Wheeled Soil Analyzer for LIBS-Based Compressive Strength Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for determining soil unconfined compressive strength are time-consuming, costly, and prone to inaccuracies, while existing in situ soil testing methods face limitations in applicability, efficiency, and potential adverse effects on soil quality.
Innovation Solution
A field portable device employing laser-induced breakdown spectroscopy (LIBS) combined with a decision tree regressor and adaptive boosting classifier to predict soil unconfined compressive strength, using spectral emission intensities, bulk density, and water content as input features.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional UCS measuring methods (manual digging, laboratory physical property measurement, GPR, ERT) are used, then measurement precision is improved, but loss of time and productivity are worsened
Solution Approach 1:
The patent replaces conventional mechanical and electrical measurement systems (manual digging, GPR, ERT) with a laser-based optical system. The LIBS device uses laser-induced breakdown spectroscopy to analyze soil composition and predict UCS, substituting mechanical excavation and electrical resistivity methods with a non-contact optical measurement approach that provides rapid results without time-consuming sample collection or complex data processing.
Solution Approach 2:
The patent changes the measurement parameters from direct mechanical strength testing to spectral analysis parameters. By measuring emission intensities at specific wavelengths (e.g., 383.28 nm for Ca II, 526.72 nm for Mg I) and combining these with bulk density and water content parameters, the system predicts UCS through machine learning models, transforming the measurement approach from direct force application to indirect spectral characterization.
2Productivity
If in situ soil testing methods are used, then loss of time is reduced, but measurement precision and reliability are worsened
Solution Approach 1:
The patent introduces machine learning models as an intermediary between the LIBS spectral measurements and the final UCS prediction. The system uses emission intensities from multiple elements (Ca, Mg, Si, Al, Fe, Na, K, Ti, Mn, Zn) combined with bulk density and water content as input features to trained regression models (Random Forest, XGBoost, Support Vector Regression). This intermediary processing layer transforms the complex spectral data into accurate UCS predictions, resolving the trade-off between rapid in situ testing and measurement precision.
3Productivity
If in situ soil testing methods are used, then loss of time is reduced, but device complexity is worsened
Solution Approach 1:
The patent creates a multi-functional integrated device that combines laser generation, spectral detection, environmental sensing (bulk density and water content measurement), and machine learning prediction capabilities in a single portable system. The LIBS device serves multiple functions: it analyzes soil composition through LIBS, measures physical properties, and predicts UCS without requiring separate equipment for sample collection, laboratory analysis, or data processing, thereby managing complexity through functional integration.
4Productivity
If in situ soil testing methods are used, then loss of time is reduced, but reliability is worsened
Solution Approach 1:
The patent implements feedback mechanisms through the machine learning models that learn from training data and continuously improve prediction accuracy. The system uses cross-validation and performance metrics (R², RMSE, MAE) to evaluate and refine the models, ensuring reliable predictions. The feedback loop between measurement, prediction, and model refinement enhances the reliability of the in situ testing method while maintaining high productivity.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Achieves high accuracy in predicting soil unconfined compressive strength, with R2-scores up to 99.03%, overcoming the limitations of conventional and in situ methods.
Implementation Method 1
The spectrometer is configured to perform laser induced breakdown spectroscopy on the soil sample and generate spectral emission intensities of the soil sample
Data Source
AI summary
A field portable device for determining the unconfined compressive strength of a soil sample includes a sample holder, a heating device, a scale, a spectrometer, and a microprocessor. The sample holder receives a soil sample. The heating device dries the soil sample for a specified time. The scale measures a weight of the soil sample and a dried weight of the soil sample. The spectrometer performs laser induced breakdown spectroscopy on the soil sample and generates spectral emission intensities of the soil sample. The microprocessor calculates a bulk density and a water content of the soil sample, actuates the spectrometer to generate the spectral emission intensities. The microprocessor applies the spectral emission intensities, the bulk density and the water content to a trained machine learning regressor combined with an adaptive boosting classifier to predict the unconfined compressive strength of the soil sample.