Universities are coming under increasing pressure to re-invent the way that engineering is taught in order to produce graduates that are capable of meeting the skills needs of the country’s industries. This paper described an active project where Design Thinking (DT) methodology is being applied in a novel way to Engineering Curriculum Development. Enterprise partners from a range of different manufacturing sectors participated in a series of Curriculum Development workshops and the results were cross referenced with subjects taught on existing engineering programmes internationally. This process highlighted the need for increased training in Lean, 6-Sigma, transversal and soft skills competencies, and the need to review how and when content is delivered. A survey was developed from the results of the workshops and sent out to a larger cohort of industry contacts for feedback on the proposed Engineering curriculum. Design Thinking methodology has helped ensure our customers’ needs are met by building the curriculum framework around competencies identified by both industry and academia while ensuring the students engage in a significant learning experience through experiential and applied learning using the latest immersive technologies.

Identification of the associations of cow feed efficiency with feeding behaviour and milk production is important for supporting recommendations of strategies that optimise milk yield. The objective of this study was to identify associations between measures of feed efficiency, feed intake, feeding rate, rumination time, feeding time, and milk production using data collected from 26 dairy cows during a 3 month period in 2018. Cows averaged (mean ± standard deviation) 2.2 ± 1.7 lactations, 128 ± 40 days in milk, 27.5 ± 5.5 kg/day milk, 1.95 ± 0.69 kg feed/1 kg milk—the measure used to express feed conversion ratio (FCR), 575 ± 72 min/day rumination time, and 264 ± 67 min/day feeding time during the observation period. The coefficient of variation for rumination time (min/d) was 12.5%. A mixed linear model was selected for analyses. The most feed inefficient cows with the highest FCR (≥2.6 kg feed/1 kg milk) showed the lowest milk yield (24.8 kg/day), highest feed intake (78.8 kg), highest feeding rate (0.26 kg/min) and BCS (3.35 point). However, the relative milk yield (milk yield per 100 kg of body weight) was the highest (4.01 kg/day) in the most efficient group with the lowest FCR (≤1.4 kg feed/1 kg milk). Our study showed that the most efficient cows with the lowest FCR (≤1.4 kg feed/1 kg milk) had the highest rumination time (597 min/day; p < 0.05), feeding time (298 min/day; p < 0.05), rumination/activity ratio (4.39; p < 0.05) and rumination/feeding ratio (2.04; p < 0.05). Less active cows (activity time 164 min/day; p < 0.05) were the most efficient cows with the lowest FCR (≤1.4 kg feed/1 kg milk). The behavioural differences observed in this study provide new insight into the association of feed behaviour and feed efficiency with milk performance. Incorporating feeding behaviour into the dry matter intake model can improve its accuracy in the future and benefit breeding programmes.

This article identifies the essential technologies and considerations for the development of an Automated Cow Monitoring System (ACMS) which uses 3D camera technology for the assessment of Body Condition Score (BCS). We present a comparison of a range of common techniques at the different developmental stages of Computer Vision including data pre-processing and the implementation of Deep Learning for both 2D and 3D data formats commonly captured by 3D cameras. This research focuses on attaining better reliability from one deployment of an ACMS to the next and proposes a Geometric Deep Learning (GDL) approach and evaluating model performance for robustness from one farm to another in the presence of background, farm, herd, camera pose and cow pose variabilities.

Legacy machinery poses a specific challenge when integrated into modern manufacturing lines. While modern machinery provides swift methods of integration and inbuilt predictive maintenance (PdM), older machines, while physically fully functional, are less attractive to reuse, a specific reason being their lack of ready-to-implement PdM hardware and models. More sustainable manufacturing operations can be achieved if the useable lifespan of functional older machinery can be extended through retrofittable PdM and modern industrial communication systems. While PdM models can be developed for a class (make/model) of machine with retrofitted sensing, it is often found that legacy machines will deviate greatly from their original form, through nonstandard maintenance and component replacement actions during their lengthy lifespan. This would mean that each legacy machine would require a custom PdM model, a cost often leading to the removal or nonusage of legacy machines. This paper proposes a framework designed for the generation of an efficient PdM algorithm which would allow for the reuse of legacy machines retrofitted with low-cost sensing in modern manufacturing for increased sustainability. Given a limited number of data samples collected from a machine to be maintained, we aim to predict a failure or/and maintenance time by making use of the difference between the characteristics of the variation of the healthy and unhealthy data collected from the machine. We measure the healthiness of the machine by using a Siamese network trained with a public dataset and fine-tuned with data samples obtained from machines with similar characteristics. Although we use different training and testing datasets coming from completely different sources, we obtain reasonable results thanks to the proposed technique. The results of simulations and the statistical analysis enable us to devise a transfer learning technique and a Siamese network employed for failure detection in the machine. The proposed system will allow for the continued use of older machines in modern facilities, enabling more sustainable manufacturing models.

This study presents a newly developed edge computing platform designed to enhance connectivity between edge devices and the cloud in the agricultural sector. Addressing the challenge of synchronizing a central database across 850 remote farm locations in various countries, the focus lies on maintaining data integrity and consistency for effective farm management. The incorporation of a new edge device into existing setups has significantly improved computational capabilities for tasks like data synchronization and machine learning. This research highlights the critical role of cloud computing in managing large data volumes, with Amazon Web Services hosting the databases. This paper showcases an integrated architecture combining edge devices, networks, and cloud computing, forming a seamless continuum of services from cloud to edge. This approach proves effective in managing the significant data volumes generated in remote agricultural areas. This paper also introduces the PAIR Mechanism, which is a solution developed in response to the unique challenges of agricultural data management, emphasizing resilience and simplicity in data synchronization between cloud and edge databases. The PAIR Mechanism’s potential for robust data management in IoT and cloud environments is explored, offering a novel perspective on synchronization challenges in edge computing.

Digital models are the foundation of digital twins, which form the basis of autonomous off-road vehicles. Developing virtual models of off-road vehicles using dynamic reduction techniques is one of several approaches. The article commences with a comprehensive overview of the most widely used dynamic reduction methods and then introduces performance metrics for assessing their efficacies in the context of digital twins. The paper additionally includes a detailed mathematical derivation of the state-space representation for reduced-order finite element models. The state-space representation of the reduced finite element models facilitates their export to problem-solving environments for dynamic analysis. The state-space models are eventually solved utilizing the built-in libraries of numerical solvers in textual and graphical programming platforms. In addition, the article identifies the set of solvers that best suit the simulation of virtual models for off-road vehicles. This article also includes an evaluation of the simulation results for digital models with modes ranging from 0 to 30 Hz. In addition, the article demonstrates the lower bound of the frequency range necessary and sufficient to be retained in off-road vehicle virtual models. Finally, the paper presents the simulation outcomes for digital models of commercial off-road vehicles with custom-built virtual modules of powertrain, electrical, and control systems in a problem-solving environment.