Thermal power generating unit load sequence prediction method related to AGC prediction signal

Abstract

The invention discloses a thermal power generating unit load sequence prediction method related to an AGC prediction signal. The method comprises the following steps: S1, collecting parameter characteristics and target characteristics of a thermal power generating unit; s2, inputting the parameter characteristics into a unit load curve prediction model; s3, mapping the parameter features through two feature mapping layers; s4, performing convolution processing through a one-dimensional convolutional neural network with a Gaussian convolution kernel, and extracting inertial features of the data; s5, performing normalization processing on the target features, and inputting the target features into a unit load curve prediction model; s6, performing data feature processing by adopting two weighting layers; s7, carrying out feature combination; and S8, performing feature combination on the inertial features extracted in the step S4 and the data features after feature combination in the step S7 to obtain a thermal power generating unit operation power prediction sequence and curve. The method solves the problem that only internal factors of the thermal power generating unit are considered and external factors of the thermal power generating unit are not considered in an existing thermal power generating unit load prediction method.

Description

Technical Field

[0001] The invention belongs to the technical field of load prediction of power generation units, and in particular, relates to a load sequence prediction method for a thermal power generation unit involving an AGC prediction signal. Background Art

[0002] With the rapid development of new energy power technology, in order to make up for the uncertainty of new energy power generation, thermal power units, especially coal-fired units, need to continuously improve their bottom-line supply guarantee and flexible adjustment functions. In recent years, the concept of marketization of the power industry has been introduced, and the power spot market in many provinces across the country has started trial operation. With the gradual marketization of the power industry, the power generation side can more easily obtain reliable AGC prediction signals. The AGC prediction signal can more efficiently obtain the unit operation load curve of the unit in the future period. This curve can help the power generation side calculate the corresponding AGC assessment indicators, and make real-time adjustments to the unit operation according to the calculation results of the AGC assessment indicators to achieve the best economy and safety.

[0003] The prediction of the operating load curve of a thermal power unit needs to consider both the internal factors and external factors of the thermal power unit. The internal factors of the thermal power unit mainly involve the main operating parameters of the unit itself. The external factors are mainly AGC instructions. In the traditional load prediction method of thermal power units, only the internal factors of the thermal power unit are considered, while the external factors of the unit are not considered. Summary of the invention

[0004] Aiming at the problem that the existing load prediction method of thermal power units only considers the internal factors of the thermal power units but does not consider the external factors of the units, resulting in errors in the predicted operating load curve of the thermal power units, the present invention provides a load sequence prediction method for thermal power units involving AGC prediction signals.

[0005] In order to achieve the above technical objectives, the technical solution adopted by the present invention is as follows:

[0006] A method for predicting a load sequence of a thermal power unit involving an AGC prediction signal comprises the following steps:

[0007] S1. Collect parameter characteristics and target characteristics of thermal power units;

[0008] S2. The parameter characteristics of the thermal power unit are input into the unit load curve prediction model;

[0009] S3, the parameter features of the thermal power unit input into the unit load curve prediction model are first mapped through two feature mapping layers, and the mapping object is the feature information at each moment;

[0010] S4, the parameter features of the thermal power unit mapped by the two feature mapping layers are then convolved by a one-dimensional convolutional neural network with a Gaussian convolution kernel to extract the inertial features of the data;

[0011] S5, normalizing the target characteristics of the thermal power unit and inputting them into the unit load curve prediction model;

[0012] S6. The target features of the thermal power unit input into the unit load curve prediction model are first processed using two weighted layers for data features;

[0013] S7, after the data features are processed by two weighted layers, the features are merged;

[0014] S8. Merge the inertia feature extracted in step S4 and the data feature after the feature merging in step S7 again to obtain the thermal power unit operation power prediction sequence and curve.

[0015] Furthermore, the parameter characteristics of the thermal power unit include the unit main steam pressure, main steam temperature, coal feed rate and intermediate point temperature, and the target characteristics of the thermal power unit include the unit load, AGC command prediction signal and current AGC command.

[0016] Furthermore, in step S3, the feature mapping layer is composed of two fully connected layers, and is connected using a residual network structure;

[0017] The calculation formula for each feature mapping layer is:

[0018] y=sigmoid(w2sigmoid(w1x+b1)+b2)+x

[0019] Where x represents the feature mapping layer input, x∈R 4×t ; t represents the length of the input data in the time dimension; w1, b1 are the weights and biases of the first fully connected layer, w1∈R 32×4 , b1∈R 32×t ; w2, b2 are the weights and biases of the second fully connected layer, w2∈R 4×32 , b2∈R 4×t ; sigmoid represents the sigmoid activation function;

[0020] The expression of the activation function is:

[0021]

[0022] x′ is obtained by processing x through the feature mapping layer, x′∈R 4×t .

[0023] Furthermore, the convolution layer in step S4 acts on the time dimension of the data, where the Gaussian convolution kernel is expressed as:

[0024] ker i =e -|k(n-i)|

[0025] For the order of time information from front to back, the corresponding convolution kernel is [ker1, ker2, ker3..., ker n ], where n represents the length of the convolution kernel and k is a trainable parameter. X1 is obtained by convolution operation of x′, X1∈R 4×(t-n+1) .

[0026] Furthermore, the target characteristics of the thermal power unit are normalized, and the three target characteristics of unit load, AGC command prediction signal, and current AGC command use the same normalization parameters. The normalization formula is:

[0027]

[0028] in is the data after normalization. i is the data before normalization, data min With data max are the minimum and maximum values ​​in the data respectively. To avoid new data exceeding the range during the prediction process, data min With data max It should be the same as the upper and lower limit threshold settings of the parameters during unit operation.

[0029] Furthermore, in the target feature of the thermal power unit, the unit load is time series data, the AGC command prediction signal and the AGC command at the current moment are both single data, and different weighted layers are used to process the target features of the thermal power unit, and the weighted layers include weighted layer 1 and weighted layer 2, and each weighted layer includes a matrix broadcast operation and a matrix weighted summation operation;

[0030] The matrix broadcast operation is used to broadcast the AGC command prediction signal or the current AGC command into the data shape of the unit load.

[0031] Furthermore, in step S7, the two weighted layers perform data feature processing and then perform feature merging:

[0032] The weighted layer 1 extracts the features between the unit load and the AGC instruction prediction signal, and the weighted layer 2 extracts the features between the unit load and the AGC instruction at the current moment;

[0033] The calculation formula of the weighted layer is:

[0034] X′=w3a+w4x

[0035] X′ is the output of the weighted layer, X′∈R 1×t , a is the matrix obtained by broadcasting the AGC instruction prediction signal or the current AGC instruction, a∈R 1×t , w3, w4 are the coefficients of the weighted layer, w3, w4∈R 1 .

[0036] Furthermore, in step S8, the features are merged:

[0037] The outputs of weighted layer 1 and weighted layer 2 are X′1 and X′2 respectively. X′1 and X′2 are concatenated along the feature dimension to obtain X2, X2∈R 2×t ;

[0038] Concatenate X1 and X2 along the feature dimension. Since the length of X1 in the time dimension is (t-n+1), X2 needs to be pruned. The information farthest from the current moment in the time dimension of X2 is removed. The number of removed information is (n-1). Concatenate the remaining part of X2 with x1 along the feature dimension to obtain X3, X3∈R 6×(t-n+1) ,

[0039] The mapping operation is performed on X3 in the feature dimension. The mapping operation uses two fully connected layers for mapping. Both fully connected layers use the sigmoid activation function. The number of neurons in the two fully connected layers is [3, 1] respectively. The data after mapping is Y, Y∈R 1×(t-n+1) In the present invention, the data sampling interval is 1 second, so t in the patent is 330 and n is 31. Y is the output sequence of the model. By denormalizing Y, the operating load curve of the thermal power unit in the next 5 minutes can be obtained.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] The present invention adds consideration of the AGC prediction signal in the unit load prediction, and adopts different processing methods for the parameter characteristics and load-related characteristics of the unit. Among them, for the unit parameter characteristics, the present invention uses a multi-layer feature mapping layer to extract data features, and learns the inertial characteristics in the data through a convolution layer with a Gaussian convolution kernel. For the target features related to the load, the present invention uses two weighted layers to extract the linear features between the AGC command and the AGC prediction signal at the current moment and the unit load. By adding the method of time series information clipping and splicing, the external factors of the thermal power unit are combined with the internal factors, which can effectively predict the unit load of the thermal power unit at future moments. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1It is an overall flow chart of a method for predicting a load sequence of a thermal power unit involving an AGC prediction signal in an embodiment of the present invention;

[0043] Figure 2 It is a structural diagram of the unit load curve prediction model in an embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to facilitate the understanding of those skilled in the art, the present invention is further described below in conjunction with embodiments and drawings. The contents mentioned in the implementation modes are not intended to limit the present invention.

[0045] like Figure 1 and Figure 2 As shown, this embodiment provides a method for predicting a load sequence of a thermal power unit involving an AGC prediction signal, comprising the steps of:

[0046] S1. Collect parameter characteristics and target characteristics of thermal power units;

[0047] S2. The parameter characteristics of the thermal power unit are input into the unit load curve prediction model;

[0048] S3, the parameter features of the thermal power unit input into the unit load curve prediction model are first mapped through two feature mapping layers, and the mapping object is the feature information at each moment;

[0049] S4, the parameter features of the thermal power unit mapped by the two feature mapping layers are then convolved by a one-dimensional convolutional neural network with a Gaussian convolution kernel to extract the inertial features of the data;

[0050] S5, normalizing the target characteristics of the thermal power unit and inputting them into the unit load curve prediction model;

[0051] S6. The target features of the thermal power unit input into the unit load curve prediction model are first processed using two weighted layers for data features;

[0052] S7, after the data features are processed by two weighted layers, the features are merged;

[0053] S8. Merge the inertia feature extracted in step S4 and the data feature after the feature merging in step S7 again to obtain the thermal power unit operation power prediction sequence and curve.

[0054] The model input is the unit main steam pressure, main steam temperature, coal feed rate, intermediate point temperature, unit load, AGC instruction prediction signal, and current AGC instruction. The model output is the unit load change curve in the next 5 minutes. Except for the AGC instruction prediction signal and the current AGC instruction, the input features of the model are all data information within a period of time. The AGC instruction prediction signal is the AGC instruction obtained 5 minutes later at the current moment.

[0055] The unit load curve prediction model is divided into a training phase and a prediction phase. In the training phase, data is taken from historical data. The training phase is mainly used to set relevant parameters for the computing device and train the model based on historical data; the prediction phase is mainly used for unit load curve prediction in real-time systems.

[0056] Training phase:

[0057] 1. Extract five data sequences from the DCS historical database: main steam pressure, main steam temperature, coal feed rate, intermediate point temperature, unit load, and AGC instructions.

[0058] 2. Use the sliding window method to construct samples of the unit's main steam pressure, main steam temperature, coal feed rate, intermediate point temperature, and unit load. According to the time information of each sample, extract the AGC instructions at the current moment of the sample and the AGC instructions 5 minutes later from the AGC instructions, and extract the unit load curve within 5 minutes for model training.

[0059] 3. Set the computing device to training mode and train the model using mean square error.

[0060] Prediction stage:

[0061] 1. Set the computing device to prediction mode. Use a sliding window to send the unit main steam pressure, main steam temperature, coal feed rate, intermediate point temperature, unit load, AGC command prediction signal, and current AGC command data to the computing device.

[0062] 2. The calculation device directly outputs the unit power curve within the next 5 minutes.

[0063] The parameter characteristics of the thermal power unit include the unit main steam pressure, main steam temperature, coal feed rate and intermediate point temperature. The target characteristics of the thermal power unit include the unit load, AGC command prediction signal and the AGC command at the current moment.

[0064] In step S3, the feature mapping layer is composed of two fully connected layers, and the residual network structure is used for connection;

[0065] The calculation formula for each feature mapping layer is:

[0066] y=sigmoid(w2sigmoid(w1x+b1)+b2)+x

[0067] Where x represents the feature mapping layer input, x∈R 4×t ; t represents the length of the input data in the time dimension; w1, b1 are the weights and biases of the first fully connected layer, w1∈R 32×4 , b1∈R 32×t ; w2, b2 are the weights and biases of the second fully connected layer, w2∈R 4×32 , b2∈R 4×t ; sigmoid represents the sigmoid activation function;

[0068] The expression of the activation function is:

[0069]

[0070] x′ is obtained by processing x through the feature mapping layer, x′∈R 4×t .

[0071] The convolution layer in step S4 acts on the time dimension of the data, where the Gaussian convolution kernel is expressed as:

[0072] ker i =e -|k(n-i)|

[0073] For the order of time information from front to back, the corresponding convolution kernel is [ker1, ker2, ker3…, ker n ], where n represents the length of the convolution kernel and k is a trainable parameter. X1 is obtained by convolution operation of x′, X1∈R 4×(t-n+1) .

[0074] The target characteristics of the thermal power unit are normalized. The three target characteristics of unit load, AGC command prediction signal, and current AGC command use the same normalization parameters. The normalization formula is:

[0075]

[0076] in is the data after normalization. i is the data before normalization, data min With data max are the minimum and maximum values ​​in the data respectively. To avoid new data exceeding the range during the prediction process, data min With data max It should be the same as the upper and lower limit threshold settings of the parameters during unit operation.

[0077] Among the target features of the thermal power unit, the unit load is time series data, the AGC command prediction signal and the current AGC command are both single data, and different weighted layers are used to process the target features of the thermal power unit. The weighted layers include weighted layer 1 and weighted layer 2, and each weighted layer contains matrix broadcast operations and matrix weighted sum operations;

[0078] The matrix broadcast operation is used to broadcast the AGC command prediction signal or the current AGC command into the data shape of the unit load.

[0079] In step S7, the two weighted layers perform data feature processing and then merge features:

[0080] The weighted layer 1 extracts the features between the unit load and the AGC instruction prediction signal, and the weighted layer 2 extracts the features between the unit load and the AGC instruction at the current moment;

[0081] The calculation formula of the weighted layer is:

[0082] X=w3a+w4x

[0083] X′ is the output of the weighted layer, X′∈R 1×t , a is the matrix obtained by broadcasting the AGC instruction prediction signal or the current AGC instruction, a∈R 1×t , w3, w4 are the coefficients of the weighted layer, w3, W4∈R 1 .

[0084] Feature merging in step S8:

[0085] The outputs of weighted layer 1 and weighted layer 2 are X′1 and X′2 respectively. X′1 and X′2 are concatenated along the feature dimension to obtain X2, X2∈R 2×t ;

[0086] Concatenate X1 and X2 along the feature dimension. Since the length of X1 in the time dimension is (t-n+1), X2 needs to be pruned. The information farthest from the current moment in the time dimension of X2 is removed. The number of removed information is (n-1). Concatenate the remaining part of X2 with X1 along the feature dimension to obtain X3, X3∈R 6 ×( t -n +1 ),

[0087] The mapping operation is performed on X3 in the feature dimension. The mapping operation uses two fully connected layers for mapping. Both fully connected layers use the sigmoid activation function. The number of neurons in the two fully connected layers is [3, 1] respectively. The data after mapping is Y, Y∈R 1×(t-n+1)In the present invention, the data sampling interval is 1 second, so t in the patent is 330 and n is 31. Y is the output sequence of the model. By denormalizing Y, the operating load curve of the thermal power unit in the next 5 minutes can be obtained.

[0088] Compared with the prior art, the present invention has the following beneficial effects:

[0089] The present invention adds consideration of the AGC prediction signal in the unit load prediction, and adopts different processing methods for the parameter characteristics and load-related characteristics of the unit. Among them, for the unit parameter characteristics, the present invention adopts a multi-layer feature mapping layer to extract data features, and learns the inertial characteristics in the data through a convolution layer with a Gaussian convolution kernel. For the target characteristics related to the load, the present invention adopts two weighted layers to respectively extract the linear characteristics between the AGC instruction and the AGC prediction signal at the current moment and the unit load. By adding the method of time series information clipping and splicing, the external factors of the thermal power unit are combined with the internal factors, which can effectively predict the unit load of the thermal power unit at the future moment. According to the load prediction results, the AGC assessment index can be calculated, which is helpful for adjusting the control strategy, and is more conducive to the safety, economy and stability of the unit operation side.

[0090] The above is a detailed introduction to a method for predicting a load sequence of a thermal power unit involving an AGC prediction signal provided by the present application. The description of the specific embodiment is only used to help understand the method and its core idea of ​​the present application. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the scope of protection of the claims of the present application.

Claims

1. A method for predicting load sequence of thermal power units involving AGC prediction signals, characterized in that: Includes steps: S1. Collect parameter characteristics and target characteristics of thermal power units; S2. The parameter characteristics of the thermal power unit are input into the unit load curve prediction model; S3, the parameter features of the thermal power unit input into the unit load curve prediction model are first mapped through two feature mapping layers, and the mapping object is the feature information at each moment; S4, the parameter features of the thermal power unit mapped by the two feature mapping layers are then convolved by a one-dimensional convolutional neural network with a Gaussian convolution kernel to extract the inertial features of the data; S5, normalizing the target characteristics of the thermal power unit and inputting them into the unit load curve prediction model; S6. The target features of the thermal power unit input into the unit load curve prediction model are first processed using two weighted layers for data features; S7, after the data features are processed by two weighted layers, the features are merged; S8. Merge the inertia feature extracted in step S4 and the data feature after the feature merging in step S7 again to obtain the thermal power unit operation power prediction sequence and curve.

2. A method for predicting load sequence of thermal power units involving AGC prediction signals according to claim 1, characterized in that: The parameter characteristics of the thermal power unit include the unit main steam pressure, main steam temperature, coal feed rate and intermediate point temperature. The target characteristics of the thermal power unit include the unit load, AGC command prediction signal and the AGC command at the current moment.

3. A method for predicting load sequence of thermal power units involving AGC prediction signals according to claim 2, characterized in that: In step S3, the feature mapping layer is composed of two fully connected layers, and the residual network structure is used for connection; The calculation formula for each feature mapping layer is: y=sigmoid(w2sigmoid(w1x+b1)+b2)+x Where x represents the feature mapping layer input, x∈R 4×t ; t represents the length of the input data in the time dimension; w1, b1 are the weights and biases of the first fully connected layer, w1∈R 32×4 , b1∈R 32×t ; w2, b2 are the weights and biases of the second fully connected layer, w2∈R 4×32 , b2∈R 4×t ; sigmoid represents the sigmoid activation function; The expression of the activation function is: x′ is obtained by processing x through the feature mapping layer, x′∈R 4×t .

4. A method for predicting load sequence of thermal power units involving AGC prediction signals according to claim 3, characterized in that: The convolution layer in step S4 acts on the time dimension of the data, where the Gaussian convolution kernel is expressed as: ker i =e -|k(n-i)| For the order of time information from front to back, the corresponding convolution kernel is [ker1, ker2, ker3..., ker n ], where n represents the length of the convolution kernel and k is a trainable parameter. X1 is obtained by convolution operation of x′, X1∈R 4×(t-n+1) .

5. A method for predicting load sequence of thermal power units involving AGC prediction signals according to claim 4, characterized in that: The target characteristics of the thermal power unit are normalized. The three target characteristics of unit load, AGC command prediction signal, and current AGC command use the same normalization parameters. The normalization formula is: in is the data after normalization. i is the data before normalization, data min With data max are the minimum and maximum values ​​in the data respectively.

6. A method for predicting load sequence of thermal power units involving AGC prediction signals according to claim 5, characterized in that: Among the target features of the thermal power unit, the unit load is time series data, the AGC command prediction signal and the current AGC command are both single data, and different weighted layers are used to process the target features of the thermal power unit. The weighted layers include weighted layer 1 and weighted layer 2, and each weighted layer contains matrix broadcast operations and matrix weighted sum operations; The matrix broadcast operation is used to broadcast the AGC command prediction signal or the current AGC command into the data shape of the unit load.

7. A method for predicting load sequence of thermal power units involving AGC prediction signals according to claim 6, characterized in that: In step S7, the two weighted layers perform data feature processing and then merge features: Weighting Layer 1 extracts features between unit load and AGC instruction prediction signal, and weighted layer 2 extracts features between unit load and AGC instruction at the current moment; The calculation formula of the weighted layer is: X=w3a+w4x X′ is the output of the weighted layer, X′∈R 1×t , a is the matrix obtained by broadcasting the AGC instruction prediction signal or the current AGC instruction, a∈R 1×t , w3, w4 are the coefficients of the weighted layer, w3, w4∈R 1 .

8. A method for predicting load sequence of thermal power units involving AGC prediction signals according to claim 7, characterized in that: Feature merging in step S8: The outputs of weighted layer 1 and weighted layer 2 are X′1 and X′2 respectively. X′1 and X′2 are concatenated along the feature dimension to obtain X2, X2∈R 2×t ; Concatenate X1 and X2 along the feature dimension. Since the length of X1 in the time dimension is (t-n+1), X2 needs to be pruned. The information farthest from the current moment in the time dimension of X2 is removed. The number of removed information is (n-1). Concatenate the remaining part of X2 with X1 along the feature dimension to obtain X3, X3∈R 6×(t-n+1) , The mapping operation is performed on X3 in the feature dimension. The mapping operation uses two fully connected layers for mapping. Both fully connected layers use the sigmoid activation function. The number of neurons in the two fully connected layers is [3, 1] respectively. The data after mapping is Y, Y∈R 1×(t-n+1) .

Images