Projects / Programmes source: ARIS

Prognostics and health management of mechanical drives based on novel MEMS sensor networks

Research activity

Code Science Field Subfield
2.11.02  Engineering sciences and technologies  Mechanical design  Special constructions know-how 

Code Science Field
T125  Technological sciences  Automation, robotics, control engineering 

Code Science Field
2.11  Engineering and Technology  Other engineering and technologies 
condition monitoring, MEMS, fault detection, fault isolation, tribology, prognostics, signal processing
Evaluation (rules)
source: COBISS
Researchers (15)
no. Code Name and surname Research area Role Period No. of publicationsNo. of publications
1.  11905  PhD Aleš Babnik  Manufacturing technologies and systems  Researcher  2014  103 
2.  34624  PhD Pavle Boškoski  Systems and cybernetics  Researcher  2013 - 2014  175 
3.  15735  PhD Gregor Dolanc  Systems and cybernetics  Researcher  2011 - 2014  210 
4.  18583  PhD Janez Jamšek  Computer science and informatics  Researcher  2011 - 2014  199 
5.  36571  Rok Jelovčan    Technical associate  2013 - 2014  86 
6.  21238  PhD Matija Jezeršek  Manufacturing technologies and systems  Researcher  2014  373 
7.  02561  PhD Đani Juričić  Systems and cybernetics  Researcher  2011 - 2014  413 
8.  20241  PhD Gregor Kandare  Systems and cybernetics  Researcher  2011 - 2012  43 
9.  19238  PhD Boris Kržan  Mechanical design  Researcher  2011 - 2014  137 
10.  24749  PhD Franc Majdič  Mechanical design  Researcher  2011 - 2014  571 
11.  04543  PhD Janko Petrovčič  Systems and cybernetics  Researcher  2011 - 2014  320 
12.  05573  PhD Jožef Pezdirnik  Mechanical design  Researcher  2011 - 2012  182 
13.  26237  PhD Marko Sedlaček  Materials science and technology  Researcher  2012 - 2013  248 
14.  00812  PhD Jožef Vižintin  Mechanical design  Head  2011 - 2014  1,144 
15.  12342  PhD Damir Vrančić  Systems and cybernetics  Researcher  2011 - 2014  338 
Organisations (3)
no. Code Research organisation City Registration number No. of publicationsNo. of publications
1.  0106  Jožef Stefan Institute  Ljubljana  5051606000  90,038 
2.  0588  University of Ljubljana, Faculty of Education  Ljubljana  1627082  30,749 
3.  0782  University of Ljubljana, Faculty of Mechanical Engineering  Ljubljana  1627031  29,130 
Mechanical drives are the most ubiquitous item of equipment in almost all industrial branches. Wear, excessive operational loads or errors in assembly might cause premature unexpected failures resulting in partial or total production downtime, damaged equipment or even loss of lives. Proper maintenance is therefore very important. According to the ARTEMIS report, the direct cost of maintenance in EU is estimated 4%- 8% of the total sales turnover. Moreover, 30-50% of the expenditure is wasted through ineffective maintenance! The problem is that currently prevailing reactive (react-to-failure) and preventive (periodic) maintenance paradigms are outdated and need to be replaced with more cost-effective predictive maintenance based on advanced diagnostic, prognostic and health management solutions (PHM). While diagnostics tends to determine condition of the component and isolate faults, the aim of prognostics is to assess the useful life of the asset. Health management refers to the ability to make intelligent decisions about maintenance actions.  Reasons that keep companies reluctant to investments in PHM are still in high capital costs, installation difficulties, and the overall complexity of the currently available monitoring systems. The aim of the project is to respond to these challenges and come up with the prototype of a versatile, easily manageable and radically low-cost platform labelled MEMS-PHM for prognostics and health management of electro-mechanical drives that will rely on cutting edge MEMS (micro-electromechanical sensor) technologies. Strong motivation for the underlying project is fuelled by several key factors: 1. PHM solutions are just emerging on the market but tailored for special target assets (e.g. military aircrafts). There is obvious need for 'general purpose' PHM solutions that would be applicable to a broader range of operating machines. 2. Almost 40% of all the machinery operating at the time being fall in the power range 5-100kW, hence representing valuable asset. According to a review done in USA only in 1% of this machinery the condition is monitored automatically all the time. The rest is poorly  monitored or monitored at best periodically. 3. Advanced generation of micro-sensors including MEMS accelerometers have recently emerged on the market. They are characterized by extremely low cost, miniature size and reliability while preserving the accuracy, bandwidth, and robustness of the traditional sensors. This project will conduct basic and applied research leading to the  anticipated major results as follows: 1. A portfolio of low cost MEMS-PHM platforms able to perform diagnostics and prognostics tasks. Autonomous energy supply via energy harvesters, no cabling and wireless communication make ground for versatile PHM functionality at the cost as low as 1/10 of the costs needed by current condition monitoring technologies. 2. Innovative tool for application SW design and automatic code generation for MEMS-PHM, hence reducing the development and configuration effort. 3. New algorithms for condition assessment and prognostics based on information fusion concepts, enabling the proposed system to gain information from various sensors like accelerometers, thermocouples, sensors for oil parameters etc. 4. Robust algorithms able to detect and isolate faults under non-stationary operating conditions and external disturbances. 5. Interface to the e-maintenance platforms. The prototype versions of the system will be validated on laboratory motor-generator test rig and  demo industrial installations, already been agreed with the companies supporting the project.
Significance for science
Although the major part of the project has been dedicated to the applied research and engineering design, a bunch of fundamental problems of global interest have been addressed. The work has built on previous results in the area of feature generation using novel entropy indices, wavelet packet transform and nonlinear system identification for condition prognostics. The most notable contributions of the underlying project can be identified as follows: 1.New method for bearing fault detection relying on Poisson model of the hits the moving parts in have with the static parts. Random intervals between two successive hits are described by Inverse Gaussian distribution. 2.We contributed an eniterly new approach to the prediction of the remaining useful life of bearings. The proposed model builds on statistical model of the remaining life whereas the model is obtained from experiments on a suitable number of equal rotational machines. The problem showed supreme performance on the data challenge, i.e. a benchmark issued by organisers of the PHM conference in 2012. The modelling framework serves as the basis of further anticipated development of diagnostics and prognostics of the rotational machines and drives. 3.New method for detection of the distributed faults in bearings. It is based on relatively simple features and decision rules which were obtained by using the simplified model of the bearing dynamics.
Significance for the country
The proposed project is expected to have great impact on further development in industry, particularly from the point of view of maintenance strategy. Currently, Slovene companies still use ineffective and expensive maintenance strategies, such as reactive and preventive approaches. For further optimisation of maintenance, a more advanced strategies of condition monitoring and automatic technical diagnosis need to be implemented. The main contribution of the project is a low-cost, compact and integrative platform MEMS-PHM. The platform has the capacity of implementing most of the tasks related to condition monitoring. Such a platform will significantly enhance the possibility of implementing predictive maintenance on a number of industrial applications. Introducing predictive strategy has the potential of reducing both, direct and indirect cost of maintenance in Slovenian companies. By promoting predictive maintenance an overall positive effects and improvements are expected in this segment of Slovenian industry, where the level of maintenance strategies is particularly low. The project contributed hardware and software, ready for direct implementation in industrial practice. More specific: 1. A low-cost autonomous MEMS-PHM platform, used as junction of various sensors; 2. MIMOSA database for data storage, allowing controlled access and connections to information system of the company; 3. Knowledge transfer and training seminars for maintenance personnel employed in industrial sector, the community that will be essential for introduction of maintenance strategies based on MEMS-PHM technology. Domel d.o.o, a company that co-funded the project, will have direct benefits from the results. Their major benefit is a successfully implemented test rig for life tests of EC motors. The fundamental component is an original system with distributed sensor network, capable of on-line monitoring and remaining useful life estimation of motors. The first version of the system consists of two smart nodes connected to vibration transducers and thermocouples, which are positioned on the housing of two bearings. The smart nodes perform measurement sessions once per hour and transfer the data over Ethernet network to a server, where further signal processing takes place. A well organised data storage in accordance with MIMOSA OSACBM standard is an important aspect for the final user. The application is implemented in MySQL database and is the first such application in our country. The system is capable of remote control of motors and condition monitoring of each unit. The software installed on the main server is capable of processing the collected data, feature extraction and evaluation of the remaining useful life of bearings. The test rig represents a step forward in development of Domel, as well as it contributes to long-term consolidation of positions in the global market of the company’s motors with electronic commutation. Currently, Domel staff, together with members of the project team, is completing expansion of the test rig from two to six test sites.
Most important scientific results Annual report 2011, 2012, 2013, final report, complete report on dLib.si
Most important socioeconomically and culturally relevant results Annual report 2011, 2012, 2013, final report, complete report on dLib.si
Views history