Advanced Analytics in Mining Engineering

As an author on business and advanced analytics management, I have many ideas in my mind. Of course, I think all of them are great, but it is always challenging to know which theoretical concepts can reach a practical result in advance.

After writing some papers and chapter books about advanced analytics and the mining industry's machine learning application, I found much demand for speaking and consulting on the subject. In that work, I talked with hundreds of managers and analytical professionals in countries worldwide. I also worked with many professors in different universities in America, Europe, Asia, and Australia to extend my knowledge of applied analytics in the mining industry.

Moreover, I have worked as an AI program leader with technology developers such as IBM, Accenture, Deloitte, and Oracle to develop suitable products for prestigious mining companies based on AI. These applications now play a critical role in predicting, optimizing, and making decisions for operation and maintenance in mining companies such as BHP, Rio Tinto, Vale, Angelo America, and Peabody Energy. After many years working in this area, I decided to write a comprehensive book to guide the researchers and industrial managers to find the analytical opportunities better and make the best decision to deploy the new science in their work.

In front of the research and development group in mining companies, there are some barriers to using practical advanced analytical approaches to solve their business problems.

The first barrier is the lack of bright and trained people who need to design innovative analytical solutions for the problem. There are two different groups of graduates who are looking for job positions in mining companies. The first group is mining engineers who do not have any data analysis experience. The second group is the IT and computer engineers who do not have any mining background. Therefore, each mentioned group cannot provide the mining companies' requirements individually. The digital mines need people familiar with the mining operations and have enough knowledge and experience to use the data analytical approaches.

The second barrier is the lack of valuable collected data to develop advanced analytical solutions. In the last decades, many new companies and start-ups have been established to make and use different tools for data collections in mine sites. However, there is no validated guideline to help the mine managers collect the necessary and correct data from equipment and process. As a result, a massive amount of noisy data is collected from mine site equipment, and the main part is not useable.

The third barrier is developing specific analytical applications to solve the unique business challenge. The mining operations are linked together, and any change in any particular process can dramatically affect the upstream and downstream activities. Therefore, the main part of developed analytical tools for the mine sites focused on a specific operation. However, we need the use the integrated approach to minimize the harmful side effects overall.

The fourth barrier is the maturity level of analytics in the mining industry. The traditional mine managers' mindsets need to be changed. In the digital mine era, we should predict and optimize instead of scene and response. AI and machine learning models can help us predict failures and avoid them, and the optimization models will support the management decisions.

The advanced analytics for mining engineering book has been designed to tackle the barriers mentioned above. The book can be used as a reference book to teach at universities, and students can use it as a reference in their research. The book covers the students and research requirements to get familiar with the analytical approaches in mining engineering. This book also can help the technology developers and companies to identify the essential parameters in the mine sites and provide suitable tools to collect valuable data for the mining operations. The book chapters have been designed based on the mining value chain operations, and there is a logical connection between the chapters to help the readers make integrated solutions. Many practical examples are designed for the chapters that help mine managers get familiar with the benefits and limitations of advanced analytics in future digital mines. The prediction, optimization, and decision-making tools introduced in the book can give a clear vision of the future of mining to managers and researchers in the mining industry.

I believe that we are at the beginning of an exciting journey to apply advanced analytics, AI, and machine learning approaches to solve the mining companies' challenges. Digital mines will be developed, and we need to support the young generation who will be the future digital revolution leaders in the mining industry. This book aims to share the knowledge and experience of authors who have worked in the analytics field in mining as executives, managers, specialists, and researchers.

I hope this book can help the people who dream of making future mining safer, more creative, and more productive.

Ali Soofastaei

ww.soofastaei-publications.com

?