Manufacturing & Industrials
Case Studies
Newsfor Manufacturing & Industrials
ARUP saves 790 engineering hours using machine learning to detect utility clash points planning a light rail system for Auckland
Arup, in a joint venture with Jacobs, was selected to plan a new light rail system for the city of Auckland. The assessment of utility systems clashing at different locations along the proposed rail line was automated using supervised learning algorithms, reducing the amount of engineering time which would have been required for manual checks by 790 hours.
Linked use case: Collate and evaluate site data for architectural planning
Abellio London claims it reduced bus collisions and injuries by 29% and 60% respectively with collision avoidance technology
London’s leading bus operators, Abellio London, have collaborated with Intel''s Mobileye to launch a trial of safety technology. The aim of the project is to reduce bus collisions with cyclists, motorcycles, pedestrians and other road users and hence injuries. 66 buses were included in the trial, on three of the company’s London routes, and were equipped with a camera unit installed on the inside of the windshield and a display placed in the driver’s cab both providing audio and visual warnings. Findings to date who that Mobileye collision avoidance technology has managed to reduce collisions by 29% and reduced injuries from such collisions by 60%.
Linked use case: Automate driving with self-driving vehicles
Abundant Robotics device autonomously harvests apples using machine vision to identify appropriate fruit
Abundant Robotics, a vendor, offers technology which is able to autonomously harvest firm fruits using machine vision. Their product detects the location of apples on branches and according to their color, which signifies if they are ready for harvest, uses a vacuum style system to pull them and collect them.
Linked use case: Deploy robots to do physical tasks in the agricultural process
Alibaba Group detects pigs'' pregnancy seven times quicker using facial recognition technology
Alibaba Group claims it has developed a system to identify pregnant pigs by observing their behaviour after mating. The task was previously a manual procedure were farmers had to observe each of their cow''s behaviour over a 21 day period. With the algorithm, it is now possible to determine if a pig is pregnant on the third day to increase the number of newborns and maximise production. The company expects that its system will be adopted by some Chinese farms in early 2019.
Linked use case: Tracking, monitoring and analysing livestock behaviour to optimise production
Aston Martin raises public first time availability target 2% to 97.5% and drives 18% reduction in safety stock value with machine learning engine
Aston Martin required a solution to be able to offer a high first time availability, having spare parts immediately available for customers, without increasing stock levels. The company implemented ToolsGroup''s advanced machine learning engine to analyse historical data on consumer behaviour to better anticipate its customers'' needs. The implementation of the technology has resulted in a reduction of inventory value of its safety stock by 18% and an improvement in FTA service levels of 97.1%, within only two months.
Linked use case: Ensure inventory availability by predicting demand and triggering appropriate action
Aucnet, a Japanese car auction service, automatically classifies cars and uploads images to an online auction site saving over 50,000 man hours annually
Aucnet, a Japanese car auction service, conducts over four million auctions per year. Each auction could take up to twenty minutes of manual work to classify and upload images of the car. Using TensorFlow, transfer learning, and advanced engineering solutions the time per auction was reduced from up to 20 minutes to "minutes." It is estimated this could save over 50,000 man hours of time annually.
Linked use case: Identify physical properties of scanned images
Audi increases dealership visits by 31% following targeted marketing using AI
Audi leveraged LoopMe''s technology to increase visits to one of their Los Angeles dealerships. With LoopMe''s targeted marketing approach the company was able to leverage location data to serve ads toward audiences more likely to visit the dealership in Sunbelt market, LA. The marketing campaign resulted in a 31% increase in the dealership''s visits.
Linked use case: Track consumer visit to physical location following digital advertising offering
Auto Trader improves second-hand vehicle valuation accuracy using machine learning
Auto Trader is training machine learning algorithms to extract data on car specifications and details. By analysing the data the technology is able to determine how each affects the valuation price of second hand cars resulting in greater accuracy.
Linked use case: Provide valuations of second hand products eg cars
Auto1 leverages machine learning to connect buyers and sellers of second hand cars across Europe
Auto1 is able to see clearing prices, assess buyers'' and sellers'' behaviour and evaluate criteria for valuation purposes with the use of machine learning. This has enabled the seller of used cars to upgrade its matching of buyers and sellers of second hand cars across European cities.
Linked use case: Provide valuations of second hand products eg cars
BBMV reduced construction worker fatigue and impairment time while on duty by 24% with sleep monitoring devices
BBMV has construction workers wearing sleep monitoring devices which feed data through fatigue detecting algorithms into an app which allows the workers and their supervisors to gauge their level of alertness and predict problems further in their shifts.
Linked use case: Monitor staff alertness levels to ensure safety and productivity
BHP saves $5.5M by predicting mining truck maintenance requirements with machine learning
BHP has established a Maintenance Centre of Excellence to analyse data from its machinery in order to predict equipment maintenance needs, improving the maintenance of trucks at several of its sites, saving $5.5 million in costs at one mine alone.
Linked use case: Predict problems and recommend proactive maintenance for mining, drilling and support equipment
BMW increases worker safety and productivity and space utilisation through human-robot-collaboration
BMW is leveraging the KUKA LBR iiwa lightweight robots at its plant in Munich, to assist workers and operators with monotonous and physically strenuous tasks. The otherwise endangering collaboration of human and robots (HRC) has become safer as the lightweight robots are enhanced with AI and machine learning technology, enabling them to be capable of working along humans and being easily programmed. BMW has managed to support its employees while also saving roughly 25% more space, as the robots do not require fences or other safeguards within the factory.
Linked use case: Accelerate and support key processes with improved human-robot collaboration
BMW will self-diagnose faults and issues limiting car performance and collect data from connected vehicles with machine learning analytics
BMW is planning to use IBM''s cloud infrastructure to deploy its new platform for collecting data from connected cars. IBM announced it''s become a "pilot partner" with the German automaker.
Linked use case: Discover anomalies across fleet of vehicle sensor data to identify potential risks
Beck''s Hybrids is predicting the highest-yielding corn seeds from more than 30,000 genetic possibilities using an AI powered modeling engine
Beck''s Hybrids is leveraging an AI-powered engine to analyze large amounts of data on sun light, rain, location, terrain, to determine which corn breeds and which conditions will produce the highest yields.
Linked use case: Predict new high value crop strain performance based on past crop trends, weather and soil data
Berkeley Lab releases reinforcement learning training platform for training autonomous vehicles on traffic regulation
The US Department of Energy’s Lawrence Berkeley National Laboratory (Berkeley Lab) has developed a driving simulation platform using reinforcement learning, with the goal of using it to train autonomous vehicles how to regulate traffic congestion.
Linked use case: Optimise experimental efficiency through refining research process and operations
Big River Steel is predicting the availability of scrap steel using a predictive AI engine
Big River Steel has implemented Noodle.ai''s enterprise AI solution aiming to optimise operations at the company''s new metal recycling and steel production facility in Arkansas. Using machine learning models, the company is able to make predictions on the availability of its raw material, scrap steel.
Linked use case: Ensure inventory availability by predicting demand and triggering appropriate action
Big River Steel makes more accurate demand predictions using machine learning
Big River Steel has implemented Noodle.ai''s enterprise AI solution aiming to optimise operations at the company''s new metal recycling and steel production facility in Arkansas. Using machine learning models, the company is able to make demand predictions based on macroeconomic and historical data.
Linked use case: Forecast product / service demand levels
Big River Steel maximises energy consumption at off-peak times to minimise energy costs using an AI powered optimisation model
Big River Steel has implemented Noodle.ai''s enterprise AI solution aiming to optimise operations at the company''s new metal recycling and steel production facility in Arkansas. Using machine learning models, the company is able to reduce energy costs by optimising scheduling and maximising energy consumption at off-peak times.
Linked use case: Optimise energy scheduling and management of power plants based on energy pricing, weather and other real time data
Big River Steel optimises production and minimises unplanned events in the production process process with machine learning
Big River Steel has implemented Noodle.ai''s enterprise AI solution aiming to optimise operations at the company''s new metal recycling and steel production facility in Arkansas. Using machine learning models, the company is able to predict unplanned events like breakouts and minimise their occurrence and effect on production.
Linked use case: Predict problems and recommend proactive maintenance for production equipment
Big River Steel predicts and optimises the maintenance of its machinery and equipment using machine learning.
Big River Steel has implemented Noodle.ai''s enterprise AI solution aiming to optimise operations at the company''s new metal recycling and steel production facility in Arkansas. Using machine learning models, the company is able to optimise and predict the maintenance of its machinery and equipment.
Linked use case: Predict maintenance requirements
Big River Steel reduces cost of outbound transportation and optimises delivery windows using machine learning
Big River Steel has implemented Noodle.ai''s enterprise AI solution aiming to optimise operations at the company''s new metal recycling and steel production facility in Arkansas. Using machine learning models, the company is able to reduce outbound transportation costs while optimising delivery windows for its customers.
Linked use case: Optimise quality of service and product delivery
Blue River Technology offers deep learning technology which is aspiring to reduce herbicide usage by offering a more precise and targeted spray application
Blue River Technology, acquired by John Deere, demonstrated the See & Spray weeding machine in the United States cotton belt during 2017 and will extend testing in 2018, as it is still preparing for a commercial launch. Their smart sprayer technology leverages deep learning algorithms to distinguish between plants and weeds with better accuracy and then uses custom nozzle designs providing spray accuracy.
Linked use case: Deploy robots to do physical tasks in the agricultural process
Bosch Thermotechnology improves field service management appointment accuracy and efficiency with machine learning
Bosch Thermotechnology implemented ClickSoftware''s Click Field Service Edge to optimise appointment accuracy and provide fast service to their customers. The software now manages the job scheduling of the company''s Belgian sales office of 90 technicians. The solution leverages ClickSoftware''s machine learning cloud and applies AI to identify patterns in the service chain data in order to be able to make more accurate predictions.
Linked use case: Optimise mobile job scheduling
CARFIT is offering real time issue detection on tires, wheels, shocks and brakes with machine learning
CARFIT, an AI startup providing vibration-based predictive maintenance for cars, has joined the NVIDIA Inception program and will be preparing a monitoring solution for wearing parts based on machine learning. This collaboration will enable the startup to enhance its technical knowledge and accelerate their development of Noise Vibration Harshness (NVH) products.
Linked use case: Predict failure and recommend proactive maintenance on vehicle components
CCC Information Services predicts repair requirements from vehicle collision photos using AI
In December 2018, CCC Information Services launched an automated estimation tool for insurers. The tool, called Smart Estimate, leverages AI to analyse collision photos. Based on analytics, the system is able to automatically assess the damage and generate estimates for cost and any parts that would need replacing. The company''s Insurance customers that already use CCC ONE® Platform services can have easy access to the tool for virtual inspections.
Linked use case: Recognise and categorise type of damage to predict insurance claim valuation through accessing photographic data