Cost prediction method of power transmission and transformation project based on kpca-la-rbm

Abstract

The invention discloses a KPCA-LA-RBM-based cost prediction method for power transmission and transformation projects, which belongs to the technical field of electric digital data processing. It includes the following steps: 1. Perform data selection and preprocessing on each sample data, and obtain a set of key influencing factors; 2. Form a training set from several sets of preprocessed sample data, and use the training set to train the KPCA-LA-RBM combined model; 3. Use the remaining data as the test set, and use the test set to predict the trained model according to the trained combination model to obtain the final prediction result. The present invention selects the first four principal components as the input vector of the combination model according to the cumulative variance contribution rate of the principal components, and improves the calculation efficiency of the model under the condition of ensuring the prediction accuracy. The combination model proposed by the invention can effectively reduce errors caused by a single model, improve prediction accuracy, improve generalization ability and robustness, and is suitable for cost prediction of power transmission and transformation projects.

Description

technical field [0001] The invention belongs to the technical field of electrical digital data processing, in particular to a KPCA-LA-RBM-based cost prediction method for power transmission and transformation projects. Background technique [0002] Electric power construction belongs to infrastructure construction. Compared with other consumer demands, the quality of infrastructure construction has a great impact on people's living standards and quality. It can be said that electric power construction is also a symbol of a city's developed level to a certain extent. In recent years, with the growth of my country's GDP, the power grid industry has developed rapidly, the scale of power transmission and transformation projects has continued to increase, and the power grid investment has also become larger and larger. In order to reasonably control costs, optimize resource allocation and effectively adjust planning arrangements in the actual construction process of electric powe...

AI Technical Summary

Problems solved by technology

[0005] However, the BP neural network algorithm has a slow convergence speed and is easy to fall into a local optimal solution. In view of the shortcomings of the algorithm, many scholars use factor analysis, fuzzy algorithm, etc. to combine with the neural network to form a new combination algorithm, or use genetic algorithm, particle swarm optimization Algorithms, etc. to improve it

[0006] Although the BP neural network algorithm has been greatly improved in terms of prediction performance and can obtain more accurate prediction results, the BP neural network is not suitable for prediction of small sample data.

Images