Intelligent optimization control method of unit load based on energy storage of cold end system

Abstract

The invention relates to an intelligent optimization control method of a unit load based on energy storage of a cold end system. The method comprises the steps of (1) establishing a neural network prediction model of load characteristics of a supercritical unit; (2) using historical operating data of the unit to train and verify the prediction model; (3) using the prediction model to predict and optimize a cold end energy storage system during a dynamic variable load phase and a load stabilizing phase of the unit; and (4) taking the deviation between each optimization result and an original control command as a compensation signal, and superimposing the compensation signal onto a corresponding control signal to implement optimization control of the unit. The method of the invention can improve the control level of the unit load and ensure the safe and reliable operation of the thermal power unit.

Description

technical field [0001] The invention belongs to the technical field of power generation, and in particular relates to an intelligent optimization control method for unit load based on cold-end system energy storage. Background technique [0002] Large-capacity ultra-(ultra)critical coal-fired units have gradually become the main unit of the power grid due to their obvious advantages in energy saving, consumption reduction and environmental pollution reduction. The continuous improvement of power supply quality indicators of the power grid requires that large-capacity super (super) critical units should have automatic generation control (AGC) and other functions, and also put forward high requirements for the load response rate and adjustment accuracy of supercritical units ( The assessment of the two detailed rules requires that the load change per minute can reach 1.5% to 2% of the rated load of the unit or even higher). Since the coordinated control system (CCS) needs to ...

AI Technical Summary

Problems solved by technology

Due to the many simplification factors of the above model, the load prediction accuracy of the model will be reduced, and the anti-interference ability will be reduced

Specific performance: 1) The hot-end parameter directly related to the power of the unit is the outlet steam temperature of the final stage superheater of the boiler, not the middle point temperature, and the outlet steam temperature of the final stage superheater of a super (super) critical boiler is directly divided by the water-to-coal ratio In addition, the process of dynamic load change is also affected by the desuperheating amount of water sprayed by superheaters at all levels, which is not reflected in the above model; 2) The work share of the medium and low-pressure cylinders of the unit accounts for about 2 / 3 of the total power of the unit, while The working capacity of medium and low pressure cylinders is closely related to the two parameters of reheat steam pressure and reheat steam temperature, which are not reflected in the above model; 3) The above model does not take into account the important cold end parameter of the unit. Condenser vacuum ( Back pressure) Affected by various factors such as circulating water pump, vacuum pump, unit shaft seal operation, etc., the vacuum change of the condenser has a great impact on the unit load and the economy of unit operation; 4) The high and medium The low-pressure cylinders are equipped with at least 8 stages of regenerative steam extraction. During the operation, due to various reasons such as high-pressure heater (high-pressure heater) decoupling, sudden change in condensate flow, etc., the amount of regenerative cycle extraction steam at all levels will be reduced. There is a sudden change, which will affect the work of the steam turbine in a short period of time (the rapid adjustment method of condensate throttling load that has appeared in recent years uses this effect), and the above model cannot reflect

Images