Current approaches to energy consumption forecasting in manufacturing systems often fail to fully capture the complex spatiotemporal relationships inherent in these systems. Manufacturing systems can be effectively modelled as networks that represent these dynamic relationships. Such a network-based representation offers a valuable opportunity to enhance existing energy consumption forecasting methods. This paper proposes a spatiotemporal framework that models manufacturing systems as spatiotemporal networks and introduces a novel spatiotemporal neural network for forecasting energy consumption of these systems. Validation using a publicly available dataset shows that the proposed framework outperforms several state-of-the-art baseline models, demonstrating its superior capability in energy forecasting with improvements of up to 53

Efficient and verifiable autonomous herbicide application on municipal pavements remains a persistent challenge, with conventional blanket spraying causing unnecessary chemical use and existing selective systems relying on costly non-imaging sensors with limited coverage. This paper therefore presents a low-cost embedded dual-band (660/850 nm) vision system for real-time weed detection and spraying, designed for deployment on municipal maintenance vehicles. The system is evaluated using three field datasets and through an exhaustive grid search, it was identified that with a lightweight local-adaptive thresholding pipeline using Normalised Difference Vegetation Index (NDVI) the system could achieve an averaged F1-score of 0.78 while operating at 20 fps on Raspberry Pi hardware. Crucially, this detection performance reduces herbicide use by 64.9%. The method also maintains a low missed-weed rate of 4.35%. These results demonstrate that significant chemical savings and reliable activation behaviour can be achieved using an interpretable, computationally lightweight vision approach, enabling scalable precision spraying for municipal roadside vegetation management.

The rapid expansion of computer, communication and consumer sectors has propelled the production of electronic information devices into a new phase of development. Consequently, the market is seeing a rise in demand for Printed Circuit Boards (PCBs). PCB defect detection demands high precision and efficiency to identify critical flaws such as spurious copper, mousebites, pinholes, spurs, open circuits and short circuits and play an important role in manufacturing. This paper evaluates You Only Look Once version 11’s (YOLOv11) performance in detecting defects on Printed Circuit Boards (PCBs) and compares it with YOLOv8 and YOLOv10. YOLOv11 achieved a precision of 98.9

The flexibility, versatility and enhanced perception of visio-tactile sensors could be beneficial for advanced robotic systems and other applications requiring precise haptic feedback. In this paper, we present a comprehensive framework that combines material classification and haptic feedback through the use of GelSight sensors. The study includes the creation of a diverse material dataset, consisting of 13 material classes of 42 distinct indoor and outdoor items, each item with multiple video samples captured over different regions and pressing conditions by human-held GelSight mini sensors. We introduce a method for detecting pressing events from recorded video samples and extracting key frames that capture important material features. We employ both traditional and deep learning-based feature extraction techniques to model material characteristics. These features are then used to classify materials with high accuracy through supervised learning methods using different image resolutions. For the traditional approach, Histogram of Oriented Gradients (HOG) feature descriptor combined with SVM gives 95.41

Digitalization in smart manufacturing is driving the use of Internet of Things (IoT) in many 3D printing environments. These sensors facilitate collection of data in the form of time series that can reflect a normal condition or faulty state. The ability to identify the normal conditions or faulty states by analysing sensor data is vital to minimise defects in additive manufacturing processes. However, detecting a defect based on correlated behaviour of multiple sensors is complex and an active area of ongoing research utilising multivariate time series. Currently, no comparative studies exist between machine learning and deep learning approaches that consider the potential correlation between multiple sensor data while constructing a fault detection model. In this work, we propose a unique computational intelligence approach to defect detection in a multi-sensor fused deposition modelling 3D printer. We decompose temperature and humidity sensor data into residual components using a seasonal-trend procedure with locally estimated scatterplot smoothing. A subtraction technique is then utilised to reduce two time series into one, by focusing directly on a “deviation from correlated behavior” of both sensor data. Five unsupervised models were used to detect defective state using the joint feature of temperature and humidity as training data. The test results demonstrated that Long Short-Term Memory-AutoEncoder outperformed other models with a recall rate of 94% in identifying all possible defects from the correlated behaviour of the sensors during print activity.

Recently, the generation of electronic waste (E-waste) has increased significantly due to rapid changes in consumer demand and advancements in technology. Recycling E-waste is essential for boosting the economy and advancing the sustainability of the electronics industry. Printed circuit boards (PCBs) contribute significantly to E-waste, as they are widely used in various electronic devices. However, a challenge in recycling E-waste is the rapidly and diversely changing material composition. To enhance the efficacy of E-waste recycling, an automated, non-invasive method is essential for process control and decision-making. By exploiting hyperspectral imaging (HSI), which offers spectroscopic analysis to accurately identify materials, this paper presents attention-based deep learning segmentation models to accurately identify components in PCBs. This approach allows for the automatic extraction of information from E-waste, leading to more efficient and optimized recycling practices.

Air quality is critical to the health, especially in industrial manufacturing environments. Pollutants such as fine particulate matter and toxic gases like CO2, NOx and VOCs are creating serious health risks. The limited ventilation at indoor manufacturing facilities makes them more vulnerable to poor air quality, causing serious health issues such as asthma and long-standing lung damage. Although existing air quality monitoring systems provide sensing capability for airborne particles or gases, they lack smart predictive capabilities to mitigate future risks in complex industrial and manufacturing environments. In this paper, we propose an air quality prediction solution that leverages real-time, streaming, time-series data collected from IoT nodes deployed at different industrial locations. The system can monitor multiple pollutants, including PM2.5, PM10, CO2, NOx, and VOCs, using variations of Long Short-Term Memory (LSTM) networks to forecast contaminated air with high accuracy. Our approach involves thorough data preprocessing and analysis activities to effectively model each contaminant. The results show significant promise for forecasting and classifying air quality and offer industries a valuable tool to proactively manage indoor environmental conditions and protect human health.

Teleoperation is the process of remotely controlling a robotic system. This paper compares two real-time 3D human pose estimation (HPE) models for teleoperating the tool centre point (TCP) of a UR5 robot arm on non-GPU hardware: BlazePose and a lightweight version of OpenPose. These models were selected for their real-time capabilities. Building on previous work, the 3D joint position of the right hand, derived from monocular RGB input, is used to generate remote control instructions for the UR5, while the left hand controls the attached RG2 gripper. A new joystick-based control system is introduced, where right-hand movement in any direction translates to continuous robot TCP movement in that direction at a fixed speed. This addresses issues with the prior mapping-based system, which relied on accurate depth estimation and often caused unintended arm movements. The two HPE models were evaluated on hold-position and pick-and-place tasks, comparing both the joystick and mapping control systems. Results indicate the lightweight OpenPose model reduces unintended movement but remains insufficient for pick-and-place tasks under the mapping system. In contrast, the joystick system enabled successful task completion with accuracy comparable to previous 2D control methods, while freeing the left hand for additional controls. Future work may enhance the system by using the left hand for rotational control.

Scale-invariant interest point detection is crucial for many computer vision tasks in dynamic environments, such as manufacturing, where identifying recurring visual landmarks is essential for process monitoring. However, existing solutions, including the Scale-Invariant Feature Transform and its descendants, incur high computational costs due to operations across multiple scales. Drawing inspiration from the Finite Element Scale-Invariant Detector, this paper introduces a novel square-spiral derivative that integrates a vectorized image addressing scheme with complementary processing techniques to enhance runtime performance. Experimental evaluations demonstrate that the proposed approach remains robust under moderate geometric and photometric transformations, achieving competitive performance compared to widely used detectors in conditions that resemble those in controlled dynamic environments. Furthermore, it significantly reduces computational overhead, providing an efficient solution for vision-based manufacturing tasks.

This paper explores the application of BlazePose, a monocular human pose estimation (HPE) model, within a teleoperation framework for a UR5 six-axis robot. Achieving teleoperation with only a single RGB camera and a device without a powerful GPU will improve accessibility and cost effectiveness of teleoperation solutions. This study evaluates the 2D pose estimation capabilities of BlazePose for robotic teleoperation tasks. Given the necessity of manipulating the UR5 in three- dimensional space, we implement a 2D-based controller that translates the teleoperator's 2D right hand position within a configurable hand workspace to the corresponding position of the robot's Tool Centre Point (TCP) within the robot's available workspace along two dimensions. The left hand is then utilised for controlling the robot's motion along the third dimension and operating the attached OnRobot RG2 gripper during the pick- and-place task. Additionally, we explore an alternative control paradigm utilising the 3D pose estimation of BlazePose for a more intuitive controller. Two experiments are conducted: the pick-and-place task to assess the 2D-based controller in common robotic tasks, and a hold position task. The hold position task aims to assess the amount of excess movement attributable to the HPE model when utilising the 3D-based controller. The results reveal that while the 2D pose estimation capabilities enable effective teleoperation, the utilisation of 3D estimation results in poor translation to robot control and significant excess motion. These findings underscore the importance of accurate depth estimation in 3D HPE models for precise and reliable teleoperation.

This paper presents a groundbreaking advancement in industrial quality control through the development of an automated soldering quality assessment system for circuit boards utilizing hyperspectral imaging (USI) technology. Building upon the transformative capabilities of USI in visual inspection, our research focuses on enhancing the precision and depth of assessment in soldering processes, a critical aspect of electronics manufacturing. By leveraging the unique spectral information captured by HSI, beyond the capabilities of traditional vision systems, our automated solution offers a comprehensive evaluation of solder quality, overcoming challenges posed by similar absorption characteristics of materials. We detail the methodology, algorithms, and integration of HSI into the inspection pipeline, highlighting its effectiveness in detecting defects, ensuring uniformity, and improving overall product quality. The application of this technology extends beyond electronics manufacturing, with potential implications for various industries requiring meticulous quality control. Through this study, we contribute to the ongoing evolution of visual inspection systems, empowering industries with advanced tools for precise and reliable quality assessment.

This paper presents a progression of a popular neuromorphic memory structure by exploring advanced forgetting models for robust long-term information storage. Inspired by biological neuronal systems, neuromorphic sensors efficiently capture and transmit sensory information using event-based communication. Managing the decay of information over time is a critical aspect, and forgetting models play a vital role in this process. Building upon the foundation of an existing popular neuromorphic memory structure, this study introduces and evaluates four advanced forgetting models: ROT, adaptive, emotional memory enhancement, and context-dependent memory forgetting models. Each model incorporates different factors to modulate the rate of decay or forgetting. Through rigorous experimentation and analysis, these models are compared with the original ROT forgetting model to assess their effectiveness in retaining relevant information while discarding irrelevant or outdated data. The results provide insights into the strengths, limitations, and potential applications of these advanced forgetting models in the context of neuromorphic memory systems, thereby contributing to the progression of this popular neuromorphic memory structure.

This paper introduces the Virtual Manufacturing Platform (VMP), a cloud-complete educational platform targeting manufacturing industries providing tutorials and sandboxing. The scope of this paper focuses on the robot control architecture of the platform which allows for seamless control of both virtual and physical robots and end-effectors accompanied by supportive educational materials. The platform seeks to de-risk automation investments for small to medium enterprises by offering confirmatory environments and knowledge transfer opportunities.

The field of neuromorphic vision systems aims to replicate the functionality of biological visual systems by mimicking their physical structure and electrical behaviour. Unlike traditional full-frame sensors, neuromorphic systems process data asynchronously and at the pixel level, modelling biological signalling processes. This allows for high-speed operations with lower energy consumption, making them suitable for applications like autonomous vehicles and embedded robotics. This work introduces the Neuromorphic Event Alarm Time-Series Suppression (NEATS) framework, designed to filter noise and detect outlier behaviours in event data without the need for 2-D transformations. NEATS employs rolling statistics and advanced neuromorphic data structures to minimise noise while identifying changes in scene dynamics. This framework injects attention into scene processing, similar to summarisation frameworks in traditional image processing. A novel event-vision alarm change collection (EACC) database is presented, containing controlled stimuli pattern changes captured using leading neuromorphic imaging devices. This database facilitates future benchmarking of neuromorphic attention frameworks, advancing the development of efficient and accurate artificial vision systems.

Friction drilling is a non-conventional hole-making process suitable for thin-section, ductile metals. During friction drilling, heat is generated due to tool rotation and the resulting flow of metal creates a bushing on the exit side of the hole. The bushing offers a longer engagement length for any subsequent thread making process. The threaded holes in this study were created by friction drilling and thread forming in 6082-T6 aluminium alloy. Four scenarios of the threaded holes were created with four levels of rotation rates of friction drilling processes (2000 rpm to 4000 rpm) and the mechanical properties of the threaded holes were compared. It was shown that 3000–3500 rpm is the optimum range of the rotation rate that achieved the higher load-bearing capacities (i.e., resistance to thread stripping) of 5.0–5.5 kN. In addition, the regions close to the thread surfaces in all scenarios were found to have experienced localised hardening to a hardness from 113 HV to around 125 HV.

The properties of Extra Low Interstitials (ELI) Ti6Al4V components fabricated via the laser-based powder bed fusion (L-PBF) process are prone to variation, particularly throughout a powder reuse regime. Interstitial pick-up of interstitial elements within the build chamber during processing can occur, most notably, oxygen, nitrogen, and hydrogen, which can impair the mechanical properties of the built component. This study analyses ELI Ti6Al4V components manufactured by the L-PBF process when subjected to a nine-stage powder reuse sequence. Mechanical properties are reported via hardness measurement and tensile testing. Results showed that from 0.099 wt.% to 0.126 wt.% oxygen content, the mean hardness and tensile strength increased from 367.8 HV to 381.9 HV and from 947.6 Mpa to 1030.7 Mpa, respectively, whereas the ductility (area reduction) reduced from around 10% to 3%. Statistical analysis based on the empirical model from Tabor was performed to determine the strength–hardness relationship. Results revealed a significant direct relationship between tensile strength and Vickers hardness with a proportionality constant of 2.61 (R-square of 0.996 and p-value of 6.57 × 10−6).

Computational simulation of the Powder Bed Fusion (PBF) process is a useful tool for predicting and analysing melt pool geometry during the deposition process. Advanced models that use Computational Fluid Dynamics (CFD) can accurately simulate the complex melt pool dynamics of the process but are typically computationally onerous to implement. CFD models require thermophysical data over a large temperature range that may be difficult to acquire for the material systems of interest. Heat conduction models, which are useful to industrial end users are easier to implement, but their accuracy can be compromised. The main difference between heat conduction and CFD modelling is the absence of convection (especially Marangoni convection). However, several sources in literature have highlighted a simple approach to mimicking the effects of Marangoni convection on the melt pool by artificially increasing the thermal conductivity of the liquid. However, due to its simplicity and lack of agreement within literature, the modified heat conduction approach is neither sufficiently robust nor universally consistent. Comparison to experimental data is lacking. In the present work, the heat conduction model is modified using an orthotropic description of anisotropic thermal conductivity in the liquid phase by applying directional correction factors. The correction factors are calibrated by comparing the predicted geometry against experimentally-obtained melt pool dimensions for single-layer, multiple tracks in Ti-6Al-4V processed by laser-PBF. After appropriate correction factors were selected, the modified heat conduction model gave results in good agreement with experiments. To test the general applicability of the approach, data from literature were analysed and simulated using the model. After correction factors were adjusted accordingly, the simulated results were validated over the range of power levels and scan speeds.

Friction drilling is a hole-making process suitable for thin sections of ductile metal. A rotating tool is plunged into the workpiece to form the pilot hole. The hole is then threaded in a follow-up process. A bushing forms on the exit side of the hole, which allows for longer engagement lengths in threaded assemblies. For comparison purposes, four combinations of threaded-hole processes were applied to 1.5 mm-section, 6082-T6 aluminium alloy. The processes involved were friction and twist drilling followed by thread forming or cutting. Vickers hardness and microstructural analyses were used to assess the condition of the material. An in-house test method was developed to measure the axial load?deflection response. Progressive failure occurred by thread stripping. Friction drilling followed by thread forming gave peak loads 35% higher than conventionally drilled and tapped holes. Also, hardness increased from 111HV in the parent metal to 125HV (with an increase in hardness to depths of 0.5 mm) due to work hardening. Evidence of precipitate dissolution was negligible which suggests that the friction drilling process operated below the solvus temperature. A novel approach for determining reliably-based, thread-stripping Factors of Safety (FoS) is presented. FoS in the range 3.61 to 4.38 gave a reliability of 95% to 99.9% against thread stripping in friction-drilled, thread formed joints.

The process of Wire Arc Additive Manufacturing (WAAM) utilizes arc welding technology to fabricate metallic components by depositing material in a selective layered fashion. Several welding processes exist that can achieve this layered deposition strategy. Gas Metal Arc Welding (GMAW) derived processes are commonly favored for their high deposition rates (1–4 kg/h) and minimal torch reorientation required during deposition. A range of GMAW processes are available; all of which have different material transfer modes and thermal energy input ranges and the resultant metallic structures formed from these processes can vary in their mechanical properties and morphology. This work will investigate single-layer deposition and vary the process parameters and process mode to observe responses in mechanical properties, bead geometry and deposition rate. The process modes selected for this study were GMAW derived process of Metal Inert Gas (MIG) and Cold Metal Transfer (CMT). Characterization of parameter sets revealed relationships between torch travel speeds, wire feed speeds and the specimen properties and proportions. Differences were observed in the cross-sectional bead geometry and deposition rates when comparing MIG and CMT samples though the influence of process mode on mechanical properties was less significant compared to process parameter selection.