The industrial world is changing with the emergence of smart industry. The consumers of today have been demanding more customisation & individualisation and to consciously handle resources as we start thinking about the impact on the environment. This trend has been forcing companies to embrace flexibility in their production lines as they are scaling up their large scaled customised production. Today’s machines are set up in a fixed, inflexible manner on the shop floor—commissioned, parameterised and tuned for one specific product produced repeatedly for months or even years. The manufacturing lines of tomorrow need to shorten production iteration cycles while maintaining their flexibility.
While developments around Industry 4.0 and Artificial Intelligence (AI) have been rapidly widening the limits of what is possible in the industrial world, engineers and scientists are facing the challenges of managing the growing complexity of software and an ever-increasing amount of data to create new business models and become market leaders.
Why are humans key to a more adaptable factory?
The overall trend is clear: it’s not the machines but the people who use and work alongside them that make a factory adaptable. The flexibility that modern factories require is often unattainable with the technology currently at our disposal. While robotically operated systems can be programmed to perform a wide range of tasks, they are driven by codes and often lack the flexibility, dexterity and problem-solving skills human workers can offer. They cannot adapt in response to sudden changes or new information, such as last minute product modifications or sudden pivots in the market. In contrast, human employees can quickly take the initiative and solve problems independently. In addition, the ability of machines is far narrower than humans; machines can only execute what they have been designed and programmed to do, while the broader innate abilities of humans result in them being more flexible than robots. As a result, manual labour is still widely used to perform a variety of tasks for manufacturing companies.
However, human-based systems come with their own set of challenges. One of the biggest drawbacks is their lack of consistency. Every individual has a different skill level, ability and affinity for the job they perform. This means that humans can’t be precisely predicted or replicated. While some workers might be great with one particular task, there may be others who may not be adept at their job. Even the same person can introduce variability over the course of a shift — who among us doesn’t get tired, distracted or sloppy from time to time? This introduces a large amount of variability. So, to build great products consistently, human-based systems also require significant investment in finding, hiring, training and retaining staff.
Data analytics on human workers
What can manufacturers do to mitigate this challenge? How do they benefit from the agility and dexterity of humans without compromising on the quality? That’s where data analytics come into play. Data analytics can help manufacturers improve productivity, quality and standardised work adherence to gain a competitive edge. Rather than reacting to problems after they occur, manufacturers can use data insights from manual assembly lines to — as described in the book Moneyball — maximise the use of the natural skills of the existing people to identify potential issues before they materialise and to take preventative action.
Using analytics to identify patterns
Spatio-temporal analysis of people at work permits us to identify workplace patterns —consistent and abnormal — despite the very different manner in which humans work. Long and short cycles epitomise temporal analysis, helping us understand opportunities to be more efficient as well as steps where associates are struggling to follow standard work. Manufacturers can identify trends and determine which steps need attention and why. With this information, manufacturers can take proactive steps to close any skills gaps by implementing spot training or more robust refreshers for the workers. Data analytics can also identify patterns that lead to mistakes or injuries that impact quality and safety.
Using analytics for quality control
In factories that produce cars or medical devices, even a small manufacturing mistake can mean the difference between life and death. Hence, it is critical for line associates to be extremely precise and consistent with standardised work. A video analytics tool can help keep track of the assembly process and monitor quality continuously by detecting if a step is skipped or performed out of sequence. If a defective unit is identified later in the processor at a customer-end, YouTube-like search functionality by serial number can help manufacturers identify if the error was caused during the assembly process and, if so, isolate any other mis-manufactured units and institute changes. On the other hand, if the defect is identified in real-time, some AI/ vision systems can immediately signal the line associate, ensure that the unit is correctly assembled and significantly reduce the cost of quality. Like a spell checker, this cognitive assistance empowers line associates to focus on the quality of their work.
Using analytics for productivity improvements
Data on the manual assembly process is also key to improving performance and running a consistently lean manufacturing process. It improves visibility and accountability and helps identify bottlenecks that can slow down production. Consider the assembly line; line associates perform work sequentially, with the quality impacting subsequent operations. Since this is an interdependent system, downstream activities can impact upstream ones, with bottlenecks plaguing the entire line and causing costly manufacturing delays. Timely access to accurate data can help companies respond quickly to changing conditions on the floor and make well-informed staffing and training decisions.
Using analytics to make better decisions
Perhaps the most significant impact of using data is scientific thinking, problem-solving and decision-making. Used correctly, data analytics can help manufacturers identify pain points, solve problems and discover new opportunities that will offer greater competitiveness. Data also provides a better understanding of customer behaviour, enabling manufacturers to tailor products more accurately to meet demand and avoid stock-outs. Data analytics can be used to create predictive models that help anticipate problems before they occur and can drive scientific thinking on the plant floor. When applied correctly, this can streamline factory operations and reduce downtime.
The human analytics connection for optimised operations
Adapting to change is going to be a necessity for survival amongst manufacturers. The contributions of humans to manufacturing will stem from their adaptability and will remain key. And, despite the increase in automation and robotics, humans will continue to be a vital part of factory operations for a long time to come. Data analytics will help manufacturers optimise their operations to get the most efficient processes on manual assembly lines.