By Eric Whitley
Food manufacturing is one of the most regulated industries in the United States and worldwide. The ultimate reason for all this regulatory oversight is obvious: to prevent the contamination of food.
Sound, world-class maintenance measures are required to ensure the highest standards of food safety. Maintenance comes in both reactive and proactive forms. The focus must be on the latter however, since reacting to a maintenance issue in a food production facility could mean contamination has already occurred. This article will provide a brief insight into how predictive maintenance is changing the face of food manufacturing.
Predictive maintenance fundamentals
Predictive maintenance is a proactive approach to maintenance management, and as its name suggests, the aim is to help predict when maintenance should be performed. It is a data-driven form of maintenance designed to analyze the current condition of equipment and machinery in order to plan for needed interventions.
Predictive maintenance achieves this by using predictive analytics that estimate potential (future) failure points. The goal is to then schedule corrective maintenance prior to the probability of these failure points occurring. Maintenance can thus be scheduled in advance, and when it is most convenient and cost-effective to do so. Other aspects of this maintenance include condition monitoring, asset health evaluation, and prognostics.
There are multiple benefits to predictive maintenance, including:
- Enabling early fault detection, i.e. halting impending failures
- Reduced risk of disruptions to production and downtime
- Improved performance of production-related assets
- Optimizing the lifespan of machinery and equipment
- Overall savings in production costs due to greater asset efficiencies
More cost-efficient maintenance costs are a further benefit. It has been estimated that predictive maintenance can reduce the mean time to repair (MTTR) by 60%.
Predictive maintenance technology
Predictive maintenance is centered around equipment that must constantly monitor, record, and analyze equipment, known as condition monitoring. Smart technology is at the core of much of this predictive technology, including the Industrial Internet of Things (IIoT), artificial intelligence (AI), and machine learning. An IIoT platform can be connected to a host of wireless sensors and probes that monitor everything in food processing operations – from temperature and conductivity to vibration and pressure levels.
These technologies allow monitoring systems to be interconnected and action data in tandem with each other. So, for example, an AI-driven sensor in a filter system can collaborate in real-time with other sensors, so that production-wide data analysis and aggregations can be done on a continuous basis.
There are various predictive maintenance technologies in food manufacturing today, of which some of the more common ones include:
- Oil analysis instruments: Oil build-ups or leakages can be detrimental to equipment. In food manufacturing, this instrumentation is primarily used for oil-using equipment, such as hydraulic systems, compressors, conveyor belts, and refrigeration systems.
- Temperature sensors: This method measures for ‘hot spots’ in electronic equipment or those with electrical circuits, which may indicate overheating or imminent fusing in equipment.
- Vibration analysis sensors: The method calculates if there are significant changes from what is a machine’s typical vibration. Deviations regarding vibration, such as those near valves or motors, allow for early detection of potential malfunction.
Industry 4.0 and predictive maintenance in food manufacturing
Food manufacturing plants are striving to become smarter and more efficient. Industry 4.0 is the next level of industrialization, one based on cloud computing, automation, connectivity, and large amounts of digital data. When Industry 4.0 is combined with the connected worker, they form the ‘smart factory’.
The smart factory is defined by its high level of digitalization, particularly in the control of machinery and production processes. It accomplishes this by using sensors and probes linked to the local IIoT and driven by AI, ML, and cloud computing so that real-time data gathering and analysis can be done and analyzed by people.
Sound familiar? Little wonder that predictive maintenance is tailor-made for the digitized, smart food manufacturing plant.
If there remain any doubts about the viability of a food manufacturing plant implementing predictive maintenance, then consider this: according to a study by the McKinsey Global Institute, it is estimated that the implementation of predictive maintenance across manufacturing will be reducing factory costs by up to 40% and result in between $240 and $627 billion in savings for the US economy.
Ultimately, predictive maintenance has a pivotal role in food safety. It will surely be a leading way in which the food contamination scandals that continue to hit the industry can be avoided in the future.
About the author: For more than 30 years, Eric Whitley has been a noteworthy leader in the manufacturing space. In addition to the many publications and articles he has written on various manufacturing topics, you may know him from his efforts leading the Total Productive Maintenance effort at Autoliv ASP or from his involvement in the Management Certification programs at The Ohio State University, where he served as an adjunct faculty member. After an extensive career as a reliability and business improvement consultant, Eric joined L2L, where he currently serves as the Director of Smart Manufacturing. His role in this position is to help clients learn and implement L2L’s pragmatic and simple approach to corporate digital transformation.
