Intellegens Case Studies Novel Deep Learning Approach for Predictive Maintenance and Process Optimization

Edit This Case Study Record

	Novel Deep Learning Approach for Predictive Maintenance and Process Optimization Intellegens

Novel Deep Learning Approach for Predictive Maintenance and Process Optimization

Intellegens

Technology Category	Analytics & Modeling - Machine Learning
Applicable Functions	Maintenance
Use Cases	Predictive Maintenance
Services	Data Science Services
Challenge	Most organisations apply a “Reactive Maintenance” approach to their processes, in which repairs and replacements are made to the equipment after a failure occurs. It costs around 10x more to repair a machine after it fails, not to mention the direct impact on revenue and customer satisfaction. Through “Preventative Maintenance” equipment is repaired or replaced at pre-set time intervals in order to avoid failure. Whilst this approach reduces unplanned downtime it is expensive as these scheduled repairs take place when there can be nothing wrong with the equipment. However, the benefits of predictive maintenance are significant, so it is becoming the preferred method for manufacturers, enabling organisations to foresee and schedule repairs and replacements when needed, achieving 100% operational uptime of the equipment. One challenge for traditional machine learning in manufacturing is that techniques require clean and complete data. However, manufacturing and process data can be sparse and noisy. Currently, it is difficult for engineers to access and interpret production process data, they rely on personal experiences and opinions to modify process parameters. This leads to inconsistent and potentially suboptimal decision making, and moreover increases the risk of process failure, increasing associated time and costs. The production line is especially difficult to model using standard techniques due to the inherent time lag and inertia between changing operating parameters and their effect. Costs associated with waste materials and failed production could also be significantly reduced with the application of relevant and innovative deep learning technology to design production processes more efficiently. Read More
Solution	Intellegens has developed a machine learning tool, Alchemite, that trains models on all available data, no matter how sparse or noisy. It brings all the available data together and use underlying correlations to accurately predict missing values and generate the most complete models possible. The technology leverages existing process data to reduce the costs of asset maintenance programs and improves the overall understanding of the complete system, optimising production lines and processes involved in manufacturing. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Machine Learning

Applicable Functions

Maintenance

Use Cases

Predictive Maintenance

Services

Data Science Services

Challenge

Most organisations apply a “Reactive Maintenance” approach to their processes, in which repairs and replacements are made to the equipment after a failure occurs. It costs around 10x more to repair a machine after it fails, not to mention the direct impact on revenue and customer satisfaction. Through “Preventative Maintenance” equipment is repaired or replaced at pre-set time intervals in order to avoid failure. Whilst this approach reduces unplanned downtime it is expensive as these scheduled repairs take place when there can be nothing wrong with the equipment. However, the benefits of predictive maintenance are significant, so it is becoming the preferred method for manufacturers, enabling organisations to foresee and schedule repairs and replacements when needed, achieving 100% operational uptime of the equipment. One challenge for traditional machine learning in manufacturing is that techniques require clean and complete data. However, manufacturing and process data can be sparse and noisy.

Currently, it is difficult for engineers to access and interpret production process data, they rely on personal experiences and opinions to modify process parameters. This leads to inconsistent and potentially suboptimal decision making, and moreover increases the risk of process failure, increasing associated time and costs. The production line is especially difficult to model using standard techniques due to the inherent time lag and inertia between changing operating parameters and their effect. Costs associated with waste materials and failed production could also be significantly reduced with the application of relevant and innovative deep learning technology to design production processes more efficiently.

Solution

Intellegens has developed a machine learning tool, Alchemite, that trains models on all available data, no matter how sparse or noisy. It brings all the available data together and use underlying correlations to accurately predict missing values and generate the most complete models possible.

The technology leverages existing process data to reduce the costs of asset maintenance programs and improves the overall understanding of the complete system, optimising production lines and processes involved in manufacturing.

Impact #1	[Cost Reduction - Waste] Reduction of material cost by minimising waste. The application of Alchemite and the ability to run virtual experiments can reduce the amount of waste produced at all stages of production.
Impact #2	[Process Optimization - Real Time Monitoring] Transparent understanding of processes. Achieve the best possible understanding of how production techniques correlate to the final properties and a platform to do virtual experiments of changing parameters that cannot be tried on a live production line. This is especially important due to the time-varying character and inherent time lag present on the production line.
Impact #3	[Product Improvement - Brand Image] Lead the market as technology innovators with an improved brand image, providing additional evidence for pioneering in industrial design that is able to leverage cutting-edge science, across all disciplines, in order to improve both manufacturing design and operating margins.

Impact #1

[Cost Reduction - Waste]

Reduction of material cost by minimising waste. The application of Alchemite and the ability to run virtual experiments can reduce the amount of waste produced at all stages of production.

Impact #2

[Process Optimization - Real Time Monitoring]

Transparent understanding of processes. Achieve the best possible understanding of how production techniques correlate to the final properties and a platform to do virtual experiments of changing parameters that cannot be tried on a live production line. This is especially important due to the time-varying character and inherent time lag present on the production line.

Impact #3

[Product Improvement - Brand Image]

Lead the market as technology innovators with an improved brand image, providing additional evidence for pioneering in industrial design that is able to leverage cutting-edge science, across all disciplines, in order to improve both manufacturing design and operating margins.

Download PDF Version

Overview

Novel Deep Learning Approach for Predictive Maintenance and Process Optimization

Operational Impact