Using condition-based maintenance to optimize smart manufacturing operations
Manufacturing companies have numerous challenges in operations management like operating below production capacity, low margins, and the lack of visibility in plant operations, to name a few. Implementing a predictive maintenance strategy such as condition-based maintenance (CBM) is a more proactive way to prevent equipment breakdowns and to solve these challenges in operations.
Maintenance practices followed by the manufacturer are crucial in addressing these issues. Typically, 40% of the manufacturers’ operating expenditure is spent on maintenance. While this is a significant amount, conventional maintenance practices such as walk-throughs, random checks, and annual shutdowns are time-consuming and prone to human error. Data generated using these methods often fail to provide insightful information on the equipment quality, plant floor operations, production inadequacies, and breakdowns.
The exigency to address these issues is driving the digital transformation across the industry. Digitization is enabling manufacturers to reform business models, enhancing their operational efficiency and improving overall equipment effectiveness (OEE). Leveraging a smart/predictive maintenance solution is an effective method manufacturers can adopt in processes to increase the uptime of equipment to improve OEE.
Emergence of smart maintenance
Actionable insights driven by strenuous data crunching analysis using traditional monitoring and maintenance practices are time-consuming for workers. Due to the factory equipment becoming more complex, outdated monitoring and maintenance techniques can bring down the plant’s overall productive capacity by 5 to 20%. Incidents of an entire plant line shutting down due to critical equipment failing have also been reported. Unanticipated equipment failure can result in increased production costs, which adversely affects asset utilization levels. These issues can be avoided by implementing a smart maintenance system designed to help companies aspiring to adapt to optimize manufacturing practices.
The next-generation equipment monitoring and maintenance strategy will enable companies to increase their control over production schedules and minimize operational uncertainty by analyzing real-time data collected for forecasting future equipment breakdowns. Global players are aware of the shift within the industry and have been exploring predictive maintenance with CBM.
How condition-based maintenance works
Condition-based maintenance (CBM) is a superior method of equipment maintenance based on using real-time data to prioritize and optimize maintenance resources. CBM incorporates next-generation technologies like artificial intelligence and Internet of Things (IoT) that enables the manufacturer to make an informed decision in a timely manner. Manufacturers who leverage from predictive maintenance solutions stand to benefit from a number of ways and can progress towards achieving operational excellence.
CBM can be efficiently implemented in three stages:
1. Digital consulting: Typical activities in the first phase include assessing the current maintenance practices, determining if any data is being captured by the manufacturer and how it can be used, assessing IT requirements for CBM deployment, and equipment evaluation.
2. Data collection and analysis: The CBM provider then strategically plans to capture data through the use of sensors and gateway vibration measurements, oil sampling, and other methods. This data is analyzed, which results in a customized CBM solution to be deployed.
3. Full plan rollout: In this final stage, all the modules of the solution are interconnected with each other and monitors various critical equipment parameters. This data can be presented in the form of reports and visualization on handheld devices to help enable manufacturers to make timely decisions to perform equipment maintenance.
Condition-based maintenance benefits
The primary purpose of a CBM solution is to predict equipment failure. Depending on the often-used ‘fail and fix’ approach to ensure machine reliability isn’t the most effective way to measure the equipment’s health with the adoption of new and more complex digitized factory equipment. CBM techniques are highly variable which is why it is critical to ensure the frequency at which the conditioned-based monitoring is taking place is optimal. For example, while doing a vibration analysis of a bearing, the primary determinant of frequency for a condition-based monitoring task is the mean time to failure (MTTF), time to failure, or the potential-to-function failure (P-F) interval. In order to be completely sure the failure is detected prior to the functional failure occurring, the bearing must be monitored at a frequency less than the MTTF interval.
CBM also improves asset effectiveness. For any business to become profitable, adequate return on investment (ROI) is imperative. Similarly, for a manufacturer, maximized asset utilization is vital with minimal equipment breakdowns. CBM allows manufacturers to establish trends, predict failures, and calculate the remaining life of an asset. Manufacturers will gain more intelligence, allowing them to make data-driven decisions for maintenance planning, spare part/inventory planning, etc.
The data will also give reliable insight into the asset history and associated process history in terms of thermal cycling, pressure cycling as well as event occurrences like high vibration, shutdown to name a few. Based on the data collected, the average life of a component can be determined and appropriate action can be taken.
Manufacturers allocate 40% of their operating expenditure towards the usage of critical equipment and an additional 5% to 8% is earmarked for maintenance of critical equipment. Any unexpected equipment failure could lead to downtime, which could negatively impact the factory’s production and hamper the company’s ability to efficiently meet market demands. In such a situation, CBM can assist the manufacturer in numerous ways.
For example, vibration analysis enables the manufacturer to determine faults in machinery parts such as bearings, shafts, couplings, rotors, and notify the stakeholder if any urgent action is required. Another breakthrough innovation is the ability for a CBM solution to predict faults that occur due to factors related to current such as overloading, short circuit, earth leakage, torque prediction, and lack of lubrication.
Continuous developments in semiconductor manufacturing and a spurt in the adoption of innovative, digital technologies have significantly lowered the cost of sensors. IT companies are deploying economical CBM solution bundling hardware and software with various techniques such as vibration measurement and analysis, infrared thermograph, current analysis, etc. It enables the collection of real-time data for critical parameters including temperature, acoustics, pressure, and vibration. This prevents unplanned downtime, annual maintenance shutdowns, minimizes human error, and eliminates labor costs to assess equipment conditions.
Cost analysis of condition-based maintenance
The cost incurred for a CBM setup is subjective to the type of machine, nature of operations, taking into considerations various factors such as preventing a bearing failure on a machine producing $10,000 worth of product per hour. One can’t avert five hours of downtime that could have amounted to a $50,000 notional loss in production. The cost could vary depending upon the value of goods and the output a particular machine produces during operation.
According to various industry benchmarks, CBM setups can help reduce maintenance costs by up to 12% in the first year, and drastically improve machinery availability by as much as 92%. CBM also helps reduce unexpected failures by about 25%; repair and overhaul time is almost cut in half. Keeping an extensive inventory of spare parts can also be reduced by 20% and reduced annual maintenance costs by 15% in the first year. Apart from the benefits to asset performance, CBM delivers multiple benefits including:
- Ensures operations are running smoothly
- Optimized production by minimizing plant interruptions due to machinery-related delays
- Higher customer satisfaction
- Superior capacity management
- Better supply chain relationships.
Consider, for example, a compressor failure in an industrial plant. In such a scenario, the damage repair and replacement cost of the compressor could be as much as $200,000. In addition to the costs incurred, it would also result in yield loss and low production time. This would impact delivery dates and service availability, which would further disrupt the production schedule.
A CBM solution would have predicted and alerted the workers to address the issue prior to the failure. The repair cost would have only been $35,000, which translates into savings of $165,000 for the manufacturer. An investment for continuous monitoring would have yielded 11 times the ROI for the manufacturer.
In another instance, a manufacture facing a problem with a conveyor motor failure led to unplanned downtime for the packaging line, which resulted in less output and revenue loss. To overcome this problem, the manufacturer decided to deploy an end-to-end CBM solution. Under this solution, an industrial edge gateway module was developed for continuous data acquisition under different load conditions.
The module also solved the data capturing and storing problem that leads to increased network traffic and higher infrastructure costs especially encountered with machine data. With the integrated machine learning and artificial learning algorithms, the module captured and analyzed critical data including vibration, temperature, and current of the conveyor motor by only sending the processed data to the cloud servers.
Further, a cloud-based analysis generated valuable insights and triggered alarms and notifications for predefined events to send warnings before a potential equipment failure. The solution also used enterprise resource planning (ERP) servers to allow automated work orders and consolidate data into reports and visualizations on hand-held devices, giving real-time insights for taking data-driven maintenance action before the fault even occurred. A CBM solution enabled the manufacturer to improve equipment uptime to approximately 93% and reduce the maintenance cost by approximately 14%. Facets like MTTF, asset health index, and time to next maintenance were also identified by the solution.
Leading global manufacturers have already taken a game-changing approach by strategically transforming maintenance solutions into smart service and asset management solutions. As technology propels the industry forward, manufacturers who take steps to implement advanced analytics maintenance will improve overall performance, reduce waste, and address unplanned sales demand effectively.
KEYWORDS: predictive maintenance, condition-based maintenance (CBM) solution
- The benefits of condition-based maintenance
- How operations can improve with a CBM
- The cost-savings involved with a CBM solution.
How can your facility operations improve by using an analytics-based maintenance approach?