Computer Vision System for Welding Inspection of Liquefied Petroleum Gas Pressure Vessels Based on Combined Digital Image Processing and Deep Learning Techniques

Artificial Intelligence-Based Smart Quality Inspection for Manufacturing

In today's era, monitoring the health of the manufacturing environment has become essential in order to prevent unforeseen repairs, shutdowns, and to be able to detect defective products that could incur big losses. Data-driven techniques and advancements in sensor technology with Internet of the Things (IoT) have made real-time tracking of systems a reality. The health of a product can also be continuously assessed throughout the manufacturing lifecycle by using Quality Control (QC) measures. Quality inspection is one of the critical processes in which the product is evaluated and deemed acceptable or rejected. The visual inspection or final inspection process involves a human operator sensorily examining the product to ascertain its status. However, there are several factors that impact the visual inspection process resulting in an overall inspection accuracy of around 80% in the industry. With the goal of 100% inspection in advanced manufacturing systems, manual visual inspection is both time-consuming and costly. Computer Vision (CV) based algorithms have helped in automating parts of the visual inspection process, but there are still unaddressed challenges. This paper presents an Artificial Intelligence (AI) based approach to the visual inspection process by using Deep Learning (DL). The approach includes a custom Convolutional Neural Network (CNN) for inspection and a computer application that can be deployed on the shop floor to make the inspection process user-friendly. The inspection accuracy for the proposed model is 99.86% on image data of casting products.

A Novel Flushing Mechanism to Minimize Roughness and Dimensional Errors during Wire Electric Discharge Machining of Complex Profiles on Inconel 718

One of the sustainability goals in the aeronautical industry includes developing cost-effective, high-performance engine components possessing complex curved geometries with excellent dimensional precision and surface quality. In this regard, several developments in wire electric discharge machining have been reported, but the influence of flushing attributes is not thoroughly investigated and is thus studied herein. The influence of four process variables, namely servo voltage, flushing pressure, nozzle diameter, and nozzle-workpiece distance, were analyzed on Inconel 718 in relation to geometrical errors (angular and radial deviations), spark gap formation, and arithmetic roughness. In this regard, thorough statistical and microscopical analyses are employed with mono- and multi-objective process optimization. The grey relational analysis affirms the reduction in the process's limitations, validated through confirmatory experimentation results as 0.109 mm spark gap, 0.956% angular deviation, 3.49% radial deviation, and 2.2 µm surface roughness. The novel flushing mechanism improved the spark gap by 1.92%, reducing angular and radial deviations by 8.24% and 29.11%, respectively.

Multilayer Game Collaborative Optimization Based on Elman Neural Network System Diagnosis in Shared Manufacturing Mode

With the dynamic sharing of global resources shifted from the independent production of a single enterprise to and the development of collaborative manufacturing, today's manufacturing industry has collaborative production among multiple enterprises. This paper extends the optimization method of the multienterprise dynamic equipment collaborative scheduling system with the dynamic manufacturing network theory approach, combining the neural network system and model predictive control theory to continuously and dynamically diagnose the changes of demand and capacity in the actual production process and design the corresponding multilayer game collaborative optimization robust model according to the uncertainty relationship. The study considers the production characteristics and management needs of multiple enterprises within the manufacturing industry, as well as the optimization of the dynamic equipment collaborative scheduling system, uncertain demand, dynamic equipment matching effectiveness, and equipment failure under the shared manufacturing model, deduces the market capacity demand for manufacturing enterprises by inverse prediction of dynamic market demand through the simple recurrent neural network (Elman network), and then maximizes the idle equipment utilization and load capacity under the shared manufacturing model in model rolling optimization. This paper gives model solutions based on big data analysis and combines improved population intelligence algorithms to determine the dynamic matching of manufacturing resources, product supply and demand paths, and transportation flows. The simulation results show that the application of model predictive control theory to the model of Elman neural network system diagnosis can effectively reduce the adverse effects of the two-way uncertainty environment on the profitability of enterprises. Meanwhile, considering the maximum performance matching of dynamic equipment scheduling and combining with robust optimization methods will reduce the cost loss of manufacturing enterprises in the worst case, and the cost loss reduction can reach 24.73%. The analysis results verify that the method is of great practical significance in the direction of intelligent production collaboration and industrial digital transformation.

Evolution of Standardized Specifications on Materials, Manufacturing and In-Service Inspection of Nuclear Reactor Vessels

The cataloguing and revision of reactor pressure vessels (RPV) manufacturing and in-service inspection codes and their standardized material specifications—as a technical heritage—are essential for understanding the historical evolution of criteria and for enabling the comparison of the various national regulations, integrating the most relevant results from the scientific research. The analysis of the development of documents including standardized requirements and the comparison of regulations is crucial to be able to implement learned lessons and comprehend the progress of increasingly stringent safety criteria, contributing to sustainable nuclear power generation in the future. A novel methodology is presented in this work where a thorough review of the regulations and technical codes for the manufacture and in-service inspection of RPVs, considering the implementation of scientific advances, is performed. In addition, an analysis focused on the differences between irradiation embrittlement prediction models and acceptance criteria for detected defects (both during manufacturing and in-service inspection) described by the different technical codes as required by different national regulations such as American, German, French or Russian is performed. The most stringent materials requirements for RPV manufacturing are provided by the American and German codes. The French code is the most stringent with respect to the reference defect size using as a criterion in the in-service inspection.

Cooperative Approaches to Data Sharing and Analysis for Industrial Internet of Things Ecosystems

The collection and analysis of industrial Internet of Things (IIoT) data offer numerous opportunities for value creation, particularly in manufacturing industries. For small and medium-sized enterprises (SMEs), many of those opportunities are inaccessible without cooperation across enterprise borders and the sharing of data, personnel, finances, and IT resources. In this study, we suggest so-called data cooperatives as a novel approach to such settings. A data cooperative is understood as a legal unit owned by an ecosystem of cooperating SMEs and founded for supporting the members of the cooperative. In a series of 22 interviews, we developed a concept for cooperative IIoT ecosystems that we evaluated in four workshops, and we are currently implementing an IIoT ecosystem for the coolant management of a manufacturing environment. We discuss our findings and compare our approach with alternatives and its suitability for the manufacturing domain.

Determination of Optimal Flat-End Head Geometries for Pressure Vessels Based on Numerical and Experimental Approaches

The experimental and numerical analyses of the pressure vessels with different flat ends are presented and discussed in the paper. The main aim of the study is to propose the optimal flat head end geometry. The analyses are focused on the comparison of standardized geometries and with the proposed elliptical cut-out. The experimental tests with the application of strain-gauge measurements and numerical modeling of the pressure vessel are conducted. The behavior under low and high pressures and the influence of the residual welding stresses, material properties, and geometrical tolerances on the level of the plastic deformation in the flat end is discussed. It is presented that the rules given in the recent standard are not sufficient for optimal selection of the optimal geometry. It is observed that in certain geometries the deviations of the pipe thickness may lead to a significant increase of the equivalent stresses. The residual welding stresses have a significant influence on the stress and strain level—particularly in the stress relief groove (SRG). The performed study and comparison of the different geometries allow for the proposal of the optimal shape of the flat end. It appeared that the pressure vessels with SRG are the most optimal choice, particularly when elliptic shapes are in use. In some cases (i.e., pipe with wall-thickness equal to 40 mm and the flat end with circular SRG), the optimal configuration is reached for dimensions beyond the admissible by code range.