Optimal Operation Scheduling Of Urban Water Supply Pump Stations

In urban water supply system,pumping station is one of the most important parts,and its power consumption accounts for a large proportion of the operation cost of the whole system.At present,most of the water supply pumping stations adopt the mode of combined operation of the power frequency pump and the variable frequency pump,which has played a certain energy-saving role.However,the scheduling is still mainly based on artificial experience,with a certain degree of blindness,resulting in a waste of energy.To sum up,it is very necessary to study the optimal operation of secondary pumping station.The main contents of this paper are divided into four parts: prediction of urban water consumption,macroscopic hydraulic model of pumping station,check of pump characteristic curve and optimal operation of pumping station.The prediction methods of urban water consumption can be divided into two methods:time series method and explanatory prediction method.For the time series method,the traditional GM(1,1)model is firstly used to establish the water consumption prediction model.The relative error of part of the time is more than 5%,and the prediction result is not satisfactory.After optimization of initial value,background value construction method and residual sequence,the prediction error of the model is less than 5%.For the explanatory prediction method,the BP neural network prediction model is established based on six factors affecting the change of water consumption,and the prediction error is less than 3%.Finally,the optimized GM(1,1)model and BP neural network are obtained based on the validity degree.The weight coefficient of the complex prediction model is set up,and the prediction results are more stable and the error is lower.This paper introduces several kinds of water supply network analysis models which are commonly used in our country,expounds the characteristics and application scope of each model,and selects macro hydraulic model through analysis in this paper.Then,according to the change of urban water consumption,the 24-hour period is divided into 5 periods.Finally,the macro hydraulic model of pumping station is established based on BP neural network.Theexample shows that the relative error of the model is less than 5%,which can meet the demand of water supply production.Firstly,the sample characteristic curve of pump is fitted.The mathematical principle of parallel operation of speed regulating pump is also analyzed,and the flow-head curve checking model is established based on lightning search algorithm.Since the pressure in the daily report of the water plant is only kept to meters,the pressure is also optimized and the pump flow-head curve is obtained in accordance with the actual operation.Then,according to the motor efficiency,the flow-power curve of the pump is checked,and the relationship between the actual power consumption and the flow rate of the pump unit is obtained.Taking the minimum total power of the pump station as the objective function,taking the water supply,the pressure,the speed regulation ratio and the high efficiency section as the constraint conditions,based on the lightning search algorithm,the optimal operation model of the secondary pumping station is established.The water volume,pressure and pump curves obtained above are brought into the model,and the optimal open pump combination and speed regulation scheme are obtained.After accounting,the scheme is shown to save 9.6% of the energy compared with the previous plan.