application of a conventional technique is limited due to the complexity of the industrial context. Different Meta heuristic optimization techniques, like the genetic algorithm (GA), differential evolution (DE), simulated annealing (SA), etc., are described in detail in this chapter. A basic algorithm, step‐by‐step procedure to develop an optimization technique and different uses of GA, DE, and SA in various fields of process optimization are explained here in order to develop an understanding of this new area. A case study in reactor optimization is illustrated to explain the advantage and ease of implementation of Meta heuristic methods over conventional methods.
Process Monitoring
Today's complex chemical plants need advanced monitoring and control systems to quickly identify the suboptimal operation of process equipment and implement a quick optimization strategy. Running the plant at the highest possible capacity for profit maximization necessitates the development of an intelligent real‐time monitoring system. However, due to the large amount of process data, it is a herculean task to monitor each and every piece of process data. Chapter 9 enlightens the readers about an online intelligent monitoring system, KPI‐based process monitoring, a cause and effect‐based monitoring system, etc. It also gives an idea regarding the development of a potential opportunity‐based dashboard, loss and waste monitoring systems, a cost‐based monitoring system, a constraints‐based monitoring system, and how all these can be integrated into business intelligent dashboards.
In