India currently has five out of the 103 lighthouses identified by World Economic Forum and would need to continue on this path if it has to achieve the aspiration of having 25% GDP contribution from the manufacturing sector.
Key focus areas for smart manufacturing
There are six key dimensions at play within the factory – safety, quality, maintenance, production, supply chain and sustainability (SQMPSS). While these have been in focus for decades, with the advent of fourth industrial revolution, the way to bridge gap between current state and technical limits have changed drastically for manufacturers.
Business excellence toolkits and technology are combined to enable smart manufacturing solutions and produce better business results. For example, with the advent of Artificial Intelligence (AI)-enabled industrial analytics and data insights, manufacturers are now able to propel productivity, uptime, and quality gains in manufacturing.
Manufacturers are now able to get input on the condition of the factory in real-time, providing insights into what needs to be done. There are algorithms designed to provide recommendations. It makes life easier for the teams that execute these six dimensions by combining the business excellence toolkits and technology.
A smart manufacturing journey
There are six levels in the smart manufacturing journey, starting with level one, which is the basic visualisation of data. At level two, we have the data integration and at level three, data analysis. The use of data analytics for prediction and prescription forms levels four and five. While achieving a symbiosis in terms of a self-healing autonomous factory is level six of the smart manufacturing journey. Most manufacturers are still at level three or four.
Level one, two: The power of digitisation
It is imperative for manufacturers to stream-line business processes, understand key parameters which impact performance across the six dimensions (SQMPSS) and have them available at ease.
This basic step helps create a ‘connected factory’ which is a core enabler for the more advanced stages of smart manufacturing. It would help us to enable traceability across the 4M (huMan, Machine, Material & Method) aspects and the operations team would not need to invest energies in gathering basic data.
Level three, four: The power of analytics
Once the base connected factory is in place, we can leverage technology to support decision making and also pre-empt future challenges – analysis and prediction. The use of analytics, level three, four facilitates root-cause analyses of issues. They correlate all the variables at play. The manufacturer can identify who was the operator who was working on the job. What the operating parameters of the machine were at that point? Were the Standard Operating Procedures (SOPs) followed properly? Is the defect arising from the incoming material? What sources are they from? These are the analytics that a manufacturer can use. The use of data analytics in level three, four of smart manufacturing enables the prediction of quality defects.
Level five: A prescription-based system
While prediction is good, it is not good-enough as manufacturers not only need to know that something can go wrong but would also want to be able to fix that in advance. This is where the prescription/recommendation layer comes in. When AI can predict the occurrence of defective parts, it becomes essential for the manufacturer to intervene. AI can also give them information on what the controllable variables are at that point and tweak the operating process parameter.
Level six: Achieving symbiosis
The final level is end-to-end connected and symbiotic, as it will have to deal with variability on its own. There may be more variables that can impact quality. For example, if there is an issue from the supplier’s end, symbiosis in this context would mean that the AI system not only adapts to the model on its own but will also connect the whole end-to-end value chain right from customer to the supplier.
Future factories: The coming decade
We expect to see a digitisation shift across manufacturing sectors worldwide over the next decade. Advances in data analytical tools and AI will further augment this transition. Manufacturers will also have an array of technology solutions from which they can choose relevant applications which are fit for purpose in their environment to further improve their efficiency and effectiveness.
With Industry 4.0, a factory’s capability to handle variability with limited human intervention will enhance, thereby making them capable to achieve better outcomes across SQMPSS dimensions. Factories of the future will be operationally superior, system driven, sustainable and continually striving towards better customer experiences.