Method for predicting cleaning rate of condenser of waste incineration power station

Abstract

The invention discloses a method for predicting the cleaning rate of a condenser of a waste incineration power station, and the method comprises the following steps: S1, calculating the overall heat transfer coefficient and cleaning coefficient of the condenser, and building a mathematical model for calculating the cleaning rate of the condenser; and S2, predicting the cleaning rate of the condenser by using a three-layer BP neural network structure. The device has the advantages of being compact in structure, high in stability, high in prediction precision and the like, the influence of multiple factors on the cleaning rate of the condenser is explored, the prediction model is established, the cleaning rate of the condenser can be accurately predicted, and the heat energy utilization rate of a waste incineration power station can be improved.

Description

Technical Field

[0001] The invention relates to the technical field of waste incineration treatment, and in particular to a method for predicting the cleaning rate of a condenser in a waste incineration power station. Background Art

[0002] The condensing steam turbine is composed of condensers and other related equipment. Among them, the condenser plays the role of a cold source in the thermal cycle of the waste incineration power plant and is an indispensable part. There are many evaluation indicators for condenser characteristics, among which the cleanliness factor is the most widely used and important one, because its value has a great effect on the operating conditions of the condenser and can reflect the degree of scaling of the condenser tube wall. The reduction of the condenser cleanliness factor, that is, the increase in the degree of scaling of the tube wall, will deteriorate the heat transfer effect of the entire condenser, leading to an increase in the heat rate and even a decrease in the output of the turbine system, which will eventually have an adverse impact on the economy and safety of the entire power plant operation.

[0003] Dirt is a substance that is not good at transferring heat, so it is a poor conductor of heat. From a numerical point of view, its thermal conductivity is almost only 1 / 10 of that of carbon steel, not to mention compared with some good thermal conductors such as copper. Therefore, once dirt is generated on the heat exchange surface, the resistance between the fluid and the wall will increase a lot, which will undoubtedly lead to the deterioration of the heat transfer performance of the condenser, and ultimately affect the safe and economical operation of the entire power plant. The impact of dirt on the condenser is roughly in the following five aspects:

[0004] (1) The heat transfer capacity of the heat exchange surface is greatly reduced, and the exhaust pressure and temperature of the steam turbine are increased, resulting in a decrease in output power and a significant increase in heat consumption rate.

[0005] (2) The dirt resistance of the condenser increases, which is equivalent to a decrease in the total heat transfer coefficient. In order to improve the disadvantages caused by the increasing dirt thermal resistance, the heat transfer area must be increased during the condenser design, and the cost of the condenser will undoubtedly increase.

[0006] (3) As dirt slowly accumulates in the flow pipe, it will reduce the flow area of ​​the fluid in the pipe, increase the flow resistance, cause the water pump and cleaning equipment to do more work, and increase energy consumption.

[0007] (4) If too much dirt accumulates, the unit may be operated at a reduced load, or even shut down to clean the dirt, which shortens the normal operation cycle of the steam turbine unit and causes economic losses to the company.

[0008] (5) Long-term accumulation of dirt may cause the performance of some instruments to decline, which may lead to accidents.

[0009] In summary, it can be seen that fouling can greatly affect the working performance of the condenser. Therefore, some anti-scaling, anti-scaling and descaling measures need to be taken to minimize the adverse effects of fouling. It is necessary not only to be able to measure the condenser cleanliness rate online, but also to conduct predictive research on it. Summary of the invention

[0010] The technical problem to be solved by the present invention is to provide a method for predicting the cleanliness rate of a condenser of a waste incineration power plant with simple principle, high stability and high accuracy in view of the deficiencies in the prior art.

[0011] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0012] A method for predicting the cleanliness rate of a condenser in a waste incineration power plant comprises the following steps:

[0013] Step S1, calculating the overall heat transfer coefficient and cleanliness coefficient of the condenser, and building a mathematical model for calculating the cleanliness rate of the condenser;

[0014] Step S2: using a three-layer BP neural network structure to predict the condenser cleaning rate.

[0015] As a further improvement of the present invention, in step S1, the overall heat transfer coefficient calculation process of the condenser is:

[0016] According to the heat transfer equation, the heat transferred from the condenser to the cooling water is: Q = A c K

[0017] Δt m =c w D w Δt (1-1);

[0018] Where:

[0019] Q represents the heat transfer (or heat load) of the condenser, W; K represents the overall heat transfer coefficient of the current condenser, W / (m 2 .K); A c Represents the total outer surface area of ​​the cooling water pipe of the condenser, m 2 ; Δt m Represents the average heat transfer temperature difference between steam and cooling water, ℃; c w Indicates the specific heat capacity of cooling water, J / (kg.K), the possible value is 4187; D w Indicates the amount of cooling water entering the condenser, kg / s; Δt indicates the temperature rise of cooling water, °C;

[0020] According to formula (1-1), the overall heat transfer coefficient of the condenser is:

[0021]

[0022] The average heat transfer temperature difference between steam and cooling water is the logarithmic mean temperature difference, as follows:

[0023]

[0024] Where: δt represents the condenser end difference, ℃; t s Indicates the saturated temperature of condensed water in the condenser, ℃; t w1 ,t w2 Respectively represent the cooling water inlet and outlet temperatures, ℃.

[0025] As a further improvement of the present invention, the overall heat transfer coefficient of the condenser is calculated according to the standard formula of the machinery industry:

[0026] K=K0β c β t β m (1-4);

[0027] Where: K represents the overall heat transfer coefficient of the current condenser, W / (m 2 .K); K0 represents the basic heat transfer coefficient, which can be obtained by consulting the appendix in the mechanical industry standard; β c Indicates the cleanliness factor of the condenser; β t Indicates the cooling water inlet temperature correction coefficient, which can be obtained by consulting the appendix in the mechanical industry standard; β m Indicates the correction factor of the wall thickness of the condenser tube material, which can be obtained by consulting the appendix in the mechanical industry standard;

[0028] From formula (1-4), we can get:

[0029]

[0030] As a further improvement of the present invention, the calculation process of the cleaning coefficient in step S1 includes:

[0031] The first step is to obtain the design parameters of the condenser, including heat transfer area, condenser tube specifications, circulating water flow, cooling water temperature, and cooling water flow rate;

[0032] The second step is to obtain the current operating parameters of the condenser, including cooling water flow rate, cooling water inlet and outlet temperatures, and turbine exhaust temperature;

[0033] Step 3: Calculate the current heat transfer coefficient of the condenser;

[0034] Step 4: Calculate the current cleanliness factor of the condenser.

[0035] As a further improvement of the present invention, in the second step, the cooling water flow rate in the condenser is calculated according to the cooling water flow rate:

[0036]

[0037] Among them, V w represents the water velocity in the condenser, m / s; n represents the total number of condensers; d2 represents the inner diameter of the condenser, m; D w Indicates the cooling water flow rate entering the condenser, m 3 / s;

[0038] The logarithmic mean temperature difference between steam and cooling water is expressed as follows from equation (3-3):

[0039]

[0040] Where: Δt m Indicates the logarithmic mean temperature difference of the condenser, °C; t s Indicates the saturated temperature of condensed water in the condenser, °C; t w1 ,t w2 Respectively represent the cooling water inlet and outlet temperatures, ℃.

[0041] As a further improvement of the present invention, in the third step, the process of calculating the current heat transfer coefficient of the condenser is:

[0042] According to formula (1-1), the following expression is obtained:

[0043] Q=c w D w Δt (1-8);

[0044] Combine (1-2) and (1-8) to calculate the current total heat transfer, and then calculate the current heat transfer coefficient:

[0045]

[0046] Where: Q represents the heat load of the condenser, W; K represents the overall heat transfer coefficient of the current condenser, W / (m 2 .K); A c Represents the total outer surface area of ​​the cooling water pipe of the condenser, which can be taken as the design parameter, m 2 ; Δt m Indicates the logarithmic mean temperature difference between steam and cooling water, °C; c w Indicates the specific heat capacity of cooling water, J / (kg.K), the possible value is 4187; D w Indicates the amount of cooling water entering the condenser, kg / s; Δt indicates the temperature rise of cooling water, ℃.

[0047] As a further improvement of the present invention, in the fourth step, the process of calculating the current cleanliness coefficient of the condenser includes obtaining a cooling water inlet temperature correction coefficient fitting curve,

[0048] β t =-6E-09t5 +1E-06t 4 -5E-05t 3 +0.0009t 2 +0.0116t+0.6746 (1-10);

[0049] Get the heat transfer coefficient fitting curve, K0 = -159.77V 2 +1596.9V+1272.1 (1-11);

[0050] Get the wall thickness correction coefficient fitting curve, β m =-0.0136x 3 +0.0773x 2 -0.2729x+1.0697 (1-12);

[0051] Combine (1-5) and (1-9) to calculate the cleanliness rate of the condenser:

[0052]

[0053] Among them: A c Represents the total outer surface area of ​​the cooling water pipe of the condenser, which can be taken as the design parameter, m 2 ; Δt m Indicates the logarithmic mean temperature difference between steam and cooling water, °C; c w Indicates the specific heat capacity of cooling water, J / (kg.K), the possible value is 4187; D w Indicates the amount of cooling water entering the condenser, kg / s; Δt indicates the temperature rise of cooling water, °C; β c Indicates the current condenser cleanliness coefficient; K0 indicates the basic heat transfer coefficient, which can be obtained by consulting the appendix in the mechanical industry standard; β t Indicates the cooling water inlet temperature correction coefficient, which can be obtained by consulting the appendix in the mechanical industry standard or calculated according to the fitting formula; β m It indicates the correction factor of the wall thickness of the condenser material, which can be obtained by consulting the appendix in the mechanical industry standard or calculated according to the fitting formula.

[0054] As a further improvement of the present invention, the step S2 further comprises:

[0055] Step S21, setting 3 input nodes, 7 hidden nodes and 1 output node to obtain a three-layer BP neural network structure in the form of 3×7×1;

[0056] Step S22, taking the exhaust temperature, the ideal heat transfer coefficient, and the actual heat transfer coefficient as given input vectors, and the measured condenser cleanliness rate as the target output;

[0057] Step S23: Analyze the prediction results of the BP neural network.

[0058] As a further improvement of the present invention, in step S21, the transfer function between the input layer and the hidden layer uses the tansig function, the output layer neuron transfer function uses the purelin function, and the training function uses the traingdx algorithm to train the network. The maximum number of learning times is set to 5000 times, the learning rate is 0.05, and the learning target is the sum of squared errors of 0.001.

[0059] Compared with the prior art, the advantages of the present invention are:

[0060] 1. The method for predicting the cleaning rate of the condenser of the waste incineration power plant of the present invention uses the BP neural network structure to make a good prediction of the general direction of the change of the cleaning rate of the condenser, which is helpful to develop a highly feasible cleaning method to achieve better planning of reasonable cleaning time and thus achieve the purpose of energy saving.

[0061] 2. The method for predicting the cleanliness rate of the condenser of the waste incineration power plant of the present invention corrects the cooling water inlet temperature, condenser tube material and wall thickness when solving the mathematical calculation expression of the cleanliness rate of the condenser. Compared with the prior art which directly obtains the calculation formula of the cleanliness rate without any correction, the method of the present invention can calculate the real-time cleanliness rate of the condenser more accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 It is a schematic diagram of a flow chart of prediction of the cleaning rate of a condenser of a waste incineration power plant in a specific embodiment of the present invention;

[0063] Figure 2 It is a schematic diagram of a cooling water inlet temperature correction coefficient curve in a specific embodiment of the present invention;

[0064] Figure 3 It is a schematic diagram of a basic heat transfer coefficient curve in a specific embodiment of the present invention;

[0065] Figure 4 It is a schematic diagram of a wall thickness correction coefficient curve in a specific embodiment of the present invention;

[0066] Figure 5 Schematic diagram of neural network training in a BP neural network structure in a specific embodiment of the present invention; wherein, Figure (a) shows a schematic diagram of relevant parameters set, and Figure (b) shows the error of the prediction result;

[0067] Figure 6 This is a comparison chart of the result value of the condenser cleanliness rate prediction using the BP neural network structure in a specific embodiment of the present invention and the actual value of the condenser cleanliness rate. DETAILED DESCRIPTION

[0068] The present invention is further described below in conjunction with the accompanying drawings and specific preferred embodiments, but the protection scope of the present invention is not limited thereby.

[0069] In the description of the present invention, it should be understood that the terms "side", "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0070] In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0071] Example

[0072] like Figure 1 As shown, the method for predicting the cleanliness rate of a condenser in a waste incineration power plant of the present invention comprises the following steps:

[0073] Step S1, calculating the overall heat transfer coefficient and cleanliness coefficient of the condenser, and building a mathematical model for calculating the cleanliness rate of the condenser;

[0074] Step S2: using a three-layer BP neural network structure to predict the condenser cleaning rate.

[0075] In this embodiment, the BP neural network structure is used to make a good prediction of the general direction of the change in the condenser cleaning rate, which is helpful to develop a highly feasible cleaning method to achieve better planning of reasonable cleaning time and thus achieve the purpose of energy saving.

[0076] In step S1 of this embodiment, the overall heat transfer coefficient calculation process of the condenser is:

[0077] According to the heat transfer equation, the heat transferred from the condenser to the cooling water is: Q = A c K

[0078] Δt m =c w D w Δt (1-1);

[0079] Where:

[0080] Q represents the heat transfer (or heat load) of the condenser, W; K represents the overall heat transfer coefficient of the current condenser, W / (m 2 .K); A c Represents the total outer surface area of ​​the cooling water pipe of the condenser, m 2 ; Δt m Represents the average heat transfer temperature difference between steam and cooling water, ℃; c w Indicates the specific heat capacity of cooling water, J / (kg.K), the possible value is 4187; D w Indicates the amount of cooling water entering the condenser, kg / s; Δt indicates the temperature rise of cooling water, °C;

[0081] According to formula (1-1), the overall heat transfer coefficient of the condenser is:

[0082]

[0083] The average heat transfer temperature difference between steam and cooling water is the logarithmic mean temperature difference, as follows:

[0084]

[0085] Where: δt represents the condenser end difference, ℃; t s Indicates the saturated temperature of condensed water in the condenser, °C; t w1 ,t w2 Respectively represent the cooling water inlet and outlet temperatures, ℃.

[0086] The overall heat transfer coefficient of the condenser is calculated according to the formula of the machinery industry standard "Steam Turbine Surface Condenser (Draft for Approval)":

[0087] K=K0β c β t β m (1-4);

[0088] Where: K represents the overall heat transfer coefficient of the current condenser, W / (m 2 .K); K0 represents the basic heat transfer coefficient, which can be obtained by consulting the appendix in the mechanical industry standard; β c Indicates the cleanliness factor of the condenser; β t Indicates the cooling water inlet temperature correction coefficient, which can be obtained by consulting the appendix in the mechanical industry standard; β m Indicates the correction coefficient of the wall thickness of the condenser tube material, which can be obtained by consulting the appendix in the mechanical industry standard;

[0089] From formula (1-4), we can get:

[0090]

[0091] The calculation process of the cleaning coefficient in step S1 of this embodiment includes:

[0092] The first step is to obtain the design parameters of the condenser, including heat transfer area, condenser tube specifications, circulating water flow, cooling water temperature, and cooling water flow rate;

[0093] The second step is to obtain the current operating parameters of the condenser, including cooling water flow rate, cooling water inlet and outlet temperatures, and turbine exhaust temperature;

[0094] Step 3: Calculate the current heat transfer coefficient of the condenser;

[0095] Step 4: Calculate the current cleanliness factor of the condenser.

[0096] In the second step, the cooling water flow rate in the condenser is calculated based on the cooling water flow rate:

[0097]

[0098] Among them, V w represents the water velocity in the condenser, m / s; n represents the total number of condensers; d2 represents the inner diameter of the condenser, m; D w Indicates the cooling water flow rate entering the condenser, m 3 / s;

[0099] The logarithmic mean temperature difference between steam and cooling water is expressed as follows from equation (3-3):

[0100]

[0101] Where: Δt m Indicates the logarithmic mean temperature difference of the condenser, °C; t s Indicates the saturated temperature of condensed water in the condenser, °C; t w1 ,t w2 Respectively represent the cooling water inlet and outlet temperatures, ℃.

[0102] In the third step, the process of calculating the current heat transfer coefficient of the condenser is:

[0103] According to formula (1-1), the following expression is obtained:

[0104] Q=c w D w Δt (1-8);

[0105] Combine (1-2) and (1-8) to calculate the current total heat transfer, and then calculate the current heat transfer coefficient:

[0106]

[0107] Where: Q represents the heat load of the condenser, W; K represents the overall heat transfer coefficient of the current condenser, W / (m 2 .K); A c Represents the total outer surface area of ​​the cooling water pipe of the condenser, which can be taken as the design parameter, m 2 ; Δt m Indicates the logarithmic mean temperature difference between steam and cooling water, °C; c w Indicates the specific heat capacity of cooling water, J / (kg.K), the possible value is 4187; D w Indicates the amount of cooling water entering the condenser, kg / s; Δt indicates the temperature rise of cooling water, ℃.

[0108] In the fourth step, the process of calculating the current cleanliness factor of the condenser includes obtaining a fitting curve of the cooling water inlet temperature correction factor.

[0109] Use the data in Table 1 to fit the cooling water inlet temperature correction coefficient:

[0110] Table 1 Cooling water inlet temperature correction coefficient table

[0111]

[0112]

[0113] like Figure 2 As shown in , the equation of the fitted polynomial curve is:

[0114] β t =-6E-09t 5 +1E-06t 4 -5E-05t 3 +0.0009t 2 +0.0116t+0.6746 (1-10).

[0115] In this embodiment, the heat exchange tubes in the condenser are condenser tubes of common size specifications. For condenser tubes with common outer diameters of 22.2 to 25.4 mm, the basic heat transfer coefficients are shown in Table 2:

[0116] Table 2 Basic heat transfer coefficient table

[0117]

[0118] like Figure 3 As shown in , the equation of the fitted polynomial curve is:

[0119] K0=-159.77V 2 +1596.9V+1272.1 (1-11).

[0120] In this embodiment, the heat exchange tubes in the condenser are titanium tubes made of conventional materials, and their wall thickness correction coefficients are shown in Table 3:

[0121] Table 3 Wall thickness correction coefficient table

[0122]

[0123] like Figure 4 As shown in , the equation of the fitted polynomial curve is:

[0124] βm=—0.0136x 3 +0.0773x 2 —0.2729x+1.0697 (1-12);

[0125] Combine (1-5) and (1-9) to calculate the cleanliness rate of the condenser:

[0126]

[0127] Among them: A c Represents the total outer surface area of ​​the cooling water pipe of the condenser, which can be taken as the design parameter, m 2 ; Δt m Indicates the logarithmic mean temperature difference between steam and cooling water, °C; c w Indicates the specific heat capacity of cooling water, J / (kg.K), the possible value is 4187; D w Indicates the amount of cooling water entering the condenser, kg / s; Δt indicates the temperature rise of cooling water, °C; β c Indicates the current condenser cleanliness coefficient; K0 indicates the basic heat transfer coefficient, which can be obtained by consulting the appendix in the mechanical industry standard; β t Indicates the cooling water inlet temperature correction coefficient, which can be obtained by consulting the appendix in the mechanical industry standard or calculated according to the fitting formula; β m It indicates the correction factor of the wall thickness of the condenser material, which can be obtained by consulting the appendix in the mechanical industry standard or calculated according to the fitting formula.

[0128] Step S2 of this embodiment further includes:

[0129] Step S21, set 3 input nodes, 7 hidden nodes and 1 output node to obtain a three-layer BP neural network structure in the form of 3×7×1. The transfer function between the input layer and the hidden layer uses the tansig function, the output layer neuron transfer function uses the purelin function, and the training function uses the traingdx algorithm to train the network. The maximum number of learning times is set to 5000 times, the learning rate is 0.05, and the learning target is the sum of squared errors of 0.001.

[0130] Step S22, taking the exhaust temperature, the ideal heat transfer coefficient, and the actual heat transfer coefficient as given input vectors, and the measured condenser cleanliness rate as the target output;

[0131] Step S23, analyzing the BP neural network prediction results.

[0132] Specifically, using the data in Table 4, the exhaust temperature, the ideal heat transfer coefficient, and the actual heat transfer coefficient are taken as given input vectors, and the measured condenser cleanliness rate is taken as the target output.

[0133] Table 4 Cleaning rate of condenser at different times after cleaning

[0134]

[0135] The BP neural network prediction of condenser cleaning rate is carried out based on MATLAB. The source program is as follows:

[0136] P=[31.5,31.5,32,32,32,32,31.5,32,32,32.5,33,33.5,33.5,34.0,34.0,34.5 ,35.0,35,35,35.5,35.5,35.5,35.5,35,35,35,35,35,35,35,35,35,35,35.5,3 6,36.5,36.5,36.5,36.5;3.25,3.25,3.25,3.2,3.15,3.15,3.15,3.15,3.15,3.14,3.13,3.14,3.15,3.20,3.25,3.25,3.25,3.25,3.25,3.21,3.16,3.17,3.18, 3.18,3.18,3.14,3.09,3.23,3.37,3.23,3.09,3.12,3.15,3.11,3.06,3.07,3.07,3.12,3.18; 2.93,2.84,2.76,2.51,2.25,2.30,2.36,2.31,2.25,2.23,2.20,2 .28,2.36,2.30,2.25,2.15,2.06,2.06,2.06,2.03,2,2.02,2.03,2.03,2.03,2.03,2.04,2.15,2.27,2.04,1.81,1.83,1.85,1.82,1.78,1.75,1.73,1.77,1.81];

[0140] T=[1;0.971;0.942;0.867;0.793;0.812;0.831;0.812;0.793;0.786;0.780;0.792;0.805;0.787;0.769;0.737;0.705;0.705;0.705;0.7 04;0.703;0.706;0.709;0.709;0.709;0.719;0.73;0.738;0.747;0. 699;0.651;0.650;0.649;0.647;0.644;0.631;0.625;0.628;0.631]

[0142] T = mean(T,2); T = T';

[0143] [p1,PS]=mapminmax(P); [t1,PS]=mapminmax(T);

[0144] % Create network

[0145] net=newff(p1,t1,7,{'tansig','tansig','purelin'},'traingdx'); net.divideFcn=";

[0146] net.trainparam.goal = 0.001; %Set the learning goal to take the sum of squared errors net.trainparam.epochs = 5000; %Set the number of training times

[0147] net.trainParam.lr=0.05; %Set learning rate

[0148] %Training network

[0149] [net,tr]=train(net,p1,t1);

[0150] %predict

[0151] Y2=sim(net,p1);

[0152] disp(['mse:'num2str(mse(t1-Y2))]);

[0153] % Prediction data restoration min_=min(T); max_=max(T);

[0154] Y.fore=(Y2+1) / 2*(max_-min_)+min_;

[0155] % Residual histogram figure(1);

[0156] error=TY.fore;count=[0:1:38];bar(count,error)grid on

[0157] xlabel("time / h"); ylabel("error")

[0158] % Actual and predicted values ​​figure(2);

[0159] plot(count,T,'-o');grid on;hold on plot(count,Y.fore,'-+');hold off

[0160] xlabel("time / h"); ylabel("cleaning rate")legend(["actual value","predicted value"])

[0161] The prediction results are as follows Figure 5 and Figure 6 As shown in Figure 6 The maximum error is close to 0.02, and the relative error is less than 2% through calculation. At the same time, by summing the errors of 39 sets of data and dividing them by 39, the average error of the model prediction error is 0.0047, which is basically negligible. Therefore, the error between the predicted value and the actual value is within the acceptable range, indicating that the model established by the BP neural network has a good approximation effect in terms of condenser cleanliness rate and has a high accuracy. Therefore, it is feasible to use the BP neural network to predict the condenser cleanliness rate.

[0162] In this embodiment, the use of BP neural network analysis can provide a basis for power plant operators to clean the condenser, which not only provides great convenience for real-time monitoring of the condenser cleaning rate, but also helps the relevant personnel of the power plant to formulate the best cleaning time and the best cleaning cycle, so as to achieve the purpose of improving operating efficiency and saving energy.

[0163] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A method for predicting the cleanliness rate of a condenser in a waste incineration power plant, characterized in that: The following steps are involved: Step S1, calculating the overall heat transfer coefficient and cleanliness coefficient of the condenser, and building a mathematical model for calculating the cleanliness rate of the condenser; Step S2: using a three-layer BP neural network structure to predict the condenser cleaning rate.

2. The method for predicting the cleanliness rate of a condenser in a waste incineration power plant according to claim 1, characterized in that: In step S1, the overall heat transfer coefficient calculation process of the condenser is: According to the heat transfer equation, the heat transferred from the condenser to the cooling water is: Q = A c K Δt m =c w D w Δt (1-1); Where: Q represents the heat transfer (or heat load) of the condenser, W; K represents the overall heat transfer coefficient of the current condenser, W / (m 2 .K); A c Represents the total outer surface area of ​​the cooling water pipe of the condenser, m 2 ; Δtm represents the average heat transfer temperature difference between steam and cooling water, ℃; c w Indicates the specific heat capacity of cooling water, J / (kg.K), the possible value is 4187; D w Indicates the amount of cooling water entering the condenser, kg / s; Δt indicates the temperature rise of cooling water, °C; According to formula (1-1), the overall heat transfer coefficient of the condenser is: The average heat transfer temperature difference between steam and cooling water is the logarithmic mean temperature difference, as follows: Where: δt represents the condenser end difference, ℃; t s Indicates the saturated temperature of condensed water in the condenser, ℃; t w1 ,t w2 Respectively represent the cooling water inlet and outlet temperatures, ℃.

3. The method for predicting the cleanliness rate of a condenser in a waste incineration power plant according to claim 2, characterized in that: Calculate the overall heat transfer coefficient of the condenser according to the standard formula of the machinery industry: K = K0βcβtβm(1-4); Where: K represents the overall heat transfer coefficient of the current condenser, W / (m 2 .K); K0 represents the basic heat transfer coefficient, which can be obtained by consulting the appendix in the mechanical industry standard; βc represents the cleanliness coefficient of the condenser; βt represents the cooling water inlet temperature correction coefficient, which can be obtained by consulting the appendix in the mechanical industry standard; βm represents the condenser material wall thickness correction coefficient, which can be obtained by consulting the appendix in the mechanical industry standard; From formula (1-4), we can get:

4. The method for predicting the cleanliness rate of a condenser in a waste incineration power plant according to claim 3, characterized in that: The calculation process of the cleaning coefficient in step S1 includes: The first step is to obtain the design parameters of the condenser, including heat transfer area, condenser tube specifications, circulating water flow, cooling water temperature, and cooling water flow rate; The second step is to obtain the current operating parameters of the condenser, including cooling water flow rate, cooling water inlet and outlet temperatures, and turbine exhaust temperature; Step 3: Calculate the current heat transfer coefficient of the condenser; Step 4: Calculate the current cleanliness factor of the condenser.

5. The method for predicting the cleanliness rate of a condenser in a waste incineration power plant according to claim 4, characterized in that: In the second step, the cooling water flow rate in the condenser is calculated according to the cooling water flow rate: Wherein, Vw represents the water velocity in the condenser, m / s; n represents the total number of condenser tubes; d2 represents the inner diameter of the condenser tube, m; D w Indicates the cooling water flow rate entering the condenser, m 3 / s; The logarithmic mean temperature difference between steam and cooling water is expressed as follows from equation (3-3): Where: Δt m Indicates the logarithmic mean temperature difference of the condenser, °C; t s Indicates the saturated temperature of condensed water in the condenser, °C; t w1 ,t w2 Respectively represent the cooling water inlet and outlet temperatures, ℃.

6. The method for predicting the cleanliness rate of a condenser in a waste incineration power plant according to claim 4, characterized in that: In the third step, the process of calculating the current heat transfer coefficient of the condenser is: According to formula (1-1), the following expression is obtained: Q=c w D w Δt (1-8); Combine (1-2) and (1-8) to calculate the current total heat transfer, and then calculate the current heat transfer coefficient: Where: Q represents the heat load of the condenser, W; K represents the overall heat transfer coefficient of the current condenser, W / (m 2 .K); A c Represents the total outer surface area of ​​the cooling water pipe of the condenser, which can be taken as the design parameter, m 2 ; Δtm represents the logarithmic mean temperature difference between steam and cooling water, ℃; c w Indicates the specific heat capacity of cooling water, J / (kg.K), the possible value is 4187; D w Indicates the amount of cooling water entering the condenser, kg / s; Δt indicates the temperature rise of cooling water, ℃.

7. The method for predicting the cleanliness rate of a condenser in a waste incineration power plant according to claim 4, characterized in that: In the fourth step, the process of calculating the current cleanliness coefficient of the condenser includes obtaining a cooling water inlet temperature correction coefficient fitting curve, βt=-6E-09t 5 +1E-06t 4 -5E-05t 3 +0.0009t 2 +0.0116t+0.6746 (1-10); Get the heat transfer coefficient fitting curve, K0 = -159.77V 2 +1596.9V+1272.1 (1-11); Get the wall thickness correction coefficient fitting curve, βm = -0.0136x 3 +0.0773x 2 —0.2729x+1.0697 (1-12); Combine (1-5) and (1-9) to calculate the cleanliness rate of the condenser: Among them: A c Represents the total outer surface area of ​​the cooling water pipe of the condenser, which can be taken as the design parameter, m 2 ; Δtm represents the logarithmic mean temperature difference between steam and cooling water, ℃; cw represents the specific heat capacity of cooling water, J / (kg.K), which can be 4187; Dw represents the amount of cooling water entering the condenser, kg / s; Δt represents the temperature rise of cooling water, ℃; βc represents the current condenser cleanliness coefficient; K0 represents the basic heat transfer coefficient, which can be obtained by consulting the appendix in the mechanical industry standard; β t Indicates the cooling water inlet temperature correction coefficient, which can be obtained by consulting the appendix in the mechanical industry standard or calculated according to the fitting formula; β m It indicates the correction factor of the wall thickness of the condenser material, which can be obtained by consulting the appendix in the mechanical industry standard or calculated according to the fitting formula.

8. The method for predicting the cleanliness rate of a condenser in a waste incineration power plant according to any one of claims 1 to 7, characterized in that: The step S2 further comprises: Step S21, setting 3 input nodes, 7 hidden nodes and 1 output node to obtain a three-layer BP neural network structure in the form of 3×7×1; Step S22, taking the exhaust temperature, the ideal heat transfer coefficient, and the actual heat transfer coefficient as given input vectors, and the measured condenser cleanliness rate as the target output; Step S23: Analyze the prediction results of the BP neural network.

9. The method for predicting the cleanliness rate of a condenser in a waste incineration power plant according to claim 8, characterized in that: In the step S21, the transfer function between the input layer and the hidden layer uses the tansig function, the output layer neuron transfer function uses the purelin function, and the training function uses the traingdx algorithm to train the network. The maximum number of learning times is set to 5000 times, the learning rate is 0.05, and the learning target is the sum of squared errors of 0.001.

Images