BRNN-GRU Model for Real-Time Jet Grouting Pile Diameter Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional technologies for high-pressure jet grouting fail to accurately predict the three-dimensional shape and diameter of high-pressure jet grouting piles in real-time, especially considering complex strata conditions, which affects safety and reliability in construction processes.
Innovation Solution
A real-time dynamic prediction system and method utilizing a bidirectional recurrent neural network (BRNN) and gated recurrent unit (GRU) to construct a prediction model for the diameter of high-pressure jet grouting piles, allowing for continuous data feedback and correction to improve prediction accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional methods are used to predict high-pressure jet grouting pile parameters, then the prediction process is simple, but the prediction accuracy is insufficient especially under complex strata conditions
Solution Approach 1:
The patent implements a feedback mechanism where the predicted pile diameter is compared with actual measured values, and the prediction model is iteratively refined using the differences between predicted and actual data. This feedback loop enables the model to continuously improve its accuracy by learning from real-world deviations, directly addressing the need for high prediction accuracy under complex strata conditions.
Solution Approach 2:
The patent employs dynamic prediction models that adapt to changing strata conditions in real-time during the jet grouting process. The model parameters are updated dynamically based on measured pile diameter variations and soil condition changes, allowing the system to maintain high prediction accuracy despite the dynamic and complex nature of ground conditions.
2Measurement precision
If real-time dynamic prediction is implemented, then prediction accuracy is improved, but computational time and processing resources increase
Solution Approach 1:
The patent performs preliminary actions by pre-processing and storing historical jet grouting data, soil parameter profiles, and predicted value benchmarks before the actual prediction process. This pre-prepared data structure enables rapid querying and comparison during real-time prediction, reducing computational time while maintaining high accuracy through efficient data retrieval and processing.
3Measurement precision
If complex strata conditions are considered in the prediction model, then prediction accuracy improves, but the difficulty of detecting and measuring increases
Solution Approach 1:
The patent introduces intermediary measurement points and sensor systems that facilitate the detection and measurement of pile diameter and soil parameters. These intermediary devices bridge the gap between complex strata conditions and the prediction model, enabling accurate data collection from difficult-to-access locations within the ground while maintaining model accuracy.
Data Source
AI summary
The present disclosure provides a real-time dynamic prediction system and method of a three-dimensional shape of a high-pressure jet grouting pile. The method includes: obtaining a training data set; a model construction module constructs a high-pressure jet grouting pile diameter prediction model based on a bidirectional recurrent neural network (BRNN) and a gated recurrent unit (GRU); a model training module trains the high-pressure jet grouting pile diameter prediction model based on the training data set; a prediction module predicts based on the trained high-pressure jet grouting pile diameter prediction model, to obtain diameter prediction information in a construction process of a construction project; and a high-pressure jet grouting pile diameter output module determines whether the diameter prediction information matches a diameter mode; if the diameter prediction information matches the diameter mode, the high-pressure jet grouting pile diameter output module outputs the diameter prediction information.