Optimizing Inventory & Anticipating Maintenance

Saffron Technology (Intel)

Optimizing Inventory & Anticipating Maintenance
Saffron Technology (Intel) Saffron Technology (Intel)
View Full Case Study
Contact Vendor
Feature New Record
OVERVIEW

An aircraft manufacturer wanted to improve their spare part inventory management for 15,000 out of production aircraft. Customers needed stock parts that couldn’t be sourced since they were never required to be repaired or replaced on the aircraft. The parts would need to be produced on demand and have a long lead time for production - typically up to six months - resulting in airlines grounding their aircraft at an average loss of one million per day. As a result, the manufacturer needed to anticipate which of their spare parts would fail before an issue was communicated - leading to better inventory planning, supply chain decision making, and a total reduction in operating costs. Additionally, the company wanted to know whether to purchase more than one spare part at a given time when a problem had been reported, whether they should stock a certain spare part in advance due to the long lead time, and whether they could reduce the number of service engineer man hours spent answering customer questions about the stock parts by having better access to information. Stocking decision was also made difficult because of limited communication between the spares management employees and the service engineers, resulting in high levels of ‘dead’ stock for the manufacturer. The goal was to reduce maintenance costs and increase customer satisfaction and retention without compromising aircraft production quality, safety and lives.

An aircraft manufacturer

Saffron was asked to unify both structured and unstructured data from 15 data sources. First Saffron ingested all the data to create an enduring knowledge store of all the data; unifying all sources for each entity (an event, a part, component, system, tail number, mechanic, pilot, date, location, airline, and more) which represents all the connections, correlations and their context for each entity. Model free similarity based reasoning was then applied SaffronMemoryBase to identify similarity patterns to answer the question “have we seen this before? If so, what did we do about it? Where the outcomes good or bad? Can I use this experience of the past to apply to this problem?” Using model-free similarity analysis, Saffron quickly identified parts requiring repair or replacement to anticipate which ones would be needed in inventory. The platform identified instances where there was an increase in activity for a certain stock part by analyzing data where aircraft operators had previously communicated issues with these stock parts. Software Components: - SaffronMemoryBase

An event, a part, component, system, tail number, mechanic, pilot, date, location, airline, and more
IT
Mature (technology has been on the market for > 5 years)
OPERATIONAL IMPACT
The manufacturer was able to identify, manage and anticipate spare part problems more accurately and efficiently than ever before.
QUANTITATIVE BENEFIT

Saffron helped the aircraft manufacturer eliminate 100+ millions of dollars wasted through operational inefficiencies while creating new revenue streams for the company, generating more than 20 times ROI on their initial investment in the solution and increasing overall customer satisfaction.

The platform allowed for considerable reduction of time spent by service engineers to answer customers’ questions, bringing the average request down from 4 hours to 5 minutes.


Fatal error: Call to a member function getLabel() on null in /efs/iotone.com/module/Application/view/application/common/IoTSnapshot_view.phtml on line 9