Artificial Intelligence, or AI, is quite the buzz word. Mention in general conversation, say if you are Axios or The New York Times, and public response is that it is something evil that will take all our jobs away.
Of course, like all technology from the beginning of human history AI can be good or bad depending upon who uses it for what reason.
Now, let me add a second stream to this brief essay. Advanced Process Control, or APC. There are some excellent APC products on the market that I’ve written about over the years. The problem I’ve heard about over those same years relates to keeping the model updated. Too many people (read managers) seem to think you set it up once and then it lasts forever. That could not be further from reality.
Yesterday I had a conversation with Pervez Choudhry, Vice President for Business at Petuum. This is a company started through AI research at Carnegie Mellon University by Eric Xing. He hired a number of Ph.D.s and post-doctoral researchers in AI along with domain experts in industries he targeted for markets and went to work.
My BS antennae always activate at the sound of AI in a press release. So, I asked Choudhry what Petuum meant by the term. That’s when he told me about the research and researchers. AI relates to machine learning. Getting a data set from a process and self-learning from new data feedback from the process.
I’m more impressed by the business model than the technology. The company hosts the application in the cloud deployed as “AI as a Service”. This system addresses the problem so many have run into about maintaining the model as the process morphs over time. A company worth watching. They could well disrupt (in a good way) this particular market.
The press release that provoked my curiosity promoted a new use case—supervised autonomous cement plant operations for CEMEX—a global building materials company.
The two companies entered into a global agreement where CEMEX can implement Petuum “Industrial AI Autopilot” with “autosteer” in all cement plants worldwide for autonomous cement plant operations. The Petuum Industrial AI Autopilot product for cement plant operations are being deployed at select CEMEX USA and Mexico plants, and will continue to be rolled out globally in 2019.
The Petuum Industrial AI Autopilot suite of products deliver real-time precise forecasts for key process variables, prescriptions for critical control variables and supervised autosteer aligned with business objectives for all cement plant operations including clinker cooler, preheater, rotary kiln, pyro process, ball mill and vertical mill processes to achieve lowered energy consumption, optimized fuel mix and increased throughput while maintaining stable operation and high product quality. Additionally, the fuel mix optimization Autopilot enables alignment of global operational excellence initiatives with local site priorities.
The joint CEMEX and Petuum teams achieved a cruise-control-like supervised “autosteer mode,” where the AI Autopilot could run operations with full engage/disengage control available to the operator.
“Petuum Industrial AI Autopilot helped us achieve something we didn’t think was possible at this time,” said Rodrigo Quintero, operations digital technologies manager at CEMEX. “We expect our yield improvements and energy savings to be up to seven percent, from the connected AI-based autopilots, which is game changing for our industry. Additionally, this is a giant step in digital transformation towards safe, highly standardized operations, that will help us strengthen our high-quality products portfolio while also ensuring we meet our operational and sustainability goals, and to minimize costs.”
The Autopilot products deployed at CEMEX for the rotary kiln and clinker cooler systems are integrated with plant control systems and OSIsoft PI data infrastructure for scalable, standardized and rapid deployments across multiple lines and plants globally.
The Autopilot products, developed and operationalized on the Petuum AI platform, can ingest data from a variety of sources including unstructured, images, structured, time series, CRM, ERP and others. The Petuum platform provides sophisticated data processing, cleansing and machine/deep learning pipelines used to implement advanced AI that is sensitive to linear, temporal, long range and non-linear data patterns in a range of industrial use cases.
“Our collaboration with CEMEX has allowed us to demonstrate that resource and skill-intensive advanced AI technologies, previously used to address complex problems only in limited settings, can now achieve tangible business impact in a wide range of real-world industrial environments,” said Dr. Eric Xing, CEO of Petuum. “We are able to achieve new levels of automation, accelerating the journey to Industry 4.0. Our vision is to bring AI benefits to a wide range of businesses in a highly cost-effective and fast manner, solving challenges that can’t be addressed by traditional techniques.”
CEMEX and Petuum will continue close collaboration to deploy additional Autopilot use-cases such as emissions reduction, fuel-mix (alternative fuel) optimization, kiln refractory, preventive maintenance, etc. for global cement plants and expand Petuum Industrial AI Autpilot to other operations worldwide.
I grew up on (ERP) pain. The quickest way to find unemployment was to be selected to be the program manager implementing the company’s new ERP system. Actually, in reality the death was long, slow, and painful. A new study conducted by my old friend Cindy Jutras lays the old myth to rest.
Ultra Consultants, an independent enterprise solution consulting firm serving the manufacturing and distribution sector, published an industry survey conducted by Mint Jutras, researchers specializing in analyzing the business impact of enterprise applications. The in-depth report resulting from the survey is titled The Real Facts about ERP Implementation: Busting the Myth of Failure, But Are You Overrating Your Success?
In late 2018, Mint Jutras surveyed more than 300 North American manufacturers and distributors, focusing on the success of their ERP implementations in terms of schedule, cost and return on investment (ROI). The study of ERP implementation success by manufacturers and distributors found 67 percent rate their implementations as successful or very successful.
The report findings show that previous statistics related to lack of ERP implementation success rates are out of date, and “flip the script” on often cited success rates from previous years. Highlights of the study include:
The Mint Jutras/Ultra Consultants study found that the primary reasons for success had to do with people and process, and not just software. Key success factors include top management support and change management.
Reasons for lack of implementation success include inadequate business process re-engineering and inadequate project planning.
While many ERP implementations meet expectations in terms of schedule, budget and ROI, the Mint Jutras/Ultra Consultants study shows a significant number of manufacturing and distribution companies over-rate their success and leave additional attainable returns on the table.
“ERP project disasters were quite common in the early days of ERP. It’s noteworthy that this study reveals as myth the once-cited high rates of failure in terms of schedules, costs and payback,” notes Cindy Jutras, President of Mint Jutras. “Solutions today are far more technology-enabled, easier to implement and use. Equally important is management support of the project, and change management initiatives.”
Notes Jeff Carr, Founder and CEO of Ultra Consultants, “This research study reflects the performance of current offerings of modern ERP systems now available to manufacturers and distributors. The report shows that the majority of ERP implementations drive value, are on time and meet budget expectations. It also reveals the importance of setting goals for a project, and putting the focus on people and processes, not just technology.”
The greater IT community makes abundant use of open source projects. These projects have proven great worth in operating systems, networking, and applications. The OT community, well, not so much. Maybe some. Microsoft and Dell Technologies, among many others, have donated millions of lines of code to open source projects.
However, the Internet of Things has proven to be one of the places where IT and OT can come together.
Meanwhile, The Eclipse Foundation has been a favorite of mine for probably 20 years. I remember downloading and playing with the Eclipse IDE for Java a long time ago. The foundation makes the news again this year announcing open source advancements in IoT.
It announced major milestones that make Eclipse IoT a leading collaboration of vendors working together to define an open, modular architecture to accelerate commercial IoT adoption. Similar to the early days of the Internet–where open source and vendor collaboration on standard building blocks brought the web to ubiquity–industry leaders including Bosch, Red Hat, Cloudera, and Eurotech are collaborating to standardize open source, modular IoT architecture components within the Eclipse IoT Working Group.
In 2011, the Eclipse IoT Working Group was launched with three projects aimed at reducing the complexity of developing Machine-to-Machine IoT solutions. Eclipse IoT quickly evolved as vendors signed up to collaborate on IoT’s end-to-end interoperability and performance challenges across key areas like constrained devices, device gateways, and scalable cloud platforms. Today the Eclipse IoT community has grown to 37 projects, 41 member companies, and 350 contributors who are building IoT solutions based on Eclipse IoT code.
In a recent case study, Bosch Software Innovations detailed the reasons why it decided in 2015 to participate in Eclipse IoT and the major advantages that open source community involvement has brought to its cloud-based IoT platform, the Bosch IoT Suite. Bosch today has more than 60 developers working on Eclipse IoT projects and has contributed around 1.5 million lines of code. The Bosch IoT Suite is based on the Eclipse Ditto, Eclipse hawkBit, Eclipse Hono, and Eclipse Vorto open source projects.
“We have accomplished so much since we began our open source strategy at Bosch,” added Caroline Buck, Product Owner, Bosch IoT Suite. “Open source development has enabled us to transform how we build software internally and it is making our organization a better product company. Any company that is serious about IoT should consider an ‘open source first’ strategy. If you are planning to do open source IoT, then Eclipse IoT is THE community we recommend.”
In a recent report–Eclipse Foundation’s Open Source IoT Activity Reaches Critical Mass–industry analyst firm 451 Research concluded: “It is time to take a look at what Eclipse IoT has to offer as organizations that choose vendor-specific (proprietary) alternatives to get started begin to run into challenges regarding scale, complexity or cost that has them interested in open source alternatives. While it is not necessarily easier to get an IoT project up and running using open source software, the long-term advantages once an IoT system reaches critical scale are clear–more predictable costs and avoidance of vendor lock-in–and they are driving enterprises to investigate open source options.”
“We are proud that Eclipse IoT is the open source community of choice for commercial-grade IoT innovation,” said Mike Milinkovich, Executive Director of the Eclipse Foundation. “Eclipse IoT projects are where industry leaders collaborate on developing the production-ready, interoperable, and flexible open source building blocks needed for the market adoption IoT. Our members are at the forefront of accelerating IoT innovation with the quality and sustainability that the Eclipse Foundation is known for.”
On Eclipse Foundation’s blog, Milinkovich described how–similar to the early trajectory of the commercial Internet, and the importance of the LAMP stack in particular–industrial IoT’s progress is being catalyzed by open source standards and interoperability that allow vendors to drive solutions forward while competing above the common infrastructure level. Eclipse IoT represents the largest open source community that’s driving these open, interoperable, and flexible components.
Eclipse IoT projects are broadly grouped under three categories of innovation critical for building an end-to-end IoT architecture:
Constrained Devices — the set of libraries that can be deployed on a constrained embedded device to provide a complete IoT development stack.
Edge Device Gateways — projects that provide capabilities to coordinate the connectivity of a group of sensors and actuators to each other and to external networks.
IoT Cloud Platform — projects that deliver the highly scalable, multi-cloud software infrastructure and services required to manage and integrate devices and their data. These technologies support deployment flexibility for running IoT workloads at the edge, on any of the leading cloud platforms (e.g. Amazon Web services, Microsoft Azure, Google Cloud), or in enterprise data centers. These projects also facilitate the interoperability of Eclipse IoT-based solutions with existing enterprise applications and other IoT solutions.
In addition to the Bosch IoT Suite, Eclipse IoT technologies are powering production-ready, commercial IoT offerings from other leading vendors. Eurotech’s award-winning Everyware IoT integrated IoT portfolio is based on Eclipse IoT projects. Everyware Software Framework is an enterprise-ready IoT edge framework based on Eclipse Kura, a Java/OSGi middleware for IoT gateways. Everyware Cloud, an enterprise-ready edition of Eclipse Kapua, offers an open, modular, and microservices-based IoT cloud platform.
“The market adoption of new business models is driving the demand for more agile, secure, and flexible solutions based on open standards and open source technologies. This trend contributed to Eurotech’s decision, in 2012, to become a founding member of the Eclipse IoT Working Group hosted by the Eclipse Foundation”, said Giuseppe Surace, Chief Product and Marketing Officer at Eurotech. “The Eclipse Foundation is the place where industry leaders collaborate to deliver innovative and extensible tools, frameworks, and runtime components for an open development environment. Within Eclipse IoT, Eurotech is working with Cloudera, Red Hat, and others to develop key IoT runtimes and other enabling technologies that will deliver an integrated, end-to-end open IoT architecture. Eurotech was the original contributor to the Eclipse Kura and Eclipse Kapua projects within the IoT Working Group. Our core objective is to ensure that when customers are ready to deploy IoT, the solutions will be there.”
IoT ecosystem leaders join Eclipse IoT to take advantage of the following opportunities:
Participate in industry collaborations to develop common open IoT platforms for Industrial IoT, Industry 4.0, Smart Home, Edge Computing, and more.
Ensure the quality and sustainability of an end-to-end enterprise IoT architecture fully based on open source and open standards
Play a role in defining Eclipse IoT strategic priorities
Gain insights into the Eclipse IoT technology roadmap and direction
Benchmark and learn best practices from peers for leveraging open IoT technologies to accelerate product development and improve time-to-revenue
It starts with digital then moving toward autonomous processes. I’ve written about the strategy ABB has followed for the past four years since Ulrich Spiesshofer assumed the CEO post. We can summarize much of the strategy and also technology roadmap from those two words.
Spiesshofer brought in Guido Jouret in 2017 from Cisco for the role of Chief Digital Officer with the task of bringing digital to all business units. He has made a lot of progress in this short period of time.
Jouret elaborated, “We aren’t trying to be a software company, but hardware requires software.”
Kevin Kosisko, business unit managing director power generation & water, industrial automation and my interview about all things digital at the ABB Customer World conference. We talked about what autonomous meant. “Things we can do without sending people,” he told me. “For example, consider an oil platform taking the first step toward autonomous. Say they must take down a well for routine inspections and then bring it back up. It’s a difficult task, not to mention danger of flying crew to platform and being in the environment. So a combination of digital + autonomous to remove as much human intervention as possible. They took 2 days out of the entire process. That’s 2 additional days of production.”
Two things he told me that highlighted themes I would hear later. The first as “autonomous” being toward the end of a continuum going beyond preventive and predictive. Second, to use the digital twin model to help operators and engineers remove manual steps from a process.
Later I found a spot at the back of a full house for a panel on autonomous—The Journey Towards Autonomy in Industrial Operations Panelists were:
Dr. Zied Ouertani, Global Digital Lead, Chemicals, ABB
David Funderberg, Technology Manager, Chemical and Refining, ABB
Businesses in the industrial space have undergone a paradigm shift to move from isolated operations to collaborative and ultimately more autonomous operations. By 2025 we will witness humans working with systems in a collaborative way, leveraging artificial intelligence (AI) seamlessly. Disruptive technologies like AI, machine learning and augmented reality (AR) have all changed the way we do everyday tasks and in some cases made them autonomous. Hands-free collaboration can help repair remote issues or predict plant incidents.
The goal does not include taking humans out of the loop. I’m afraid I instigated a post-panel discussion where an editor argued that very definition of autonomous is “without humans”. So, he was asking the usual question you get from newspaper reporters and politicians—are they doing away with humans in production and manufacturing. Rebuttal came from one of the panelists who suggested he look at autonomous as part of a continuum, e.g., preventive->predictive->prescriptive->self-healing->operates with minimal supervision. This is applicable probably not to an entire plant, but to certain processes.
Digital
Guido Jouret spoke later on the status of digital at ABB following two years into his digital transformation leadership. He said the digital emphasis has led to more interactions with customers. And there are 185% 18.5% more customers year over year. ABB gets invited at earlier stages of the project process allowing it more input and influence. The company also has better C-level conversations with customers. ABB Ability should be considered a new technology platform.
As march into Women’s History Month, I welcome Isabel Yang, CTO at Advanced Energy Industries. As a minority woman in a C suite position at a publicly traded manufacturing company, Isabel has a plethora of unique insight on her path to success as well as advice for all women looking to spearhead their careers.
Yang says, “I believe women need to shape their own destiny in their careers and lives. Now more than ever, we must work to establish a set of core skills early in our careers and gradually grow ourselves into experts, then progressively branch out to learn about adjacent areas or new areas to acquire new skills.”
