Energy-saving effect determining method and system based on support vector regression

Abstract

The invention relates to the technical field of data prediction, in particular to an energy-saving effect determining method and system based on a support vector regression. The method includes that a support vector regression algorithm is used for calculating a unit product energy consumption predicted value Xp; an actual value Xt of the unit product energy consumption is read from a data base, and the unit product energy consumption predicted value Xp and the actual value Xt of the unit product energy consumption are unit product energy consumption of the same time period; energy-saving effect eta of a unit product is calculated according to a formula. By means of the method, data hysteresis can be effectively avoided, and energy-saving assessment accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of data prediction, in particular to a method and system for determining energy-saving effects based on a regression support vector machine. Background technique [0002] At present, in many high-energy-consuming and high-emission manufacturing enterprises, operators do not have a strong awareness of energy conservation, and still retain the previous concept of simply considering the minimization of production time, that is, rushing to catch up with time and progress, and not paying enough attention to energy consumption in production. Environmental pressure is very high. In order to cultivate the energy-saving awareness of operators, it is necessary for enterprises to evaluate the energy-saving effect on the basis of the workshop, so as to alert operators. After adopting certain energy-saving measures, such as purchasing new equipment, improving processes, etc., enterprises often need to use some means to ...

AI Technical Summary

Problems solved by technology

[0004] The commonly used method of evaluating the energy-saving effect is simple and easy to implement, but there are some defects. For example, if a certain energy-saving measure is adopted in June, then the commonly used method of evaluating the result effect uses the energy consumption per unit product in June and 5 The monthly energy consumption per unit of product is compared, but the impact of some factors has been ignored, the most obvious is the impact of the weather. The temperature in June is significantly higher than that in May, so the energy consumption of enterprises on cooling will be obvious. increase, because it is very likely that the workshop in May does not need to turn on the air conditioner, but it needs to be turned on in June, and it is well known that the power consumption of the air conditioner is high. The energy consumption per unit of product is compared to evaluate the energy-saving effect. There is a lag in energy consumption data, so the evaluation error is obviously large

Images