Construction engineering project progress prediction system and method based on deep learning

Abstract

The invention discloses a construction engineering project progress prediction system and method based on deep learning, which belong to the field of the construction industry. A model building process comprises the steps of extracting historical data; performing data cleaning, correction, supplement and regularization processing on the historical data to obtain to-be-trained data; constructing aninitial prediction model and carrying out training; verifying the model according to the special data, and outputting the initial prediction model passing the verification as a progress prediction model; the progress prediction process comprises the steps of obtaining current actual project information and inputting the current actual project information into the progress prediction model, and predicting predicted project progress information associated with the actual project information. The method has the beneficial effects that a set of progress prediction method suitable for different subdivision fields and scenes is established, historical data are preprocessed and processed through a deep learning algorithm, meanwhile, a special scene is simulated emphatically, a corresponding prediction result is output as the special scene needing to be considered in progress prediction, and an early warning prompt can be given.

Description

technical field [0001] The present invention relates to the field of construction industry, in particular to a system and method for predicting construction project progress based on deep learning. Background technique [0002] The forecast of construction project progress is an important basis for construction enterprises to formulate construction plans and control the construction process, and it plays a very important role in guiding and arranging construction project management. The progress of the project is not only constrained by the objective time period requirements of each process itself, but also by various external forces, natural environmental factors, internal and external partners, and other factors. Therefore, the reliability and accuracy of prediction methods often have differences Big deviation. The prediction of construction project progress is mainly based on the prediction of each process link involved in the Work Breakdown Structure (WBS) in the projec...

AI Technical Summary

Problems solved by technology

[0003] At present, most of the mainstream project schedule forecasting methods focus on one of the above or a combination of multiple items to predict and calculate, and give corresponding forecast results. These forecasting methods have certain limitations and rely too much on historical data. The processing and processing of data is relatively straightforward, and does not fully reflect the horizontal correlation of historical data; when applying data mining technology, changes due to changes in various objective conditions are rarely considered, such as the improvement in efficiency caused by the improvement of construction technology; for Abnormal historical situations, such as project delays due to bad weather in historical projects, these data are often not taken into consideration, and are usually discarded as outliers in schedule prediction, and there is no deduction of multi-frame differences for the prediction results The progress in emergencies is usually the predicted result under ideal conditions; the forecast subdivision of engineering projects is too single and lacks diversity, for example, in the field of construction engineering projects, civil engineering, housing construction, roads, municipal, bridge and tunnel There are often great differences in the corresponding characteristics and the division of work structures in different fields. Existing prediction algorithms are difficult to apply to different subdivision fields, and often require a lot of manual adjustments before they can be applied to new scenarios. Therefore, for For the above problems, it is urgent to design a construction project schedule prediction system and method based on deep learning to meet the needs of actual use.

Images