How the Watchmaker Saved Time by Reduced Rework..

The watchmaker—a humble artisan—has withstood 500 years of evolution. As a large-scale manufacturer, the watchmaker's problem is a classic example of the difficulty of balancing the need for quality and quantity production, all managed in good time! And the biggest concern is the waste created from human error that leads to heavy production losses. Here is a use case on how one of India's leading watchmakers reduced rework with our Bodhee ® Production Performance Monitoring AI App to achieve its manufacturing goals. [1]

Under the Watchful Eye of the Bodhee® Production Performance Monitoring AI App

Today the technologically advanced society may stand separated into two halves—the watch lovers and those who foresee the end of the era of watch wearing. Whether you like Smart-watches or traditional watches, the timepiece can never go out of style. The recent world watch industry statistics have inspired the thought as it shows how the market size has recovered despite the economic crisis that followed the Covid shock. [2] 

However, watchmaking has changed dramatically in recent years. Automation and digital technology have revolutionized the way watches are made, and the demand for high precision quality has never been greater. Watchmakers must now have a keener eye for excellence at every step in the production process. And the monitoring must ensure that the production lines are running quickly and efficiently. 

Watches with defects get returned for reworking. Sometimes the errors are non-rectifiable, and the products may get entirely rejected as waste. While waste is a watchmaker’s nightmare, reworking also entails lost material, time wasted in the making, additional cost of labor to rework and repair the parts. Not to mention dealing with customer disappointment. 

In this blog post, we’ll enumerate how one of India’s largest watchmakers secured the future of its production and market share by proactively adopting our Bodhee® Production Performance Monitoring AI App. Here’s a real-world story of how our AI app helped the company overcome challenges, optimize its manufacturing processes, and reduce reworking. 

Before AI adoption- too much rework and wasted time, money, and resources.

Watch-making is a precision process. The margin for errors is minimal to zero. The process has multiple sub-steps, and not all steps are automated. So, some critical tasks were completed manually. That was when process deviations were creeping in and causing a disturbance in the manufacturing. Sometimes there were variations in the number of times the watch dials passed through the electroplating solutions. At other times, the loading of jigs was incorrect, or the electroplating solution did not get replenished on time. Also, the lack of automation created data silos, which made accurate data analysis a challenge. There was no visibility and no digital record of how the production process actually got completed on the shop floor or which processes were showing violations.  

Unfortunately, in multiple instances, the consequence of process deviations got noticed far too late. The company had to bear heavy losses when customers returned the watches due to quality issues. The watchmakers realized process adherence is crucial as the impact of errors in production proved significant in terms of effort and costs in reworking. Above all, customer satisfaction was another important manufacturing goal they were losing.

After Bodhee® Production Performance Monitoring AI App: 

Here’s the real-world story of how our AI app helped the company overcome challenges and optimize its manufacturing processes. 

Once Bodhee® Production Performance Monitoring AI App was implemented, the app monitored all production processes in real-time and recommended a plan in sync with shopfloor activities. A digital simulation of the workflow was created, and the app helped identify the critical process deviations in every sub-step.  

Installation of RFID readers at designated points tracked each jig at order level as it moved along the production process. By providing actionable insights for better process control, our AI app helped avoid critical process variations and improved production efficiency. 

Thus, the real-time Monitoring dashboard and the Digital Twin traced the errors for all orders and sorted the causes by process and parameters. That enabled the customer to track the orders, gain process control, and avoid wastage or reworking. The increase in visibility created a substantial business impact through improved quality production, which also meant reduced wastage and increased savings on production costs.

Visibility of not only the entire LIVE process but the historical production runs as well, was instrumental in solving quality issues. 

Business Benefits: Reduction in Rework by 8-10 % 

Conclusion: 

“A stitch in time may save nine,” is an old proverb, which essentially means it’s better to solve a problem right away, to stop it from becoming a much bigger one. 

Let’s rephrase that to context, “An AI app in time saves 9…” 

References: 

[1] Neewee. (n.d.-a). Case studies Archive – Neewee. Neewee. https://neewee.ai/case-studies/ 

[2] Davosa Swiss. (2022, February 15). Watches Industry Statistics & Analysis. Davosa USA. https://www.davosa-usa.com/blogs/story-time/luxury-watches-industry-statistics-industry-analysis 

Related Blog

Our 5 Most Popular AI and ML Algorithms and How They Are Used by Businesses Today

"Machine Learning algorithms are magic!" You have heard that a lot, but what are algorithms, and more importantly, how do Read more

Data Visualization: The Lynchpin of AI/ML and Business Analytics

In today’s digital age, data is everything. Data acquired might be massive in volume, but how do you make sense Read more

The 7 Sins of Manufacturing: Why Smart Projects Fail

What are the seven deadly sins of Smart manufacturing and how would you know that you have been committing them? Read more

How Does Industrial Edge Computing Increase Your Competitive Edge?

Is there a solution for the heavy computation and industrial big data analytics that the manufacturing sector requires? Centralized data Read more