nach oben

2021 | Buch

Kapitel lesen Erstes Kapitel lesen

Guide to Industrial Analytics

Solving Data Science Problems for Manufacturing and the Internet of Things

verfasst von: Prof. Richard Hill, Dr. Stuart Berry

Verlag: Springer International Publishing

Buchreihe : Texts in Computer Science

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

This textbook describes the hands-on application of data science techniques to solve problems in manufacturing and the Industrial Internet of Things (IIoT). Monitoring and managing operational performance is a crucial activity for industrial and business organisations. The emergence of low-cost, accessible computing and storage, through Industrial Digital of Technologies (IDT) and Industry 4.0, has generated considerable interest in innovative approaches to doing more with data.

Data science, predictive analytics, machine learning, artificial intelligence and general approaches to modelling, simulating and visualising industrial systems have often been considered topics only for research labs and academic departments.

This textbook debunks the mystique around applied data science and shows readers, using tutorial-style explanations and real-life case studies, how practitioners can develop their own understanding of performance to achieve tangible business improvements. All exercises can be completed with commonly available tools, many of which are free to install and use.

Readers will learn how to use tools to investigate, diagnose, propose and implement analytics solutions that will provide explainable results to deliver digital transformation.

Inhaltsverzeichnis

Frontmatter

Introductory Concepts

Frontmatter

1. An Introduction to Industrial Analytics

Abstract

Introductory concepts in analytics, the digitalisation of industry, data science and machine learning are explained and discussed.

Richard Hill, Stuart Berry

2. Data, Analysis and Statistics

Abstract

Statistical thinking is a large part of how we approach the analysis of data. A range of simple descriptive statistics is often sufficient for us to acquire an improved understanding of our data. Looking at features such as missing values, the mean, the range of the data, the presence of outliers and the shape of a distribution can tell us a lot about the data under scrutiny. We can use visualisation approaches both as a part of the process of analysis and as a means of explaining what we have discovered to others. These methods are usually enough to provide either the answers we need, or they narrow down subsequent investigations.

Richard Hill, Stuart Berry

3. Measuring Operations

Abstract

This chapter introduces some concepts from operational research that will help relate analysis techniques to the real world. In particular, the relationship between work in progress and lead time length is explored using examples to explain important characteristics of business operations.

Richard Hill, Stuart Berry

4. Data for Production Planning and Control

Abstract

This chapter commences with a discussion of the use and non-use of data within manufacturing and proceeds by investigating measures of optimality used to assess the benefits of an efficient and effective planning and control system indicating the commonly used approaches to production planning and control and the data needs of these techniques. Finally, we present models for typical manufacturing firms which have been derived from a series of case studies. Operating practices in small and larger manufacturing firms are compared so as to deduce optimal approaches to their production planning and control systems and their implied data requirements.

Richard Hill, Stuart Berry

Methods

Frontmatter

5. Simulating Industrial Processes

Abstract

An approach to modelling business processes as a queueing model is described. The model is examined and used to demonstrate how questions can be posed that enhance the understanding a system. The model is then translated into a simulator that represents the system, producing results to a variety of questions that are useful for operations management.

Richard Hill, Stuart Berry

6. From Process to System Simulation

Abstract

Business operations typically comprise a number of stages where information or physical materials are processed. Such systems are described as networks of queueing models, and these descriptions are used to build a simulation, using an example business process. The simulation is developed to show how a manager may explore system enhancements using a model.

Richard Hill, Stuart Berry

7. Constructing Machine Learning Models for Prediction

Abstract

Machine learning (ML) is a set of techniques that enable computer algorithms to be refined over time automatically, by way of experience. Such techniques are attractive for the management of operations as they enable predictions to be made that are informed by the context in which a dataset has been produced. This chapter demonstrates the effectiveness of ML techniques by way of application.

Richard Hill, Stuart Berry

Application

Frontmatter

8. Case Study: Confectionery Production

Abstract

This case study is based around a confectionery production unit. This firm produces sugar- and chocolate-based confectionery mainly sold through its own retail outlets. The case study highlights the problems created by the firm through the lack of availability of ‘good’ data this lack of good/timely data inhibited the effective planning and control of their production processes. These problems resulted in the low morale of production workers, and they were blamed for not achieving production targets and the production a high percentage of reject goods, and the subsequent loss of profits.

Richard Hill, Stuart Berry

9. Minimum Information Set for Effective Control

Abstract

Information flow within organisations is generally accepted as being important, but without quantifiable evidence it can be difficult to make a business case to invest in improvements. This chapter appraises different approaches to managing orders and demonstrates how the costs of poor information flow can be accounted for and evaluated.

Richard Hill, Stuart Berry

10. Business Adoption of Analytics

Abstract

Barriers to the accessibility of technology that integrates cyber-physical systems are either lowering or being removed. Manufacturing enterprises thrive on the generation and consumption of data, yet many organisations do not exploit the potential of the information they already own. This chapter describes how academic staff from the University of Huddersfield’s, Centre for Industrial Analytics (CIndA), developed a practical and holistic approach to collaboration with businesses in relation to the adoption of Industry 4.0 in the Yorkshire Region. Researchers at the university were able to develop a multi-faceted model of engagement which a) drives a partnership between business and academic capabilities, aligning strategic and holistic approaches to industrial liaison combined with b) the active involvement of specialist IDT start-ups.

Richard Hill, Stuart Berry

Backmatter

Titel: Guide to Industrial Analytics
verfasst von: Prof. Richard Hill
Dr. Stuart Berry
Verlag: Springer International Publishing
Electronic ISBN: 978-3-030-79104-9
Print ISBN: 978-3-030-79103-2
DOI: https://doi.org/10.1007/978-3-030-79104-9

Springer Professional

Über dieses Buch

Inhaltsverzeichnis

Frontmatter

Introductory Concepts

Frontmatter

1. An Introduction to Industrial Analytics

2. Data, Analysis and Statistics

3. Measuring Operations

4. Data for Production Planning and Control

Methods

Frontmatter

5. Simulating Industrial Processes

6. From Process to System Simulation

7. Constructing Machine Learning Models for Prediction

Application

Frontmatter

8. Case Study: Confectionery Production

9. Minimum Information Set for Effective Control

10. Business Adoption of Analytics

Backmatter

Premium Partner