Knowledge-Based Decision Support for Concept Evaluation Using the Extended Impact Model of Modular Product Families

The design of modular product families enables a high external variety of products by a low internal variety of components and processes. This variety optimization leads to large economic savings along the entire value chain. However, when designing and selecting suitable modular product architecture concepts, often only direct costs are considered, and indirect costs as well as cross-cost center benefits are neglected. A lack of knowledge about the full savings potential often results in the selection of inferior solutions. Since available approaches do not adequately address this problem, this paper provides a new methodological support tool that ensures consideration of the full savings potentials in the evaluation of modular product architecture concepts. For this purpose, the visual knowledge base of the Impact Model of Modular Product Families (IMF) is used, extended and implemented in a model-based environment using SysML. The newly developed Sys-IMF is then applied to the product family example of electric medium-voltage motors. The support tool is dynamic, expandable and filterable and embedded in a methodical procedure for knowledge-based decision support. Sys-IMF supports decision makers in the early phase of interdisciplinary product development and enables the selection of the most suitable modular solution for the company.

Development and Proof-of-Concept Evaluation of a Sensory Science-Based Model for Product Development of Vegetable-Based Products for Children

Children’s vegetable intake is too low, and a key barrier to the inadequate intake is low acceptance. To facilitate successful development of new vegetable-based products for children, a sensory science approach to product development has been taken. A new theoretical model is proposed, the CAMPOV model: Children’s Acceptance Model for Product development of Vegetables. The model is informed by scientific literature and considers biological, psychological, and situational, and intrinsic and extrinsic product factors relevant to children’s acceptance of vegetables, with a focus on modifiable factors at the product level. Simultaneously, 14 new vegetable-based product concepts for children were developed and evaluated through focus groups with 5–8-year-olds (n = 36) as a proof-of-concept evaluation of the model. Children had high interest in six of the concepts. Factors identified from the literature that positively associated with the children’s interest in the concepts included bright colours, bite-sized pieces, good taste, fun eating experience, and familiarity. The CAMPOV model and proof-of-concept evaluation results can guide further sensory and consumer research to increase children’s acceptance of food products containing vegetables, which will in turn provide further insights into the validity of the model. The food industry can use the model as a framework for development of new products for children with high sensory appeal.

Development of a Digital ESP Performance Monitoring System Based on Artificial Intelligence

Wintershall Dea is developing together with partners a digital system to monitor and optimize electrical submersible pump (ESP) performance based on the data from Mittelplate oil field. This tool is using machine learning (ML) models which are fed by historic data and will notify engineers and operators when operating conditions are trending beyond the operating envelope, which enables an operator to mitigate upcoming performance problems. In addition to traditional engineering methods, such a system will capture knowledge by continuous improvement based on ML. With this approach the engineer has a system at hand to support the day-to-day work. Manual monitoring and on demand investigations are now backed up by an intelligent system which permanently monitors the equipment. In order to create such a system, a proof of concept (PoC) study has been initiated with industry partners and data scientists to evaluate historic events, which are used to train the ML-systems. This phase aims to better understand the capabilities of machine learning and data science in the subsurface domain as well as to build up trust for the engineers with such systems. The concept evaluation has shown that the intensive collaboration between engineers and data scientist is essential. A continuous and structured exchange between engineering and data science resulted in a mutual developed product, which fits the engineer's needs based on the technical capabilities and limits set by ML-models. To organize such a development, new project management elements like agile working methods, sprints and scrum methods were utilized. During the development Wintershall Dea has partnered with two organizations. One has a pure data science background and the other one was the data science team of the ESP manufacturer. After the PoC period the following conclusions can be derived: (1) data quality and format is key to success; (2) detailed knowledge of the equipment speeds up the development and the quality of the results; (3) high model accuracy requires a high number of events in the training dataset. The overall conclusion of this PoC is that the collaboration between engineers and data scientists, fostered by the agile project management toolkit and suitable datasets, leads to a successful development. Even when the limits of the ML-algorithms are hit, the model forecast, in combination with traditional engineering methods, adds significant value to the ESP performance. The novelty of such a system is that the production engineer will be supported by trusted ML-models and digital systems. This system in combination with the traditional engineering tools improves monitoring of the equipment and taking decisions leading to increased equipment performance.

The relation between head circumference and mid pelvic circumference: A simple index for cephalo-pelvic disproportion evaluation

Introduction: Cephalo-pelvic-disproportion (CPD) is one of the most common obstetric complications. Since CPD is the disproportion between the fetal head and maternal bony pelvis, evaluation of the head-circumference (HC) relative to maternal bony pelvis may be a useful adjunct to pre-labor CPD evaluation. The aim of the present study was a proof-of-concept evaluation of the ratio between HC to pelvic circumference (PC) as a predictor of CPD. Methods: Of 11,822 deliveries, 104 cases that underwent an abdomino-pelvic CT for any medical indication and who underwent normal vaginal deliveries (NVD) (n=84) or cesarean deliveries (CD) due to CPD (n=20) were included retrospectively. Maternal pelvis dimensions were reconstructed and neonatal HC, as a proxy for fetal HC, were measured. The correlation between cases of CPD and Cephalo-Pelvic Circumference Index (CPCI), which represents the ratio between the HC and PC in percent (HC/PC *100) was evaluated. Results: The mid-pelvis cephalo-pelvic circumference index (MP-CPCI) was larger in CD groups as compared to the NVD group: 103±11 vs. 97±8% respectively (p=0.0003). In logistic regression analysis, the MP-CPCI was found to be independently associated with CD due to CPD: each 1% increase in MP-CPCI increased the likelihood of CD for CPD by 11% (aOR 1.11, CI 95% 1.03-1.19, p=0.004). The adjusted odds ratio for CD due to CPD increased incrementally as the MP-CPCI increased, from 3.56 (95%CI, 1.01-12.6) at MP-CPCI of 100, to 5.6 (95%CI, 1.63-19.45) at 105, 21.44 (95%CI, 3.05-150.84) at 110, and 28.88 (95%CI, 2.3-362.27) at MP-CPCI of 115 Conclusions: The MP-CPCI, representing the relative dimensions of the fetal HC and maternal PC, is a simple tool that can potentially distinguish between parturients at lower and higher risk of CPD. Prospective randomized studies are required to evaluate the feasibility of prenatal pelvimetry and MP-CPCI to predict the risk of CPD during labor.

Design and proof-of-concept evaluation of a touchless connector system for preventing peritoneal dialysis-associated peritonitis.

In this paper, we describe the design of a touchless peritoneal dialysis connector system and how we evaluated its potential for preventing peritoneal dialysis-associated peritonitis, in comparison to the standard of care. The unique feature of this system is an enclosure within which patients can connect and disconnect for therapy, protecting their peritoneal catheters from touch or aerosols. We simulated a worst-case contamination scenario by spraying 40mL of a standardized inoculum [1x107 colony-forming units (CFU) per milliliter] of test organisms, Staphylococcus epidermidis ATCC1228 and Pseudomonas aeruginosa ATCC39327, while test participants made mock connections for therapy. We then compared the incidence of fluid path contamination by test organisms in the touchless connector system and the standard of care. 4 participants were recruited to perform a total of 56 tests, divided in a 1:1 ratio between both systems. Peritoneal dialysis fluid sample from each test was collected and maintained at body temperature (37 C) for 16 hours before being plated on Luria Bertani agar, Mannitol Salts Agar and Pseudomonas isolation agar for enumeration. No contamination was observed in the test samples from the touchless connector system, compared to 65%, 75% and 70% incidence contamination for the standard of care on Luria Bertani agar, Mannitol Salts Agar and Pseudomonas isolation agar respectively. In conclusion, the results show that the touchless connector system can prevent fluid path contamination even in heavy bacterial exposures and may help reduce peritoneal dialysis-associated peritonitis risks from inadvertent contamination with further development.

Leveraging End-User Data for Enhanced Design Concept Evaluation: A Multimodal Deep Regression Model

Design concept evaluation is a key process in the new product development process with a significant impact on the product's success and total cost over its life cycle. This paper is motivated by two limitations of the state-of-the-art in concept evaluation: (1) The amount and diversity of user feedback and insights utilized by existing concept evaluation methods such as quality function deployment are limited. (2) Subjective concept evaluation methods require significant manual effort which in turn may limit the number of concepts considered for evaluation. A Deep Multimodal Design Evaluation (DMDE) model is proposed in this paper to bridge these gaps by providing designers with an accurate and scalable prediction of new concepts' overall and attribute-level desirability based on large-scale user reviews on existing designs. The attribute-level sentiment intensities of users are first extracted and aggregated from online reviews. A multimodal deep regression model is then developed to predict the overall and attribute-level sentiment values based on the features extracted from orthographic product images via a fine-tuned ResNet-50 model and from product descriptions via a fine-tuned BERT model, and aggregated using a novel self-attention-based fusion model. The DMDE model adds a data-driven, user-centered loop within the concept development process to better inform the concept evaluation process. Numerical experiments on a large dataset from an online footwear store indicate a promising performance by the DMDE model with 0.001 MSE loss and over 99.1% accuracy.