**Description**

1. Are you interested in starting your career with a deep tech company working with leading Aerospace and Defence companies like Airbus, GKN, BAE Systems etc.?
2.  Are you interested in decarbonising the manufacturing industry using innovative AI technology?
3. Do you enjoy working on cutting-edge, scalable technology in a team environment?

If the above questions excite you, then please continue reading!

At Intellium AI, we hire the best minds in technology to innovate and build solutions that our customers desperately want to adopt AI successfully within their businesses. We have built an Enterprise AI platform to give our customers the power of AI irrespective of their skill background.

You will be matched to a manager and mentor in your role. You will have the opportunity to perform a state-of-the-art literature review in the field of green and sustainable manufacturing and make an impact on the evolution of our products, as well as lead mission-critical projects early in your career. Your design, code, and raw smartness will contribute to solving some of the most complex technical challenges in the areas of automation, optimisation, scalability, and security.

**Key Job Responsibilities**

- Develop supervised and unsupervised machine learning models, for example, XGBoost, KNN etc.
- Develop deep learning models using Neural Networks, e.g. Auto Encoders, Generative Adversarial Networks (GANs), Federated Learning etc.
- Develop Explainable AI modules to present machine learning results to end users
- Implement optimisation algorithms using the trained machine learning (surrogate) models
-  Develop uncertainty quantification modules to highlight the uncertainty in model prediction
- Implement cutting-edge AI algorithms from published scientific documents
- Write technical articles/blogs on industrial use cases


**Qualifications** 

- Master’s in data science with a background in Engineering 
- Mastery of Python programming language
- Strong written and verbal communication skills
- Basic working experience/knowledge in Unix/Linux environment
- Basic knowledge of containerised applications, for example, Docker 
- Basic knowledge of GPU-based highly parallel software development

**Location**

- Bristol-UK

**Apply To**

info@intellium.ai

Data Scientist - Intern

**Description** 

1. Are you interested in starting your career with a deep tech company working with leading Aerospace and Defence companies like Airbus, GKN, BAE Systems etc.?
2. Are you interested in decarbonising the manufacturing industry using innovative AI technology?
3. Do you enjoy working on cutting-edge, scalable technology in a team environment?

If the above questions excite you, then please continue reading! 

At Intellium AI, we hire the best minds in technology to innovate and build solutions that our customers desperately want to adopt AI successfully within their businesses. We have built an Enterprise AI platform to give our customers the power of AI irrespective of their skill background.
          
As a Data Scientist, you will have an opportunity to shape our AI products as well as lead mission-critical projects early in your career. Your design, code, and raw smartness will contribute to solving some of the most complex industrial challenges.

**Key Job Responsibilities**
- Develop supervised and unsupervised machine learning models, for example, XGBoost, KNN etc.
- Develop deep learning models using Neural Networks, e.g. Auto Encoders, Generative Adversarial Networks (GANs), Federated Learning etc. 
- Develop Explainable AI modules to present machine learning results to end users 
- Implement optimisation algorithms using the trained machine learning (surrogate) models
- Develop uncertainty quantification modules to highlight the uncertainty in model prediction 
- Implement cutting-edge AI algorithms from published scientific documents
- Write technical articles/blogs on industrial use cases.


**Qualifications** 
- Master’s in data science with a background in Engineering
- Mastery of Python programming language 
- Strong written and verbal communication skills
- Basic working experience/knowledge in Unix/Linux environment
- Basic knowledge of containerised applications, for example, Docker
- Basic knowledge of GPU-based highly parallel software development

**Experience**
- Minimum 1 yr industry experience in applying AI in a commercial environment


**Location** 

Bristol-UK


**Apply To**

info@intellium.ai

Data Scientist

Artificial intelligence can potentially transform businesses and societies, but many organisations struggle to implement AI technologies effectively. One solution to help accelerate AI adoption is identifying and empowering "AI champions" within organisations.

AI champions are employees who are passionate about the potential of AI and act as a catalyst in their companies to integrate AI successfully. They can help in several ways:

- Identifying use cases. AI champions are closely familiar with their companies' products, services, and processes. This puts them in a great position to spot opportunities where AI could drive real value. They can help identify promising use cases and applications of AI that could benefit their organizations.
- Educating others. There is still a lot of mystery and confusion surrounding AI, its capabilities, and its limitations. AI champions can help educate their colleagues about what AI is, how it works, and its potential applications and benefits for their industry and company. This education and awareness building is crucial to gaining buy-in and adoption.
- Experimenting. The best way to learn how AI can help is by experimenting. AI champions can help run pilot projects and experiments applying AI to problems to see what works well and what doesn't. They can closely monitor experiments and share lessons learned to determine how to implement the best AI going forward.
- Addressing challenges. The process of implementing AI will inevitably surface challenges, issues, and blockers. AI champions can help address these challenges, such as data gaps or regulations around data and AI use. Their passion and expertise can help companies figure out solutions to implement AI.

In summary, AI champions can help blaze the trail for AI adoption at their organizations by identifying opportunities, educating colleagues, running experiments, and addressing challenges. Identifying and supporting AI champions is a simple but effective strategy to accelerate the integration of AI and realize its potential to transform businesses.


large_half_engineer_and_half_ai_person.png

medium_half_engineer_and_half_ai_person.png

small_half_engineer_and_half_ai_person.png

thumbnail_half_engineer_and_half_ai_person.png

half_engineer_and_half_ai_person.png

Importance of AI Champions to accelerate AI adoption

AI Champions: The Key to Unlocking Enterprise AI Success

**Introduction**

Boosting productivity in manufacturing environments is a critical task for ensuring the success of any business in this industry. Traditional methods of improving productivity, such as optimizing processes and streamlining operations, can only take a business so far. To truly take their productivity to the next level, manufacturers must embrace new technologies, such as artificial intelligence (AI).

**Business Pain Points**

One of the biggest challenges facing manufacturers today is the need to continuously improve their productivity. This can be difficult, as there are many factors that can impact productivity, such as changes in market demand, new regulations, and shifts in the global economy. Additionally, many manufacturers struggle to keep pace with the rapid pace of technological change, making it difficult to take advantage of new tools and techniques that can improve productivity.

**AI Solution**

To address these challenges, many manufacturers are turning to AI-powered solutions to boost their productivity. These systems use advanced machine learning algorithms to analyze data from various sources, such as sensors, control systems, and production logs, to identify opportunities for improvement. By leveraging this data, manufacturers can optimize their processes, streamline their operations, and increase their overall efficiency.

**Business Benefits**

The use of AI to boost manufacturing productivity has a wide range of benefits. By identifying opportunities for improvement, manufacturers can increase their output, reduce their costs, and improve their bottom line. Additionally, by staying on the cutting edge of technology, manufacturers can remain competitive in today's fast-paced market, enabling them to better serve their customers and grow their business. Overall, AI-powered solutions are the key to improving productivity in the manufacturing industry.

large_Screenshot 2022-12-12 at 16.01.14.png

medium_Screenshot 2022-12-12 at 16.01.14.png

small_Screenshot 2022-12-12 at 16.01.14.png

thumbnail_Screenshot 2022-12-12 at 16.01.14.png

Screenshot 2022-12-12 at 16.01.14.png

Maximizing Manufacturing Productivity with AI: The Future of Industry

How can AI help with boosting manufacturing productivity?

**Introduction**

Anomaly detection in manufacturing environments is a critical task for ensuring the smooth and efficient operation of production lines. Traditionally, this has been done manually by skilled technicians, who must constantly monitor the various systems and processes in place to identify any potential issues. However, as manufacturing becomes increasingly complex and automated, it is becoming increasingly difficult for human operators to keep up with the sheer volume of data that must be analyzed.

**Business Pain Points**

One of the biggest challenges facing manufacturers today is the need to quickly and accurately detect anomalies in their production processes. Failure to do so can result in a wide range of problems, including production delays, quality issues, and even safety hazards. Additionally, manually monitoring systems and processes can be time-consuming and costly, diverting resources away from more productive tasks.

**AI Solution**

To address these challenges, many manufacturers are turning to AI-driven anomaly detection solutions. These systems use advanced machine learning algorithms to analyze data from various sources, such as sensors, control systems, and production logs, to identify potential anomalies in real-time. This allows manufacturers to quickly and accurately identify any potential issues, enabling them to take corrective action before problems arise.

**Business Benefits**

The use of AI-driven anomaly detection in manufacturing environments has a wide range of benefits. By automating the process of detecting anomalies, manufacturers can reduce the time and cost associated with manual monitoring, freeing up resources for more productive tasks. Additionally, by identifying potential issues early on, manufacturers can avoid costly production delays, quality issues, and safety hazards, ultimately improving their bottom line. Overall, AI-driven anomaly detection can help manufacturers to improve the efficiency and effectiveness of their operations, enabling them to better compete in today's highly competitive market.

large_160260082579dff774ab3d7bafafdfa4079951d1e0.webp

medium_160260082579dff774ab3d7bafafdfa4079951d1e0.webp

small_160260082579dff774ab3d7bafafdfa4079951d1e0.webp

thumbnail_160260082579dff774ab3d7bafafdfa4079951d1e0.webp

160260082579dff774ab3d7bafafdfa4079951d1e0.webp

Maximizing Efficiency with AI-Driven Anomaly Detection in Manufacturing Environments

How can AI help with manufacturing anomaly detection?

**Introduction**

AI-driven industrial inspection automation is a powerful strategy for improving the efficiency and accuracy of industrial inspections. By using data and machine learning algorithms, businesses can automate their inspection processes and reduce the need for manual labor.

**Business Pain Points**

Traditional industrial inspection processes are often labor-intensive and time-consuming, requiring skilled workers to manually inspect equipment and identify defects. This can be costly and can lead to a lack of consistency and accuracy in the inspection process. In addition, manual inspection processes can be dangerous, as they require workers to be in close proximity to potentially hazardous equipment.

**AI Solution**

AI-driven industrial inspection automation uses data and machine learning algorithms to automate the inspection process. This allows businesses to identify defects and anomalies in equipment more quickly and accurately, without the need for manual labor. In addition, AI-driven inspection automation can reduce the need for workers to be in close proximity to hazardous equipment, improving safety and reducing the risk of accidents.

**Benefits**

The benefits of AI-driven industrial inspection automation are numerous. By automating the inspection process, businesses can reduce the need for manual labor and improve the efficiency and accuracy of their inspections. In addition, AI-driven inspection automation can improve safety by reducing the need for workers to be in close proximity to hazardous equipment. Overall, AI-driven inspection automation is a powerful tool for improving the performance of industrial inspection processes.

large_2b.Improve-Operational-Efficiency-With-Predictive-Quality-Control(Build).jpg

medium_2b.Improve-Operational-Efficiency-With-Predictive-Quality-Control(Build).jpg

small_2b.Improve-Operational-Efficiency-With-Predictive-Quality-Control(Build).jpg

thumbnail_2b.Improve-Operational-Efficiency-With-Predictive-Quality-Control(Build).jpg

2b.Improve-Operational-Efficiency-With-Predictive-Quality-Control(Build).jpg

Transform your industrial inspection process with AI-driven automation

How can AI help with automating Industrial Inspection?

**Introduction**

AI-driven supply chain optimization is a powerful strategy for improving the efficiency and performance of a business's supply chain. By using data and machine learning algorithms, businesses can optimize their supply chain operations and achieve a competitive advantage.

**Business Pain Points**

Traditional supply chain management can be complex and time-consuming, requiring manual processes and decision-making. This can lead to inefficiencies and a lack of agility, which can impact a business's ability to respond to changes in demand or the market. In addition, managing the supply chain can be costly, as it requires a significant investment in resources and infrastructure.

**AI Solution**

AI-driven supply chain optimization uses data and machine learning algorithms to automate and optimize supply chain operations. This allows businesses to make more accurate and timely decisions, resulting in a more efficient and agile supply chain. In addition, AI-driven supply chain optimization can reduce the need for manual processes and decision-making, resulting in lower costs and improved productivity.

**Benefits**

The benefits of AI-driven supply chain optimization are numerous. By improving the efficiency and agility of the supply chain, businesses can achieve a competitive advantage and respond quickly to changes in demand or the market. In addition, AI-driven supply chain optimization can reduce costs and improve productivity, resulting in higher profits and a more sustainable business model. Overall, AI-driven supply chain optimization is a powerful tool for improving the performance of a business's supply chain.

large_iStock-1124533201.jpg

medium_iStock-1124533201.jpg

small_iStock-1124533201.jpg

thumbnail_iStock-1124533201.jpg

iStock-1124533201.jpg

Defence

Aerospace

Automotive

Optimize your supply chain with AI-driven solutions: Improve efficiency, reduce costs, and gain a competitive advantage

Industrial application of Artificial Intelligence

How can AI help with Supply Chain optimisation?

**Introduction**

Predictive maintenance is a powerful strategy for optimizing the performance of industrial equipment and reducing downtime. By using data and machine learning algorithms, businesses can predict when maintenance is needed and schedule it before failure occurs. This allows them to avoid unexpected outages and maintain a high level of productivity.

**Business Pain Points**

Traditional maintenance strategies are often reactive, meaning they are only performed after equipment has failed. This can result in unplanned downtime, which can be costly and disruptive to business operations. In addition, scheduled maintenance can be time-consuming and costly, as it requires equipment to be taken offline during regular working hours.

**AI Solution**

Predictive maintenance uses data and machine learning algorithms to predict when equipment is likely to fail. This allows businesses to schedule maintenance at a convenient time, before failure occurs. This can significantly reduce downtime and improve productivity. In addition, predictive maintenance can reduce the need for scheduled maintenance, as it allows for a more targeted and efficient approach.

**Benefits**

The benefits of predictive maintenance are numerous. By reducing downtime, businesses can maintain a high level of productivity and avoid the costs associated with unplanned outages. In addition, predictive maintenance can reduce the need for scheduled maintenance, resulting in lower costs and less disruption to business operations. Overall, predictive maintenance is a powerful tool for optimizing the performance of industrial equipment and improving business performance.

large_2c.Improve-Industrial-Productivity-With-IoT-And-Deep-Learning(Build).jpg

medium_2c.Improve-Industrial-Productivity-With-IoT-And-Deep-Learning(Build).jpg

small_2c.Improve-Industrial-Productivity-With-IoT-And-Deep-Learning(Build).jpg

thumbnail_2c.Improve-Industrial-Productivity-With-IoT-And-Deep-Learning(Build).jpg

2c.Improve-Industrial-Productivity-With-IoT-And-Deep-Learning(Build).jpg

Energy

Transport

Construction

Reduce downtime and improve productivity with AI

How can AI help with predictive maintenance?

Intellium AI has appointed Ian Risk (pictured) as a new non-executive director (NED)

In his new role, Ian — who is a highly experienced technology and innovation professional — will provide strategic advice to the board on Intellium’s product development and customer success. 

Ian commented on his appointment, “I am delighted to join the team at the Bristol based start-up Intellium AI. Digital transformation should be an essential part of the strategy for 
every company to ensure they remain or become more competitive, but for many is out of reach due to a lack of skills. The technology under development at Intellium addresses this need, it is far more inclusive for those lacking a data science background, thereby enabling more widespread adoption of artificial intelligence throughout organisations. By democratising the access to data and providing the tools to everyone to exploit it, we can address the critical issues facing us all, such as more efficient use of energy to meet our net zero targets.”

Kiran Krishnamurthy, CEO of Intellium AI, commented, “I have long known Ian since our days at the Airbus Innovations team. Between us, we have more than 60 years of industry domain expertise. This is crucial to successfully adopt technology like AI, where a deep understanding of the industry background is paramount. I am very excited to have Ian on board in our mission to make AI technology widely accessible across the business user community.

Ian joins Intellium on the 3rd of October, 2022.

About Ian Risk

Prof. Risk has more than 40 years of experience in the development, management and execution of collaborative research projects, primarily within the aerospace sector. He has created and managed some of the largest UK industrial R&D projects and many within the EU Framework Programme. He has held senior positions with UK industrial and research organisations and brings a wealth of operational and technological knowledge to Intellium AI. 

About Intellium

Intellium AI is a deep tech company based in Bristol-UK, making complex AI technology accessible to all Engineers working in the high value design and manufacturing industry.


large_Ian Risk.jpg

medium_Ian Risk.jpg

small_Ian Risk.jpg

thumbnail_Ian Risk.jpg

Ian Risk.jpg

small_Ian Risk joins forces with Intellium AI.png

thumbnail_Ian Risk joins forces with Intellium AI.png

Ian Risk joins forces with Intellium AI.png

Intellium AI has appointed Ian Risk to the Board

Ian Risk joins forces with Intellium AI

If you were leading an innovative business transformation initiative in your organisation and had the choice between developing a *complex technology of high business value per user but having a lower user base* or a *simpler technology of lower business value per user but having a wider user base*, which option would you select?  

The choice is never easy. However, it could determine the speed of technology adoption in your organisation. I have had the privilege of being involved in both scenarios, which have heavily influenced my thinking and corporate strategy.

More than 20 years ago, when I was working at Airbus on creating the A380 aircraft, I helped develop software that automatically generated manufacturing instructions for robots based on the part's design. The software was a *technological success* that automated a business process and resulted in significant time savings per use, realising cost savings for the Company. The only caveat was that due to the product complexity, the software developers ended up being the primary end users, leading to the software being regarded as an *adoption failure*.

Having learnt this lesson on A380, we made increasing the software user base a business requirement whilst designing the software architecture for the subsequent aircraft, the Airbus A400M. The software for the same application was simplified to make it more business user friendly, resulting in widespread adoption. Features that resulted in all-or-nothing benefits were removed and gave a chance for the end users to reap micro benefits, even in situations where full exploitation of software automation was not possible.

The increased adoption of simplified software created an increasing community of technology evangelists who helped to identify further opportunities to make business processes more efficient, leading to cost and time savings. 

> The community aspect of technology creation has an amazing leveraging effect.

I am now seeing a similar trend in the industry with AI adoption. Many companies are exploring the latest and greatest AI algorithms and trying to automate the entire business process with AI. The AI skills and the data literacy to undertake complex digital transformation don't yet exist in these organisations. This leads to a gap in communication and expectation, which could eventually lead to failure in AI adoption.

Conversely, organisations focusing on increasing digital skills while initially choosing simpler AI use cases are co-creating inclusive community-based technology. 

> The ROI of initial AI projects is an increase in data and AI literacy across the community.

This creates a community of *technology evangelists* who go on to identify further digital transformation opportunities to make business processes more efficient, realising significant cost and time savings.

So, to answer my original question, technology that is co-created by involving a community of business and technical users has a higher chance of delivering value resulting in successful business adoption. 

> Creating or leveraging a community of practice is the secret sauce for successful technology adoption.


Written By,
Kiran Krishnamurthy
CEO, Intellium AI

small_Secret Sauce AI adoption.png

thumbnail_Secret Sauce AI adoption.png

Secret Sauce AI adoption.png

The secret sauce of successful AI adoption

Bristol based deep tech company Intellium AI is supporting BAE Systems through an Innovate UK sponsored project to reduce material waste and carbon footprint across the supply chain. A novel Artificial Intelligence (AI) solution is set to be implemented to connect suppliers remotely whilst preserving supply chain data privacy.

Intellium AI is working with BAE Systems and other industry partners including Codegate, Digital Catapult, Maher and MTC on  Innovate UK’s Manufacturing Made Smarter project, INTELI. The initiative forms part of BAE Systems’ Factory of the Future, a developmental facility which is developing and testing industry 4.0 technologies that will transform and enhance manufacturing for the future. 

BAE Systems is working with UK industry to drive a digitally led, affordable solution for Tempest, the UK’s next generation combat air system.   The INTELI project is addressing a key challenge facing the manufacturing industry that relies on sharing complex and sensitive data between supply chain partners.

The INTELI project is targeting the manufacture of a prototype aircraft component produced by Maher, a tier 1 supplier to BAE Systems using a novel manufacturing process. BAE Systems’ INTELI lead Ismail Master said “Intellium AI’s privacy preserving AI solution seeks to enable our supply chain to safely and efficiently share real-time and remote insights to ensure that the aircraft product quality is right first time. By harnessing the power of accurate, secure and connected data in this way, we will be able to reduce the amount of manufacturing rework required, which directly links to savings in material waste.  Not only will this drive time and cost savings, but, as importantly it supports the Company’s commitment to achieve net-zero greenhouse gas emissions across its operations by 2030, and across a wider supply chain by 2050.”

Kiran Krishnamurthy, CEO of Intellium AI, has previous experience with these challenges in the aerospace industry where he has used AI to overcome the amount of manual rework required in assembling a long range aircraft wing. 

Kiran said “Although the external organisations involved in the supply chain agreed that data should be leveraged to improve process efficiency, there were barriers in sharing data to achieve this. Concerns about data sharing are understandable when protecting Intellectual Property and managing data correctly is so important.”

Drawing from their experience, Intellium AI is developing a solution that generates AI driven supply chain insights, whilst preserving privacy, as business data never leaves the boundaries of an organisation. 

Kiran continued, “Such privacy preserving AI technology is already used in other industries. For example, we all want predictive texting on our mobile keypads to be accurate to save time and effort, yet we don’t want our private messages to be accessed by any third party to train AI models. Privacy preserving predictive texting has been developed to address this challenge and is already in use in some mobile devices”. 

### About Intellium AI

Intellium AI is an AI-for-Engineering deep tech company based in Bristol-UK working with leading blue chip companies in the Manufacturing industry. Kiran Krishnamurthy, CEO Intellium AI, previously worked at Airbus UK for 18+ years and has strong interest in developing technology that accelerates decarbonisation of the manufacturing industry and support industry achieve the Net Zero targets. 

Contact us via info@intellium.ai or www.intellium.ai/contact to evaluate your Net Zero status and actions.

### About BAE Systems

At BAE Systems, our advanced defence technology protects people and national security, and keeps critical information and infrastructure secure. We search for new ways to provide our customers with a competitive edge across the air, maritime, land and cyber domains. We employ a skilled workforce of 89,600 people in more than 40 countries, and work closely with local partners to support economic development by transferring knowledge, skills and technology.


Bristol based deep tech company Intellium AI is supporting BAE Systems through an Innovate UK sponsored project to reduce material waste and carbon footprint across the supply chain. A novel Artificial Intelligence (AI) solution is set to be implemented to connect suppliers remotely whilst preserving supply chain data privacy.

Intellium AI collaborate with BAE Systems to exploit the use of AI in the Supply Chain

The emergence of Artificial Intelligence (AI) technologies and the growth in big data have opened up novel and exciting digital transformation opportunities. Yet, very few companies have been successful in adopting and exploiting the full potential of AI and so gaining a competitive edge. One of the most significant barriers to this is the shortage of ‘industry relevant’ AI skills, followed by additional barriers such as unclear starting point, AI hype, information overload, fear of the unknown, software and hardware complexities, and potentially substantial financial investment without clear ROI etc.


IntelliumAI, a company based in the southwest of the UK, has developed a solution to address these challenges and accelerate the adoption of AI both in large OEMs and SMEs. Leveraging their expertise in the high value manufacturing industry as well as cutting-edge AI technologies, IntelliumAI has developed a cloud-based enterprise AI platform called ‘AiBoost®’ to accelerate the adoption of AI in the industry. The platform aims to create ‘citizen data scientists’ within businesses by giving AI ‘power to people’. This enables users with a wide range of skill levels to get started on the AI journey in a governed, automated and scalable manner.


Some of the main features of the AiBoost® platform are; ‘AI Workbench’: A virtual workbench to standardise and automate end-to-end AI workflow covering model training, evaluation, inspection and prediction, ‘Rules Factory’: An intelligent algorithm to generate easy-to-understand rules and insights from large volumes of data and ‘Explainable AI’: A framework for robust, fair and transparent AI to build trust and confidence in the AI-based automated decision-making process.


SMEs are especially poised to benefit from the AiBoost® platform as it abstracts the software and hardware intricacies from the end users and allows them to focus on their core expertise. This results in significant productivity gains at a substantially lower financial investment. Typical advantages of the AiBoost® platform include; accelerated product design cycles, faster manufacturing maturity, reduced manufacturing cost, lower operational costs, increased productivity and quicker time to market.

large_959923725e78450d61b1ef323596be4296c5edf30.webp

medium_959923725e78450d61b1ef323596be4296c5edf30.webp

small_959923725e78450d61b1ef323596be4296c5edf30.webp

thumbnail_959923725e78450d61b1ef323596be4296c5edf30.webp

959923725e78450d61b1ef323596be4296c5edf30.webp

Power of AI in your hands with AiBoost®!

MLOps

AutoML

Explainable AI (XAI)

AiBoost® : A toolkit for the 21st century engineers.


## Problem Statement

Record demand for commercial aircrafts (prior to the pandemic and hopefully the demand will resume shortly) had led to huge backlog of orders (greater than 7 years in case of single aisle aircrafts). This had resulted into pressure to ramp up the production rate and reduce the delivery lead times.

However, simultaneously, aerospace manufacturers were also faced with a challenge to reduce the energy consumption at their facilities. This was a result of  commitment towards net zero emissions and increasing industrial sustainability.

Combination of the above two factors had led to the need for investigating novel methods for identifying opportunities that could lead to reduction in energy consumption whilst meeting the business objective of increasing production rate at high quality.

We developed an Artificial Intelligence solution to identify novel opportunities to reduce carbon foot print in high volume manufacturing environment.

Some of the salient features of our solution are as below.

## Solution Main Activities

- Manufacturing process parameters data was captured for drilling operations 
- Corresponding energy consumption data captured
- Performed data pre-processing and visualisation, feature engineering and subsequent down selection
- Development, evaluation and down selection of various supervised machine learning models

## Key Achievements

- Key parameters driving increased energy consumption were identified.
- Revised machine routing and parameter fine tuning led to reduced energy consumption, whilst still delivering the necessary quality and production rate.
- Energy consumption was reduced by 5% - a huge impact for an initial assessment.
- Spread awareness about benefits of data analytics techniques applicable to shop floor environment
- Promoted a culture for data curation and data harvesting within the business

large_2a.Improve-Industrial-Energy-Efficiency-With-Artificial-Intelligence(Build).jpg

medium_2a.Improve-Industrial-Energy-Efficiency-With-Artificial-Intelligence(Build).jpg

small_2a.Improve-Industrial-Energy-Efficiency-With-Artificial-Intelligence(Build).jpg

thumbnail_2a.Improve-Industrial-Energy-Efficiency-With-Artificial-Intelligence(Build).jpg

2a.Improve-Industrial-Energy-Efficiency-With-Artificial-Intelligence(Build).jpg

Boost industrial energy efficiency & sustainability

Recruitment

Boost energy efficiency and sustainability with AiBoost

Energy-Efficiency.mp4

## Problem Statement

At a large aircraft manufacturing company, during Wing assembly stages, small gaps were seen between the interfacing components. These gaps had to be filled by a manual ‘overhead operation’ called Shimming. This operation was a significant disruption to enable the desired ramp rate and increased the manufacturing costs. Hence the objective of this activity was to understand the root cause leading to gapping and extract non-intuitive insights to reduce shimming process.

## Solution Main Activities

- Collected key product characteristics data for all the interfacing components (i.e. Wing Covers, Ribs etc.), Jig calibration data and Wing deflection
- Combined previously isolated ‘historical data set’ with the corresponding ‘events in real life’ i.e. gaping during assembly
- Developed supervised machine learning algorithm to identify the root cause characteristics leading to gaping

## Key Achievements

- Predictive data analytics that enabled the aircraft manufacturer to reduce and eliminate cost of non-quality i.e. reduce amount of gap-filling per wing assembly and enable production ramp up
- Prediction algorithm predicting gap filling cases with 95 % accuracy to enable accurate workforce deployment planning
- Spread awareness about benefits of data analytics techniques applicable to shop floor environment
- Promote a culture for data curation and data harvesting within the business

large_3b.Reduce-Asset-Reduce-Downtime-With-Predictive-Maintenance(Operate).jpg

medium_3b.Reduce-Asset-Reduce-Downtime-With-Predictive-Maintenance(Operate).jpg

small_3b.Reduce-Asset-Reduce-Downtime-With-Predictive-Maintenance(Operate).jpg

thumbnail_3b.Reduce-Asset-Reduce-Downtime-With-Predictive-Maintenance(Operate).jpg

3b.Reduce-Asset-Reduce-Downtime-With-Predictive-Maintenance(Operate).jpg

Boost manufacturing productivity with AiBoost®

Root Cause Analysis with AI

## Problem Statement

At a large aircraft manufacturing company, during robotic drilling and Wing assembly operation, key product characteristics were measured only at predefined intervals to reduce cycle time. However, any anomaly detected by this approach was 'reactive to the event' and the production had to be halted till solution to fix anomaly was identified and implemented. Hence a more comprehensive, automated and proactive quality inspection process was required to predict and prevent production line disturbance.

## Solution

We employed a holistic approach of tracking and processing every aspect of manufacturing process (IoT data). Supervised machine learning algorithm was developed to deduce insights by correlating historical manufacturing key process characteristics (IoT process data) with corresponding key product characteristics (inspection data). The algorithm was then able to detect anomalies and make proactive predictions about the product characteristics.


## Key Achievements

- Fast and easy analysis of IoT and metrology data by manufacturing engineers.
- The machine learning model highlighted the specific manufacturing parameters driving quality issues.
- Prescriptive analysis highlighted parameters resulted in 10% reduction in the cost of quality.
- The results were achieved with in 4 weeks (rather than 6 months) by involving lean six sigma practitioners rather than expensive data scientist.
- Promoted a culture of data curation and data harvesting within the business.
- Reduced/eliminating inspection step.
- Improved yield and production efficiency.

large_3a.Maximize-Asset-Utilization-With-Predictive-Maintenance(Operate).jpg

medium_3a.Maximize-Asset-Utilization-With-Predictive-Maintenance(Operate).jpg

small_3a.Maximize-Asset-Utilization-With-Predictive-Maintenance(Operate).jpg

thumbnail_3a.Maximize-Asset-Utilization-With-Predictive-Maintenance(Operate).jpg

3a.Maximize-Asset-Utilization-With-Predictive-Maintenance(Operate).jpg

Industrial Inspection with AI

Intellium AI

logo.svg

favicon.svg

Login

We are a small passionate team, always trying to learn and adapt to new technologies.

Careers