Data-informed inverse design by product usage information: a review, framework and outlook

Hou, Liang; Jiao, Roger J.

doi:10.1007/s10845-019-01463-2

Cited by 62 publications

(53 citation statements)

References 192 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2. Using cyber-infrastructure (van Horn et al, 2012), the captured usage data are fed back into the product creation process (Porter and Heppelmann, 2014;Jun et al, 2007), where they are valuable in all stages (Holler et al, 2017;Hou and Jiao, 2020;Jun et al, 2007), but offer the highest value in the early stages like product planning as these are characterized by lots of uncertainties and the determination of lifecycle costs (Holler et al, 2016b;Holler et al, 2017). Here, the data are used to objectively quantify product performance and usage profiles (van Horn et al, 2012) to find usage-centric improvements for the product under consideration (Holler et al, 2016b;Holmström Olsson and Bosch, 2013;Jun et al, 2007;Hou and Jiao, 2020;van Horn et al, 2012).…”

Section: Main Conceptsmentioning

confidence: 99%

“…3. To identify improvements, statistical analysis, data mining and machine learning techniques must be applied (Hou and Jiao, 2020;Igba et al, 2015). The data analysis can (a) build upon the available data in a bottom-up approach (less effort and faster implementation) or (b) start with a predefined objective in a top-down approach (more effort, clear future-focus) (Wilberg et al, 2017b).…”

Section: Main Conceptsmentioning

confidence: 99%

“…Figure 1: The six main concepts of usage data-driven product planning 6. By feeding back usage data into product planning, usage data-driven product planning represents an inverse design approach which will not replace, but complement the traditional, assumptionbased forward design (Hou and Jiao, 2020;Wilberg et al, 2017a). In conjunction, inverse and forward design form a reinforcing loop for the continuous and iterative improvement of product design (Hou and Jiao, 2020).…”

Section: Iced21mentioning

confidence: 99%

See 2 more Smart Citations

Understanding Usage Data-Driven Product Planning: A Systematic Literature Review

et al. 2021

View full text Add to dashboard Cite

Cyber-physical systems (CPS) are able the collect huge amounts of data about themselves, their users, and their environment during their usage phase. By feeding these usage data back into product planning, manufacturers can optimize their engineering and decision-making processes. Despite promising potentials, most manufacturers still do not analyze usage data within product planning. Also, research on usage data-driven product planning is scarce. Therefore, this paper aims to identify the main concepts, advantages, success factors and challenges of usage data-driven product planning. To answer the corresponding research questions, a comprehensive systematic literature review is conducted. From its results, a detailed description of usage data-driven product planning consisting of six main concepts is derived. Furthermore, taxonomies for the advantages, success factors and challenges of usage data-driven product planning are presented. The six main concepts and the three taxonomies allow for a deeper understanding of the topic while highlighting necessary future actions and research needs.

show abstract

Section: Main Conceptsmentioning

confidence: 99%

Section: Main Conceptsmentioning

confidence: 99%

Section: Iced21mentioning

confidence: 99%

See 1 more Smart Citation

Understanding Usage Data-Driven Product Planning: A Systematic Literature Review

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The data-driven analysis approach towards product design is grounded on the premise that, when manufacturers know how customers are using the products, they can tailor their products much better to actual needs. This enables design decisions to be based on facts and not assumptions [9] The Chatty Factories concept focuses on the opportunity to collect data from IoTenabled sensors embedded in products (Chatty devices) during real-time use by consumers, explores how that data might be immediately transferred into usable information to inform design, and considers what characteristics of the manufacturing environment might optimise the response to such data. Figure 1 illustrates the Chatty Factories concept.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Learning for Product Use Activity Recognition: An Exploratory Study of a “Chatty Device”

Lakoju

Ajienka

Khanesar

et al. 2021

Sensors

View full text Add to dashboard Cite

To create products that are better fit for purpose, manufacturers require new methods for gaining insights into product experience in the wild at scale. “Chatty Factories” is a concept that explores the transformative potential of placing IoT-enabled data-driven systems at the core of design and manufacturing processes, aligned to the Industry 4.0 paradigm. In this paper, we propose a model that enables new forms of agile engineering product development via “chatty” products. Products relay their “experiences” from the consumer world back to designers and product engineers through the mediation provided by embedded sensors, IoT, and data-driven design tools. Our model aims to identify product “experiences” to support the insights into product use. To this end, we create an experiment to: (i) collect sensor data at 100 Hz sampling rate from a “Chatty device” (device with sensors) for six common everyday activities that drive produce experience: standing, walking, sitting, dropping and picking up of the device, placing the device stationary on a side table, and a vibrating surface; (ii) pre-process and manually label the product use activity data; (iii) compare a total of four Unsupervised Machine Learning models (three classic and the fuzzy C-means algorithm) for product use activity recognition for each unique sensor; and (iv) present and discuss our findings. The empirical results demonstrate the feasibility of applying unsupervised machine learning algorithms for clustering product use activity. The highest obtained F-measure is 0.87, and MCC of 0.84, when the Fuzzy C-means algorithm is applied for clustering, outperforming the other three algorithms applied.

show abstract

“…With the recent advances in information gathering techniques, the deviation data could be collected during the product usage stage, which provides a resource base for knowledge discovery in the design field [9]. The whole process would form a closed-loop product usage data-informed inverse design [10]. In recent years, machine learning algorithms make it possible to mine useful information based on limited data.…”

Section: Introductionmentioning

confidence: 99%

A Data-Driven Methodology to Improve Tolerance Allocation Using Product Usage Data

Gao

Zheng

et al. 2021

Journal of Mechanical Design

View full text Add to dashboard Cite

Industry 4.0 puts forward new requirements for the sustainable service of products. With the recent advances in measurement technologies, global and local deformations in inaccessible areas can be monitored. Product usage data such as geometric deviation, position deviation and angular deviation that lead to product functional performance degradation can be continuously collected during the product usage stage. These technologies provide opportunities to improve tolerance design by optimizing tolerance allocation using product usage data. The challenge lies in how to assess these deviations for identifying relevant field factors and reallocate the tolerance value. In this paper, a data-driven methodology based on the deviation for tolerance analysis is proposed to optimize the tolerance allocation. A feature graph of a mechanical assembly is established based on the assembly relationship. The node representation in the feature graph is defined based on the unified Jacobian-torsor model and the node label is calculated by a synthetic evaluation method. A novel algorithm based on the graph neural networks (GNNs) is proposed to investigate hidden relations between nodes in the feature graph and calculate labels of all nodes. A modification necessity index (MNI) is defined for each tolerance between two nodes based on their labels. A deviation difference matrix is constructed to calculate the MNI of each tolerance for identifying the to-be-modified tolerance value with high priorities for product improvement. The effectiveness of the proposed methodology is demonstrated through a case study for the optimal tolerance allocation of a press machine.

show abstract

Data-informed inverse design by product usage information: a review, framework and outlook

Cited by 62 publications

References 192 publications

Understanding Usage Data-Driven Product Planning: A Systematic Literature Review

Understanding Usage Data-Driven Product Planning: A Systematic Literature Review

Unsupervised Learning for Product Use Activity Recognition: An Exploratory Study of a “Chatty Device”

A Data-Driven Methodology to Improve Tolerance Allocation Using Product Usage Data

Contact Info

Product

Resources

About