SENSYCUT- Sensor Enabled Systems for Precision Cutting
Lead Research Organisation:
University of Bath
Department Name: Mechanical Engineering
Abstract
UK is the world's 9th largest manufacturing country [1]. Machining is one of the most used processes for producing precision parts used in aerospace and automotive industries. The demand for high performance and quality assured parts requires high precision, often over a large scale resulting in increased manufacturing costs. It has become a rule of thumb that precise machines with stiff structures and large foot prints are required for machining precision parts. As a consequence, machining costs grow exponentially as the precision increases. This has resulted in the development of expensive and non-value adding off-line verification and error compensation methods. However, these methods do not take the impact of cutting tool/workpiece geometry, cutting forces and time variable errors into account. The uptake of additive manufacturing has also resulted in generation of optimised parts often with complex geometries and thin and high walls which require finish machining with long slender tools. In these scenarios, cutting forces can bend the tool and the workpiece resulting in geometrical inaccuracies. Fluctuating cutting forces result in chatter leading to damaged surface integrity and short tool life.
Using new sensors, advanced signal processing and intelligent control systems can provide the ability to detect geometrical and surface anomalies when machining, and provide data to generate strategies to prevent costly mistakes and poor quality. However, off-the-shelf sensors and data transmission devices are not necessarily suitable for monitoring and controlling machining processes. Existing high precision sensors are either too large or too expensive making them only useful for laboratory applications. Conventional statistical and process control methods cannot cope with high data sampling rates required in machining.
The proposed research will realise low-cost sensors with nano scale resolution specific to machining, tools and intelligent control methods for precision machining of large parts by detecting and preventing anomalies during machining to ensure high precision part manufacture and prevent scrap production.
[1] Rhodes, C., 2018, Briefing Paper No. 05809, Manufacturing: International comparisons, House of Commons Library.
Using new sensors, advanced signal processing and intelligent control systems can provide the ability to detect geometrical and surface anomalies when machining, and provide data to generate strategies to prevent costly mistakes and poor quality. However, off-the-shelf sensors and data transmission devices are not necessarily suitable for monitoring and controlling machining processes. Existing high precision sensors are either too large or too expensive making them only useful for laboratory applications. Conventional statistical and process control methods cannot cope with high data sampling rates required in machining.
The proposed research will realise low-cost sensors with nano scale resolution specific to machining, tools and intelligent control methods for precision machining of large parts by detecting and preventing anomalies during machining to ensure high precision part manufacture and prevent scrap production.
[1] Rhodes, C., 2018, Briefing Paper No. 05809, Manufacturing: International comparisons, House of Commons Library.
Organisations
- University of Bath (Lead Research Organisation)
- Czech Technical University in Prague (Collaboration)
- University of Kentucky (Collaboration)
- University of Tennessee (Collaboration)
- McGill University (Collaboration)
- Chemnitz University of Technology (Collaboration)
- TechSolve (Collaboration)
- All British Precision Ltd (Project Partner)
- Nikken UK (Project Partner)
- Renishaw PLC (Project Partner)
- Sandvik Coromant UK Ltd (Project Partner)
- GKN AEROSPACE SERVICES LIMITED (Project Partner)
- The Welding Institute (Project Partner)
Publications
Axinte D
(2022)
What micro-mechanical testing can reveal about machining processes
in International Journal of Machine Tools and Manufacture
Dogan H
(2023)
Investigation of chatter detection with sensor-integrated tool holders based on strain measurement
in Procedia CIRP
Dogan H
(2023)
Towards Sustainable and Intelligent Machining: Energy Footprint and Tool Condition Monitoring for Media-Assisted Processes
in Journal of Machine Engineering
Ghadbeigi H
(2024)
An analytical power-based approach to predict orthogonal cutting force for sintered Al2124/SiC metal matrix composite
in CIRP Annals
Jamshidi H
(2023)
A Finite Element Assessment of The Workpiece Plastic Deformation in Machining of Ti-6Al-4V
in Procedia CIRP
Liao Z
(2024)
Review of current best-practices in machinability evaluation and understanding for improving machining performance
in CIRP Journal of Manufacturing Science and Technology
Malakizadi A
(2022)
Recent advances in modelling and simulation of surface integrity in machining - a review
in Procedia CIRP
Mypati O
(2024)
Chip Morphology Prediction in Inconel 718 Milling through Machine Learning to Control Surface Integrity
in Procedia CIRP
| Description | The project is on track to meet the objectives of the SENSYCUT. These include a sensor integrated system consisting of multiple high end sensors for monitoring of machining systems for producing defect free parts. New methods have been designed, developed and tested for early detection of tool wear to prevent damage to high value precision parts. A new sensory system has been designed and is being developed. |
| Exploitation Route | Further application for research funding to investigate the new findings. Further industry-academia funding to transfer the technologies and learnings from this project to industrial applications. Potential for spin offs or licensing the IP generated after protection. |
| Sectors | Environment Manufacturing including Industrial Biotechology |
| Description | Twinning IZTECH in Robotics Manufacturing Systems (TWIN-IT-ROMANS) |
| Amount | £107,079 (GBP) |
| Funding ID | 10130829 |
| Organisation | United Kingdom Research and Innovation |
| Sector | Public |
| Country | United Kingdom |
| Start | 08/2024 |
| End | 09/2027 |
| Title | Tool wear, cutting forces and vibrations |
| Description | This is a dataset of various sensor signals (forces, vibrations, surface roughness, acoustic emissions) from machining experiments whilst monitoring the tool condition. |
| Type Of Material | Database/Collection of data |
| Year Produced | 2024 |
| Provided To Others? | No |
| Impact | Generating machining databases where various machining parameters are monitored is very time consuming and costly. These datasets are valuable for training and validating various data-driven models such as deep learning. |
| Description | Integrated Machining Performance for Assessment of Cutting Tools (IMPACT) |
| Organisation | Chemnitz University of Technology |
| Country | Germany |
| Sector | Academic/University |
| PI Contribution | The IMPACT is an initiative by Prof I.S. Jawahir born out of the International Academy of Production Engineers where four of the SENSYCUT investigators are members of and is divided into 5 topics. The SENSYCUT research team took leadership of three of the research topics in this collaboration: i) Design and development of smart tooling/sensors for closed-loop adaptive machining, ii) best-practices in machinability evaluation and industrial knowledge and iii) AI-based multi-objective optimization of total machining performance. This involved performing three state of the art reviews and a round robin test to benchmark and compare the performance of various sensors used for monitoring machining using different setups and machines in various laboratories across the world. The knowledge generated enables us to understand how the data used for training on a machine tool can be transferred to other machines and setups. |
| Collaborator Contribution | Project partners supported the development of the state of the art review papers, brought in different perspectives from across the world and contributed to the round robin tests. Additionally, two of the other topics were led by the partners. Topic E was co-led by SENSYCUT research team and researchers from the University of Chemnitz. |
| Impact | https://doi.org/10.1016/j.cirpj.2024.01.012 https://doi.org/10.1016/j.cirpj.2024.02.008 https://doi.org/10.1016/j.cirpj.2024.05.001 3 technical presentations |
| Start Year | 2021 |
| Description | Integrated Machining Performance for Assessment of Cutting Tools (IMPACT) |
| Organisation | Czech Technical University in Prague |
| Country | Czech Republic |
| Sector | Academic/University |
| PI Contribution | The IMPACT is an initiative by Prof I.S. Jawahir born out of the International Academy of Production Engineers where four of the SENSYCUT investigators are members of and is divided into 5 topics. The SENSYCUT research team took leadership of three of the research topics in this collaboration: i) Design and development of smart tooling/sensors for closed-loop adaptive machining, ii) best-practices in machinability evaluation and industrial knowledge and iii) AI-based multi-objective optimization of total machining performance. This involved performing three state of the art reviews and a round robin test to benchmark and compare the performance of various sensors used for monitoring machining using different setups and machines in various laboratories across the world. The knowledge generated enables us to understand how the data used for training on a machine tool can be transferred to other machines and setups. |
| Collaborator Contribution | Project partners supported the development of the state of the art review papers, brought in different perspectives from across the world and contributed to the round robin tests. Additionally, two of the other topics were led by the partners. Topic E was co-led by SENSYCUT research team and researchers from the University of Chemnitz. |
| Impact | https://doi.org/10.1016/j.cirpj.2024.01.012 https://doi.org/10.1016/j.cirpj.2024.02.008 https://doi.org/10.1016/j.cirpj.2024.05.001 3 technical presentations |
| Start Year | 2021 |
| Description | Integrated Machining Performance for Assessment of Cutting Tools (IMPACT) |
| Organisation | McGill University |
| Country | Canada |
| Sector | Academic/University |
| PI Contribution | The IMPACT is an initiative by Prof I.S. Jawahir born out of the International Academy of Production Engineers where four of the SENSYCUT investigators are members of and is divided into 5 topics. The SENSYCUT research team took leadership of three of the research topics in this collaboration: i) Design and development of smart tooling/sensors for closed-loop adaptive machining, ii) best-practices in machinability evaluation and industrial knowledge and iii) AI-based multi-objective optimization of total machining performance. This involved performing three state of the art reviews and a round robin test to benchmark and compare the performance of various sensors used for monitoring machining using different setups and machines in various laboratories across the world. The knowledge generated enables us to understand how the data used for training on a machine tool can be transferred to other machines and setups. |
| Collaborator Contribution | Project partners supported the development of the state of the art review papers, brought in different perspectives from across the world and contributed to the round robin tests. Additionally, two of the other topics were led by the partners. Topic E was co-led by SENSYCUT research team and researchers from the University of Chemnitz. |
| Impact | https://doi.org/10.1016/j.cirpj.2024.01.012 https://doi.org/10.1016/j.cirpj.2024.02.008 https://doi.org/10.1016/j.cirpj.2024.05.001 3 technical presentations |
| Start Year | 2021 |
| Description | Integrated Machining Performance for Assessment of Cutting Tools (IMPACT) |
| Organisation | TechSolve |
| Country | United States |
| Sector | Private |
| PI Contribution | The IMPACT is an initiative by Prof I.S. Jawahir born out of the International Academy of Production Engineers where four of the SENSYCUT investigators are members of and is divided into 5 topics. The SENSYCUT research team took leadership of three of the research topics in this collaboration: i) Design and development of smart tooling/sensors for closed-loop adaptive machining, ii) best-practices in machinability evaluation and industrial knowledge and iii) AI-based multi-objective optimization of total machining performance. This involved performing three state of the art reviews and a round robin test to benchmark and compare the performance of various sensors used for monitoring machining using different setups and machines in various laboratories across the world. The knowledge generated enables us to understand how the data used for training on a machine tool can be transferred to other machines and setups. |
| Collaborator Contribution | Project partners supported the development of the state of the art review papers, brought in different perspectives from across the world and contributed to the round robin tests. Additionally, two of the other topics were led by the partners. Topic E was co-led by SENSYCUT research team and researchers from the University of Chemnitz. |
| Impact | https://doi.org/10.1016/j.cirpj.2024.01.012 https://doi.org/10.1016/j.cirpj.2024.02.008 https://doi.org/10.1016/j.cirpj.2024.05.001 3 technical presentations |
| Start Year | 2021 |
| Description | Integrated Machining Performance for Assessment of Cutting Tools (IMPACT) |
| Organisation | University of Kentucky |
| Country | United States |
| Sector | Academic/University |
| PI Contribution | The IMPACT is an initiative by Prof I.S. Jawahir born out of the International Academy of Production Engineers where four of the SENSYCUT investigators are members of and is divided into 5 topics. The SENSYCUT research team took leadership of three of the research topics in this collaboration: i) Design and development of smart tooling/sensors for closed-loop adaptive machining, ii) best-practices in machinability evaluation and industrial knowledge and iii) AI-based multi-objective optimization of total machining performance. This involved performing three state of the art reviews and a round robin test to benchmark and compare the performance of various sensors used for monitoring machining using different setups and machines in various laboratories across the world. The knowledge generated enables us to understand how the data used for training on a machine tool can be transferred to other machines and setups. |
| Collaborator Contribution | Project partners supported the development of the state of the art review papers, brought in different perspectives from across the world and contributed to the round robin tests. Additionally, two of the other topics were led by the partners. Topic E was co-led by SENSYCUT research team and researchers from the University of Chemnitz. |
| Impact | https://doi.org/10.1016/j.cirpj.2024.01.012 https://doi.org/10.1016/j.cirpj.2024.02.008 https://doi.org/10.1016/j.cirpj.2024.05.001 3 technical presentations |
| Start Year | 2021 |
| Description | Integrated Machining Performance for Assessment of Cutting Tools (IMPACT) |
| Organisation | University of Tennessee |
| Country | United States |
| Sector | Academic/University |
| PI Contribution | The IMPACT is an initiative by Prof I.S. Jawahir born out of the International Academy of Production Engineers where four of the SENSYCUT investigators are members of and is divided into 5 topics. The SENSYCUT research team took leadership of three of the research topics in this collaboration: i) Design and development of smart tooling/sensors for closed-loop adaptive machining, ii) best-practices in machinability evaluation and industrial knowledge and iii) AI-based multi-objective optimization of total machining performance. This involved performing three state of the art reviews and a round robin test to benchmark and compare the performance of various sensors used for monitoring machining using different setups and machines in various laboratories across the world. The knowledge generated enables us to understand how the data used for training on a machine tool can be transferred to other machines and setups. |
| Collaborator Contribution | Project partners supported the development of the state of the art review papers, brought in different perspectives from across the world and contributed to the round robin tests. Additionally, two of the other topics were led by the partners. Topic E was co-led by SENSYCUT research team and researchers from the University of Chemnitz. |
| Impact | https://doi.org/10.1016/j.cirpj.2024.01.012 https://doi.org/10.1016/j.cirpj.2024.02.008 https://doi.org/10.1016/j.cirpj.2024.05.001 3 technical presentations |
| Start Year | 2021 |
| Title | SENSYCUT tool condition monitoring |
| Description | SENSYCUT tool wear condition monitoring is a deep learning model that uses SENSYCUT sensor signals to detect and predict cutting tool condition during machining. |
| Type Of Technology | Software |
| Year Produced | 2025 |
| Impact | Cutting tools are made of critical raw materials (CRM) such as cobalt and tungsten. Typically, 30-50% of the cutting tools remaining useful life is wasted as a result of changing them early prior to reaching their tool life criterion. Using the SENSYCUT tool condition monitoring system, tool utilisation can be increased to as much as 95% significantly reducing CRM consumption for tooling as well as the associated tooling costs for production. |
| Description | Smallpeice Summer School |
| Form Of Engagement Activity | Participation in an open day or visit at my research institution |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Schools |
| Results and Impact | A group of 50 widening participation (WP) pupils from across the country visited the Sustainable and Intelligent Manufacturing research group at the University of Bath. The visit was part of the lectures and tours given to a summer school organised by colleagues at the University of Bath with a charity called the Smallpeice Trust. The SENSYCUT research team demonstrated the technologies that we are developing and explained the research that we are doing in SENSYCUT. Additionally, the team explained why the research matters in the industrial context and the wider environmental and economical impact that it can have. |
| Year(s) Of Engagement Activity | 2023,2024 |
| Description | Tour of advanced manufacturing research group for year 9 pupils |
| Form Of Engagement Activity | Participation in an open day or visit at my research institution |
| Part Of Official Scheme? | No |
| Geographic Reach | Regional |
| Primary Audience | Schools |
| Results and Impact | A group of year 9 pupils from a local secondary school Alderman White visited University of Nottingham Advanced manufacturing research group. It involved discussion about different manufacturing processes and how things are made with the pupils and it raised their interest in knowing more about manufacturing of aerospace parts. |
| Year(s) Of Engagement Activity | 2022,2024 |
