Utilising the power of AI in Thermal Spray coatings
- May 15, 2024
Introduction
The combination of Artificial Intelligence (AI) and conventional manufacturing processes pave the way for new possibilities for efficiency and precision in the dynamic field of industrial innovation, helping companies make smarter decisions and adapt to changing market demands. Businesses may improve supply chain management, forecast maintenance requirements, streamline workflows, and maintain quality standards by combining AI’s data-driven insights with conventional manufacturing techniques. AI and traditional manufacturing are collaborating to develop flexible, responsive production systems that can grow in a constantly evolving technical and commercial landscape, rather than just increasing productivity. CoBRAIN exploits this technological synergy, aiming to offer sustainable thermal spray coatings suitable and specialised for each end-user from different industrial sectors.
Thermal Spray (TS) Coatings
Thermal Spray (TS) coatings have been thoroughly presented in a previous CoBRAIN blog article. In general, TS coatings offer improved surface qualities like wear resistance, corrosion protection, and thermal insulation, making them essential in a wide range of industries, including aerospace and automotive. Traditionally, the optimisation of these coatings relies heavily on empirical methods and manual adjustments, often leading to suboptimal results and increased production costs (Rogachev, 2020).

The Role of Artificial Intelligence (AI) in TS coatings
In the field of thermal spray coatings, Artificial Intelligence (AI) serves as a transformative force, reshaping traditional methodologies into data-driven, adaptive processes. Through machine learning algorithms, AI can analyse performance data, environmental variables, material properties, and equipment specifications to identify the optimal parameters during the coating process. This predictive capability empowers engineers and technicians to effectively adjust parameters such as spray distance, gas flow rates, and substrate temperatures to achieve desired coating characteristics with high accuracy.
Furthermore, AI facilitates real-time monitoring and control, enabling continuous feedback loops that dynamically adapt to changing conditions during the coating process. From sensors in the coating equipment, a large amount of data on parameters such as temperature, pressure, and coating thickness are usually collected. AI algorithms swiftly analyse these data, promptly identifying anomalies or deviations from the desired outcome. Automated systems have the ability to instantly adapt in order to preserve process stability and quality, which lowers the probability of errors and increases overall efficiency.
Moreover, AI-driven quality control mechanisms play a vital role in ensuring the integrity of thermal spray coatings. AI systems can inspect coated surfaces with unparalleled precision, detecting imperfections such as cracks, porosity, or unevenness that may compromise performance or longevity. This proactive approach to quality assurance not only minimises the risk of product failures but also streamlines post-coating inspection processes, saving time and resources.
Essentially, a new age of efficiency, reliability, and creativity will be marked by the use of AI with thermal spray coating technologies. By harnessing the power of data analytics, predictive modeling, and real-time control, AI empowers manufacturers to optimise coating processes, enhance product quality, and unlock new possibilities for material design and performance. As AI continues to evolve, its role in numerous industrial applications, such as thermal spray coatings, will offer continuous advancements, in this case, surface engineering and manufacturing (Mahendru, et al., 2023).

CoBRAIN Pushing the Boundaries
CoBRAIN aims to contribute to the field of thermal spray coatings by offering significant advances towards increased production efficiency and sustainability. CoBRAIN being in the centre of this AI-driven shift, combines state-of-the-art AI technology with experimental data to develop the next generation of thermal spray coatings. The partners in CoBRAIN aim to utilise AI in a different way than real-time optimisation and adaptive process control. They are developing mathematical models and utilising Machine Learning (ML) and Deep Learning (DL) algorithms that will be combined to create a Decision Support Tool able to give guidelines for specific Thermal Spray coating applications, on a range of input parameters.
Central to the success of CoBRAIN is its collaborative approach, which fosters knowledge exchange and cross-disciplinary synergy among academic researchers and industrial partners. CoBRAIN guarantees that its research findings are both scientifically and industrially relevant by including stakeholders from a variety of industries, such automotive, energy, and manufacturing. This fosters innovation and competitiveness within the European coatings industry.

Benefits of AI in Thermal Spray Coatings
There are numerous advantages to using AI in thermal spray coatings (Malamousi et al., 2022), (Thakur et al., 2023), (Vasudev et al., 2024):
Optimised Coating Performance: AI’s data analysis makes it easier to find the best material-process combinations and anticipate performance results with accuracy. This allows coatings to be customised for certain requirements, such as durability, corrosion resistance, and thermal insulation. Furthermore, AI continuously improves its recommendations based on data it receives in real-time about coating performance. This guarantees that coating quality and efficacy will continue to improve under a variety of operational scenarios.
Reduced Costs and Waste: AI dynamically optimises coating processes in real time, assuring quality while consuming less material. This goes beyond simply reducing trial-and-error cycles. This flexible strategy reduces waste while optimising resource utilisation, which lowers costs and has long-term benefits. Furthermore, AI-driven predictive maintenance foresees equipment problems, allowing for preemptive interventions to avoid unplanned maintenance and downtime, which lowers operating costs and improves overall efficiency. AI greatly improves coating processes’ ecological and economic aspects through these capabilities.

Enhanced Productivity: AI streamlines manufacturing workflows by reducing manual intervention, guaranteeing consistency in quality, and increasing efficiency in thermal spray coating operations. This simplified method ensures batch output homogeneity while increasing production rates. AI systems also provide real-time feedback and monitoring, enabling operators to quickly correct process irregularities and maximise uptime while minimising downtime. By means of these integrated functions, artificial intelligence (AI) enables smooth operations and ongoing enhancement of coating processes, hence augmenting productivity, and reliability.
Accelerated Innovation: AI’s ability to examine complex relationships between material properties, process factors, and performance criteria speeds up the investigation of new coating formulations and design ideas. The invention cycle is accelerating, which makes it easier to create cutting-edge coatings with improved performance characteristics. Furthermore, AI-powered design optimisation technologies generate and assess several design iterations more quickly and thoroughly than traditional techniques. Researchers might find novel solutions that could go unnoticed otherwise by expanding the breadth of design investigation, which promotes ongoing improvement in coating technology.
In general, many decision support tools have been developed using AI in the manufacturing industry. As AI technology continues to advance, we can expect to see even more innovative tools and applications emerging to help manufacturers improve their operations and stay competitive in the global market.
Conclusions
In modern industries the integration of AI functions as a sophisticated tool that assists in optimising processes, ensuring efficient resource utilisation and environmental sustainability. When combined with thermal spray coating, this synergy opens a whole new chapter for enhancing the strength, durability, and eco-friendliness of manufactured goods.
Projects like CoBRAIN are shining examples of the synergy between innovative thinking and advanced technology. They show us how we can use AI to analyse data and make decisions, making surfaces tougher and more resilient than ever before. The goal of projects like CoBRAIN is more than just cosmetic improvements; it’s an important shift in manufacturing toward techniques that put sustainability and efficiency first.
Therefore, the collaboration between AI and thermal spray coating isn’t merely an upgrade in technology; it signifies a fundamental shift in our approach to production. It’s about innovative techniques that maximise productivity while also encouraging environmental responsibility. And as projects like CoBRAIN lead the way, we are heading toward a time when sustainability and innovation coexist, creating a world in which every product is both smart and durable.
References
Rogachev A., Structure, Stability, and Properties of High-Entropy Alloys, The Physics of Metals and Metallography, 121 (8): 733–764, 2020.
Mahendru P., et. al., Artificial Intelligence Models for Analysing Thermally Sprayed Functional Coatings, Journal of Thermal Spray Technology, 32 (2-3): 388–400, 2023.
Malamousi K., et. al., Digital transformation of thermal and cold spray processes with emphasis on machine learning, Surface and Coatings Technology, 433: 128 -138, 2022.
Thakur L., et. al., Artificial Intelligence and Machine Learning in the Thermal Spray Industry: Practices, Implementation, and Challenges (1st ed.), CRC Press, 2023.
Vasudev H., et. al., Prediction and performance of thermal cladding using artificial intelligence and machine learning: Thermal Claddings for Engineering Applications (1st ed.), CRC Press, 2024.