To maximize its value, the design, development and implementation of structural health monitoring (SHM) should focus on its role in facilitating decision support. In this position paper, we offer perspectives on the synergy between SHM and decision-making. We propose a classification of SHM use cases aligning with various dimensions that are closely linked to the respective decision contexts. The types of decisions that have to be supported by the SHM system within these settings are discussed along with the corresponding challenges. We provide an overview of different classes of models that are required for integrating SHM in the decision-making process to support the operation and maintenance of structures and infrastructure systems. Fundamental decision-theoretic principles and state-of-the-art methods for optimizing maintenance and operational decision-making under uncertainty are briefly discussed. Finally, we offer a viewpoint on the appropriate course of action for quantifying, validating, and maximizing the added value generated by SHM. This work aspires to synthesize the different perspectives of the SHM, Prognostic Health Management, and reliability communities, and provide directions to researchers and practitioners working towards more pervasive monitoring-based decision-support.

As the popularity of adhesive joints in industry increases, so does the need for tools to support the process of selecting a suitable adhesive. While some such tools already exist, they are either too limited in scope or offer too little flexibility in use. This work presents a more advanced tool, that was developed together with a team of adhesive experts. We first extract the experts’ knowledge about this domain and formalize it in a Knowledge Base (KB). The IDP-Z3 reasoning system can then be used to derive the necessary functionality from this KB. Together with a user-friendly interactive interface, this creates an easy-to-use tool capable of assisting the adhesive experts. To validate our approach, we performed user testing in the form of qualitative interviews. The experts are very positive about the tool, stating that, among others, it will help save time and find more suitable adhesives.

The number of publications on methods in product development is increasing constantly. In addition to scientific models, method guidelines exist in practice to support the selection of suitable methods. When looking more closely, it is noticeable that new methods are not new developments of methodical principles, but rather adaptations and summaries of known methods to specific application areas.Although approaches to standardize methods exist, they are usually formulated too abstractly to be useful to project managers as a support for method decision making.In our contribution, we analyse common methods of technical product development regarding similarities in content and time. In doing so, we were able to derive a method DNA on the basis of which all methods can be described and, above all, distinguished in a verifiable manner. In addition to essential activity blocks, the DNA also includes the description of temporal sequences, which in particular enables a differentiation between agile and classic methods. Ultimately, the method DNA not only offers the chance to make methodical work comprehensible, but also the possibility to select methods specifically for upcoming development steps arises through the classification option.

Wind energy’s ability to liberate the world from conventional sources of energy relies on lowering the significant costs associated with the maintenance of wind turbines. Since icing events on turbine rotor blades are a leading cause of operational failures, identifying icing in advance is critical. Some recent studies have utilized deep learning (DL) techniques to predict icing events with high accuracy by leveraging rotor blade images, but these studies only focus on specific wind parks and fail to generalize to unseen scenarios (e.g., new rotor blade designs). In this paper, we aim to facilitate ice prediction on the face of lack of ice images in new wind parks. We propose the utilization of synthetic data augmentation via a generative artificial intelligence technique—the neural style transfer algorithm to improve the generalization of existing ice prediction models. We also compare the proposed technique with the CycleGAN as a baseline. We show that training standalone DL models with augmented data that captures domain-invariant icing characteristics can help improve predictive performance across multiple wind parks. Through efficient identification of icing, this study can support preventive maintenance of wind energy sources by making them more reliable toward tackling climate change.

Qualitative interviews of farmers were carried out as part of a project focusing on developing animal welfare assessment systems (AWASs) in dairy, pig and mink production systems (26 farms in total). The aims of the interviews were to investigate farmers’ perceptions and experience of how an AWAS worked, and to explore their expectations for future use of AWASs. All interviews were taped, transcribed and analysed using a grounded-theory approach. The importance of different elements of the AWAS differed between farmers, and between farmers and the AWAS project implementation group. More direct associations between welfare assessment and production results (and other ‘common measures ‘) were requested by farmers. The whole AWAS ‘package’ was viewed as being too complex and expensive for most farmers, particularly as it involved multiple assessments over time. A range of themes emerged from the analysis. One of these, here referred to as ‘us and them’, is explored and discussed in this paper. Farmers were concerned that the AWAS could be used negatively in relation to consumers and political decisions, and they underlined that if the AWAS was to be used as a decision support tool (ie a system to assist them in making decisions about improvements in their herds and to guide their initiatives and improvements), it should include dialogue and details of local farm conditions. Qualitative interviews were found to provide valuable insight into farmers’ perceptions and expectations of animal welfare assessment methods.

A welfare assessment system is being developed for commercial organic egg production based on indicators of behaviour, health, system, and management, which is the general Danish Institute for Agricultural Science (DIAS) concept for assessing animal welfare at farm level. The welfare assessment system works as an advisory tool for farmers, helping them to improve welfare in their flocks. Identification of individual animals in organic egg production is impossible; therefore, management and welfare assessment are based on flock evaluation. Mortality is often a major welfare problem in organic egg production, to some extent caused by inefficient disease detection and control. Health indicators are therefore closely monitored, including variations in live weight, mortality, food and water consumption, and autopsies. Severe outbreaks of feather pecking and cannibalism causing excess mortality are often induced by the presence of stressors. Various stressors, as well as indicators of stress, are therefore included in the welfare indicator protocol. Finally the daily management effort and routines are evaluated on the basis of a management plan prepared by the farmer and a consultant in cooperation, as well as by use of interviews.

The choice of components in industrial design involves setting design parameters that typically must reside inside permissible ranges called “design margins”. This paper proposes a novel automated method called the Margin-Based General Regression Neural Network (MB-GRNN) that classifies design errors for design parameters that are outside of permissible ranges as outliers, directly from industrial design data, using an unsupervised machine learning approach. The method is based on a modified GRNN that estimates extremal margin boundaries of design parameters by self-learning the features from datasets. These extremal permissible margin boundaries are determined by “stretching out” the upper and lower GRNN surfaces using an iterative application of stretch factors (a second kernel weighting factor). The method creates a variable insensitive band surrounding the data cloud, interlinked with the normal regression function, providing upper and lower margin boundaries. These boundaries can then be used to determine outliers and to predict a range of permissible values of design parameters during design. Pushing out extremal margin boundaries reduce the false identification of outliers. This classification technique could be used by industrial engineers to detect likely outliers and to predict a range of permissible output limits for chosen design parameters. The efficacy of this method has been validated against the widespread Parzen window method by comparing experimental results from three multivariate datasets. It was found that the two methods have different but complementary capabilities. The MB-GRNN also uses a modified algorithm for estimating the smoothing parameter using a combination of clustering, k-nearest neighbor, and localized covariance matrix.

This paper presents a methodology to support the decision-making process during the planning of ship operations. The methodology is designed with the aim of identifying and providing the operator with the best Estimated Time of Departure (ETD)–Estimated Time of Arrival (ETA) window of opportunity to execute the journey/operation between two predefined locations. To achieve this purpose, the International Maritime Organization (IMO) stability criteria are exploited in the process to formulate an operational safety criterion based on fuzzy reasoning as a function of the METeorological and OCeanographic (METOC) and sailing conditions. This allows for the analysis of the set of Pareto routes computed by a weather routing systems relying on a multi-objective set-up. The proposed methodology is tested in an operational scenario in the Mediterranean Sea.

Key to bridging knowing–doing gaps is analysis of the constraints binding interactions between decision-makers and conservation biologists to clarify the problems they address. We apply this analysis to decision situations in the Northern Vosges (France), which illustrate three kinds of constraints: governance, framework and initiative. We explore how conservation biologists can mitigate constraints so as to foster more ambitious conservation actions in each case. The first case explores attempts at reintroducing the lynx (Lynx lynx). In this case, we show that governance plays a key role, in the sense that conservation actions should focus on improving the acceptability of reintroductions to key stakeholders. The second case refers to water monitoring schemes. Here we show that framing is the dominant constraint. This means that conservation actions are tightly limited by the use of a restrictive scientific apparatus. The last case study, fish stock protection, is constrained by initiative. Here, decision-makers have too much leverage to implement solutions they favour, even if they are not the best options in conservation terms. Exploring how our framework relates to the existing literature allows us to highlight its usefulness for rationalizing conservation problem framing and for strengthening the ambitions of conservation actions.

Rough sleeping is a chronic experience faced by some of the most disadvantaged people in modern society. This paper describes work carried out in partnership with Homeless Link (HL), a UK-based charity, in developing a data-driven approach to better connect people sleeping rough on the streets with outreach service providers. HL's platform has grown exponentially in recent years, leading to thousands of alerts per day during extreme weather events; this overwhelms the volunteer-based system they currently rely upon for the processing of alerts. In order to solve this problem, we propose a human-centered machine learning system to augment the volunteers' efforts by prioritizing alerts based on the likelihood of making a successful connection with a rough sleeper. This addresses capacity and resource limitations whilst allowing HL to quickly, effectively, and equitably process all of the alerts that they receive. Initial evaluation using historical data shows that our approach increases the rate at which rough sleepers are found following a referral by at least 15% based on labeled data, implying a greater overall increase when the alerts with unknown outcomes are considered, and suggesting the benefit in a trial taking place over a longer period to assess the models in practice. The discussion and modeling process is done with careful considerations of ethics, transparency, and explainability due to the sensitive nature of the data involved and the vulnerability of the people that are affected.

When designing complex systems, multiple people contribute to the process of information collection in support of decision making. In this paper, we study information collection in the Issue Resolution Decision Support (IRDS) framework. We assess the difficulties associated with uncertainty in the often scarce data when implementing the framework in a company and map out how the data sources are scattered across the organization. We study the elicitation process and propose to leverage sensitivity analysis to better allocate data collection efforts.

Quantifying reasonable crop yield gaps and determining potential regions for yield improvement can facilitate regional plant structure adjustment and promote crop production. The current study attempted to evaluate the yield gap in a region at multi-scales through model simulation and farmer investigation. Taking the winter wheat yield gap in the Huang-Huai-Hai farming region (HFR) for the case study, 241 farmers’ fields in four typical high-yield demonstration areas were surveyed to determine the yield limitation index and attainable yield. In addition, the theoretical and realizable yield gap of winter wheat in 386 counties of the HFR was assessed. Results showed that the average field yield of the demonstration plots was 8282 kg/ha, accounting for 0.72 of the potential yield, which represented the highest production in the region. The HFR consists of seven sub-regions designated 2.1–2.7: the largest attainable yield gap existed in the 2.6 sub-region, in the southwest of the HFR, while the smallest was in the 2.2 sub-region, in the northwest of the HFR. With a high irrigated area rate, the yield gap in the 2.2 sub-region could hardly be reduced by increasing irrigation, while a lack of irrigation remained an important limiting factor for narrowing the yield gap in 2.3 sub-region, in the middle of the HFR. Therefore, a multi-scale yield gap evaluation framework integrated with typical field survey and crop model analysis could provide valuable information for narrowing the yield gap.

Farmers, who have to decide which pesticide to use against a particular crop-damaging pest, need to take into account country-specific regulations (e.g. permitted levels of pesticide residues), application instructions and financial considerations. The fact that these data are stored in different locations, sometimes using different terminology or different languages, makes it difficult to gather these data and requires that farmers are familiar with the variety of terms used, which consequently hampers the efficiency and effectiveness of the decision process. To overcome these challenges, a Web application for pest control is proposed to facilitate the integration of information coming from different Internet sources and representing different terminologies by using an ontology. The application is based on a pest-control ontology (formal representations of domain knowledge that can be interpreted by computers) that accounts for various pesticide regulations of different countries to which the crop is exported. In recent years, ontologies have become a major tool for domain knowledge representation and a core component of many knowledge management systems, decision support systems and other intelligent systems, inter alia, in the context of agriculture. The pest-control ontology developed in the current research includes pest-control concepts that have yet to be covered by existing ontologies. It is demonstrated in the specific case of pepper in Israel. The ontology is expressed using Web Ontology Language (OWL) and thus can be shared on the Web and reused by other ontologies and systems. In addition, a comprehensive method for developing and evaluating agricultural ontologies is presented.

In multi-domain product development organizations, there is a continuous need to transfer captured knowledge between engineers to enable better design decisions in the future. The objective of this paper is to evaluate how engineering knowledge can be captured, disseminated and (re)used by applying a knowledge reuse tool entitled Engineering Checksheet (ECS). The tool was introduced in 2012 and this evaluation has been performed over the 2017–2018 period. This case study focused on codified knowledge in incremental product development with a high reuse potential both in and over time. The evaluation draws conclusions from the perspectives of the knowledge workers (the engineers), knowledge owners and knowledge managers. The study concludes that the ECS has been found to be valuable in enabling a timely understanding of technological concepts related to low level engineering tasks in the product development process. Hence, this enables knowledge flow and, in particular, reuse among inexperienced engineers, as well as providing quick and accurate quality control for experienced engineers. The findings regarding knowledge ownership and management relate to the need for clearly defining a knowledge owner structure in which communities of practice take responsibility for empowering engineers to use ECS and as knowledge evolves managing updates to the ECS.