Last year at the Ignition Community conference, Inductive Automation's Kevin McClusky (co-director of sales engineering) and Kathy Applebaum (senior software engineer) explored the various ways in which machine learning can be applied in industry. In this presentation, they delved deep into the types of machine learning most applicable to industry and the algorithms behind them. You can read more about this 2018 presentation in the article "How to Apply Industrial Machine Learning," which was based on that presentation. At this year's event, McClusky and Applebaum came together again to highlight the integration of more machine learning capabilities into Ignition over the past year, as well as to showcase four industrial use cases of machine learning being explored by Ignition users. Newly available machine learning capabilities in Ignition enable users to take advantage of the Apache Math 3 library previously added to Ignition 7.9.10 just prior to the release of Ignition 8.

To integrate strategic, tactical and operational decisions, the two-stage optimization has been widely used to guide dynamic decision making. In this paper, we study the two-stage stochastic programming for complex systems with unknown response estimated by simulation. We introduce the global-local metamodel assisted two-stage optimization via simulation that can efficiently employ the simulation resource to iteratively solve for the optimal first- and second-stage decisions. Specifically, at each visited first-stage decision, we develop a local metamodel to simultaneously solve a set of scenario-based second-stage optimization problems, which also allows us to estimate the optimality gap. Then, we construct a global metamodel accounting for the errors induced by: (1) using a finite number of scenarios to approximate the expected future cost occurring in the planning horizon, (2) second-stage optimality gap, and (3) finite visited first-stage decisions. Assisted by the global-local metamodel, we propose a new simulation optimization approach that can efficiently and iteratively search for the optimal first- and second-stage decisions. Our framework can guarantee the convergence of optimal solution for the discrete two-stage optimization with unknown objective, and the empirical study indicates that it achieves substantial efficiency and accuracy.

AI is changing the way we work, live and solve challenges. It can improve healthcare, protect elephants from poachers, and work out how broadband should be distributed. But it could be most valuable as a range of applications helping humanity fight our biggest threat – climate change. AI can strengthen climate predictions, enable smarter decision-making for decarbonising industries from building to transport, and work out how to allocate renewable energy. AI's relevance as a climate change fighting tool comes at a time when there are increasing ethical concerns linked largely to a data-hungry form of the technology called machine learning, where computer systems analyse patterns in existing data to make predictions and decisions.

Robotics, automation and data are not new in manufacturing. In fact, manufacturing is one of the most data-rich industries; however, it's been estimated that about 95% of all industrial data is unused. The reason for this is legacy equipment and operational systems that tend to be proprietary and siloed, incapable of communicating with each other. What is new is that technology has reached an inflection point – robotics automation systems, sensor data, analytics, the Internet of Things (IoT) and artificial intelligence have the potential to transform manufacturing and industrial processes. As plant floor operations technologies converge with IT, a host of use cases across the manufacturing cycle becomes possible to ignite innovation, create more efficient operations, and enable new business models and revenue streams. For example, prescriptive maintenance enabled by AI/L models can automate the actions needed for maintenance of heavy equipment and large assets.

JAGGAER has itself been moving towards closed-loop feedback systems that rely on machine learning for continuous improvement. Here we describe an example: the JAGGAER Digital Assistant. JAGGAER, ERP and third-party data is fed into a central data layer. The information is used in traditional analytics and reporting, but what is new is that algorithms are now providing real-time support for decisions, recommendations and actions. Typically, there might be several recommendations and the end-user takes a decision based on which of these makes most sense.

Model-based reinforcement learning could enable sample-efficient learning by quickly acquiring rich knowledge about the world and using it to improve behaviour without additional data. Learned dynamics models can be directly used for planning actions but this has been challenging because of inaccuracies in the learned models. In this paper, we focus on planning with learned dynamics models and propose to regularize it using energy estimates of state transitions in the environment. We visually demonstrate the effectiveness of the proposed method and show that off-policy training of an energy estimator can be effectively used to regularize planning with pre-trained dynamics models. Further, we demonstrate that the proposed method enables sample-efficient learning to achieve competitive performance in challenging continuous control tasks such as Half-cheetah and Ant in just a few minutes of experience.

Royal Dutch Shell is heavily investing in research and development of artificial intelligence (AI), which it hopes will provide solutions to some of its most pressing challenges. From meeting the demands of a transitioning energy market, urgently in need of cleaner and more efficient power, to improving safety on the forecourts of its service stations, AI is at the top of the agenda. I have been working with Shell over the past months to help create a data strategy, which gave me a thorough insight into Shell's AI priorities and initiatives. Current initiatives include deploying reinforcement learning in its exploration and drilling program, to reduce the cost of extracting the gas that still drives a significant proportion of its revenues. Elsewhere across its global business, Shell is rolling out AI at its public electric car charging stations, to manage the shifting demand for power throughout a day.

Satellite imagery holds a wealth of information that could be useful for industries, science and humanitarian causes, but one big and persistent challenge with it has been a lack of effective ways to tap that disparate data for specific ends. That's created a demand for better analytics, and now, one of the startups that has been building solutions to do just that is announcing a round of funding as it gears up for expansion. Descartes Labs, a geospatial imagery analytics startup out of Santa Fe, New Mexico, is today announcing that it has closed a $20 million round of funding, money that CEO and founder Mark Johnson described to me as a bridge round ahead of the startup closing and announcing a larger growth round. The funding is being led by Union Grove Venture Partners, with Ajax Strategies, Crosslink Capital, and March Capital Partners (which led its previous round) also participating. It brings the total raised by Descartes Labs to $60 million, and while Johnson said the startup would not be disclosing its valuation, PitchBook notes that it is $220 million ($200 million pre-money in this round).

What the Amazon founder and CEO wants for his empire and himself, and what that means for the rest of us. Where in the pantheon of American commercial titans does Jeffrey Bezos belong? Andrew Carnegie's hearths forged the steel that became the skeleton of the railroad and the city. John D. Rockefeller refined 90 percent of American oil, which supplied the pre-electric nation with light. Bill Gates created a program that was considered a prerequisite for turning on a computer. At 55, Bezos has never dominated a major market as thoroughly as any of these forebears, and while he is presently the richest man on the planet, he has less wealth than Gates did at his zenith. Yet Rockefeller largely contented himself with oil wells, pump stations, and railcars; Gates's fortune depended on an operating system. The scope of the empire the founder and CEO of Amazon has built is wider. Indeed, it is without precedent in the long history of American capitalism. More product searches are conducted ...

Grid analytics solutions are providing the utility industry with the right set of opportunities for revitalizing operations and embracing advanced capabilities. FREMONT, CA: Utilities is on the brink of transforming into a more efficient and service-oriented industry. The growing inclusion of smart meters, intelligent devices and IoT endpoints, is enabling utility companies to have greater access to electricity transmission, distribution and consumption data. With 5G-induced low latency connectivity on the cards, utility companies are expecting a significant improvement in real-time access to operational data. The acquired data can be used optimally when utility companies leverage analytics solutions to generate useful and actionable insights from it.