To Örebro University

The incorporation of artificial intelligence, multi-sensor perception, and cyber-physical control into mining operations offers tremendous opportunities for increasing productivity, safety, and sustainability. However, present frameworks focus on discrete subsystems rather than providing a unified, safety-constrained optimization method that has been verified in both surface and underground environments. This paper describes a scalable, hierarchical autonomous mining architecture that incorporates sensor fusion, edge intelligence, fleet coordination, and digital twin-based decision support. It is designed to operate in GNSS-denied conditions and extreme climatic constraints common to Nordic mining environments. A mathematical modeling approach formalizes vehicle dynamics, drilling mechanics, and multi-agent fleet coordination inside a safety-constrained multi-objective optimization formulation. The framework is validated using Monte Carlo simulation with uncertainty measurement, sensitivity analysis, and statistical hypothesis testing. The preliminary results show improvements over a typical baseline, with productivity increasing by approximately 24.3% ± 3.2%, energy consumption decreasing by 12.8% ± 2.5%, and safety risk decreasing by 48.6% ± 4.1%. A sensitivity study identifies localization accuracy, communication delay, and optimization weighting as the primary system performance drivers. The suggested framework serves as a reproducible and transferable reference model for next-generation intelligent mining systems, having direct applications to both industrial deployment and future research in autonomous resource extraction.

Aluminum alloy AA8011 is widely utilized in automotive and lightweight engineering applications, although traditional fusion welding frequently produces faults due to its high thermal conductivity and restricted weldability. This work investigates High Power Diode Laser Beam Welding (HPDLBW) of 2 mm AA8011 sheets employing laser power (3.2-3.4 kW), welding speed (17-23 mm/s), shielding gas (20 L/min) and beam diameter (3-4 mm) built with a Taguchi L9 orthogonal array. A response surface model linked process factors to mechanical responses, including impact energy, hardness, and tensile strength. Optimal settings for multi-objective optimization (P = 3.3 kW, v = 17 mm/s, d = 3.5 mm) resulted in 110 J of impact energy, 33 HV0.5 of hardness, and 69 N/mm² of tensile strength. Analysis of variance revealed that laser power accounted for up to 38.6% of the variation in weld penetration, confirms its prominent role in melt pool development, while tensile strength improved by a maximum of 14.2% under optimal conditions. Under optimum conditions, microstructural research revealed refined fusion zones, minimized intermetallic formation, and little porosity. The work shows that Taguchi-based modeling and optimization give a predictive framework for enhancing AA8011 weld performance, and it establishes HPDLBW as a dependable method for lightweight alloy joining. The study demonstrates HPDLBW as a viable and scalable joining technology for lightweight aluminum structures, with lower heat input, improved surface polish, and practical significance for the automotive and packing industries.

High Power Diode Laser Beam Welding (HPDLBW) is a popular method for combining austenitic stainless steels because it has great electrical efficiency, precisheat input control, and stable conduction-mode welding. Welding AISI 304 (SS304remains difficult because of porosity, hot cracking, residual stresses, and heat-affected zone (HAZ) sensitization. This work uses Taguchi design of experimentand analysis of variance (ANOVA) to evaluate the effect of HPDLBW procesparameters on weld shape, microstructure, and mechanical performance, as welas to construct optimum processing-properties connections. Butt joints of 1.5 mthick SS304 sheets were welded using variable laser power (1500–2000 W), weld-ing speed (3–5 m·min⁻¹), and beam diameter (0.2–0.4 mm). Results demonstrate that raising laser power and reducing welding speed increased penetration depth by up to ~ 45%. Intermediate conditions generated defect-free welds with balanced bead geometry. The optimal parameter configuration (2000 W, 4 m·min⁻¹, 0.3 mm resulted in a maximum tensile strength of 657.4 N·mm⁻², representing a ~ 58% improvement over the lowest-strength condition, with fracture occurring in the parent material. Microhardness rose by approximately 21% in the HAZ and 18% in the weld metal relative to the base metal due to grain refinement and reduced δ-ferrite production. Impact hardness remained constant (104–111 J) under all situations. ANOVA revealed that laser power was the most important factor (48–60% contribution), followed by welding speed, with beam diameter having only a modest effect. These findings show that optimized HPDLBW may produce high-integrity SS304 joints appropriate for structural and precision manufacturing applications.

Manufacturers have seen noteworthy variations as a result of Industry 5.0 in recent years. They have seen firsthand the growth of robotics, cloud computing, and the Net of Things (NoT) in driving automation and data technology. Thanks to the seamless integration of software, hardware, and staff, smart factories are becoming increasingly prevalent, and an increasing number of manufacturers are experiencing success with “as-a-Service” business models. Industry 5.0 is now significantly more accessible to small and medium-sized businesses due to its growing maturity. Utilizing technology that gathers, organizes, and combines data with information from your ERP to improve your shop floor efficiency and provide insights is now a lot simpler. These days, it costs much less time, money, and effort for businesses of all sizes to gain realworld experience.

These days, there's a shift away from the industry 5.0 model's emphasis on efficiency towards the realization that mechanized, smart plants must nevertheless prioritize people. More and more people are emerging to believe that social and technical systems can coexist to increase resilience, sustainability, and customization. Restoring people to the centre of industrial production will allow Industry 5.0 to make better use of their skills in creativity, critical thinking, and problem-solving.

This work focuses on how Industry 5.0 uses contemporary technology (Industrial Net of Things (INoT), AI, and Cloud Computing) in significant ways. It intends to investigate the possible uses, advantages, and difficulties related to the implementation of the technologies in smart industries. This survey's contributions include giving a thorough summary of the body of research on the applications, procedures, technologies, and prospects around the usage of INoT, AI, and cloud computing in industry V.0. It pays close attention to several concerns linked to Synthetic Intelligence (SI) and big data in smart sectors, such as security and privacy issues with data, challenges related to interpretation, and adversarial attacks on AI models. This chapter also gives an overview of INoTs, a crucial component of Industry 5.0, and examines the methods used by AI and big data approaches to extract insights from the data created in INoTs.

Joining dissimilar metals is gaining popularity in the automotive, aerospace, marine, and energy industries due to its potential for weight reduction, cost savings, and improved performance under challenging operational conditions. Thermal fatigue at the hot and cold ends of an engine reduces the component lifespan in engine exhaust systems composed of identical materials. Corrosion at the hot end is caused by oxidation and spalling of the surface oxide layer, whereas pitting corrosion occurs at the cold end due to the condensation of combustion gases. These problems can be avoided by adopting dissimilar metal welds, which have superior heat and corrosion resistance. These issues can be remedied by utilizing a dissimilar metal. This study utilized Gas Tungsten Arc Welding (GTAW) to evaluate the weldability and characterization of two stainless-steel combinations: SS316L-SS410 and SS310-SS410 in sheet form. Taguchi L9 and L4 orthogonal arrays were used to optimize various process parameters such as welding torch angle, filler rod angle, filler diameter, welding speed, current, gas flow rate, pulse frequency, and wire feed rate. Filler electrodes ER316L and ER309, which met AWS A5.12 M/A5.12:2009 criteria, were investigated for their impact on weld quality. Experimental trials were augmented with finite element simulations in ANSYS 2021R1 to predict temperature distribution, molten metal flow behavior, and residual stress evolution. The findings underline the importance of process parameter selection in lowering heat-affected zone (HAZ) distortion and cold crack susceptibility while boosting weldment tensile strength, hardness, and structural integrity. It provides practical directions for creating defect-free and durable dissimilar weld connections in complicated engineering applications.