PRESS-NEWS.org - Press Release Distribution
PRESS RELEASES DISTRIBUTION

Process monitoring of P-GMAW-based wire arc direct energy deposition of stainless steels via time-frequency domain analysis and Isolation Forest

2025-11-11
(Press-News.org) Qualification of additively manufactured parts can now be supported by Artificial Intelligence. Researchers have developed a new method to process high-frequency welding data collected from a Wire Arc Direct Energy Deposition process, achieving an improvement in anomaly detection performance from 57% to 85.3%. This demonstrates the potential of AI in this field. Published in Advanced Manufacturing, the proposed methodology has the potential to reduce both the time and cost associated with AM production, ultimately lowering overall product costs.

Additive manufacturing (AM) today enables the production of components that are difficult or even impossible to fabricate using traditional technologies. It also helps reduce scrap rates (generally referred to as the buy-to-fly ratio) and the environmental impact associated with each part’s production. However, due to the complex physical phenomena involved, AM parts are often more prone to defects, leading to scrap, financial losses for companies, and increased production costs per part. For this reason, every AM product, particularly those intended for structural or safety-critical applications in metals, must undergo certification through non-destructive testing (NDT) equipment. However, these procedures are typically performed on random samples and are time-consuming. To address this issue, Dr Giulio Mattera from the University of Naples “Federico II” (Italy) and his colleagues, and Professor Zengxi Pan from the University of Wollongong (Australia) have developed a methodology that employs Artificial Intelligence to streamline the certification process, with potential benefits in terms of both cost reduction and product quality improvement.

“Data exhibit complex structures and relationships, especially in welding-based technologies,” explains Dr Mattera. “Therefore, a more sophisticated analysis of the data, enabled by the combination of advanced data analytics tools and Artificial Intelligence, can outperform traditional methods based on simple statistical descriptors such as the mean and variance of the process.”

The newly developed approach processes welding current and voltage data collected at high frequencies, above 5,000 samples per second, to extract information from both the time and frequency domains. This allows for the capture of not only the statistical descriptors of these process variables but also the structural patterns underlying their repetitive nature.

As Dr Mattera emphasises, “A stable welding process, such as the Wire Arc Direct Energy Deposition process, is characterised by the repetition of similar waveforms in both welding current and voltage, which are directly associated with the melting and deposition of the filler wire in the component.” For the research team, by jointly analysing information from both domains, it becomes possible to better assess process stability and identify any anomalous conditions that may be linked to defects, thereby preventing quality degradation.

“Another key innovation of this work lies in the minimal prior knowledge required to replicate the methodology across different industrial systems,” explains Dr Mattera. “Unlike conventional AI models that demand extensive datasets containing both good and defective samples, our approach only needs data from non-defective conditions. This drastically cuts down the time and cost of data collection. The model then learns to recognise normal behaviour and automatically flags any anomalies, effectively detecting defects without ever having seen one.”

The researchers carried out a series of experiments in which they varied several process parameters to collect data from high-quality deposition conditions. They then trained an AI model - specifically, an algorithm known as Isolation Forest - to learn the map of normal behaviour within the data. When tested, the algorithm successfully identified anomalous conditions and assessed the component’s quality. In one case, it detected irregularities that indicated the need to clean the welding torch nozzle during production, preventing the formation of defects such as porosity in the metal part. Such defects, if left unchecked, could compromise the mechanical properties of the final product.

“By comparing the proposed methodology with traditional Statistical Process Monitoring (SPM) techniques, we found that our method was able to detect anomalous conditions that conventional approaches could not,” said Dr Mattera. “This shows that current in-process monitoring techniques are effective at identifying extreme conditions but are not suitable for preventive analysis, where the system is monitored and maintained before a defect occurs.”

In the study, traditional Statistical Process Monitoring methods struggled to detect irregularities. The results showed that the SPM approach correctly identified only 43 anomalies, while 105 were missed or misclassified as normal. By contrast, the proposed AI-based method performed far better, correctly identifying 116 anomalies and missing just 32, demonstrating its much greater accuracy in spotting potential defects.

“The results of this study are very encouraging. We’re putting significant effort into this line of research to provide industry with new tools and to demonstrate their potential impact for both manufacturers and end users,” concluded Dr Mattera. “I would like to thank the entire research team for their work over the years, as well as our industrial partners for their continued support.”

He added, “Despite the promising results, our next step is to refine the methodology and turn it into a practical tool for manufacturing. We are working on adding features such as explainability and quality index estimation, which will make it more intuitive and easier for humans to interact and collaborate with intelligent machines.”

Dr Mattera and his co-authors acknowledge this as an important step toward integrating AI into manufacturing for quality improvement. However, they note that further regulatory and legal developments will be essential for real industrial adoption. “In the meantime,” Dr Mattera concluded, “we’re pushing the research forward to make these tools ready and to help mature this field for industrial use.”

This paper ”Process monitoring of P-GMAW-based wire arc direct energy deposition of stainless steels via time-frequency domain analysis and Isolation Forest” was published in Advanced Manufacturing.
Mattera G, Manoli E, Pan Z, and Nele L. Process monitoring of P-GMAW-based wire arc direct energy deposition of stainless steels via time-frequency domain analysis and Isolation Forest. Adv. Manuf. 2025(2):0010, https://doi.org/10.55092/am20250010. 

END



ELSE PRESS RELEASES FROM THIS DATE:

The 4th International Conference on Green Building, Civil Engineering and Smart City (GBCESC 2025)

2025-11-11
With the development of science and technology, green technology and various advanced information technology have been utilized to make cities more and more low-carbon, intelligent and ecological.  Cities can operate more efficiently and the life quality of urban residents can be improved as civil construction, city planning, management and services developed. GBCESC 2025 aims to offer research scholars and engineers a platform for the interchange of cutting-edge technological achievements.  During ...

Omni-modal language models: Paving the way toward artificial general intelligence

2025-11-11
The survey “A Survey on Omni-Modal Language Models” offers a systematic overview of the technological evolution, structural design, and performance evaluation of omni-modal language models (OMLMs). The work highlights how OMLMs enable unified perception, reasoning, and generation across modalities, contributing to the ongoing progress toward Artificial General Intelligence (AGI). Recently, Lu Chen, a master’s student at the School of Computer and Artificial Intelligence, Shandong Jianzhu University, in collaboration with Dr. Zheyun ...

Fractal-based metamaterial improves sound fields in car cabins

2025-11-11
WASHINGTON, Nov. 11, 2025 — Car enthusiasts will pay hundreds of dollars for stereo systems that will improve the sound quality in their cars. However, the inherent directionality of speakers and complex shapes of car cabins can exacerbate sound disparities between the drivers and passengers, no matter how advanced a speaker system. In the Journal of Applied Physics, by AIP Publishing, researchers from a collaboration of institutions in China created a prototype using a fractal to mitigate the sound differences. Fractals are unique shapes that can be split into infinitely smaller ...

Maternity care access and infant mortality

2025-11-11
About The Study: In this population-based cross-sectional study, infant mortality risk was inversely associated with county-level access to maternity care, with the highest risk in counties with no access. When examined by race and ethnicity, differences in mortality risk between living in a full access and no access county were observed among white infants only, indicating that unmeasured barriers may limit the protective effect of access for some racial and ethnic groups.  Corresponding Author: To contact the corresponding author, Ripley Lucas, MPH, email RLucas@marchofdimes.org. To ...

Self-administered hypnosis vs sham hypnosis for hot flashes

2025-11-11
About The Study: In this randomized clinical trial, the clinical hypnosis group experienced significantly greater reductions of hot flash scores and daily interference from hot flashes compared with the active control condition at week 6. This study suggests that hypnosis delivered through self-administered audio files is a clinically significant and effective method to reduce hot flashes in postmenopausal women.  Corresponding Author: To contact the corresponding author, Gary Elkins, PhD, email gary_elkins@baylor.edu. To ...

Chatting with your cells

2025-11-11
(Vienna, 11 November 2025) Using sophisticated RNA sequencing technology, biomedical researchers can measure the activity of our genes across millions of single cells, creating detailed maps of tissues, organs, and diseases. Analysing these datasets requires a rare combination of skills: deep understanding of the biology, and the ability to develop computer code that turns data into insights. What if we could equip biomedical researchers with an AI assistant that sees the data, supports the analysis, ...

Genetic testing trifecta predicts risk of sudden cardiac death and arrhythmia

2025-11-11
Novel study used whole genome sequencing to combine monogenetic and polygenetic testing, which are often siloed in research and practice More physicians should order genetic testing but much of the workforce isn’t trained in it Findings lay the groundwork for developing targeted therapies  CHICAGO --- In a new Northwestern Medicine study, scientists have developed a more precise genetic risk score to determine whether a person is likely to develop arrhythmia, an irregular heartbeat that ...

Moving past the mouse – genetic advances inspire new frontiers

2025-11-11
Recent epic leaps in genetics have created a biodiversity library. As the genetic make-up of animals, plants, fungi, bacteria, and viruses has been mapped, researchers racing to develop solutions to today’s global challenges run into a question: Why be limited to a mouse? Electric eels, octopi, birds, sponges, and plastic-gobbling bacteria are amongst the new stages on which discovery is unfolding. The challenge is to refine the theater to optimize performance. In today’s Nature Reviews Biodiversity, Michigan State University evolutionary biologist Jason Gallant presses a case for research – from classrooms and laboratories to funding agencies ...

Exercise and L-BAIBA supplement boost muscle and bone health in aging mice

2025-11-11
“These findings suggest a physiological interaction between exercise and L-BAIBA supplementation to improve soleus muscle and bone properties and reduce bone marrow adiposity.” BUFFALO, NY — November 11, 2025 — A new research paper was published in Volume 17, Issue 10 of Aging-US on October 1, 2025, titled “L-β-aminoisobutyric acid (L-BAIBA) in combination with voluntary wheel running exercise enhances musculoskeletal properties in middle-age male mice.” In this study led by first author ...

Designation of JMIR Bioinformatics and Biotechnology as official society journal elevates visibility for MidSouth researchers

2025-11-11
(Toronto and Little Rock, November 11, 2025)  JMIR Publications, a premier open access publisher of digital health research, and The MidSouth Computational Biology and Bioinformatics Society (MCBIOS), a leading professional organization for computational biology and bioinformatics, today announced a strategic, long-term partnership. This agreement formally designates JMIR Bioinformatics and Biotechnology as the official journal of MCBIOS. This landmark Memorandum of Understanding (MOU) creates a stable, high-impact venue for MCBIOS members to publish their research, particularly the output from the Society's annual conference. Both organizations are now ...

LAST 30 PRESS RELEASES:

PolyU research drives commercialization of energy-efficient solar cell technology towards 40% efficiency milestone

New NIH-funded Johns Hopkins Medicine study finds high-risk individuals who have mild dilatation of the pancreatic duct have increased risk for pancreatic cancer

Mapping metabolic dysfunction-associated steatotic liver disease models of care across 17 Middle East and North Africa countries: Insights into guidelines, infrastructure, and referral systems

Process monitoring of P-GMAW-based wire arc direct energy deposition of stainless steels via time-frequency domain analysis and Isolation Forest

The 4th International Conference on Green Building, Civil Engineering and Smart City (GBCESC 2025)

Omni-modal language models: Paving the way toward artificial general intelligence

Fractal-based metamaterial improves sound fields in car cabins

Maternity care access and infant mortality

Self-administered hypnosis vs sham hypnosis for hot flashes

Chatting with your cells

Genetic testing trifecta predicts risk of sudden cardiac death and arrhythmia

Moving past the mouse – genetic advances inspire new frontiers

Exercise and L-BAIBA supplement boost muscle and bone health in aging mice

Designation of JMIR Bioinformatics and Biotechnology as official society journal elevates visibility for MidSouth researchers

Brain activity goes to extremes in soccer fans

AI-based analysis of CT scans taken for many reasons may also reveal weakened bones

SwRI expands Metering Research Facility capabilities for hydrogen research and testing

Widely cited stat on global water and food security ‘hearsay’ and fragile for policymaking

Forever chemicals affect the genes of unhatched ducklings

American Pediatric Society announces election of 2026 members

A fix for frost: Engineers use electricity to zap ice without heat or chemicals

The growing crisis of chronic disease in animals

Clinical characteristics and outcomes of portal vein thrombosis in patients with porto-sinusoidal vascular disease

Two major irrigation statistics may be wrong

A ubiquitous architectural pattern in nature

The first four years of PNAS Nexus

Research alert: GLP-1 drugs linked to dramatically lower death rates in colon cancer patients

VR headsets may make dry eye less likely: World's first time-course observation during a VR session

CASIA-EXO: A novel exoskeleton for adaptive motor learning in post-stroke rehabilitation

Topology-aware deep learning model enhances EEG-based motor imagery decoding

[Press-News.org] Process monitoring of P-GMAW-based wire arc direct energy deposition of stainless steels via time-frequency domain analysis and Isolation Forest