Machine Learning applications in Secondary Sector-Part 1

Four stages classify the industrial revolution. The first stage was mechanisation of production using water and steam power followed by mass production with the help of electricity. The next stage was a digital revolution with the use of electronics and information technology to automate further production. Industry 4.0 or ‘smart factory’ is the subsequent stage facilitated by machine learning applications in secondary sector to produce systems that monitor physical processes and communicate with each other and humans in real-time.

Following are some of the examples of machine learning applications in secondary sector of economy:

Automobile Production

The data about the driving environment obtained through many sources such as onboard cameras, global positioning systems or engine combination failures help intelligent systems in varied fields of automotive industry. Examples of these intelligent vehicles technologies include Aston Martin DB9 engine control system, use of Direct Labour Management System at Ford Motor Company to enhance assembly process planning, standardize labour time required and meet consistency of vehicle process manufacturing. Ford also uses data mining techniques to find occasions to cut materials from a supplier.  Hence, these systems help in improving the operative productivity of assembly process and reduce manufacturing costs.

Jaguar Land Rover is using latest machine learning and artificial intelligence techniques to propose a “self-learning car” with an ability to learn preferences and driving style and offer a broad area of services to the driver. Jaguar’s smart assistant will be able to plan the car navigation according to calendar schedule, adjust car settings and adapt car temperature after a certain activity by the driver. Google’s driverless cars and Telsa Motors use the software’s ability to recognize objects in different road environments to facilitate the driver to hand over control under specific conditions and help in making smart driving judgements. Thus, the system helps in reducing collisions without eliminating the fun of driving.

Textile Production

Some of the uses of machine learning applications in secondary sector are classified as:

  • Identification, classification and analysis of textile defects such as classify fabric stitching defects.
  • Monitor and optimize processes such as predicting performance limits for airbags or sewing performance of woven textiles for efficient planning.
  • Predict physical properties of textiles by using image system and trained neural networks to classify cotton or animal fibres. It is also used to study a link between the shrinkage of yarn and various factors.
  • Marketing and planning such as being used by Hong Kong garment industry to allocate resources to serve the needs of the overseas market.

Read More

Leave a Reply