Manufacturing Analytics

Act Challenges faced by Companies in Manufacturing Sector?

The most compelling motivation that the makers and customers are not going close by close by, that the buyers are sought after and the item life cycles are decreasing in size. Assembling examination should a lot keep pace while overseeing costs and dangers to the organization. Numerous innovations, like the web of things, enormous information, and prescient examination in Manufacturing, are moving a huge change across assembling investigation. Makers that are including these new advancements into their creation lifecycles are getting more proficient and firmly associated.

These advances are likewise contributed producers to deal with the key difficulties, for example, making it simpler to incorporate various frameworks, cycles, and individuals. Venture Resource Planning instruments are being utilized for assortment of advances between numerous cycle lines inside the organizations. This single wellspring of information is utilized for satisfying a great deal of Manufacturing Analytics. AI techniques are utilized to run or work quality checks

Case Study 1: How to manage the supply-chain based on products’ sales prediction
Business Problem Statement

Due to the increased uncertainty and current market conditions, the prediction of sales of products has become a challenge. This in-turn is leading to a long Supply Chain. Management of the supply chain is becoming cumbersome, and is resulting in degradation in quality of inventory.

Business Challenges

  • Long Supply chain due to inappropriate inventory management
  • Uncertain demand leading to incorrect planning of products requirement
  • Increase in the cost of supply chain management
  • Increase in efforts due to maintenance of products in inventory
  • Just-in-time manufacturing for dynamic demands

Business Solutions

  • Built prediction model to predict the sales of the number of products at a particular region, considering various demographics
  • Used forecasting methods on variables such as repeat purchase rates, secondary sales, stock coverage, etc., among others to determine the forecast of sales of products
  • Statistical methods used on historical data helped in determining the trends of sales of products
  • Repeat purchase patterns are considered to attain the accuracy in sale prediction of the products

Business Impact

  • Reduction in length by reducing the number of channels of Supply chain
  • Reduction in costs incurred in managing supply chain
  • Reduction in human effort involved in sorting, disposal and book-keeping of the products
  • Improved feasibility and flexibility of supply chain management
  • Increase in profits due to effective decision-making

Case Study 2: How to automate manual inspection of circuits on assembly chain process by image processing using Deep Learning
Business Problem Statement

Research has facts to say that companies, which do not embrace technology will die down soon. History has time & again proved that companies, which waste the knowledge of the employees by having them participate in extensive manual laborious work will not survive the competition. In the wake of major disruptions in technological space, companies are still struggling with the manual quality audit process of the goods & services they provide. Industrial revolution, which is trying to solve these challenges, is in nascent stages & starting at a steady pace. However, the applications of the same is not well known to many. Research is still going on in the space of computer vision to solve a lot of these problems.

Business Challenges

  • Time-consuming manual effort to inspect each high-end circuit board
  • Lack of synchronization between the speed of manufacturing & manual inspection leading to incorrect sample size selection
  • Lot of errors in manual inspection process because of time constraint
  • Lack of confidence on the manufactured lot even if the samples are not defective
  • Increase in scrapped circuits, which are identified during assembling process, leading to wastage of raw material, time & effort

Business Solutions

  • Defective circuit boards are identified using image processing. This is achieved by capturing & comparing the Images, of each circuit board, against the historical defective boards, by applying deep learning techniques
  • Classification models automatically segregates the defective circuit board from the non-defective
  • Quality inspection team is upfront provided information on probability of circuit board being defective, leading to inspection of those, which have slightly above threshold probability of being defective

Business Impact

  • Reduction in manual inspection effort by 72%
  • Reduction in the sample size without compromising the effectiveness of inspection process
  • Reduction in the number of human errors in wrongly classifying the circuit boards as non-defective despite being defective
  • Reduced wastage of material, time & effort

Case Study 3: How to reduce blade manufacturing lot rejection by predicting the lot, which exceeds the lot rejection threshold
Business Problem Statement

Despite the sample size being biased, there are chances that the entire manufactured lot gets rejected due to the stringent quality audit process. This triggers the customers losing trust on the quality standards of manufacturing vendor, thereby the vendor losing future business through the same channel and also through the references. Vendors also lose precious manufacturing time, raw materials, human effort and should invest their efforts in re-manufacturing the entire lot.

Business Challenges

  • Increase in the number of vehicle breakdowns while in use
  • Increase in the number of roadside assistance requests spiraling the warranty costs
  • Customers dissatisfaction due to vehicle breakdown or failure of parts during journey
  • Static servicing date alerts leading to redundant maintenance of vehicles
  • Unavailability of failed vehicle components due to improper supply-chain management
  • Increase in number of warranty & insurance claims

Business Solutions

  • Internet of things’ devices installed on vehicles that capture live-streamed data of 196 components, thereby making live health monitoring possible
  • Automotive telematics solution and Mobile app were developed to gauge the performance of the vehicle
  • Vehicle breakdown prediction model was built to predict the vehicle’s probable breakdown time
  • Predicting critical vehicle component failure leading to reduced service time, better inventory management & streamlining the supply chain process

Business Impact

  • Reduction in number of vehicle breakdowns by preemptive maintenance alerts rather than static time bound alerts
  • Reduction in number of warranty claims
  • Reduction in number of insurance claims
  • Reduction in inventory cost
  • Improvement in turn-around time for replacing failed/’will soon fail’ components
  • Increased customer satisfaction leading to improved brand building
  • Increased fuel efficiency leading to environment-friendly transportation

Case Study 4: Want to know how to reduce the warranty cost of heavy machinery sold to customers, by predicting the machinery failure & adjusting the warranty period
Business Problem Statement

Defects in Machinery leads to a huge hole in the bottom line of Manufacturing companies. It also dents the reputation of the products coming out of the manufacturer and also the repeat business. In case of heavy machines, it is still worse due to the expensive components utilized in them. In these contemporary market circumstances, detecting machinery failure is a difficult issue.

Business Challenges

  • Increase in the burden on Manufacturers’ bottom line due to warranty costs of Heavy machines
  • Unable to determine the appropriate warranty duration to satisfy both customers as well as top management of manufacturing companies
  • Lack of techniques in proactively identifying defects in machinery
  • Difficulty in identifying inadequate engineering process in the value chain

Business Solutions

  • Built simulation based prediction model to simulate the manufacturing process to predict the defective components in Heavy Machines
  • Statistical methods used on historical data, resulted in validating the product performance
  • Built prediction model to predict whether the component is defective or not
  • Using data optimization techniques, the warranty periods are effectively estimated, at the same time increased satisfaction

Business Impact

  • Reduced warranty costs
  • Optimized Warranty periods
  • Reduction in number of defectives in machinery
  • Reduced downtime by effectively identifying the exact root-cause
  • Increased profit margins
  • Increase in customer satisfaction
  • Improved reputation of manufacturers

Contact Us