Format: Paperback
Machine Learning in Mineral Process Engineering: A Practitioner’s Handbook is written for metallurgists, process engineers, plant engineers, and technical professionals who want to understand where machine learning can genuinely add value in mineral processing—and where conventional engineering methods remain the better choice. The book approaches machine learning from an engineering perspective rather than a data-science perspective. Its purpose is not to turn the reader into a programmer, but to provide the technical judgement required to recognise suitable applications, challenge weak assumptions, work effectively with data-science teams, and decide whether a model is reliable enough for use on an operating plant. A central principle runs throughout the handbook: machine learning should complement engineering knowledge, not replace it. First-principles models, mass and energy balances, process control, and metallurgical understanding remain fundamental. Machine learning becomes valuable where complex relationships exist in plant data that cannot conveniently be described by conventional models. The handbook takes the reader from fundamental concepts through practical plant applications, including: Read more
Machine Learning in Mineral Process Engineering: A Practitioner’s Handbook is written for metallurgists, process engineers, plant engineers, and technical professionals who want to understand where machine learning can genuinely add value in mineral processing—and where conventional engineering methods remain the better choice. The book approaches machine learning from an engineering perspective rather than a data-science perspective. Its purpose is not to turn the reader into a programmer, but to provide the technical judgement required to recognise suitable applications, challenge weak assumptions, work effectively with data-science teams, and decide whether a model is reliable enough for use on an operating plant. A central principle runs throughout the handbook: machine learning should complement engineering knowledge, not replace it. First-principles models, mass and energy balances, process control, and metallurgical understanding remain fundamental. Machine learning becomes valuable where complex relationships exist in plant data that cannot conveniently be described by conventional models. The handbook takes the reader from fundamental concepts through practical plant applications, including: Read more