What business or technical problem are you trying to solve through digitalization technologies? What data do I need to gather to address this problem and what is the quality of those data? Working backwards to get the technology solutions? “Nail the problem, then scale it"

What is relevant to where you are now in your journey How do you move past testing and piloting and achieve real business results? Strategy versus a tactical integration planning? Emphasizing the difference between products and projects, and why it matters. How do you make good decisions about what to scale up and when, and what to abandon?

• Dr. Yves Gorat Stommel, Head of Cognitive Solutions, Evonik Digital
  ×

  Yves Gorat Stommel

  Head of Cognitive Solutions

  Evonik Digital

  

  Yves Gorat Stommel is currently working as the head of the Cognitive Solutions team, with a strong focus on setting-up and implementing a comprehensive, company-wide Artificial Intelligence and data analysis strategy. In his current function, Yves’ motivation stems from bringing together people, technology and positive change. By continuously questioning, improving and re-imagining operational and business processes – amongst others by looking at the company through the new “lens” of enabling and disruptive Artificial Intelligence – value is created for both the company and its employees. This does not only require identifying, benchmarking and implementing best practices, but more importantly targeted communication, linking knowledge and an emphasis on global instead of local mindsets and approaches.

• Cheryl Ingstad, Director, Office of Artificial Intelligence & Technology Office, US DOE
  ×

  Cheryl Ingstad

  Director, Office of Artificial Intelligence & Technology Office

  US DOE

  

  Cheryl Ingstad serves as the Director of the Artificial Intelligence & Technology Office (AITO) for the Department of Energy (DOE). AITO was created on September 5, 2019, to serve as the central body responsible for the development, coordination and application of Artificial Intelligence, building upon the Department of Energy’s capabilities as a world-leading enterprise in scientific discovery and technological innovation. Ingstad comes to DOE from 3M Company, where she led critical commercialization efforts in AI/Machine Learning research and development. Before 3M, Ingstad was an early leader in the Defense Intelligence Agency’s Information Operations Branch. Ingstad holds a MA in International Economics and International Relations from Johns Hopkins University’s School of Advanced International Studies, and a BS from Georgetown University. She is also a graduate of the US Army Signal Officer Basic Course and the US Army Intelligence Analysis Course.

• Walter Curley, *Invited, Senior Engineer - Continuous Improvement, Nova Scotia Power
  ×

  Walter Curley

  Senior Engineer - Continuous Improvement

  Nova Scotia Power

  
• Luis Ruano, Technical Commercial Engineer, Beyond Limits
  ×

  Luis Ruano

  Technical Commercial Engineer

  Beyond Limits

  

  Luis Ruano is a Technical Commercial Engineer at Beyond Limits with a background in chemical engineering. Prior to joining Beyond Limits, an industrial AI technology company, supported clients in the Oil & Gas industry by strategically analyzing their needs and discovering opportunities to help them implement AI solutions that will generate the greatest value by addressing their most pressing problems. As a technical product expert, Luis consults with clients to identify areas that are ripe for disruption and a good fit for Beyond Limits’ suite of solutions to maximize efficiency and transform workflows. Luis has also spearheaded the digital transformation development for a multinational oil and gas corporation, as well as worked as an offshore maintenance and production engineer in the Gulf of Mexico. Luis received his bachelor’s degree in Chemical Engineering from Brigham Young University.

• Angela Langner-Thiele, Digital Strategist, Evonik Industries
  Tools Alone Do Not Create Value: Technology Acceptance at Evonik

  Tools Alone Do Not Create Value: Technology Acceptance at Evonik

  ×
  ×

  Angela Langner-Thiele

  Digital Strategist

  Evonik Industries

  
• James Martin, Global Operational Excellence Manager, Allnex USA
  Driving Energy Efficiency with Advanced Analytics

  Driving Energy Efficiency with Advanced Analytics

  ×

  Many manufacturers list sustainability as one of their main corporate objectives. These companies that optimizing their processes to reduce energy consumption and waste gives them a significant competitive advantage. However, identifying opportunities for continuous improvement in this area is difficult, as process engineers often do not have the advanced analytics applications required to investigate their process in a rapid, in-depth way. It is extremely difficult for plant engineers to eliminate waste and improve efficiency when they spend most of their analytics time sifting through time series data in spreadsheets. One analytical technique that engineers can use to improve energy efficiency is through energy modeling. In a process plant, there are hundreds of items of equipment that contribute to the total energy use. Sensor data from this equipment are stored in time series data historians. Subject matter experts (SMEs) can use this data to build predictive models of total energy consumption using each individual item’s sensor data as inputs. With this method, they can determine if each piece of equipment is operating efficiently based on the coefficients in the model. Using traditional analytics tools like spreadsheets, energy models are difficult to build and maintain, and they quickly become outdated and obsolete. Companies like Allnex, however, use Seeq Workbench’s Prediction Tool to construct energy models that they use to decrease their total energy consumption with minimal capital expense. In addition, Allnex engineers operationalize these models by building monitoring dashboards in Seeq Organizer Topic to detect, in near real time, if energy use is deviates from the model. Compared to the hundreds of hours required to build energy models with spreadsheets, the engineers at Allnex have used the Seeq to build and monitor energy models in significantly less time.
  ×

  James Martin

  Global Operational Excellence Manager

  Allnex USA

  

• Isabelle Lacaille, Data Infrastructure Engineer, Lonza AG/Ltd
  Operations Data Visibility fuels Productivity at Lonza

  Operations Data Visibility fuels Productivity at Lonza

  ×

  Chemical processing companies do not have to wait for advanced analytics to benefit from digitalization. Simply increasing operations visibility provides immediate and significant value. This was Lonza’s experience when implementing its own digitalization initiative, PIVOT (Productivity Improvements via Operations Technology). As a global company, Lonza had to adopt a strategy to support small, diverse production sites. One example was a chemical plant with less than 100 employees, facing a growing demand for its product. Lonza implemented a global data infrastructure using OSIsoft’s PI System, and put in place tools for data visualization and analysis such as SEEQ and Microsoft Power BI. The PI System allowed raw data from disparate systems (e.g. control systems, analytical instruments) to be combined and contextualized. Power BI presented an aggregated view of the data that could be filtered by batch, production line or production period of interest. SEEQ provided engineers with a powerful analytics tool to drill into raw data signals and uncover insights. With these tools, it became possible to track key performance indicators and anticipate production issues before they occurred, helping the site adopt a proactive approach to operations. Remote support groups were able to access the same data in real-time, and provide recommendations for process changes. These improvements yielded significant improvements in cost benefit and production volume for the plant. Increased operations visibility also enables advanced digitalization projects. The combination of analytical results with process data provided a clear picture of in-process samples for each batch. This allowed the team to identify a strong use case for on-line analytical instruments and model predictive control. The strong foundation of operations visibility at Lonza will fuel its digitalization roadmap for years to come.
  ×

  Isabelle Lacaille

  Data Infrastructure Engineer

  Lonza AG/Ltd

  

  Isabelle is a Data Infrastructure Engineer at Lonza. She is a member of the Operations Technology group, which supports the Specialty Chemicals division. Prior to this, Isabelle was working as a Systems Engineer at OSIsoft, helping customers gain insights from their operations data. She holds a Master’s degree in Chemical Engineering from McGill University.

• Misbah Syed, Data Scientist, Evonik Corporation
  Forecasting the concentration of chemical components in a production plant through AutoML

  Forecasting the concentration of chemical components in a production plant through AutoML

  ×
  ×

  Misbah Syed

  Data Scientist

  Evonik Corporation

  

  Misbah has worked on applications of Advanced Process Controls and Machine Learning based predictive models in the chemical manufacturing industry. With background in Chemical Engineering, he augments theoretical process engineering with modern data driven approaches to optimize production processes.
• Gupreet Kainth, Principle Design Engineer, Cyient, Inc
  Multi-Objective Design Optimization of Hydro Generators using Genetic Algorithm

  Multi-Objective Design Optimization of Hydro Generators using Genetic Algorithm

  ×

  Hydro generator design optimization poses an engineering problem constituting conflicting multi-objectives and constraints. Finding a techno-commercially competitive value proposition for the client by arriving at a design uniquely defined by a set of independent design variables (e.g. parameters related to magnetic core, rotor pole, stator & rotor winding etc.) is the challenge. The conventional design approaches have limitations of not adequately exploring the vast design/solution space and missing potential good solutions. An intelligent application to adequately address exploration in the multi-dimensional solution space has been developed by utilizing Genetic Algorithm (GA) in the design process. GAs are a branch of Artificial Intelligence and derivative-free equivalent of Reinforcement Learning. These are nature inspired evolutionary computations relying on Darwin’s principle of survival of the fittest and mimic the operations of natural selection, crossover, and mutation to evolve a population of solutions over generations. Being derivative free, GAs can operate on discontinuous and non-differentiable objective functions. This paper presents, the experience of software application development employing the advanced version of GA namely Non-Dominated Sorting Genetic Algorithm with elitist strategy (NSGA-II) for generator design optimization. The objectives of optimization include cost minimization and efficiency maximization while respecting associated constraints (e.g. temperature rises, transportation constraints, Inertia requirement etc.) The optimization application developed, within the purview of established synchronous generator design principles, caters to optimization tasks corresponding to a vast range of generator specifications. The optimization run delivers not one but a set of Pareto-Optimal solutions enabling stakeholders to make a choice. The choice empowers OEMs and power plant developers with enhanced flexibility in techno-commercial decision making. This application is being used by Hitachi Mitsubishi Hydro, Japan. A typical optimization run intelligently scans approximately 100,000 solutions in 6-7 hours. The methodology has potential for new insights and solutions for widespread applications in machinery and system design.
  ×

  Gupreet Kainth

  Principle Design Engineer

  Cyient, Inc

  

  Is Principle Design Engineer at Cyient Limited, Hyderabad in Turbo Machinery Group. He received a Bachelor of Technology Degree in Mechanical Engineering from IIT Delhi in the year 2001. He has around 18 years of engineering design & management experience in Green Field & Brown Field projects while working with OEMs like Hitachi Mitsubishi Hydro, Japan; Voith Hydro, Austria; Alstom Power, India & BHEL, India with particular focus on Hydro Generators. Apart from core mechanical engineering experiences, he is an Optimization, Artificial Intelligence & Machine Learning enthusiast.
• Leslie Rittenberg, Refinery & Process Manufacturing Product Manager, Beyond Limits
  Machine Learning and AutoML

  Machine Learning and AutoML

  ×
  ×

  Leslie Rittenberg

  Refinery & Process Manufacturing Product Manager

  Beyond Limits

  

  Leslie Rittenberg is the Refinery & Process Manufacturing Product Manager for Beyond Limits, an industrial-grade artificial intelligence technology company built for demanding sectors including energy and utilities. Leslie has over 30-years of experience in the Power and Oil & Gas industries. Prior to joining Beyond Limits, Leslie held leadership positions with a major O&G company for multiple refining assets as well as their Corporate Downstream Technology Center, where she led the development of their downstream manufacturing digital strategy. Leslie recently joined the Beyond Limits team that brings in a unique brand of Cognitive AI to solve complex business and operational problems in manufacturing settings such as refineries. Beyond Limits’ use cases go beyond conventional AI by incorporating and encoding human business reasoning in combination with live plant data to impact operational frontline decision making. Leslie holds an MBA and a degree in Chemical Engineering.