Method for predicting dioxin emission concentration
AssigneeBeijing University of Technology
InventorsJian TANG, Heng XIA, Junfei QIAO, Zihao GUO
Life of this patent
Estimating the term…
Abstract
A method for predicting dioxin (DXN) emission concentration based on hybrid integration of random forest (RF) and gradient boosting decision tree (GBDT). A random sampling of a training sample and an input feature is performed on a modeling data with a small sample size and a high-dimensional characteristic to generate a training subset. J RF-based DXN sub-models based on the training subset are established. J×I GBDT-based DXN sub-models are established by performing I iterations on each of the RF-based DXN sub-models. Predicted outputs of the RF-based DXN sub-model and the GBDT-based DXN sub-model are combined by a simple average weighting method to obtain a final output.
Claims5
A method for predicting dioxin (DXN) emission concentration, comprising:
- (S1) performing, by a training sample and input feature random sampling module, a random sampling with replacement on a training sample set {X∉RN×M, y∉RN×1}N times and a random selection of a fixed number of input features from the training sample set to generate a training subset wherein X={xn}n=1N∉RN×M, which represents an input data {x|x1, . . . , xm, . . . xM} consisting of a process variable of a municipal solid waste incineration (MSWI) process acquired by a process control system while collecting a DXN test sample;
- the process variable comprises furnace temperature, activated carbon injection amount, stack emission gas concentration, grate speed, primary air flow and secondary air flow;
- N is the number of training samples;
- M is the number of the process variable;
- and y={yn}n=1N∉RN×1, which represents an output data consisting of the DXN emission concentration at an end of the MSWI process, wherein the end of the MSWI process is a stack emission end, and the DXN emission concentration is obtained by online collection and offline analysis;
- (S2) establishing, by a random forest (RF)-based DXN sub-model establishing module, a RF-based DXN sub-model {fRFj(⋅)}j=1J by utilizing the training subset {Xj, yj}j=1J;
- and subtracting a predicted value {ŷj}j=1J of the DXN emission concentration from a measured value {yj}j=1J of the DXN emission concentration to obtain a prediction error {ej,0}j=1J;
- (S3) performing, by a gradient boosting decision tree (GBDT)-based DXN sub-model establishing module, iteration I times on each of a new training subset {Xj, ej,0}j=1J to build I×J GBDT-based DXN sub-models {{fGBDTj,i(⋅)}j=1J}j=1J;
- wherein the new training subset is formed by the prediction error {ej,0}j=1J as an output data true value and an input data of a training subset {Xj}j=1J;
- (S4) subjecting, by a simple average-based DXN integrated prediction module, the RF-based DXN sub-model {ŷRFj}j=1J and the GBDT-based sub-model {{fGBDTj,i(⋅)}j=1J}j=1J to simple averaging to establish a DXN emission concentration prediction model fDXN(⋅);
- and
- (S5) taking the input data {x|x1, . . . , xm, . . . xM} as an input of the DXN emission concentration prediction model;
- and calculating, successively by the RF-based DXN sub-model establishing module, the GBDT-based DXN sub-model establishing module and the simple average-based DXN integrated prediction module, a current DXN emission concentration value as a DXN emission concentration predicted value of the MSWI process.
Dependencies are inferred from the claim text.