River flow monitoring data quality control method based on chaotic neural network

Abstract

The invention discloses a river flow monitoring data quality control method based on a chaotic neural network. The method comprises the following steps: a, sorting historical flow data in a chronological order to obtain time series data; b, normalizing the time series data; c, calculating the optimal time lag [tau] and the optimal embedding dimension m, and converting the one-dimensional time series data into multi-dimensional spatial sample data; d, proportionally dividing the multi-dimensional spatial sample data into multi-dimensional spatial training sample data and multi-dimensional spatial test sample data; e, using the multi-dimensional spatial training sample data to train and construct a GMDH neural network, using the multi-dimensional spatial test sample data to test the GMDH neural network so as to obtain a GMDH neural network model; f, detecting the abnormal value of river flow monitoring data; g, inspecting the completeness of the data within 24 hours of a day; and h, storing the revised river flow monitoring data is stored in a database. The method is able to improve the quality of river flow monitoring data.

Description

technical field [0001] The invention relates to a river flow monitoring method, in particular to a method for controlling the quality of river flow monitoring data based on a chaotic neural network. Background technique [0002] Hydrological data is the core of the entire hydrological industry. With the development of society and economy, people's living standards continue to improve, and people have more and more requirements for flood and drought disaster prevention, meteorological disaster prevention, water and soil vegetation conservation, water environment protection, and water resource testing. The higher the level, the higher the standards for hydrological data analysis, processing, exchange, storage, protection, and information disclosure. Due to the large amount of historical hydrological data, the data are complicated and the quality is uneven, and the lack of management makes it difficult to control the quality of hydrological data. At present, the quality contro...

AI Technical Summary

Problems solved by technology

The control methods for the lack of flow monitoring data in hydrological stations mainly include artificial filling method, mean value method, mathematical statistics and other methods. However, the above methods have not fully coupled the change law of hydrological historical data, and the method itself has certain defects; the flow monitoring of hydrological stations The detection method of data outliers usually adopts the control chart monitoring mode, which judges the rationality of the data and whether it needs to be corrected by analyzing the distribution characteristics of the points on the control chart. However, the control chart monitoring mode does not consider the timing of the flow time series data Considering the complete set of data, the data with obvious distortion is easy to be found, while the data with less obvious distortion is difficult to distinguish

Therefore, the existing technology has the problem of poor quality of river flow monitoring data

Images