Ctrl2Go
Fostering the New Age of Intelligent Analytics and Predictive Analysis

Capital intensive industries like manufacturing, oil and gas, mining, and railroad operation aim to maximize asset reliability and availability and thus boost their bottom-line profitability. Unplanned downtime, excessive inventory of maintenance parts, and unnecessary maintenance, continuously costs these industries hundreds of billions of dollars annually. With Industry 4.0, “maintenance” should not be limited to preventing downtime of individual assets alone. Instead, maintenance programs demand inclusion of Predictive Maintenance techniques that incorporate a range of AI approaches. Accurate equipment assessment should include: overall equipment health, existing defects, anomaly detection, degradation and failure forecasting, and detailed demand for MRO (spare-parts, workforce) per each asset or equipment type. This increases productivity by 25% or more and reduces breakdowns by nearly 70%. In a nutshell, predictive maintenance allows organizations to be proactive and prevent unplanned reactive maintenance, without incurring high costs or any downtime.

“Our solution was created for a single purpose—to give the user a true asset health condition and an accurate prediction failure model,” says Kenneth Scherwinski, President of US Operations at Cltr2Go. “Our AI-based predictive maintenance solution provides a holistic view of asset health, identifies risk with high accuracy, and gives all the essential details about the equipment failure. This gives our clients actionable intelligence to reduce risks and asset maintenance costs as well as increase productivity. Digital is the way to add enterprise value.”

In an interview with CIO Applications Magazine, Scherwinski shares insights about the company and how Ctrl2Go is helping businesses to extend equipment life, reduce downtime, and improve production efficiency with their comprehensive suite of offerings.

Can you give us a brief overview of the company?

Ctrl2GO is an international group of companies with solutions in the field of predictive maintenance services for the railway, oil and gas, energy, manufacturing, mining, and any other asset intensive industry. Our AI solution was developed years ago out of a contractual obligation from one of our European clients for asset uptime and reliability. Since then, we have been working to fine tune our predictive maintenance solution to add enterprise value by monitoring the true health condition of assets and predicting when equipment is going to fail. We want to expand our brand name and proven solution from the European market to the North American and South American markets.

Can you tell us about your solution and how your clients can benefit from it?

Our solution, Ctrl4Maintenance, does not rely solely on AI for predictive analytics, unlike many of our competitors. Our added expertise in mathematical modeling and physical engineering, that we have developed over the years in numerous industries, makes our solution unmatched. In addition, being manufacturer agnostic, Ctrl4Maintenance is the standard for predictive maintenance that provides actionable intelligence on production assets. The solution is highly integrable.

For example, it can consolidate multiple maintenance and data visualization systems such as multiple SCADA’s, SAP and other ERP and MES software products. This consolidation allows for a single view from the companies’ control and command center. Ctrl4Maintenance is easily scalable vertically and horizontally, in the cloud or on premise, thus giving customers ability to continuously evolve their predictive maintenance aspects.

We help our clients by providing the software, data science expertise, and industry experts, thus providing a complete predictive maintenance solution. If a client has developed their own software platform and require data science expertise, we can provide this along with industry expertise.

We currently monitor >10,000 assets every day and our clients see real value:

• >$19M annually in cumulative cost savings
• ~145,000 man-hours reduction in reactive maintenance time
• 23% improvement in asset availability
• >17% reduction in emissions
• >11% reduction of spare parts stock
• Improvements in HSEQ (Health, Safety, Environmental, Quality) scores

With such results, we aim to become a valued partner for companies headed down the digital transformation path to Industry 4.0 and beyond.

Can you brief us about your client on-boarding process and methodology?

We start with our client’s business objectives and gauge the data driven results our clients want to achieve. Then, we identify the gaps in the current data, current business processes, and the missing requirements for the most accurate predictive maintenance solution. Some of our clients begin to see data in the first 2 weeks, and most clients have reached the initial phase of the Predictive Maintenance project within the first 3 months. We work with IoT sensors, SCADA, data historian software, and many others, to understand the type and condition of data. Next, we start the implementation process and align the IT infrastructure to create a customized user interface for their application. We provide our clients with digital twin representations of their components with different subsets, heat maps, and risks associated with each individual asset including their location (if data is available).

What are the key differentiating factors that make you stay ahead of the competition?

With years of experience in the European market, Ctrl2Go has analyzed millions of data points across numerous verticals, created thousands of failure models, thus gaining extensive experience in multiple industries. This experience and expertise benefits every customer and project, in maximizing the bottom line for our clients.

Our team of equipment engineers, reliability engineers, and data scientists who understand complex machines, their elements, and operations makes us somewhat unique in the AI Predictive Maintenance space. Ctrl4Maintenance is an open architecture solution that allows for complete self-reliance in using the software and in utilizing“ citizen data scientists” to create in-house Python based data rules that can easily be added to the AI engine.

Can you share a client success story with us?

Our largest European deployment of predictive maintenance is for LocoTech LLC. We continuously improve their traffic safety by reducing the number of rolling stock asset failures. In addition, our PdM solution reduces the client’s overall annual costs by cutting unscheduled down time of the locomotives. The solution pays for itself in the first month of the year, for the entire year. Our successes include: reduction of unscheduled repairs by 60%, decrease in fuel consumption by 0.9%, and reduction in unproductive locomotive downtime. Through our executive readiness, we increased our client’s operational efficiency by >7%, generating a profit margin of ~22%. This value is carried directly to the bottom line.

What does the future hold for the company?

We are currently working on a number of solutions that will help transform our clients’ current operations with more intelligent systems, thus allowing more asset monitoring with less manpower.

Our objective is to remain focused on customizing our platform to deliver according to our clients’ demands. Further, we will continuously fine-tune our AI algorithms and analyze the feedback from our clients to make our solutions more effective. We continue to always look at the business case first then develop our unique offering around our client’s unique use case. That is the path to success.