Abstract :A model has been developed for the health assessment of a chlorine compressor that is capable of constructing Health Indicators (HI). This model is an LSTM Autoencoder, which works as follows: an LSTM-based encoder maps a multivariate input sequence to a fixed-dimensional vector representation. The decoder, another LSTM network, uses this vector representation to produce the target sequence. The loss between the reconstructed sequence and the input sequence forms the basis for the HI. The model is trained exclusively with healthy data. The LSTM-AE is designed to reconstruct the measurements independently of the operating conditions, enhancing the model’s robustness in varying operational contexts. Health assessment is conducted by using the constructed HI to classify the health state of the compressor. The first instance of the compressor being marked as unhealthy triggers the start of fault identification. The proposed method is tested on real-world data through a case study on chlorine compressors, resulting in an identification accuracy of 73% and a precision of 56% for the three considered failure mechanisms.

The need for a fast transition towards clean electricity generation pushed large investments in high-risk, high-impact technologies such as floating Airborne Wind Energy Systems (AWESs), which are expected to be highly cost efficient with respect to state-of-the-art offshore wind energy technology. Current research on the matter does not address the design challenge of a tailored floater, necessary to suit at most the unique features of such systems, and foster their industrial and commercial development. This study proposes a simulation-based design optimisation framework for the floating structure and associated mooring system tailored to offshore AWES deployment. By reviewing conventional floating wind energy solutions and analysing expected AWES loading conditions, a spar-like floater and taut mooring system are proposed as the baseline design for a numerical case study. A state-of-the-art first-order potential flow model is employed for the floater, coupled with a novel quasi-static model for the mooring system, to simulate system motions in the frequency domain. The design optimisation aims to minimise capital expenses and wave-induced motions, with constraints on the strength and fatigue lifetime of mooring ropes. A multi-objective genetic algorithm is used to explore the design space and approximate the Pareto front, with sensitivity analyses on the latter revealing the significant impact of mooring line materials on system performance. Verification of the optimisation results includes an assessment of aerodynamic loads using a decoupled AWES model and time-domain simulations in OrcaFlex for selected configurations under various wave conditions. Although the quasi-static mooring model showed coherence with dynamic simulations, optimal configurations deviated significantly from the initial spar-like design, indicating potential benefits from alternative baseline designs. The impact of AWES aerodynamic loads on deck motions highlights the need to integrate them into the design process. Despite these challenges, the proposed simulation-optimisation framework shows promise as a powerful tool for the preliminary design of floating AWESs, paving the way for future refinements.

A significant push toward sustainability has emphasized the need to make all vessels as energy efficient as possible. Close attention must be paid to the performance evaluation of the vessel’s main energy consumer, particularly the engine. Moreover, prioritizing the efficient operation of the engine is essential for maintaining the vessel’s operational safety. Engine performance evaluation has been conducted using various methodologies, based on either field testing data or physical and data-driven models. This research focuses on developing a condition monitoring model that is effective even with limited data availability, highlighting the correlation between subsystem degradation and its impact on the overall underperformance of the engine. The literature review examines potential methods for condition monitoring of marine diesel engines, with a focus on their modeling purposes. These methods are classified based on their theoretical foundation: White-box models, which are based on first principles, and Black-box models, which rely on the interrelationships between input and output parameters using available mathematical tools. Additionally, the literature discusses Grey-box models, which combine physics-based principles with data-driven approaches. The modeling purpose of the methods analyzed is identified as either parameter estimation or fault detection and isolation, depending on the available data and the chosen methodologies. To achieve the objective of this thesis, a structured model development process is formulated. This process begins with defining the available parameters and determining which are inputs and which are outputs. The dataset then undergoes pre-processing steps before being divided into training, validation, and testing datasets. The modeling procedure begins by developing a basic model using shop test data (manufacturer data) to benchmark target parameters and determine whether a data-driven or hybrid model is necessary for engine condition monitoring. A neural network is then employed to capture data variance and leverage its ability to identify non-linear relationships. Building on the baseline neural network model, the loss function is customized to incorporate physics-based information into the data-driven model. This integration is achieved using two methods: either by approximating shop test data to represent engine behavior or by incorporating physical equations derived from mean value engine models. These physicsbased elements are introduced as new loss terms within the loss function evaluation. Each of the five developed model variations is then validated for their predictive capacity, with evaluation metrics compared to identify the most promising approach. Additionally, the models are assessed for their ability to generalize to unseen data. After concluding the modeling process, a case study was developed to examine the practical application of the best model in creating a condition monitoring tool. This tool relies on monitoring the residual trends of target parameters and correlating these trends with potential fault types in engine subsystems. By analyzing these residual trends, the model can effectively link subsystem degradation to overall engine underperformance, providing valuable insights for fault detection. Transitioning to the conclusions, it becomes clear that incorporating physics-based information, particularly from mean value models, yields superior results in capturing the variance of actual measurements and accurately predicting different operational conditions. This highlights the critical importance of developing hybrid approaches that combine the strengths of data-driven models while addressing their inconsistencies, thereby producing results closer to the ground truth. Further recommendations include integrating recurrent neural networks and establishing a decision support system to help identify the root causes of degradation and suggest necessary actions. Overall, developing a condition monitoring model proves beneficial for identifying underperformance and ensuring the correct operation of the vessel.

An unfamiliar subject to the contemporary connecting options for cranes on pontoons is removability; Various difficulties and obstructions related to the heavy-duty nature of the equipment lead to a limited amount of practiced conventional connecting options for this purpose, which all have the absence of removability in common. Furthermore, the consideration of various types of efficiencies and performance aspects has not been common practice within this field. The aim of developing a removable and efficient crane-to-pontoon connection system is therefore set.
An initial literature research is performed in order to obtain a variety of connecting options which have the potential of forming the basis of a new removable connection system, optimized for crane-to-pontoon configurations. Subsequently, creating a unique rating system, specifically for crane-to-pontoon connection systems, led to a substantiated selection process for the most feasible option among the potential connecting options. The turnbuckle option obtained the highest ranking and was therefore selected to proceed the design process with.
Developing the turnbuckle option into a complete connection system and accomplishing all defined aims led to an encounter with various engineering challenges. An integral design process led to the discovery of a proficient combination of components, which overcome the challenges and provide satisfaction with respect to the aims of the project.
The parameters of the developed conceptual design are finally quantified in order to prove feasibility and efficiency. Applicable design parameters are found which pass the safety requirements, while minimizing the material consumption. With these parameters, the removable design is compared to conventional real case connection systems in terms of cost-efficiency, which resulted in the observation that multiple millions of euros in long-term savings are anticipated per deployed crane due to the removability feature.

With the development of society and the requirements for clean energy, offshore wind farms (OWFs) that can generate steady and continuous electricity have been built. With harsher weather conditions and more powerful wind resources, the wind turbines at offshore wind farms are significantly larger than those at onshore wind farms. The complex weather conditions and mechanical structure of wind turbines pose problems for their operation and maintenance (O&M).
The cost of vessel chartering significantly contributes to the overall cost of operating and maintaining an offshore wind farm. By selecting the optimal fleet mix for executing the maintenance, the vessel chartering cost can be reduced, reducing the operation and maintenance costs of the offshore wind farm. This reduces the levelized cost of energy from the offshore wind farm. This report developed a simulation and optimization model based on mixed integer linear programming to determine the opti-mal fleet mix for executing the maintenance tasks by minimizing the vessel acquisition cost. The Monte Carlo simulation is implemented to statistic an optimal strategy for chartering the vessels.
Chapter 1 introduces the offshore wind farm (OWF) and its operation and maintenance (O&M) activi-ties. Chapter 2 provided a literature review on the latest progress of the offshore wind farm’s operation and maintenance. Chapter 3 provides a simulation model for component wear, maintenance require-ment generation, and maintenance task execution. The process of optimization is explained in detail. Chapter 4 presents the mathematical model of the optimizer, which arranges the vessels and executes maintenance tasks. Chapter 5 presents a case study based on the latest progress data. The Monte Carlo simulation yields the optimal initial purchased fleet mix derived based on the Monte Carlo simu-lation. Finally, Chapter 6 gives the conclusion and recommendations for future studies.

Wind energy is growing to be an essential part of the transition towards sustainable energy sources. To facilitate this, it is crucial that wind farm operators can offer competitive energy prices compared to fossil fuel sources; effective and efficient wind farm operations are therefore imperative. However, many full-scale wind farms deal with wake effects, e.g. the disturbed air that travels downstream of a turbine and potentially ends up in other neighbouring turbines. The result of this lower-velocity, higher-turbulence flow field is both decreased power production and increased fatigue loads. One proposed solution for this problem comes in the form of 'wake steering': the yawing (rotating) of upstream turbines' nacelles to facilitate a degree of control over the deflection of wakes. By doing so, the problematic disturbed flow fields can be strategically guided between downstream turbines to maximise collective power production. However, the yawing action itself brings some adverse effects: the upstream turbines, now no longer directly facing the wind, feel decreased power production and increased fatigue loads themselves. These fatigue effects, accumulating over time, can eventually cause increased maintenance costs and nullification of any revenue gains through power optimisation. The problem thus becomes a farm-wide collective revenue optimisation task. This thesis investigates how long-term revenue in wind farms can be maximised, considering both profits through power optimisation and maintenance costs through fatigue-induced component failures due to wake steering control. First, a realistic wind farm simulation environment is constructed, based on a Graph Neural Network (GNN) surrogate wind farm simulation model, to facilitate efficient reinforcement learning training. Next, the environment is used to train fully centralised reinforcement learning agents based on a GNN architecture, resulting in agents that can generalise across all wind conditions and unseen wind farm layouts. Ultimately, the results show that an 'informed' agent that considers all profits and costs involved manages to significantly reduce the cost of energy compared to 'greedy' (power optimisation only), 'risk-averse' (damage minimisation only) and 'baseline' (zero-yaw) policies, furthermore considerably maximising long-term wind farm revenue by as much as 20%. Altogether, this thesis shows promising results in using graph-based reinforcement learning to train maintenance-conditioned, inflow-agnostic, and layout-agnostic wake steering controllers for wind farm revenue optimisation.

The amount of floating offshore wind farms under development has drastically increased over the past years as the technology becomes viable for pre-commercial and commercial scale projects. Projects of this size require a streamlined, efficient production of the complete floating offshore wind turbine (FOWT), not only for manufacturing the floater but also for assembling the complete system. Most assembly tasks could, in theory, take place in a port, which is generally preferred, but most ports do not have the sufficient port infrastructure to perform those tasks, while the required infrastructure upgrades are very expensive. This is a significant challenge for smaller-scale, first-mover floating wind farms, which do not have sufficient units to justify those substantial investments for the assembly. To overcome this issue, a jack-up type wind turbine installation vessel could be used nearshore to integrate the wind turbine on the floating unit. This would ensure the realisation of the project without major infrastructure investments. At the same time, it could utilise the sheltered area's advantages and be a kick-off for large-scale projects in the region.

This proposed concept has so far not been investigated in academic research. Therefore, this thesis aims to create a general understanding of the system and its characteristics. Based on the example of Port Talbot in the UK, it should be examined how the concept can be implemented in a location. Furthermore, a response analysis of the system is done in SIMA for the single blade installation to understand which motions characterise the integration task and which environmental conditions limit the operation. Those operational limits are then implemented in a Python model of the complete integration sequence to conduct an operability analysis which should also give estimates for the required installation time and costs of the system when subject to wind and wave loads. Based on the findings of those studies, the technical and economic feasibility of the concept should be investigated.

The study has found that the wave-induced floater motions are mainly governing the systems motions during the single blade installation, which leads to very strict operational limits for the waves during the mating procedure. The technical feasibility of the proposed system is given if it is not subject to large tides and if a sufficient control mechanism is implemented for the installation. The operability analysis has shown that the system can be economically feasible if smaller projects should be implemented. For large projects, it is likely more feasible to invest into the port infrastructure.

The research on sustainable energy is growing, among which, wind energy catching growing attention and the potential has been supported by more and more countries. Compared with onshore wind farms, offshore wind farms have more advantages including the abundant wind resource at the offshore location and more possible construction areas. While for an offshore wind farm, the operation and maintenance cost is the most significant part and fleet management contributes a lot to it.

In order to optimize the fleet size and mix problem for an offshore wind farm based on a simulation method, this thesis has performed a few research steps. Firstly, a literature view on the modeling methods of fleet size and mix problems for offshore wind farms is finished. Different modeling methods and different factors considered in the model are viewed. Then, two simulation models, the open-loop simulation model and the feedforward simulation model, are introduced, including the model inputs, model agent and process, and model outputs. Afterward, the simulation-optimization methodology is introduced and the optimization algorithm used in this research is introduced. Next, one case study using two models separately for a long-term optimization and a short-term optimization is executed and followed by the results of these two simulation models as well as the comparison of the results from them.

This thesis aims to combine the optimization method with a simulation model for offshore wind farms, which can be regarded as a decision support tool for fleet size and mix problems and is expected to be a practical technology for the operator/researcher of the offshore wind farm in the future.

Until recently, tenders in Europe were awarded to wind farm developers based on the highest auction prices or the lowest subsidized bids. The wind industry has suggested that non-price-related criteria should be considered for tenders, like plans to reduce greenhouse gas emissions. As a result of the sustainable tender criteria, greenhouse gas emissions are a relatively new KPI for offshore wind farm developers.

Studies have shown that the costs and wind farm availability are sensitive to the fleet composition and were commonly used as criteria in offshore wind fleet optimization models. Offshore wind greenhouse gas emissions were shown to be sensitive to the offshore wind fleet composition as well but thus far not used as criteria for fleet composition decision-making. This study aims to develop an offshore wind O&M multi-objective fleet optimization model that includes GHG emissions as the third criterion for the fleet composition. The model is rendered as a deterministic MIP problem. An epsilon constraint method-inspired approach is proposed to reformulate the multi-objective into a set of perturbed single-objective models, which can be solved using a commercial MIP solver.

Floating offshore wind turbines offer opportunities to harvest wind energy at deep-water locations, where the construction of fixed-base turbines is infeasible. The dynamic power cables, which interconnect turbines and transport the generated electricity, are under large dynamic stresses due to the environmental loads and the motion of the floating platform. Limited knowledge about the structural behaviour of these cables is available, which is why there is need for new analysis and design methods. This MSc thesis presents a method for the preliminary design optimization of the dynamic power cable configuration. A parametric model of a dynamic power cable is built in the commercial software package OrcaFlex, from which motions, loads and fatigue on the cable can be calculated. Following that, a radial basis function model-based optimization algorithm is applied to find the optimal cable configuration for an arbitrary environmental scenario. The key performance indicator here is fatigue damage on the copper conductor, which is expected to be critical due to the cyclic loading on the cable and the poor mechanical properties of copper. Experiments are carried out to test the optimization model’s validity in terms of convergence, robustness and efficiency. The final method is capable of consistently finding a near-optimal dynamic power cable configuration design within reasonable time. Additionally, findings are presented about the fatigue behaviour of the DPC, what causes the fatigue damage and how to mitigate the effects.

Offshore wind energy can play a key role in the energy transition. Reducing installation costs for offshore wind installation projects helps to be cost-competitive with other renewable energy technologies. Installation costs can increase when the installation project planning is delayed. Literature shows that offshore wind installation projects are delayed by weather conditions exceeding operational limits and downtime caused by vessels and equipment. However, the magnitude and causes of downtime due to equipment breakdown are unclear. Additionally, no method is found in the literature to reduce downtime due to equipment breakdown in offshore wind installation. Data-analysis of observed failure data shows that equipment breakdown causes downtime during pinpile installation during the spring and summer seasons. Root-cause analysis indicates that scheduled preventive maintenance is often postponed on the critical path when weather conditions are favourable for installation. These decisions are made based on knowledge of oil and gas projects, but that knowledge is not applicable anymore. In this study a new method is proposed, which includes equipment characteristics and preventive maintenance on the critical path of an installation schedule, using discrete-event simulation (DES). In the DES model, four designs are simulated to gain insight into the effect of decision-making on the critical path on key performance indicators. The designs are based on the planned maintenance pillar of the Total Productive Maintenance framework. Implementing equipment breakdown and preventive maintenance in the installation schedule gives insight into the effects of decision-making before project execution. The results of this study indicate that the downtime due to breakdown and preventive maintenance of the hammer can be reduced by 10% if preventive maintenance is prioritized on the critical path.

In the competitive offshore wind installation market, contractors like DEME strive to optimize operations. This thesis centers on the optimization of the support vessel fleet composition, which consist of a num- ber of walk to work vessels, and are a crucial part of inter-array cable installation. By fine-tuning this composition, operational expenses can be reduced by 10-20% to current industry practices.
The cable installation process involves a complex set of operations, each necessitating a crew to be present on the foundations. Support vessels play a central role in routing of these crews and their equip- ment to these foundations.This thesis introduces an innovative approach that integrates operational scheduling and crew routing into a single formulation for optimizing the fleet of walk-to-work vessels. This hybrid model combines elements of a continuous-time rich multi-visit multi-period Vehicle Routing Problem with a time-varying Resource Constrained Project Scheduling Problem. It also factors in the substantial impact of weather conditions on offshore operations by accounting for variable weather win- dows in each scheduling period.
The formulated model is rigorously verified and validated to ensure it closely mirrors real-world sup- port vessel behavior. Although it slightly underestimates fuel consumption, this discrepancy is deemed acceptable given its minor role in the overall objective. Sensitivity analyses highlight the critical impor- tance of accurate performance data for the cable laying vessel, which significantly influences the model’s outcomes. However, the model is found to be most effective for modeling a single cable string compris- ing 6-8 turbines, with scalability issues arising when attempting to expand beyond this scope.
A focused case study delves into the impact of various weather conditions and inter-array distances on the optimal vessel composition. The study evaluates two types of walk-to-work vessels, individually and in combination. Results reveal that, under the assumption of zero downtime, the industry norm of chartering cheaper vessels is cost-effective, while the pricier vessel results in a 10% costlier solu- tion. As weather conditions worsen, a composition of costlier vessels proves more cost-effective over the scheduling horizon. Such conditions are to be expected in far offshore locations, especially on the cheaper vessels, which have lower workability limits. The study identifies potential cost reductions of up to 25%, with even marginal downtime conditions yielding 10-20% reductions to the industry standard. Moreover, delays imposed on the cable laying vessel are significantly reduced when utilizing a compo- sition that includes at least as one of the more expensive vessels.
In summary, this thesis establishes a foundation for optimizing support vessels in offshore wind installa- tion. The presented model introduces a novel framework, combining multi-visit routing with time-varying resource scheduling, while considering shared vehicles and coupled routing and scheduling over a multi- period horizon. For regions prone to harsh weather conditions, such as those further offshore and during winter months, it is advised to utilize more expensive vessels that have higher workability limits and bet- ter performance figures. Additionally, there appears to be limited justification for simultaneous use of multiple vessels during the cable installation, as the added costs do not seem to outweigh the marginal improvements in installation duration. Future research should focus on refining solution methods for the proposed formulation and incorporating crew transfer vessels into the fleet composition.

The maritime industry is preparing for a future where human presence is no longer required on board of ships. This will revolutionize the global execution of maritime operations and consequentially introduce unprecedented challenges to the corresponding logistics. This paper presents a non-standard facility location problem (FLP) that arises in the maritime survey industry. The goal is to determine a number of uncapacitated facilities and assign a heterogeneous fleet of both remotely operated vessels and traditional vessels to the located facilities in order to serve the inspection demand of offshore infrastructures such as oil platforms and wind parks. The facilities serve as sites where vessels can refuel and accommodate crew changes. Both current traditional vessels and future uncrewed surface vessels (USVs) are considered in the heterogeneous fleet that respectively combines the distinctive routing behavior of centroid-like hubs and drone-like \textit{one-to-one} trips simultaneously. A mixed-integer linear programming (MILP) model is constructed to determine the optimal harbor locations and the associated vessel fleet size \& mix to perform the inspection demand of North-Sea assets over a multi-period time interval. The simulation results are reported for a real case study commissioned by geo-data company Fugro. The results of the model suggest that the effective establishment of facility locations and corresponding fleet allocation can reduce the total costs and environmental footprint of the survey operations in the North-Sea. This research provides a first piece of reflection regarding MIP problems for remote and autonomous operations in the maritime industry. The research pointed out that the complexity of USV operations in combination with traditional vessels is difficult to capture within an acceptably sparse facility location problem. Finally, this study identifies the stochasticity of inspection operations to be the most promising future contribution to automation research in the maritime industry.

During the lifetime of an offshore wind farm, the operation and maintenance (O&M) costs account for a large portion of the total expenses. This is mainly caused by the high cost of vessels. In order to increase the competitiveness of offshore wind compared to onshore wind and other renewable energy sources, it is essential to decrease the cost of power generation of offshore wind. In this context, the scope of this research is the optimization of fleet management decisions, often referred to as the fleet size and mix problem, for the maintenance of offshore wind farms. Therefore, the literature on available solution methods and existing models have been reviewed first. Based on a comparison of the existing models, a simulation model is developed and presented in this report. The developed methodology is illustrated with a case study example. The model is verified by comparing the expected and actual results of various verification experiments. Moreover, several sensitivity analyses are performed. In the last section of this report, recommendations for features that can be added to the model are given. The developed methodology can be used to optimize fleet management decisions for a given maintenance strategy and, in addition, the consequences of various decisions can be evaluated since the model predicts the O&M costs and wind farm power production.

Floating photovoltaic (FPV) is an emerging concept. Potential is recognized in combining FPV and off­ shore wind farms to create an offshore wind and solar farm. One of the remaining uncertainties around the potential of an offshore wind and solar farm is the value of the operations and maintenance cost. As one of the main contributing factors to operations and maintenance costs of offshore wind farms is the accessibility, integration of the transport for maintenance of the wind turbines and solar units can minimize the costs. By means of a route and scheduling optimization tool the optimal route and sched­ ule of maintenance support vessels for a virtual OWSF is investigated. The research indicates that the optimal route and schedule of maintenance support vessels for a virtual OWSF does not include integration of the transport. The main reason is the low costs of an RHIB compared to the cost of a CTV or SOV. However, the optimal route and schedule is very case dependent. Thus recommended is to apply the model to multiple case studies to form a general conclusion.

The main purpose of this report is to investigate flaws within Cornelis Tromp 25T lemniscate crane upper arm joint. This is done in order to figure out why the joint structure is experiencing significant crack propagation and what potentially could have led to a structural joint failure and death of an operator within a crane of the same model.

Assessment is performed by simulating stress distribution within the problematic joint structure and assessing high-cycle fatigue damage accumulation around its welds. Loading conditions affecting crane upper arm are established through multi-body dynamic simulations, which are meant to replicate operation of a lemniscate crane. Multi-body dynamic model is verified for its accuracy using available crane operation measurement data. Loads are acquired within the time domain and include temporal effects of luffing, slewing and hoisting operations as well as pontoon motion.

Fatigue analysis is performed to evaluate damage accumulation within the tubular joint structure of the crane upper arm. A detailed shell finite element model is established to acquire time-dependent stress responses. During stress evaluation stage - a particularly large stress concentration has been observed at the joint brace saddle position. To assess which method best simulate damage accumulation in the joint structure - three specific fatigue assessment approaches are tested: nominal stress approach, hot-spot stress approach and multi-axial fatigue approach. Nominal and hot-spot stress approaches are evaluated and compared to determine how inclusion of stress concentration effects into fatigue assessment influence damage accumulation results. Result comparison has shown a large disparity in results with hot-spot stress approach, indicating that the method capable of determining locations of dangerous stress accumulation, in relation to what has been observed in the real structure.

Evaluation is performed to determine whether multi-axial fatigue assessment is needed to improve calculation results of fatigue damage accumulation.
Based on stress direction properties within the analysed structure - most favorable multi-axial fatigue assessment approach (capable of analysing proportional stress responses) is used. Multi-axial fatigue assessment method results are then compared with results of conventional hot-spot stress approach to evaluate the differences in damage accumulation rate. Analysis results have shown that both methods are capable of determining locations of critical points with present disparity within magnitude of damage accumulation. This indicates that hot-spot stress fatigue approach, which uses Von Mises stress, is more conservative out of two methods. Fatigue analysis has also presented that original joint structure is inherently flawed, as its stress concentration locations are not easily accessible without crane disassembly and its structural capacity has been underestimated during design stage.

Finally methods for extending operational life of crane upper arm structure are evaluated. Three methods for reducing stress within the structure are assessed: increase of structural capacity, stress redistribution and load reduction. Increase of structural capacity is performed by adjusting thickness of relevant joint elements, with optimal thickness being established using a sensitivity analysis algorithm, which simultaneously acquires combined thickness setup for multiple joint elements - making the joint capable of surviving predetermined fatigue life. Stress redistribution approach is implemented by producing an alternative upper arm joint design, which could be exchanged with the problematic original joint during crane refurbishment. Load reduction approach is performed to investigate whether it would be possible to increase fatigue life of the original joint structure without affecting work efficiency, by only adjusting crane motion profile within multi-body dynamic simulation environment. All three methods are quantified and compared through fatigue damage factor results acquired using multi-axial fatigue assessment method. Result comparison has shown that joint redesign is the most preferred approach due to its ability to efficiently improve fatigue life of the structure without significant structural weight increase, while exposing any potential points for crack initiation to locations easily accessible for inspection and repair.

Industrial electric motors are at the heart of almost every industry. They are a 47 billion USD market in 2020 and consume 70% of all industrial electricity. They are generally paired with a gearbox and load, which is referred to as an electric gearmotor system. Being so essential means that it is important to avoid failures, 98% of 300 researched companies by ITIC reported a cost of 100.000 USD every hour of downtime. To detect failures a technology called fault detection and diagnosis (FDD) is used, which is a method to foresee failures or faults in a system that deteriorates over time through evaluating the state of the system. It is an extensively academically research subject, however, has hardly been adopted in industrial settings where electric gearmotor systems are applied. Thus, a FDD model was developed to provide insight, knowledge, and a practical example into the necessities of an industrial FDD model. This was achieved through conducting an analysis on the state-of-the-art of FDD in industrial settings and conducting a literature review on FDD. Based on an analysis of the conclusions a hybrid diagnostics model was developed. For the fault detection a model-based solution was used, it compared the predicted torque to the measured torque of a motor to create a health indication value. If this value crosses a pre-determined threshold an alarm would go off. For fault identification a decision tree machine learning algorithm is used to identify: blockage, bearing, gear or random failure in a system. To verify and validate the hybrid diagnostics model it was applied to a client of SEW Eurodrive where data was available of a known system. The system had a fault detection accuracy as high as 94% and could classify failures with an accuracy of 93%.

As part of the fatigue assessment of a stinger, member loads on tubular joints are determined with a beam model. A beam model is a simplified method of modelling complex structures out of circular hollow sections. In a standard beam model, no attention is paid to modelling the tubular joint itself. In the model, beam elements of the braces are extended from the surface of the chord to the centerline of the chord. This connection is considered as rigid. In reality, tubular joints possess considerable elastic flexibility through local deformation of the chord wall. It is suggested that modelling local joint flexibly leads to a reduction of member-loads and thereby an increase of predicted fatigue life. A method to determine and model local joint flexibility in a beam model is developed. A numerical test-case is performed to investigate the influence of modelling LJF on the predicted fatigue life of the braces in the stinger. As effect of modelling LJF, the accumulated fatigue damage in the critical hot spots of the braces has changed with factor 0.29 up to factor 2.88. This would result in a change in predicted fatigue of factor 0.35 up to 3.45 as effect of modelling LJF.

In this report, a model is presented that automates and optimizes the loading processes for the transport of steel structures at the company of ASK Romein. This transport can be captured in two main loading processes: the loading division, which consists of allocating items to different trailers, and the loading sequence, which considers placing the items onto their respective trailer.
The possibility of automating the process of the loading division is investigated. This includes the digital generation of the loading sequence process. Achieving a form of automation would both mean a reduction in time required to create a loading division as well as allow for optimizing the number of required trailers.
Using an extensive literature review as well as an in-depth investigation of the current situation at the company, a model is developed, which consists of an ALNS heuristic responsible for the loading division, and a new function, the layer heuristic, proposed in this report, that digitally generates the loading sequence.
The proposed model is validated using various experiments on real-life data, including several sensitivity analyses. For the used data set, the model is able to reduce the existing loading division by at least 24%, and the computation time is superior to the current time required to create a loading division. Because the loading sequence process is created digitally, the model is capable of checking all the loading conditions, such as axle loads, even before the actual loading sequence has taken place.

For the shared mobility service providers, it is essential to have an economic operation and therefore, it is necessary to maximise their fleet utilisation. Of influence on the latter is the availability of the spare parts. The topics for which spare part forecasting research is already performed are different in several ways compared to the field of free-floating shared vehicles. The many different users with each different driving skill, wear and tear by operation, events as vandalism and traffic accidents and constantly standing out on the street result in sudden failures of parts. Three different forecast models are presented in this paper. The effect of including demand generating factors in the forecast approach is analysed. The methods show that a better forecast performance can be achieved while including demand generating factors into the analysis. The forecast accuracy can be further improved and some suggestions for improvement are given in the paper.