J Coy

Acoustic based condition monitoring of a diesel engine using self-organising map networks

In this paper, the acoustic based condition monitoring of a diesel engine is investigated. Firstly, an experimental test rig is set up to simulate engine faults. Acoustic signals are measured from the test diesel engine under different conditions. To analyse the measured acoustic signals, a two-dimensional topological seif-organising map (SOM) network is employed in this paper to perform feature extraction. The extracted features are processed by both statistical and spectral methods. The results show that the extracted features are able to show the differences between the engines normal and faulty conditions.

Integration of the Cimosa and high-level coloured Petri net modelling techniques with application in the postal process using hierarchical dispatching rules

Abstract Enterprise processes, i.e. business and manufacturing, rely on enterprise modelling and simulation tools to assess the quality of their structure and performance in an unobtrusive and cost-effective way. Each of these processes is a collaboration of inseparable elements such as resources, information, operations, and organization. In order to provide a more complete assessment of enterprise processes, a simulation approach that allows communication and interaction among these elements needs to be provided. The simulation approach requires an analysis of the performance of each element and its influence on other elements in an object-oriented way. It also needs to have the capability to represent the structures and dynamics of the elements mentioned, and to present the performance assessment comprehensively. This will ensure a more holistic simulation modelling task. These simulation requirements have motivated the investigation of the novel integration of two popular enterprise process modelling methods: Cimosa and high-level coloured Petri net. The Cimosa framework is used to formalize the enterprise modelling procedure in the aspects of representing process elements, structure, behaviours, and relationships. The high-level coloured Petri nets method provides the mechanism to simulate the dynamics of objects and their characteristics, and also to enable communication among the objects. The approach is applied on a postal process model, which involves elements from manufacturing processes, i.e. machine processing (sorting), inventory (storage), product flow, and resource planning. Simulation studies based on the hierarchical dispatching rules show that the integrated approach is able to present vital information regarding the communication method, resource management, and the effect of interactions among these manufacturing process elements, which are not provided by the current modelling system in the postal company. The current paper has presented a novel mechanism, i.e. Cimosa—HCTSPN modelling approach, to extract information on process elements and their interactions. It has also presented the novel hierarchical dispatching rules and contributed to the extension of information that can be represented for a postal process.

Smarter maintenance through internet-based condition monitoring with indirect sensing, novelty detection, and XML

Abstract In engineering, combining a number of solutions and technologies can result in more effective systems than using only one approach on its own. In particular, it has been shown that in condition monitoring (CM), smarter maintenance systems may be obtained by integrating various sensors together. This paper extends this idea by integrating various non-homogeneous technologies horizontally. The proposed system is an internet-based condition monitoring (e-CM) prototype that can identify abnormal tension in moving belts. It is shown that by applying a classification technique, known as novelty detection, it is possible to decide the status of belt tension by processing the belt vibration signals from an optical sensor (i.e. an indirect sensing approach). A novel method for industrial network communication using XML to create a single standard format for sensor information is also used to link the sensor to the process controller via the internet using the flexible CAN bus technology; this is used together with low-cost microcontrollers with a built-in ethernet link for data acquisition and transmission. The resulting integrated approach is more efficient because: (a) it can reduce waste by minimizing process interruptions caused by direct belt inspection methods while obtaining high detection accuracy (99.67 per cent) and (b) it can provide on-line remote CM that is cost-effective, simple, standardized, and scalable across a wide area and for a relatively large number of sensors. This improvement is especially important when applied to bottleneck processes and critical components.

The Smart Parcel Concept for Condition Monitoring of Materials Handling Machinery

Complex machinery which bears loads over large distances requires a large capital outlay to monitor condition at many points. Hand-held monitoring units necessitate knowledgeable operators and are of limited use when applications involve areas inaccessible during operation. This paper presents the idea of deploying a ‘smart parcel’ to navigate the process, reporting on performance. Equipment was mounted on a receptacle belonging to such a machine, and sound data was recorded for later analysis. Frequencies present were compared with component characteristic frequencies in order to ascertain robustness of method as compared to traditional installations. The presence of common information and also some that are not obtainable by other means has rendered the theory a viable proposal.Copyright

A Novel Approach for Extracting Sensor Information From Different Industrial Networks for Internet Based Condition Monitoring Applications

Automated Condition Monitoring (ACM) has become a necessity for complex modern day systems. The advent and ever increasing popularity of Internet has given a new dimension to ACM. Many Internet Based Condition Monitoring (IBCM) solutions have since been implemented. There are many types of Industrial Networks that are used in the industry to implement ACM. The protocols and information sent through these networks are very different from one another. Sharing information between industrial networks and presenting it for consolidated monitoring can be a daunting task. This paper describes a novel way for extracting sensor information from different industrial networks into a single standard format using Extensible Markup Language (XML). Implementation of the solution with an Industrial Network, Controller Area Network (CAN), is also shown. The results demonstrate that by using this approach communication between automated systems and mechatronic devices will become more integrated, more efficient and less complex.Copyright

Online thermal imaging: a simple approach

Continuous monitoring of plant and processes is widely practised but the use of thermal imagers in such systems has always been restricted by camera cost. A radiometric thermal imager can be regarded as equivalent to multiple single point radiometers or a matrix of thermocouples but with the advantages of far denser coverage, non-contact measurement, simpler installation and data processing; in addition several of the advantages of conventional machine vision systems such as shape and position recognition can be provided. IRISYS has developed a multipoint radiometer utilising its low-cost infrared array technology. This unit provides continuous real-time temperature monitoring of 256 data points at an affordable price; it is housed in a small, light-weight, sealed and robust metal case and generates RS232 or Ethernet data output. This paper reviews the radiometer technology and its application to single and multi-camera systems.