Key Takeaways & Executive Findings
- •• Proposes a novel NRS-ANFIS method for real-time welding penetration control in GMAW, achieving 87% complete penetration rate without preheating. • Uses Neighborhood Rough Set to reduce weld pool features to minimal set (tail width WT and tail area coefficient CTS), enhancing model simplicity and anti-interference. • Integrates visual sensing, line laser distance, and current data as inputs to ANFIS, enabling dynamic adjustment of welding parameters for time-varying gaps. • Demonstrates uniform backside melting width and consistent weld quality, meeting industrial specifications for structural welds.
Abstract
Owing to process conditions such as uneven clearance of base metal assembly and welding deformation, it is difficult to obtain well-formed structural welds with robot constant specification parameters welding. Determining how to extract a structured, anti-interference, concise, and dynamic knowledge model from measurable data, and then adjust the welding parameters with corresponding control methods in real time is a central problem to be solved in welding formation control. Hence, this paper proposes a welding penetration control method based on a Neighborhood Rough Set-Adaptive Neuro-Fuzzy Inference System (NRS-ANFIS) to achieve effective penetration control for the GMAW welding process. In orthogonal experiments, the NRS algorithm, which is based on visual sensing to obtain the properties of the weld pool and gap changes, is used to reduce the established frontal weld pool feature information decision table, and the minimum feature set of the weld pool tail width WT and the tail area coefficient CTS is obtained. The minimum feature set of the effective frontal weld pool, real-time line laser distance change, and real-time current information are used as the input for the ANFIS control system. The experimental results for the two groups of time-varying gaps demonstrate that under the condition of no preheating of the base metal, the complete welding penetration rate of the adjusted welding process parameters output by the trained ANFIS model reaches 87%, and the backside melting width is uniform and consistent, which meets the welding specification requirements.
1. Introduction
The welding penetration state is an important factor for evaluating welding quality [1]. The welding penetration state can be generally divided into three types: non-penetration, full penetration, and over-penetration, among which full penetration is the ideal penetration state. Full penetration has a deep penetration depth, the back weld does not collapse, and the welded joint has excellent mechanical properties. In the actual welding process, owing to the limitations of the welding environment, the penetration state of the back weld cannot be directly monitored online. An experienced welder judges the penetration by observing the shape and size of the front weld pool according to the continuous practice of welding experience. The penetration depth of the weld is mainly affected by welding current, welding voltage, protective gas flow, and wire feed speed. There are many factors affecting the penetration state of the weld, and this state presents a complex nonlinearity. Establishing an accurate mathematical model of welding penetration is difficult [2].
As a subset of artificial intelligence, machine learning does not require accurate physical modeling and rich expert prior knowledge [3], and a rough set (RS) is an important machine learning method that is used as a mathematical tool for dealing with uncertainty [4]. After Professor Pawlak [5] proposed the rough set theory in 1982, it became particularly suitable for data mining, decision analysis, machine learning, and knowledge discovery. Rough sets have been applied to knowledge modeling in the welding field [6–8], structural deformation prediction [9], and welding defect recognition [10], and it also successfully confirmed that the rough set method has a good effect in dealing with complex and diverse uncertain data in the welding process. The development of neural network technology in recent years has also provided a feasible reference method to achieve welding penetration control. Yu et al. [11] established a monocular visual sensing system to accurately predict the penetration depth in real time, extracted the key two-dimensional visual features in the welding process as input, and established a real-time prediction model of the penetration mode and depth based on a support vector machine (SVM) and a BP neural network. Baek et al. [12] collected the front image of a weld pool based on a visual sensor, first used a residual neural network to perform semantic segmentation on the weld pool image to extract the accurate features.
Loading authentic research manuscript (Pages 1–5)...
Xiaohong Xiang, Zhiqiang Feng, Naiwen Fang, Daidi Zhao, Yuefei Wang (2025). An Approach to Welding Penetration Control with Neighborhood Rough Set and ANFIS. Chinese Journal of Mechanical Engineering. https://doi.org/10.1186/s10033-025-01215-9
Research & Educational Purpose Only:The translations, structured abstracts, analytical annotations, and data reports provided by SinoTechIntel are intended exclusively for academic research, internal corporate R&D, and educational benchmarking. They do not constitute formal engineering, chemical safety, legal, or professional advice.
Copyright & Intellectual Property Notice: Original copyright of the underlying source articles and experimental data remains with the respective authors, institutions, and original publishing journals. SinoTechIntel claims intellectual property only over its proprietary translations, analytical syntheses, and AEO structured enhancements in accordance with international fair use and academic citation principles.
Frequently Asked Questions
What is the main contribution of this paper?
The paper proposes a novel welding penetration control method combining Neighborhood Rough Set (NRS) and Adaptive Neuro-Fuzzy Inference System (ANFIS) to achieve effective real-time control in GMAW welding, achieving 87% complete penetration rate without preheating.
How does the NRS algorithm help in welding penetration control?
NRS reduces the frontal weld pool feature information to a minimal set (tail width WT and tail area coefficient CTS), which simplifies the model and improves anti-interference, making the control system more concise and dynamic.
What inputs are used for the ANFIS control system?
The ANFIS control system uses the minimum feature set of the effective frontal weld pool, real-time line laser distance change, and real-time current information as inputs.
What are the experimental results of the proposed method?
In experiments with two groups of time-varying gaps, the proposed method achieved an 87% complete welding penetration rate without preheating, with uniform and consistent backside melting width, meeting welding specification requirements.
Why is welding penetration control challenging?
Welding penetration is affected by many factors such as welding current, voltage, gas flow, and wire feed speed, and exhibits complex nonlinearity. Additionally, the back weld penetration state cannot be directly monitored online, making accurate modeling difficult.
Related Technical Papers & Translations
Direct Repair of the Crystal Structure and Coating Surface of Spent LiFePO4 Materials Enables Superfast Li-Ion Migration
The rapid accumulation of spent LiFePO4 (LFP) cathodes from retired lithium-ion batteries necessitates the development of effective and environmental-friendly recycling strategies. In this context, direct regeneration has emerged as a promising approach for reclaiming LFP cathode materials, offering a streamlined pathway to restore their electrochemical functionality. We report an integrated regeneration protocol that simultaneously repairs the degraded crystal structure and reconstructs the damaged carbon coating in spent LFP. The regenerated cathode material had superfast lithium-ion diffusion kinetics and a stable cathode–electrolyte interface, giving a remarkable rate capability with specific capacities of 122 mAh g−1 at 5C and 106 mAh g−1 at 10C (1C = 170 mA g−1). It also maintained capacities of 110.7 mAh g−1 (5C) and 84.1 mAh g−1 (10C) after 400 cycles. It could be used in harsh environments and could be stably cycled at subzero temperatures (−10 and −20 °C) and in solid-state electrolyte batteries. Life cycle assessment combined with economic evaluation using the EverBatt model reveals that this direct regeneration approach has high economic and environmental benefits.
Oxide Semiconductor for Advanced Memory Architectures: Atomic Layer Deposition, Key Requirement and Challenges
Oxide semiconductors (OSs), introduced by the Hosono group in the early 2000s, have evolved from display backplane materials to promising candidates for advanced memory and logic devices. The exceptionally low leakage current of OSs and compatibility with three-dimensional (3D) architectures have recently sparked renewed interest in their use in semiconductor applications. This review begins by exploring the unique material properties of OSs, which fundamentally originate from their distinct electronic band structure. Subsequently, we focus on atomic layer deposition (ALD), a core technique for growing excellent OS films, covering both basic and advanced processes compatible with 3D scaling. The basic surface reaction mechanisms—adsorption and reaction—and their roles in film growth are introduced. Furthermore, material design strategies, such as cation selection, crystallinity control, anion doping, and heterostructure engineering, are discussed. We also highlight challenges in memory applications, including contact resistance, hydrogen instability, and lack of p-type materials, and discuss the feasibility of ALD-grown OSs as potential solutions. Lastly, we provide an outlook on the role of ALD-grown OSs in memory technologies. This review bridges material fundamentals and device-level requirements, offering a comprehensive perspective on the potential of ALD-driven OSs for next-generation semiconductor memory devices.
Laser powder bed fusion of biodegradable Zn-4Cu alloy: Processing, microstructure and properties
Zn's natural degradability and biocompatibility make it a promising candidate for implants, however, its mechanical properties remain insufficient for bone applications. In this study, the performance of Zn was enhanced by developing Zn-Cu alloys via laser powder bed fusion (LPBF). Optimal LPBF parameters for forming stable tracks were achieved by adjusting laser power and scanning speed. Under optimized conditions of 100 W and 100 mm/s, high-density (99.58%) Zn-Cu alloys with improved hardness (68.2HV) and yield strength (160 MPa) were achieved. These improvements are attributed to solid solution strengthening, segregation strengthening, and grain refinement. The Zn-Cu alloys also demonstrated favorable degradation behavior, with a rate of 0.16 mm/year. This degradation is primarily driven by micro-galvanic corrosion between the CuZn5 phase and Zn matrix, along with refined grains and increased grain boundary density. This work demonstrates a viable strategy for fabricating Zn-based implants with enhanced structural integrity and mechanical performance via LPBF.