L.V. Antonov - Post-graduate Student, Department ««Physics and Applied Mathematics»», Murom Branch Vladimir State University named after A.&N. Stoletovs. E-mail: LevAntonov@yandex.ru A.D. Varlamov - Ph. D. (Eng.), Associate Professor, Department «Information Systems», Murom Branch Vladimir State University named after A.&N. Stoletovs. E-mail: Varlamov_Aleks@mail.ru A.A. Orlov - Dr. Sc. (Eng.), Associate Professor, Head of Department ««Physics and Applied Mathematics»», Murom Branch Vladimir State University named after A.&N. Stoletovs. E-mail: AlexeyAlexOrlov@gmail.com

The production process includes a large number of production objects (animals), modern equipment and large number of factors (production characteristics) that require monitoring. Automated systems of livestock enterprises make data analysis from a large number of sensors and equipment for detailed control over a condition animals Manual control of critical situations and changes in the production process (breakdown of equipment, animal diseases), which gives the stopping of the production process and the additional costs is not possible. Relevance to the development of additional program means and algorithms for automation livestock enterprises to eliminate the imperfections of modern tools and the active development of the industry are show in the article. Problem of identification postpartum periods estrus for dairy farming\'s animals is presented in the article. Analysis of foreign and domestic literature devoted to research its issue performed. The analysis showed that foreign automated information systems are not able to accurately determine the periods of postnatal subinvolution, making the existence of the animal useless and raises additional costs for its maintenance. Analysis foreign work demonstrates that changing the state of animal, is associated with the postnatal subinvolution, independent of increase in the motor activity of the animal. Solution of the problem is provided by data approximation of the activity animal and the application of the rules of three-sigma for the difference between of the original time series and approximation time series. The developed algorithm received experimental evaluation. The results of the algorithm are measured by four characteristics. The results of the algorithm work is better than analogues for all characteristics. The developed algorithm will be the basis system of the automated intellectual control of the production enterprises and will allow to solve number of problems related to the symptoms disease identification at an early stage of their occurrence.

 

1. Bulman D.C., Lamming G.E. Milk progesterone levels in relation to conception, repeat breeding and factors influencing acyclicity in dairy cows. J. Reprod // Fertil. 1978. V. 54. P. 447−458.
2. Lovendahl P., Chagunda M. Assessment of fertility in dairy cows based on electronic monitoring of their physical activity // Proceedings of the 8th World Congress on Genetics Applied to Livestock Production, Belo Horizonte, MG, Brazil. 2006. P. 496−500.
3. De Mol R.M., Woldt W.E. Application of fuzzy logic in automated cow status monitoring // J. Dairy Sci. 2001. V. 84. P. 400−410.
4. Firk R., Stamer E., Junge W., Krieter J. Automation of estrus detection in dairy cow // A review. Livest. Prod. Sci. 2002. V. 75. P. 219−232.
5. Roelofs J.B., van Eerdenburg F.J., Soede N.M., Kemp B. Various behavioral signs of estrous and their relationship with time of ovulation in dairy cattle // Theriogenology. 2005. V. 63. P. 1366−1377.
6. Roelofs J.B., van Eerdenburg F.J., Soede N.M., Kemp B. Pedometer readings for estrous detection and as a predictor for time of ovulation in dairy cattle // Theriogenology. 2005. V. 64. P. 1690−1703.
7. Zarchi N., Ingi R. Improving Oestrus Detection in Dairy Cows by Combining Statistical Detection with Fuzzy Logic Classification // Proceedings Workshop on Advanced Control and Diagnosis. 2009.
8. Eradus W., Scholten H. Cate Oestrus detection in dairy cattle using a fuzzy inference system in Control applications and ergonomics in agro-culture // (CAEA), IF AC Workshop, Athens, Greece. 1998. V. 66 P. 185−188.
9. Yang Y. Rechnergestutzte ostrusuberwachung bei milchkuhen unter anwendung der fuzzy-logic-methode // Herbert Utz, Munchen 1998.
10. Firk R., Stamer E., Junge W., Krieter J. Oestrus detection in dairy cows based on serial measure-ments using univariate and multivariate analysis // Archiv fur Tierzucht. 2003. V. 46. P. 127−142.
11. Firk R., Stamer E., Junge W., Krieter J. Improving oestrus detection by combination of activity measurements with information about previous oestrus cases // Livestock Production Science. 2006. V. 82. P. 97−103.
12. Antonov L.V., Varlamov A.D. Avtomatizacija processa monitoringa zhivotnovodcheskogo predprijatija na osnove issledovanija vremennykh rjadov parametrov krupnogo rogatogo skota // Sovremennye problemy nauki i obrazovanija. 2013. № 6.
13. Orlov A.A., Antonov L.V. Obzor i analiz sovremennykh informacionnykh reshenijj avtomatizacii zhivotnovodcheskikh khozjajjstv // Sovremennye problemy nauki i obrazovanija. 2013. № 6.