Case study:
Smart Factory Solution for Textile Manufacturing

A leading clothes manufacturer headquartered in Hong Kong with factories in China and Cambodia, came to us to help them manage their operations more efficiently.

They are known to provide one-stop services from design to product development for well-known global brands like Marks & Spencer and Triumph.

However, with operations in diverse geographical locations, it is sometimes difficult for them to manage operations efficiently which could potentially compromise their product delivery and supply chain schedule.

As such, this could subsequently lead to other problems with their clients and damage their reputation.

In order to manage operations more efficiently in manufacturing, it is crucial to first understand and study the process and procedures in place to determine whether current operations are up to standard.

One practice that is commonly used in the industry is called work sampling. This involves asking industrial engineers (IEs) to measure the proportion of time spent by their workers in various defined categories of activities, and compare those with the overall planned proportion.

Though the results do come in handy, it is nevertheless a tedious and time-consuming manual procedure.

With Motherapp’s PowerArena, this tedious process of work sampling can be automated:

• Data collection: A simple webcam is connected to our deep learning algorithm to sense and recognise each worker’s activities.
• Data processing: The proportion of time spent by workers on different activities are computed in real time.
• Data-driven action: If the proportion of time is significantly deviated from the planned proportion, an alert is triggered and our client will then be easily notified of the root cause in real time.

• The industrial engineer’s time is saved from tedious tasks like manual work sampling, and can be better spent elsewhere.
• The visibility of the factory floor is greatly enhanced with real time status monitoring.
• The client can get additional insights from the data through data analysis, such as the performance of different production lines over time, and the factors that contribute to such potential differences.