Ananda Prasanna Jagadeesan

A product configurator for cloud manufacturing

Product configurators have become an important enabler for enterprises to achieve product customization in order to address individual customers’ requirements. Despite adoption across a wide range of application domains from automotive to consumer goods, even state-of-the-art product configuration systems are limited in their ability to quickly respond to changes in the production systems that deliver the goods specified. Enabled by the emerging paradigm of cloud manufacturing, the authors propose a “configurable configurator” that is automatically updated to reflect changes in the supply chain. The paper reports the ongoing research and development towards a dynamically generated system that supports product configuration, visualization and assessment from the cloud manufacturing concept of Manufacturing-as-a-Service (MaaS). In addition to outlining the architecture of such a system, an overview of its modules and integration to the cloud manufacturing platform is described. Lastly, the case study of a customizable facade module is presented with two different scenarios to demonstrate the prototype implementation and validate the proposed approach.

Realising the affective potential of patents: a new model of database interpretation for user-centred design

ABSTRACT This research sets out a new interpretation of the patent database using affective design parameters. While this resource contains a vast quantity of technical information, its extraction and use in practical design settings is extremely challenging. Until now, all filing and subsequent landscaping or profiling of patents has been based on their technical characteristics. We set out an alternative approach that utilises crowdsourcing to first summarise patents and then applies text analysis tools to assess the summarising text in relation to three affective parameters: appearance, ease of use, and semantics. The results been used to create novel patent clusters that provide an alternative perspective on relevant technical data, and support user-centric engineering design. The workflow and tasks to effectively interface with the crowd are outlined, and the process for harvesting and processing responses using a combination of manual and computational analysis is reviewed. The process creates sets of descriptive words for each patent which differ significantly from those created using only functional requirements, and support a new paradigm for the use of big data in engineering design – one that utilises desirable affective qualities as the basis for scouring and presenting relevant functional patent information for concept generation and development.

Crowdsourcing solutions to 2D irregular strip packing problems from Internet workers

Many industrial processes require the nesting of 2D profiles prior to the cutting, or stamping, of components from raw sheet material. Despite decades of sustained academic effort, algorithmic solutions are still sub-optimal and produce results that can frequently be improved by manual inspection. However, the Internet offers the prospect of novel ‘human-in-the-loop’ approaches to nesting problems that uses online workers to produce packing efficiencies beyond the reach of current CAM packages. To investigate the feasibility of such an approach, this paper reports on the speed and efficiency of online workers engaged in the interactive nesting of six standard benchmark data-sets. To ensure the results accurately characterise the diverse educational and social backgrounds of the many different labour forces available online, the study has been conducted with subjects based in both Indian IT service (i.e. Rural BPOs) centres and a network of homeworkers in Northern Scotland. The results (i.e. time and packing efficiency) of the human workers are contrasted with both the baseline performance of a commercial CAM package and recent research results. The paper concludes that online workers could consistently achieve packing efficiencies roughly 4% higher than the commercial based-line established by the project. Beyond characterising the abilities of online workers to nest components, the results also make a contribution to the development of algorithmic solutions by reporting new solutions to the benchmark problems and demonstrating methods for assessing the packing strategy employed by the best workers.

Enabling product customisation in manufacturing clouds

Cloud manufacturing has emerged as new manufacturing paradigm providing a service-oriented approach to integrate distributed manufacturing resources and to utilise available manufacturing capabilities for collaborative and networked production. With increasing demand for complex customer-oriented products, cloud manufacturing presents provides a promising solution to address the challenges involved in customised specification and production across the supply chain. In this chapter, a concept and architecture is proposed to enable the dynamic customisation of products based on the availabilities of the production network from the cloud manufacturing concept of Manufacturing-as-a-Service (MaaS). An overview of the MaaS concept and architecture is described, which include the core components for product configuration, manufacturing service management and the integration of factory-IT systems. In addition, the proposed manufacturing service description used to enable the provision of customised options is presented. Finally, a case study is presented which demonstrates the feasibility of MaaS concept for customised products. This is followed by an evaluation of the implemented cloud manufacturing platform provided from an industrial perspective.

Computing the Incomputable with Human Processing Units

Initially commercial crowdsourcing services (such as Amazon’s Mechanical Turk) were focused largely on providing micro-labor services for tasks such as image labeling and text processing. However it is becoming increasingly apparent that these services can also be regarded as providing parallel, on-demand, networks of (so-called) ‘Human Processing Units’ (HPUs). Such services are able to provide specialist computational facilities in a manner analogous to the way Graphics Processing Units (GPUs) support the specialist process of high speed rendering. This paper describes how this new technology could extend the functionality of mechanical CAD/CAM or PLM systems. Crucial to the commercial feasibility of such systems is the ability to access networks of HPUs where engineering data can be processed securely (unlike open crowdsourcing sites such as mTurk). The paper reports the initial results of work done to establish the feasibility of a proposed architecture for integrating HPUs into desktop CAD that uses established BPO centers in rural India to provide a secure source of geometric intelligence.

Fast human classification of 3D object benchmarks

Although a significant number of benchmark data sets for 3D object based retrieval systems have been proposed over the last decade their value is dependent on a robust classification of their content being available. Ideally researchers would want hundreds of people to have classified thousands of parts and the results recorded in a manner that explicitly shows how the similarity assessments varies with the precision used to make the judgement. This paper reports a study which investigated the proposition that Internet Crowdsourcing could be used to quickly and cheaply provide benchmark classifications of 3D shapes. The collective judgments of the anonymous workers produce a classification that has surprisingly fine granularity and precision. The paper reports the results of validating Crowdsourced judgements of 3D similarity against Purdues ESB and concludes with an estimate of the overall costs associated with large scale classification tasks involving many tens of thousands of models.

A novel hybrid intelligence approach for 2D packing through internet crowdsourcing

Packing problems on its current state are being utilized for wide area of industrial applications. The aim of present research is to create and implement an intelligent system that tackles the problem of 2D packing of objects inside a 2D container, such that objects do not overlap and the container area is to be maximized. The packing problem becomes easier, when regular/rectangular objects and container are used. In most of the practical situations, the usage of irregular objects comes to existence. To solve the packing problem of irregular objects inside a rectangular container, a hybrid intelligence approach is introduced in our proposed work. The combination of machine intelligence and human intelligence is referred as the hybrid intelligence or semi-automated approach in the proposed methodology. The incorporation of human intelligence in the outcome of machine intelligence is possible to obtain using the internet crowdsourcing as we wish to handle the packing problem through internet crowdsourcing involving rural people. The proposed methodology is tested on different standard data sets and it is observed that it has clear advantage over both manual as well as fully automated heuristic based methods in terms of time and space efficiency.

Social implications of crowd sourcing in rural Scotland

Various surveys mentioned that the benefits of ubiquitous crowdsourcing are reaped by people located in metro and smaller cities. The reach of crowdsourcing to rural population is questionable. The aim of this research is to bridge widening urban and rural divide by providing knowledge-intensive crowdsourcing tasks to rural work force which could provide long term benefits to them as well as improve supporting infrastructure. This paper reports an initial study of the demographic of small samples of twenty two rural homeworkers in Scotland, their motivation to do crowdsourcing work, present main occupation, computer skills, views on rural infrastructure and finally their skills on solving three spatial visualization tests. The survey shows that flexible hours of working, extra income, and work life balance are the three important factors emphasized as motivational constructs to do crowdsourcing work. Their skills on solving a spatial visualization test is equivalent to the literature reported results, and also high correlations are identified between these tests. These results demonstrate that with minimum training the homeworkers could able to solve knowledge-intensive industrial spatial reasoning problems to increase their earning potentials.