May 16, 2021

McKinsey: adopting a smart approach to big data

McKinsey
Big Data
AI
Machine Learning
4 min
Industrial companies are using AI to improve plant operations. To be successful, they will need to leverage big data with the help of domain experts

Industrial companies are embracing artificial intelligence (AI) as part of the fourth digital revolution. AI leverages big data; it promises new insights that derive from applying machine learning to datasets with more variables, longer timescales, and higher granularity than ever.

Big Data

According to a new McKinsey report, using months or even years’ worth of information, analytics models can tease out efficient operating regimes based on controllable variables, such as pump speed, or disturbance variables, such as weather. These insights can be embedded into existing control systems, bundled into a separate advisory tool, or used for performance management.

Artificial Intelligence

McKinsey recommends that to succeed with AI, companies should leverage historical data via automation. They will need to adapt their big data into a form amenable to AI. This ‘smart data’ can improves predictive accuracy and support root-cause analysis. Additionally, bolstering and upskilling expert staff to manage the process can result in an EBITDA increase of 5 to 15%.

Smart Data

A common failure mode for companies looking to leverage AI is poor integration of operational expertise into the data-science process. McKinsey advocates applying machine learning only after process data have been analysed, enriched, and transformed with expert-driven data engineering using the following steps:

Define the process

Outline the steps of the process with experts and plant engineers, sketching out physical changes (such as grinding and heating) and chemical changes (such as oxidation and polymerization). Identify critical sensors and instruments, along with their maintenance dates, limits, units of measure, and whether they can be controlled.

Enrich the data

Raw process data nearly always contain deficiencies. Thus, creating a high-quality dataset should be the focus, rather than striving for the maximum number of observables for training. Teams should be aggressive in removing nonsteady-state information, such as the ramping up and down of equipment, along with data from unrelated plant configurations or operating regimes. Generic methods to treat missing or anomalous data should be avoided, such as imputing using averages, “clipping” to a maximum, or fitting to an assumed normal distribution. Instead, teams should start with the critical sensors identified by process experts and carefully address data gaps using virtual sensors and physically correct imputations.

Reduce the dimensionality

AI algorithms build a model by matching outputs, known as observables, to a set of inputs, known as features, which consist of raw sensor data or derivations thereof. Generally, the number of observables must greatly exceed the number of features to yield a generalized model. A common data-science approach is to engineer input combinations to produce new features. When combined with the sheer number of sensors available in modern plants, this necessitates a massive number of observations. Instead, teams should pare the features list to include only those inputs that describe the physical process, then apply deterministic equations to create features that intelligently combine sensor information (such as combining mass and flow to yield density). Often, this is an excellent way to reduce the dimensionality of and introduce relationships in the data, which minimize the number of observables required to adequately train a model.

Apply machine learning

Industrial processes can be characterized by deterministic and stochastic components. In practice, first principle–based features should provide the deterministic portion, with machine-learning models capturing the statistical portion from ancillary sensors and data. Teams should evaluate features by inspecting their importance and therefore their explanatory power. Ideally, expert-engineered features that capture, for example, the physics of the process should rank among the most important. Overall, the focus should be on creating models that drive plant improvement, as opposed to tuning a model to achieve the highest predictive accuracy. Teams should bear in mind that process data naturally exhibit high correlations. In some cases, model performance can appear excellent, but it is more important to isolate the causal components and controllable variables than to solely rely on correlations. Finally, errors in the underlying sensor data should be evaluated with respect to the objective function. It is not uncommon for data scientists to strive for higher model accuracy only to find that it is limited by sensor accuracy.

Implement and validate the models

Impact can be achieved only if models (or their findings) are implemented. Taking action is critical. Teams should continuously review model results with experts by examining important features to ensure they match the physical process, reviewing partial dependence plots (PDPs) to understand causality, and confirming what can actually be controlled. Additional meetings should be set up with operations colleagues to gauge what can be implemented and to agree on baseline performance. It is not uncommon for teams to convey model results in real time to operators in a control room or to engage in on-off testing before investing in production-grade, automated solutions.

Conclusion

Industrial companies are looking to AI to boost their plant operations—to reduce downtime, proactively schedule maintenance, improve product quality, and so on. However, achieving operational impact from AI is not easy. To be successful, these companies will need to engineer their big data to include knowledge of the operations (such as mass-balance or thermodynamic relationships). They will also need to form cross-functional data-science teams that include employees who are capable of bridging the gap between machine-learning approaches and process knowledge. Once these elements are combined with an agile way of working that advocates iterative improvement and a bias to implement findings, a true transformation can be achieved.

Share article

Jun 2, 2021

Ericsson Private 5G to transform secure on-site connectivity

Ericsson
Boliden
5G
Smart Mining
3 min
Ericsson Private 5G is a next-gen private cellular 4G & 5G network tailored to drive Industry 4.0 and the digital transformation of industries like mining

Ericsson has launched Ericsson Private 5G. It offers secure and simple 4G LTE and 5G Standalone (SA) connectivity primarily targeting manufacturing, mining and process industries, offshore and power utilities, as well as ports and airports.

 

Ericsson

Ericsson Private 5G optimizes and simplifies business operations with cloud-based network management, keeps sensitive data on-premise, has zero downtime upgrades and guarantees high performance through Service-Level Agreements (SLAs).

It is easily installed within hours at any facility and can be scaled to support larger coverage areas, more devices and higher capacity when needed. The product is designed to be flexible and will support a range of deployment sizes, depending on requirements, to suit varied needs. Businesses can manage their networks and integrate with IT/OT systems via an open API.

5G

Ericsson Private 5G builds upon Ericsson’s 4G/5G radio and dual mode core technology, enabling a wide variety of use cases for both indoor and outdoor environments while integrating well with business operations, devices and applications. As a result, companies can improve productivity, give their customers more value and provide better working environments for employees.

Innovative use cases include tracking assets and real-time automation to improve productivity in warehouses, and a digital twin that can help to optimize manufacturing operations. Efficient quality inspections can also be performed via augmented reality or smart surveillance drones to increase worker safety, particularly in potentially hazardous environments such as ports and mines.

Boliden

Ericsson already has a significant track record of operational 4G and 5G private network deployments with customers worldwide. Ericsson Private 5G builds on the success of that solution portfolio and deployment insights, as well as insights from projects such as 5G-Industry Campus Europe.

Peter Burman, Program Manager Mine Automation, at Swedish mining company Boliden, commented: “Automation, and safety through automation in our mining operations is an absolute must for us. Ericsson Private 5G is exactly what Boliden needs to bring high quality, fast and secure connectivity into potentially hazardous environments allowing us to mobilize efficiency and safety improving use cases.

Niels König, Coordinator 5G-Industry Campus Europe, Fraunhofer Institute for Production Technology IPT added: “Private 5G networks are highly attractive for producing companies because of the uncompromised performance that 5G can bring, allowing them to tackle the challenges of production. Efficiently deploying and using network solutions in enterprises requires simplicity in installation, flexibility in connecting to existing production IT and lean operations while at the same time being able to scale the network to meet future challenges. Ericsson Private 5G delivers exactly these capabilities.”

Ericsson

Enterprise Networks

Leo Gergs, Senior Analyst, ABI Research, noted: “With this new offering, Ericsson will be able to address key trends in the enterprise cellular market.  The value proposition will appeal to operators and service providers as the solution hides technology complexity and therefore reduces the barrier of entry to deployment for many different flavors of enterprise networks.”

Thomas Noren, Head of Dedicated Networks, Business Area Technologies and New Businesses, Ericsson, revealed: “With Ericsson Private 5G, we take the best of Ericsson’s current portfolio and top it up with the best of our new technology. We do this to give businesses what they need to improve productivity, enable new offerings and give employees a better working environment. With Ericsson Private 5G, we also give operators a better way to serve business customers and leverage their assets - in short, to grow beyond mobile broadband.”

Ericsson recently joined a three-year initiative to develop autonomous, carbon-neutral mining processes supported by 5G connectivity. Funded by the EU’s Horizon 2020 research and innovation program, the $16mn Next-Generation Carbon-Neutral Pilots for Smart Intelligent Mining Systems (NEXGEN SIMS) project is being coordinated by Swedish mining and infrastructure equipment manufacturer, Epiroc, in cooperation with a range of industry-diverse partners, including: Ericsson, K+S, Boliden, Agnico Eagle Finland, KGHM Polska and Luleå University of Technology.

Share article