Zahid Usman

A model-driven ontology approach for manufacturing system interoperability and knowledge sharing

The requirements for the interoperability of semantics and knowledge have become increasingly important in Product Lifecycle Management (PLM), in the drive towards knowledge-driven decision support in the manufacturing industry. This article presents a novel concept, based on the Model Driven Architecture (MDA). The concept has been implemented under the Interoperable Manufacturing Knowledge Systems (IMKS) project in order to understand the extent to which manufacturing system interoperability can be supported using radically new methods of knowledge sharing. The concept exploits the capabilities of semantically well-defined core concepts formalised in a Common Logic-based ontology language. The core semantics can be specialised to configure multiple application-specific knowledge bases, as well as product and manufacturing information platforms. Furthermore, the utilisation of the expressive ontology language and the generic nature of core concepts help support the specification of system mechanisms to enable the verification of knowledge across multiple platforms. An experimental demonstration, using a test case based on the design and manufacture of an aerospace part, has been realised. This has led to the identification of several benefits of the approach, its current limitations as well as the areas to be considered for further work.

Towards a formal manufacturing reference ontology

Due to the advancement in the application of Information and Communication Technology (ICT), manufacturing industry and its many domains employ a wide range of different ICT tools. To be competitive, industries need to communicate effectively within and across their many system domains. This communication is hindered by the diversity in the semantics of concepts and information structures of these different domain systems. Whilst international standards provide an effective route to information sharing within narrowly specified domains, they are themselves not interoperable across the wide range of application domains needed to support manufacturing industry due to the inconsistency of concept semantics. Formal ontologies have shown promise in removing interpretation problems by computationally capturing the semantics of concepts, ensuring their consistency and thus providing a verifiable and shared understanding across multiple domains. The research work reported in this paper contributes to the development of formal reference ontology for manufacturing, which is envisaged as a key component in future interoperable manufacturing systems. A set of core manufacturing concepts are identified and their semantics have been captured in formal logic based on exploiting and extending existing standards’ definitions, where possible combined with an industrial investigation of the concepts required. A successful experimental investigation has been conducted to verify the application of the ontology based on the interaction between concepts in the design and manufacturing domains of an aerospace component.

Towards the ontology-based consolidation of production-centric standards

Production-centric international standards are intended to serve as an important route towards information sharing across manufacturing decision support systems. As a consequence of the textual-based definitions of the concepts acknowledged within these standards, their inability to fully interoperate becomes an issue, especially since a multitude of standards are required to cover the needs of extensive domains such as manufacturing industries. To help reinforce the current understanding to support the consolidation of production-centric standards for improved information sharing, this article explores the specification of well-defined core concepts that can be used as a basis for capturing tailored semantic definitions. The potentials of two heavyweight ontological approaches, notably Common Logic (CL) and the Web Ontology Language (OWL), as candidates for the task are also explored. An important finding regarding these two methods is that while an OWL-based approach shows capabilities towards applications that may require flexible hierarchies of concepts, a CL-based method represents a favoured contender for scoped and facts-driven manufacturing applications.

Extending product lifecycle management for manufacturing knowledge sharing

Product lifecycle management provides a framework for information sharing that promotes various types of decision-making procedures. For product lifecycle management to advance towards knowledge-driven decision support, then this demands more than simply exchanging information. There is, therefore, a need to formally capture best practice through-life engineering knowledge that can be fed back across the product lifecycle. This article investigates the interoperable manufacturing knowledge systems concept. Interoperable manufacturing knowledge systems use an expressive ontological approach that drives the improved configuration of product lifecycle management systems for manufacturing knowledge sharing. An ontology of relevant core product lifecycle concepts is identified from which viewpoint-specific domains, such as design and manufacture, can be formalised. Essential ontology-based mechanisms are accommodated to support the verification and sharing of manufacturing knowledge across domains. The work has been experimentally assessed using an aerospace compressor disc design and manufacture example. While it has been demonstrated that the approach supports the representation of disparate design and manufacture perspectives as well as manufacturing knowledge feedback in a timely manner, areas for improvement have also been identified for future work.

A Manufacturing Foundation Ontology for Product Life Cycle Interoperability

This paper presents the idea of a proposed Manufacturing Foundation Ontology (MFO) aimed at acting as a basis for the Product Life Cycle (PLC) interoperability. MFO is aimed to have the provision for introducing interoperability not only across departments but across organization as well. The proposed idea shows the development of a MFO in several layers and various levels in those layers. The foundation ontology will act as a basis for building Interoperable knowledge bases or ‘World Models’ from a library of formally defined concepts in a heavy weight ontology. MFO must be flexible enough to allow organizations to be able to model their own domains with the flexibility to use the terms they want. Rules and axioms governing each and every concept add rigour to the semantics of the MFO and restrict the use of concepts to facilitate interoperability with a minimum effect on flexibility to model.

A Manufacturing Core Concepts Ontology for Product Lifecycle Interoperability

This paper proposes a manufacturing core concepts ontology (MCCO) aimed at providing support for product life cycle interoperability. The potential focus of the work is interoperability across the production and design domains of product lifecycle. A core set of manufacturing concepts and their key relationships are identified in MCCO. Semantics are captured formally through heavyweight logic using rigorous rules and axioms. Three different levels of specialization have been identified according to the degree of specialization required. Each level provides an immediate route to interoperability for the concepts specialized from that level. MCCO enable knowledge sharing across design and production domains through core concepts. A successful initial experimental implementation has been done to demonstrate the working of MCCO.

Exploiting unified modelling language UML as a preliminary design tool for Common Logic-based ontologies in manufacturing

This paper proposes a particular method which utilises the unified modelling language (UML) as a design visualisation tool for modelling ontologies based on the Common Logic knowledge representation language. The use of this method will enable Common Logic ontological concepts to be more readily accessible to general engineers and provide a valuable ontology design aid. The method proposed is explored using the knowledge frame language (KFL) which provides constructs to facilitate ontology building and is built on Common Logic. The major constructs of KFL are briefly defined and a description of how each construct may be represented in UML is given. Examples are presented showing how the constructs may be modelled in UML and a Common Logic-based implementation founded on a UML design is illustrated and discussed. The manufacturing domain is utilised as an experimental basis for demonstrating the proposed method.

Interoperable manufacturing knowledge systems

For many years now, the importance of semantic technologies, that provide a formal, logic-based route to sharing meaning, has been recognised as offering the potential to support interoperability across multiple-related applications and hence, drive manufacturing competitiveness in the digital manufacturing age. However, progress in support of manufacturing enterprise interoperability has tended to be limited to fairly narrow domains of applicability. This paper presents a progression of research and understanding, culminating in the work undertaken in the recent EU FLEXINET project, to develop a comprehensive manufacturing reference ontology that can (a) support the clarification of understanding across domains, (b) support the ability to flexibly share information across interacting software systems and (c) provide the ability to readily configure company knowledge bases to support interoperable manufacturing systems.

3D vision assisted flexible robotic assembly of machine components

Robotic assembly systems either make use of expensive fixtures to hold components in predefined locations, or the poses of the components are determined using various machine vision techniques. Vision-guided assembly robots can handle subtle variations in geometries and poses of parts. Therefore, they provide greater flexibility than the use of fixtures. However, the currently established vision-guided assembly systems use 2D vision, which is limited to three degrees of freedom. The work reported in this paper is focused on flexible automated assembly of clearance fit machine components using 3D vision. The recognition and the estimation of the poses of the components are achieved by matching their CAD models with the acquired point cloud data of the scene. Experimental results obtained from a robot demonstrating the assembly of a set of rings on a shaft show that the developed system is not only reliable and accurate, but also fast enough for industrial deployment.

Learning industrial robot force/torque compensation: A comparison of support vector and random forests regression

Haptics, as well as force and torque measurements, are increasingly gaining attention in the fields of kinesthetic learning and robot Learning from demonstration (LfD). For such learning techniques, it is essential to obtain accurate force and torque measurements in order to enable accurate control. However, force and torque measurements using a 6-axis force and torque sensor mounted at the end effector of an industrial robot are known to be corrupted due to the robots internal forces, gravity, un-modelled dynamics and nonlinear effects. This paper presents an evaluation of two techniques, SVR and Random Forests, to recover the external forces and accurately selected possible contact situations by estimating a robots internal forces. The performance of the learned models have been evaluated using different performance metrics and comparing them with respect to the features contained in the input space. Both SVR and Random Forests require low computational complexity without intensive training over the operational space under the given ssumptions. In addition, these methods do not need data to be available online. The SVR and Random Forests models are experimentally validated using Motoman SDA10D dual-arm industrial robot controlled by Robot Operating System (ROS). The experiments showed that force and torque compensation based on Random Forests has outperformed Support Vector Regression.