X

To extract shale oil and gas, specialized equipment is used to fracture rock via a process called hydraulic fracturing (or “fracking”). To do this efficiently, users must know when their equipment needs maintenance. If the equipment stops working while in the well, millions of dollars are lost due to downtime and logistics. Additionally, our client, a major oilfield equipment company, needed a way to make their product stand out. They wanted to accomplish this by providing oil and gas software solutions but had no idea on how to develop and deliver software in the cloud.

Machine uptime is one of the most vital performance factors for electric rotating machinery. In times when an hour of downtime can equate to thousands of dollars in losses, securing predictability turns into a high priority for all industrial businesses. Manufacturers operate in an extremely volatile environment, thus avoiding unplanned downtime becomes critical for achieving desired business outcomes. Predictive maintenance is no longer a nice-to-have but a necessity to survive and thrive in unfavourable conditions. Start from the basics. Making machines perform better means, first and foremost, understanding how the machine works, extracting relevant data, and gaining meaningful insights into ongoing processes. The power of the machine lies in utilizing its full potential.

Daimler AG was looking for a way to maximize the number of flawlessly produced cylinder-heads at its Stuttgart factory by making targeted process adjustments. The company also wanted to increase productivity and shorten the ramp-up phase of its complex manufacturing process.

At the corporation’s Mizushima plant near Okayama, pH measurement during the neutralization of strong acids is closely monitored. For this important measurement Tsutomu Ishikawa and Naoto Ogura, engineers at the plant’s Instrumentation and Engineering Department were not satisfied with the performance of the pH sensors they were using.For this reason, sensors were regularly exchanged at the plant to minimize the chance of failure in the process. But the operation cost was high and Mr. Ishikawa and Mr. Ogura needed a better solution. Specifically, they required to know in advance when a pH sensor would need to be cleaned, calibrated or replaced: “We wanted to grasp how deposits forming on the pH sensors would affect the timing of sensor maintenance and exchange.”

Utility companies that operate hydro turbines have a vested interest in performing regular maintenance to prevent unexpected failures. Most maintenance occurs on a scheduled basis where the asset is taken offline, inspected, and repaired proactively if needed. Hydro turbine units are highly reliable, meaning that few examples of unplanned downtime exist. However, these failures are very costly to their operators.Given the sensitivity operators have to unplanned downtime, many have equipped turbines and generators with sensors and platforms to collect valuable performance information in real-time. But because there are so few historical hydro failures to compare against, rich streaming data and legacy statistics-based analysis are not very accurate at predicting true failure events. In fact, they often create more problems by overloading monitoring teams with benign false positives that result in unnecessary downtime to evaluate. This begs the question: Can artificial intelligence help maintenance teams extract more value out of their data?

KONE already provided traditional maintenance services for its more than 400,000 building owner and facilities management customers, but it sought cloud-based analytics technology to capture and use the vast amount of data generated by its elevator and escalator equipment worldwide to transform its service offerings. “We knew that digitalization was changing the industry, and we wanted to become a forerunner, not a follower in this development,” says Markus Huuskonen, the Director of Maintenance Processes and Connected Services at KONE.

Traditional measurement tools are ineffective when it comes to slowly rotating equipment. There are faults like Bearing Failure, Ring Plugging, Gear Tooth Crack and many more which can lead to the shutdown of machines. 1 minute of downtime cost the company $10. RingPluggingis a very common issue which Pinnacle Pellet was facing very frequently due to diverse feed quality into the machines. Product ring plugging can be detected as sound levels increase in specific roller bearings.

A major European aircraft component supplier encountered this challenge first-hand. A mission-critical, programmable milling machine failed, halting the organization’s production process. Despite the customer team’s expertise, the problem proved challenging to diagnose. At first, it appeared the downtime resulted from a damaged spindle, the most complicated part of the milling machine. However, a costly and time-consuming spindle replacement did not correct the situation. The team was forced to perform an extensive system evaluation to identify the culprit.

The challenge was to harvest and sift through this data, recognize the patterns that indicate a high likelihood of asset failure, identify the most urgent issues, and get the right information to its engineers with enough lead time for them to take effective action.“Before, we only used between 10 and 12 percent of the operational data we collected, which is the industry average,” comments Benn. “By the time we had searched for, collated and forwarded the right information to the right people, we might respond too late to avoid impact to operations, or have to make last-minute changes to our maintenance schedule, which reduces efficiency. Our challenge was to provide right-time, actionable, effective information proactively, rather than in a reactive or look-back assessment.”“What we wanted was a way to identify patterns in that sensor data that would give us an early warning of asset failure. We saw an opportunity to use analytics technology to extract greater value from the systems and data we already possessed, which would help us to, for example, avoid preventable failures and potentially save millions of dollars.

Sean Simon is the SVP of Operations at CIG Logistics, where sand is transloaded and stored for third parties in the oil and gas industry. Before looking into CMMS solutions, his team spent three years trying to manage their maintenance operations with a paper-based system, leaving them with the major issue of not being able to gather or access data. “There’s no way to mine paper. There was no daily summary, no way of tying together comments or keywords.” As a result, trying to track and schedule preventive maintenance was nearly impossible. “It was like owning a car in the 1950s. You had to try to remember the last time you did something and guess at the maintenance that needed to be done in the future”.

The client wanted to reduce downtime and production losses by effectively prioritizing maintenance activities and proactively replacing components before failure.

In late 2015, a deployed combustion turbine experienced a row two vane failure, which caused massive secondary damage to the compressor, resulting in nearly two months of downtime and up to $30M in repairs costs and lost opportunity. This failure, though rare, is representative of typical catastrophic events that are very difficult to catch. Though the onsite plant operations team had been monitoring the asset, this specific failure mode was previously unknown and very nuanced, and existing alarms did not have enough information for SMEs to properly diagnose it in time.The OEM decided to evaluate SparkCognition’s predictive analytics solution, SparkPredict®, with the following objectives:1. Demonstrate the ability to detect and distinguish operational and anomalous online steady-state conditions based on blind data provided from the turbine.2. Provide additional insights about the key contributing factors to the underlying anomalies.3. Provide a UI that interfaces to live streaming data from the asset.

Simplifying maintenanceHana Financial Group had recently consolidated the infrastructure and resources of 11 of its affiliates at a local IBM data centre. However, the business was left with more than 100 service and maintenance contracts that needed to be reviewed and renewed periodically. These contracts also involved 100 separate bills that Hana Financial Group had to manage. Managing such a large volume of bills was cumbersome and sometimes resulted in late payments. The group wanted to improve efficiency and eliminate the overhead involved with managing these contracts by consolidating its heterogeneous IT systems and data storage systems under more consistent processes.

To optimize its Sigma Smart AirService, Kaeser worked with SAPDigital Business Services to deploySAP Leonardo IoT capabilities as its innovation foundation together with SAP Asset Intelligence Network and SAP Predictive Maintenance and Service. Kaeser’s new solution connects its compressors smartly in the cloud, allowing it to offer a next-generation service at a lower price.Challenges:- Service team unable to access calibration data and other equipment-specific information, which was stored in on-premise systems- No solution to meet the needs of dealers and companies’ service providers- Need for track-and-trace capabilities with selected suppliers to scale-up potential

The calendar machine run by a motor has a shaft mounted gearbox connected to the roller. This gearbox allows maximum paper load and feeds the paper with reduced speed to the roller. In spite of scheduled preventive maintenance, it was observed that gearbox used to fail frequently. The rise in vibrations leading to the eventual failure of gearbox adversely affected the quality of the paper. Monitoring the gearbox was thus vital and critical.

A large power utility in Hawaii was looking for more frequent condition monitoring on their Balance of Plant (BOP) generation assets. They had experienced significant equipment failures that occurred between their scheduled quarterly walkaround condition monitoring routes.

C&W Services was using a manual condition monitoring program at one of its leading life sciences’ client up until last year. At best, data was collected manually every 30 days, even on the most critical machines, using a handheld data logger. After the data collection, all of the data analysis had to be outsourced to a third party for analysis. This approach has several limitations:1. Unplanned Downtime2. Shortage of Manpower3. Safety and Access to Machines4. Inconsistent Readings Collected by Manual Processes

The major press line in the company has a circular saw machine which cuts metal rods with precision in predefined lengths for further heating in the furnace. The cut pieces are then fed to the forging line to make automotive components. The length and perpendicularity of the cut pieces are crucial to obtain a good quality forging.It was observed that circular saw failed to maintain the precise length and perpendicularity while cutting the metal rods leading to heavy rejections. This was a serious concern and routine preventive maintenance was unable to overcome it.

In 2016, Arizona Public Service (APS) decided to enter the California ISO (CAISO) market, which allows them to sell power into the California market. One of their key assets was Sundance, a 420 MW unmanned peaker plant located 50 miles outside Phoenix. The entry into the CA energy market meant that starts tripled and run hours doubled almost immediately at the plant. They started looking for wireless Predictive Maintenance (PdM) system because the running hours were typically when no one was on site, which meant that traditional forms of PdM were not possible. Typically, a specialist would collect vibration and other condition data on equipment, but it had to be taken during operation, and it was difficult to get personnel out to the site.“Reliability was foremost on our minds,” commented Don Lamontagne, Supervisor of Equipment Reliability Engineering. “We faced huge loss of potential revenue, as well as fines if we weren’t able to generate power when it’s needed.”

Like many organizations, Anaren had a homegrown work order application that had basic asset management functionality. “It was menu driven, so quite cumbersome,” explained Bill, “reporting was limited and it still relied heavily on paper transactions and records. We looked at our business needs going forward and decided this was one area that could be modernized.” On launching the Manufacturing CMMS project, Bill, the business analyst of the company identified three major areas for improvement:1. Improve efficiency by eliminating paper.2. Improve the control of preventive maintenance. 3. Improve inventory management.

The 1000 Ton main forging press had a 75 HP motor and fed a trimming machine. The motor pulley combination was situated on top of the Press at a height of about 15 feet thereby reducing its access for routine maintenance. The company found difficulty ensuring constant uptime of the Press.

In the capital-intensive oil and gas industry, businesses rely heavily on expensive assets that are deployed in harsh environmental conditions. From a drilling point in the sea to an intermediate station in the desert, the dynamic environmental conditions at each point along the long line affect the performance of the assets deployed along the line. The systems that are used to support these mission-critical assets must also be highly reliable, responsive and secure.One company that operated a long-distance gas pipeline encountered numerous challenges with the overall efficiency of its pipeline, ranging from sub-optimal usage to wastage of natural resources. Even with the optimal equipment and setup, the wide array of variables in operating conditions combined with the sheer distance covered by the pipeline made running the business difficult.In this case, there were 22 injection stations along the length of the pipeline, operating under very disparate conditions with different efficiencies. This made it difficult to identify the interdependent effectiveness of these injection stations, despite having a large data set on various parameters at each injection substation. Even a single instance of failure could cost the company hundreds of thousands of dollars in lost revenue as well as any additional costs for repairs that had to be made.The company was spending $5 million per mile of pipeline annually in corrective maintenance. Along with this, the loss of revenue due to the undelivered material was estimated at $250 million. With energy prices dropping, the loss in revenue directly reduced the bottom line of the company. With the clock ticking and revenue dipping, building a perfect efficiency improvement model became a top priority.