Preventing Machine Downtime by Predicting it Beforehand

For the past few months, I have been observing the growth of the manufacturing sector in India, and how the contribution of the manufacturing sector to the India’s gross domestic product (GDP) will increase from the current levels of ~16% to 25% by 2022.

One of the major concerns and challenges of having a seamless manufacturing output is to prevent & avoid unfavorable machine performance. With the assumption that machines will degrade over time, manufacturing companies, prior to advanced technology intervention, aimed at focusing on preventive and reactive maintenance of the health of their machines, but the use of deep learning technology is leading towards a new age term method to safeguarding the health of machines, coined in the industry as predictive maintenance.

Predictive maintenance technology approaches can help the manufacturing sector to find the optimal inflection point between costs and machine failures. But, predictive maintenance is not as simple as a plug ‘n’ play solution as the requirement of machine learning requires layers of historic data to be collected over time.

Consider the life-cycle of a CNC machine. Today, most CNC manufacturers define the maintenance cycles based on the type of work the CNC machine does for their customer. It is based on their individual experience and judgement. However, if we were to get not just real-time data on the display but also store and analyze the historical data and use of the CNC machine, deep learning algorithms could find out the pattern of use and predict the maintenance and life of the CNC machine.

False positives would occur, i.e. a situation where the algorithm may predict the maintenance incorrectly based on the parameters it has to play with. With some human intervention, this pattern is corrected, learnt, and applied on the following data set to improve the result. So, the algorithm can learn from its mistake and give more relevant and accurate results over time.

Using cloud based scalable technologies, we could reduce the infrastructure requirements at each premise and even customize the maintenance cycle for each CNC machine based on the customer’s usage patterns. This will not only reduce the cost of maintenance but also improve the efficiency – a win win for both the CNC machine manufacturer and their customer!

Deep Neural Networks are used in this approach to learn from sequences from data. Unscheduled machine downtime can be damaging for any business. Preemptive identification of these issues can help enhance quality of production and significantly improve supply chain processes. The advantages of using predictive maintenance strategies can enhance overall operational efficiency.

Predictive Maintenance strategy is built on the fundamental methodology of Internet of Things (IoT). IoT will not be functional without data and machine learning. This approach is not only about gathering data, but also creating an ecosystem to predict and make decisions as a response to the sequences of data collected. Predictive maintenance will be a larger opportunity as global economies progress, and IT solutions providers need to look at this opportunity to further innovate to help manufacturing companies disrupt their industries.

Advertisements

About Gautam Rege

Rubyist, Entrepreneur and co-founder of Josh-Software - one of the leading Ruby development shops in India.
This entry was posted in General. Bookmark the permalink.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s