By Dinesh Pilgaokar
Track and Trace Systems in the manufacturing supply chain are gradually going digital and steadily embracing newer technologies, resulting in increased transparency, predictability, adaptability and robustness. Adoption at different levels and various types of automation has boosted the confidence of manufacturers to embrace more tools to heighten productivity and efficiency.
The role of AI will gain more importance in the coming times. AI substitutes human intelligence & behaviour, such as learning and predicting, based mainly on significant amounts of data acquired, analysed and acted upon instantly.
Manufacturers, especially in life sciences and other related industries, are always desirous of a ‘golden batch.’ The frequency of attaining a golden batch has increased over time. Achieving or surpassing the quality parameters allows for setting new benchmarks, and AI catalyses the frequency.
Experience and skill was the key to achieving such batches, with a lot of dependency on other factors of the human mind. AI can generate an in-depth analysis of batch production, including time, OEE, speed, settings, and conditions. Deep Sense AI can detect and analyse deviations: cost of raw materials, utilities, manpower, and rejections. It can recognise images, patterns and recommendations based on various data insights.
AI-powered analytics can improve machine utilisation and quality and reduce waste by detecting faulty products. AI can also automate recommendations for ideal machines and operators for optimised productivity.
More efficient and effective productivity and predictive maintenance can directly improve product safety and reduce maintenance costs and product downtime. Also, improved data collection at higher frequency and analysis in the different manufacturing phases will increase product quality and ensure safety.
AI-powered product designs will increase the potential for personalised products.
Regulations and compliances in most industries today depend on SOPS, which are person or human-dependent. Add to it a higher attrition rate that leads to the need for frequent personnel training to adapt to SOPs. Virtual agents can deliver instructions on tablets or other devices to reduce assembly errors and teach new operators in the workplace, ensuring compliance and standardisation of processes.
A McKinsey Global Institute (MGI) report predicts that AI could increase global output by approximately 16% by 2030. Notwithstanding consumer privacy and data security, some innovative consumer products equipped with sensors can provide real-life insights into how a product is being used by consumers and performing. This can give critical information to manufacturers on when a product embedded with AI might need repairs, enabling organisations to forecast when equipment will fail so that its repair can be scheduled on time.
Automobiles use connected sensors, which play a vital role in preventing accidents from occurring due to malfunctioning or product failure. A closely knit tracking system enables traceability through the interconnected ecosystem of vendors and suppliers.
AI can detect failures and quality issues not observed through manual inspections and enable issue detection before products are sold. Traceability and genealogy can help a product recall much faster.
AI used in isolation may not be as effective as when combined with automated processes. Adopting the optimal method and practice to identify and track a product in the manufacturing life cycle could be more effective. Predictive maintenance allows for downtime reduction and could increase a product’s lifetime while also reducing maintenance costs.
The author is chief customer officer, Bar Code India
