Energy and environment are top priorities for the EU’s Europe 2020 Strategy. Both fields imply complex approaches and consistent investment. The paper presents an alternative to large investments to improve the efficiencies of existing (outdated) power installations: namely the use of data-mining techniques for analysing existing operational data. Data-mining is based upon exhaustive analysis of operational records, inferring high-value information by simply processing records with advanced mathematical / statistical tools. Results can be: assessment of the consistency of measurements, identification of new hardware needed for improving the quality of data, deducing the most efficient level for operation (internal benchmarking), correlation of consumptions with power/ heat production, of technical parameters with environmental impact, scheduling the optimal maintenance time, fuel stock optimization, simulating scenarios for equipment operation, anticipating periods of maximal stress of equipment, identification of medium and long term trends, planning and decision support for new investment, etc. The paper presents a data mining process carried out at the TERMICA - Suceava power plant. The analysis calls for a multidisciplinary approach, a complex team (experts in power&heat production, mechanics, environmental protection, economists, and last but not least IT experts) and can be carried out with lower expenses than an investment in new equipment. Involvement of top management of the company is essential, being the driving force and motivation source for the data-mining team. The approach presented is self learning as once established, the data-mining analytical, modelling and simulation procedures and associated parameter databases can adjust themselves by absorbing and processing new relevant information and can be used on a long term basis for monitoring the performance of the installation, certifying the soundness of managerial measures taken and suggesting further adjustments
Fayyad, U., Piatetsky-Shapiro, G., and Smyth, P. (1996), The KDD process for extracting useful knowledge from volumes of data. Communications of the ACM, 39(11):27-34
LCP (2006), Reference document on best available techniques for large combustion plants, available at http://eippcb.jrc.ec.europa.eu/reference/lcp.html , accessed August 30, 2013.
EE (2009), Reference document on best available techniques for energy efficiency available at http://eippcb.jrc.ec.europa.eu/reference/ene.html accessed August 30, 2013.
ECMA (2006), Reference document on economic and cross-media effects, available at http://eippcb.jrc.ec.europa.eu/reference/BREF/ecm_bref_0706.pdf . accessed August 30, 2013.
Ruan, Da et al, (eds.) (2005), Intelligent Data Mining, Springer Verlag, Berlin
EMA (2001), Environmental and management accounting, UN Division for sustainable development, UN, New-York, 2001
ISO 14051 (2011), Environmental Accounting - Material Flow Cost Accounting - General Framework , available at , http://www.iso.org/iso/catalogue_detail?csnumber=50986 accessed August 30, 2013
Nisbet, M. et al (2012), Demolition and Deconstruction: Review of the Current Status of Reuse and Recycling of Building Materials. Available at ftp://ftp.techenv.com/pub/Retrofit/AWMA%20paper_WM1b.pdf , accessed April 3, 2012
SYMONDS (1999), Construction and Demolition Waste Management Practices and Their Economic Impacts. A Study Prepared by SYMONDS Group (UK) in association with ARGUS (Germany), COWI Consulting Engineers and Planners (Denmark) and PRC Bouwcentrum (the Netherlands) for The European Commission, DG-XI.
Venta, G. and Nisbet, M. (2000), Potential for Reduction of CO2 Emissions in Canada through Greater Use of Fly Ash in Concrete, CANMET/ACI International Symposium on Concrete Technology for Sustainable Development, Delta, Canada.
Voina, N.I. (1981), The Theory and Practice of Pulverized Fly Ash Utilization (in Romanian), Ed. Tehnica, Bucharest, 488pp.
Wirth, R. and Hipp, J., (2000), CRISP-DM: Towards a standard process model for data mining. In Proceedings of the 4th International Conference on the Practical Applications of Knowledge Discovery and Data Mining, pages 29-39, Manchester, UK