Dimensionless Features Research Articles

Pressure Drop Estimation of Two-Phase Adiabatic Flows in Smooth Tubes: Development of Machine Learning-Based Pipelines

The current study begins with an experimental investigation focused on measuring the pressure drop of a water–air mixture under different flow conditions in a setup consisting of horizontal smooth tubes. Machine learning (ML)-based pipelines are then implemented to provide estimations of the pressure drop values employing obtained dimensionless features. Subsequently, a feature selection methodology is employed to identify the key features, facilitating the interpretation of the underlying physical phenomena and enhancing model accuracy. In the next step, utilizing a genetic algorithm-based optimization approach, the preeminent machine learning algorithm, along with its associated optimal tuning parameters, is determined. Ultimately, the results of the optimal pipeline provide a Mean Absolute Percentage Error (MAPE) of 5.99% on the validation set and 7.03% on the test. As the employed dataset and the obtained optimal models will be opened to public access, the present approach provides superior reproducibility and user-friendliness in contrast to existing physical models reported in the literature, while achieving significantly higher accuracy.

A dimensionless feature for continuous bridge health monitoring with tiltmeter measurements

Structural Health Monitoring (SHM) is an essential tool for bridges especially if they have a long period of activity. The bridge considered in this work allows the crossing of the river Po between Lombardia and Emilia-Romagna in Italy. It is about 1.2 km long and has 35 main spans: 25 simply supported beams and 10 cantilevers. The bridge, in use since 1958, underwent a closure period and extraordinary maintenance in 2019 due to severe structural problems. After reopening, the bridge is continuously monitored with a system of 88 bi-axial tiltmeters installed in May 2022. The sensors measure static inclinations (< 1Hz) providing information on the deflection and torsion of the bridge spans. The monitoring system returns a set of summary statistics for each inclination signal gathered in the last hour. Statistics like the mean are used to examine anomalous span drifts in the long term. Instead, the Interpercentile Range is used to evaluate span movements in the short term. In fact, the latter proved to be a good indicator of the hourly traffic load on the bridge, assuming a constant structure stiffness. Therefore, an SHM strategy is to monitor span movements, on a daily basis, using traffic as an active load. This makes it possible to identify any increases in bridge oscillations in relation to a reference condition, calculated over a given monitoring period. For this purpose, a dimensionless metric is proposed as monitoring feature. First, a theoretical analysis of metrics is presented. Then, results obtained from experimental bridge monitoring data are shown.

Using the Buckingham π Theorem for Multi-System Transfer Learning: A Case-Study with 3 Vehicles Sharing a Database

Many advanced driver assistance schemes or autonomous vehicle controllers are based on a motion model of the vehicle behavior, i.e., a function predicting how the vehicle will react to a given control input. Data-driven models, based on experimental or simulated data, are very useful, especially for vehicles difficult to model analytically, for instance, ground vehicles for which the ground-tire interaction is hard to model from first principles. However, learning schemes are limited by the difficulty of collecting large amounts of experimental data or having to rely on high-fidelity simulations. This paper explores the potential of an approach that uses dimensionless numbers based on Buckingham’s π theorem to improve the efficiency of data for learning models, with the goal of facilitating knowledge sharing between similar systems. A case study using car-like vehicles compares traditional and dimensionless models on simulated and experimental data to validate the benefits of the new dimensionless learning approach. Preliminary results from the case study presented show that this new dimensionless approach could accelerate the learning rate and improve the accuracy of the model prediction when transferring the learned model between various similar vehicles. Prediction accuracy improvements with the dimensionless scheme when using a shared database, that is, predicting the motion of a vehicle based on data from various different vehicles was found to be 480% more accurate for predicting a simple no-slip maneuver based on simulated data and 11% more accurate to predict a highly dynamic braking maneuver based on experimental data. A modified physics-informed learning scheme with hand-crafted dimensionless features was also shown to increase the improvement to precision gains of 917% and 28% respectively. A comparative study also shows that using Buckingham’s π theorem is a much more effective preprocessing step for this task than principal component analysis (PCA) or simply normalizing the data. These results show that the use of dimensionless variables is a promising tool to help in the task of learning a more generalizable motion model for vehicles, and hence potentially taking advantage of the data generated by fleets of vehicles on the road even though they are not identical.

Data-driven prediction of dimensionless quantities for semi-infinite target penetration by integrating machine-learning and feature selection methods

This study employs a data-driven methodology that embeds the principle of dimensional invariance into an artificial neural network to automatically identify dominant dimensionless quantities in the penetration of rod projectiles into semi-infinite metal targets from experimental measurements. The derived mathematical expressions of dimensionless quantities are simplified by the examination of the exponent matrix and coupling relationships between feature variables. As a physics-based dimension reduction methodology, this way reduces high-dimensional parameter spaces to descriptions involving only a few physically interpretable dimensionless quantities in penetrating cases. Then the relative importance of various dimensionless feature variables on the penetration efficiencies for four impacting conditions is evaluated through feature selection engineering. The results indicate that the selected critical dimensionless feature variables by this synergistic method, without referring to the complex theoretical equations and aiding in the detailed knowledge of penetration mechanics, are in accordance with those reported in the reference. Lastly, the determined dimensionless quantities can be efficiently applied to conduct semi-empirical analysis for the specific penetrating case, and the reliability of regression functions is validated.

Fault diagnosis technology of CNC electromechanical system in mechanical engineering equipment manufacturing under structural coupling

Abstract This study addresses the fault diagnosis technology of CNC electromechanical systems in mechanical engineering equipment manufacturing, and explores the fault detection methods under the influence of structural coupling to improve the accuracy and efficiency of fault diagnosis. The study first analyzes the time-domain and frequency-domain features for fault diagnosis, including quantitative and dimensionless features used to identify different types of faults. Subsequently, the study explores feature dimensionality reduction methods, including algorithms such as PCA, LLE and t-SNE, and compares the effectiveness of their application in fault diagnosis. The research focuses on proposing a lightweight deep learning fault diagnosis framework called LTCN-BLS, which combines 2-DLTCN and 1-DLTCN branches, and an ILAEN-based BLS classifier to effectively extract and fuse time-domain and time-frequency-domain features of the data. The experimental results show that the LTCN-BLS framework has high accuracy and low network complexity in fault diagnosis, and has obvious advantages in early fault monitoring, degradation assessment, and robustness compared with traditional methods.

Adaptive deep neural networks for solving corner singular problems

Deep neural networks (DNNs) for numerical solutions to partial differential equations (PDEs) have exhibited their remarkable merits of meshless methods, dimensionless features, and nonlinear approximation powers. The majority of conventional DNNs are mainly concentrated on the low- or high-dimensional PDE with smooth solutions. In singular problems the DNN does not behave so efficiently as in the smooth problem because of low regularities of the solution. In this paper, we propose a novel adaptive DNN for the PDE with corner singular solutions. In the corner singular problem gradients of solution vary rapidly around some particular vertices or lines. This poses a difficulty in development of DNN solvers. We design adaptive DNN techniques for the corner singularity, which incorporates (a) an adaptive loss function that assigns radial weights to local losses, (b) an adaptive activation function that varies the choice of activation functions from neuron to neuron, and (c) an adaptive sampling strategy that selectively focuses on sampling points near the singular locations. The adaptive DNN with these adaptive schemes greatly enhances approximation accuracy and computation efficiency. This is verified by a comprehensive series of numerical experiments of 2D and 3D corner singular problems. The comparison analyzes with the existing DNN solvers are also made to demonstrate effectiveness of the new method. The L2 relative errors of the proposed adaptive DNN are reduced by an order of magnitude with respect to several conventional DNN methods.

Quantifying the heterogeneous impacts of the urban built environment on traffic carbon emissions: New insights from machine learning techniques

The configuration of the urban built environment is critical for promoting sustainability and achieving carbon neutrality. However, existing studies mostly use linear and spatial econometric models to investigate the relationship between urban built environments and traffic carbon dioxide (CO2) emissions, in-depth studies exploring the heterogeneous impacts of related features on traffic CO2 emission by interpretive machine learning models are scarce. Hence, we extract four dimensionless features to depict the size, compactness, irregularity, and isolation of built-up areas, and road network-related features (i.e., average cluster coefficient, road topological density, and road geometric density), respectively. Subsequently, we develop an interpretive machine learning framework based on the extracted features related to the urban built-up areas and road networks. The interpretive results of the proposed framework uncover that urban morphological features, especially population density (POP), GDP per capita (GDPpc), and urban physical compactness (UPC), have a heterogeneous impact on the per capita traffic emission (PCCE) across different cities. GDPpc is more like a linear relationship with PCCE, and UPC has a significant influence on PCCE when its value is between 62% and 78%. Our results also reveal the nonlinear relationships and interactive effects between these features, providing the implications of urban morphological planning and carbon emission reduction.

Measurement of adverse cosmesis in breast cancer: A deep learning approach

Background and PurposeAdverse cosmesis or poor aesthetic appearance of the breast after breast conservation surgery (BCS) and/or radiation therapy (RT) is highly correlated with quality-of-life (QOL) in breast cancer patients. Existing methods for objective assessment of cosmesis utilize human-designed features that are calculated using outlines and/or key-points from breasts. These are complicated and time consuming to obtain. Our purpose is to develop and validate a deep neural network (DNN)-based approach for classifying adverse cosmesis from frontal digital images of patients who have undergone BCS and RT using an approximate region-of-interest (ROI) containing the breast. Materials and MethodsWe used 6 datasets (5 from BCS/RT-related clinical trials) to conduct our study. Training subsets (80% of patients) from 3 datasets (RAPID, OPAR, and PORTO) were used to train 3 independent support vector classifiers for classifying adverse cosmesis using the features extracted from preprocessed, approximate breast ROIs passed through a pretrained DNN, called ResNet-18. The trained classifiers/models were evaluated through 5 experiments: holdout validation, treatment-arm specific validation in RAPID, external validation (included datasets from the remaining 3 trials), assessment of the effect of preprocessing, and comparison with BCCT.core software. Area-under-the receiver operating characteristics (AUC) was used as the primary evaluation measure. Treatment-arm specific probability values were compared by the Mann-Whitney U test. ResultsAUC (0.78, 0.88, 0.94) values increased from RAPID to OPAR and PORTO respectively for holdout validation. The median probability of adverse cosmesis was higher in the same treatment arm in accordance with the interim results of the RAPID trial and differed significantly between the treatment arms (p = 0.006). For external validation, best AUC values were obtained by the model trained in RAPID (AUCs > 0.78). Preprocessing improved the performance to a large extent (average AUC: 0.87 vs 0.79 for internal validation, 0.78 vs 0.64 for external validation). AUCs of the individual models using DNN-based features were higher in 7 of 9 validation tests and statistically similar to the human-designed, dimensionless features extracted from BCCT.core software. ConclusionAppropriately preprocessed, approximate breast ROIs can be represented by DNN-based features to identify adverse cosmesis from frontal images of breast cancer patients treated with BCS/RT. Adaptations to this approach may be necessary for its applicability to images with non-frontal views and different quality. This work serves as a foundation for developing robust DNN-based platforms for evaluating cosmesis in clinical trials.

Intelligent Analysis of Vibration Faults in Hydroelectric Generating Units Based on Empirical Mode Decomposition

Implementing intelligent identification of faults in hydroelectric units helps in the timely detection of faults and taking measures to minimize economic losses. Therefore, improving the accuracy of fault signal recognition has always been a research focus. This study is based on the improved empirical mode decomposition (EMD) theory to study the denoising and feature extraction of vibration signals of hydroelectric units and uses the backpropagation neural network (BPNN) to establish corresponding connections between signal features and vibration fault states. The improved EMD in this study can improve the performance of noise reduction processing and contribute to the accurate identification of vibration faults. The vibration fault identification criteria can adopt three dimensionless feature parameters: peak skewness coefficient, valley skewness coefficient, and kurtosis coefficient of the second- and third-order components of the signal, with recognition rates and accuracy reaching 90.6% and 96.2%, respectively. This paper’s area under the curve (AUC) values were 0.7365, 0.7335, 0.9232, and 0.9141 for abnormal sound detection of the fan, water pump, slide, and valve, respectively, with an average AUC value of 0.8268. This paper’s accuracy is 90.1%, and the loss function value is 0.27. The validation results demonstrate that this paper’s method has high intelligent fault analysis capabilities. The experimental results confirm that this method can effectively detect vibration signals in hydroelectric units and perform effective noise reduction processing, thereby improving the diagnostic accuracy of fault signals. Therefore, this method can be effectively applied to the detection of vibration faults in hydroelectric units.

A novel approach for quality control of automated production lines working under highly inconsistent conditions

When addressing product quality standards in manufacturing lines, a critical issue is the identification of the parameters that define the quality of the final product and their tracking. The problem of process control under inconsistent working condition of an automatic machinery, i.e. when some parameters are highly variable, is still quite unexplored in literature. This objective becomes even more challenging when the most important process variables are not directly measurable. This paper demonstrates that it is possible to achieve quality control by coupling a soft sensor, whose predictive model is a neural network, with an anomaly detector. The methodology has been applied to automatic machinery placed in a manufacturing line, where high variability in production rate has an important effect on the measured physical variables. This makes automated and accurate quality control difficult, due to the fact that in this test case the data collected are accelerometers signals, extremely sensible to variation in machine productivity by definition. It is shown that this approach outperforms many other classification methods (Support Vector Machines, Ensemble Bagged Tree, Discriminant Analysis, K-nearest neighbours and the direct application of a Neural Network) proposed in the past, achieving satisfactory results evaluated on the basis of four metrics (Accuracy, precision, recall and F1-score), even if anomalous data have been collected in a limited number of machine’s working points. In particular, an accuracy over 92% has been reached also for production rates where only nominal conditions are collected. This procedure exceeds the direct training of a neural network (accuracy of 57.6% at new production rates), as well as the application of shallow methods based on the extraction of dimensionless features (around 35% in accuracy at new production rates).

A Fault Diagnosis Method for Lithium Batteries Based on Optimal Variational Modal Decomposition and Dimensionless Feature Parameters

Abstract Due to the frequent occurrence of electric vehicles safety accidents caused by battery system failures, in order to ensure the normal operation of the vehicle, it is crucial to do a fault diagnosis of the electric vehicle lithium battery. This paper presents a fault diagnosis method for lithium batteries based on optimal variational modal decomposition and dimensionless feature parameters for identifying faulty batteries. The method first preprocesses the voltage signal of a lithium battery by optimal variable mode decomposition to obtain the high- and low-frequency components of the signal and reconstructs the high- and low-frequency components. Then, the dimensionless feature parameters are extracted according to the reconstructed signal, and feature reduction of the dimensionless feature parameters is carried out by a locally linear embedding algorithm. Finally, a local outlier factor algorithm is used to detect faulty batteries. After verified by the operation data before the real electric vehicle's thermal runaway failure, this method can detect the faulty battery timely and accurately.

Fault Feature Extraction of Bearings for the Petrochemical Industry and Diagnosis Based on High-Value Dimensionless Features

The time and frequency domain features of a petrochemical unit have a variety of effects on the fault type of bearings, and the signal exhibits nonlinearity, unpredictability, and ergodicity. The detection system's important data are disrupted by noise, resulting in a huge number of invalid and partial records. To reduce the influence of these factors on feature extraction, this work presents a method for the fault feature extraction of bearings for the petrochemical industry and for diagnosis based on high-value dimensionless features. Effective data are extracted from the obtained data using a complex data preprocessing approach, and the dimensionless index is expressed. Then, based on the distribution rule of the dimensionless index, the high-value dimensionless features are retrieved. Finally, to ensure sample completeness, a high-value dimensionless feature augmented model is developed. This approach is applied to the bearing fault experiment platform of a petrochemical unit to effectively classify the bearing fault features, which benefits theoretical guidance for the feature extraction of bearings for a petrochemical unit.

Research on rolling bearing fault diagnosis method based on ARMA and optimized MOMEDA

In actual operating conditions, rolling bearings vibration signals are easily covered by heavy noise, increasing the difficulty of fault diagnosis. A fault diagnosis method based on auto regressive moving average (ARMA) model and multipoint optimal minimum entropy deconvolution adjusted (MOMEDA) algorithm is proposed to address this issue. Firstly, ARMA model is used to remove the intrinsic components and pre-whitening the signals. Then parameters of MOMEDA are optimized by Sparrow Search Algorithm (SSA), the periodic fault signals are recovered by the optimized MOMEDA and the secondary noise reduction of the signals is realized. Finally, a class of time-domain average dimensionless features, namely average pulse factor, average kurtosis factor and average margin factor, are proposed and combined with the Gini index as fault diagnosis indexes then input into ELM classifier to identify fault types. Experimental results show the proposed method can identify fault types effectively and achieve accurate diagnosis of rolling bearings.

Machine learning based pressure drop estimation of evaporating R134a flow in micro-fin tubes: Investigation of the optimal dimensionless feature set

The present study is focused on proposing, implementing, and optimizing machine learning based pipelines for estimating the pressure drop in evaporating R134a flow passing through micro-fin horizontal tubes. Accordingly, an experimental activity is first conducted, in which the pressure drop of the flow at various operating conditions is measured. Physical models that are available in the literature are then implemented and the corresponding accuracy, while being applied to the obtained dataset, is determined. Machine learning based pipelines, with dimensionless parameters provided as features and two-phase flow multipliers as targets, are then developed. In the next step, a feature selection procedure is performed and an optimization process is then conducted to find the algorithms and the corresponding hyper-parameters, using which results in the highest possible accuracy. The optimal pipeline is demonstrated to be the one in which the liquid only two-phase multiplier is chosen as the target and is provided with only 5 dimensionless parameters as selected input features. Employing the latter pipeline leads to a mean absolute relative deviation (MARD) of 6.27 % on the validation set and 6.41 % on the test set, which is notably lower than the one achieved using the most promising physical model (MARD of 18.74 % on the validation set and 18.08 % on the test set). Furthermore, as the dataset and the obtained optimal pipeline will be made publicly accessible, the proposed methodology also offers higher ease of use and reproducibility.

Similarity and Froude Number Similitude in Kinematic and Hydrodynamic Features of Solitary Waves over Horizontal Bed

This study presents, experimentally, similarity and Froude number similitude (FNS) in the dimensionless features of two solitary waves propagating over a horizontal bed, using two wave gauges and a high-speed particle image velocimetry (HSPIV). The two waves have distinct wave heights H0 (2.9 and 5.8 cm) and still water depths h0 (8.0 and 16.0 cm) but identical H0/h0 (0.363). Together with the geometric features of free surface elevation and wavelength, the kinematic characteristics of horizontal and vertical velocities, as well as wave celerity, are elucidated. Illustration of the hydrodynamic features of local and convective accelerations are also made in this study. Both similarity and FNS hold true for the dimensionless free surface elevation (FSE), wavelength and celerity, horizontal and vertical velocities, and local and convective accelerations in the horizontal and vertical directions. The similarities and FNSs indicate that gravity dominates and governs the wave kinematics and hydrodynamics.

Research on Accurate Prediction of the Container Ship Resistance by RBFNN and Other Machine Learning Algorithms

Resistance is one of the important performance indicators of ships. In this paper, a prediction method based on the Radial Basis Function neural network (RBFNN) is proposed to predict the resistance of a 13500 transmission extension unit (13500TEU) container ship at different drafts. The predicted draft state in the known range is called interpolation prediction; otherwise, it is extrapolation prediction. First, ship features are extracted to make the resistance Rt prediction. The resistance prediction results show that the performance of the RBFNN is significantly better than the other four machine learning models, backpropagation neural network (BPNN), support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGBoost). Then, the ship data is processed in a dimensionless manner, and the models mentioned above are used to predict the total resistance coefficient Ct of the container ship. The prediction results show that the RBFNN prediction model still performs well. Good results can be obtained by RBFNN in interpolation prediction, even when using part of dimensionless features. Finally, the accuracy of the prediction method based on RBFNN is greatly improved compared with the modified admiralty coefficient.

An intelligent fault diagnosis method for roller bearing using symplectic hyperdisk matrix machine

Support matrix machine (SMM) is a new and effective classification method, which has been applied in the field of image processing. In this paper, an improved SMM called symplectic hyperdisk matrix machine (SHMM) is proposed and applied to the roller bearing fault diagnosis. In SHMM, the symplectic geometry similarity transformation (SGST) is used to obtain the dimensionless feature matrix, which protects the signal structure information while weakening the interference of noise. Then, different types of hyperdisks are constructed to divide different types of data, several more realistic hyperdisk prediction models can be obtained and the problem of under estimation is avoided. In order to fully mine the spatial structure information, the feature matrix is mapped to the high-dimensional space by kernel technology, and the decision function is established by using the structure information hidden of the input matrix in the SHMM. Experimental results of three datasets of roller bearing show that, compared with symplectic geometry matrix machine (SGMM), SMM, support vector machine (SVM) and radial basis function (RBF) neural network methods, the proposed SHMM has good application effect in roller bearing fault diagnosis.

Milling chatter detection by multi-feature fusion and Adaboost-SVM

Unstable chatter vibration in the milling process significantly affect the machining quality and efficiency. In order to suppress or avoid the chatter vibration in the cutting operation, detection of chatter onset is highly needed. Until now, most of the existing chatter detection methods designed chatter indicators by extracting signal features, and the threshold of designed chatter indicator is usually needed, which is difficult to determine and might not be applicable in different cutting conditions. In fact, chatter detection is essentially a typical classification problem, hence milling chatter detection based on machine learning method is presented in this paper. In order to obtain the needed data set, milling experiments under different cutting conditions were performed. Multi-features are utilized for the chatter detection, including the dimensionless features in time domain and frequency domain, and the automatic features extracted by stacked-denoising autoencoder (SDAE). In order to improve the accuracy of chatter classification and avoid the negative effects of possible samples with wrong labels, adaptive boosting (Adaboost) algorithm that consists of a series of weak classifiers by support vector machine (SVM) is utilized and further improved. Experimental verification and performance analysis are also performed, and the results show that the presented method can detect the chatter with a high accuracy and is applicable in different milling conditions.

Machine learning based models for pressure drop estimation of two-phase adiabatic air-water flow in micro-finned tubes: Determination of the most promising dimensionless feature set

The present study is focused on determining the most promising set of dimensionless features and the optimal machine learning algorithm that can be employed for data-driven frictional pressure drop estimation of water (single-phase) and air-water mixture (two-phase) flow in micro-finned horizontal tubes. Accordingly, an experimental activity is first conducted, in which the frictional pressure drop of both water and air-water flows, at various flow conditions, is measured. Next, machine learning based pipelines are developed, in which dimensionless parameters are provided as features and the friction factor (for the single-phase case) and the two-phase flow multipliers (for the two-phase case) are considered as the targets. Next, the feature selection procedure is performed, in which the most promising set of features, while employing a benchmark algorithm, is determined. An algorithm optimization procedure is then performed in order to choose the most suitable algorithm (and the corresponding tuning parameters) that lead to the highest possible accuracy. Moreover, the state-of-the-art physical models are implemented and the corresponding accuracy, while being applied to the experimentally obtained dataset, is determined.It is demonstrated that only 5 dimensionless features are selected (among 23 provided features) in the obtained pipeline developed for the estimation of the two-phase gas multiplier (in the extraction procedure of which, the single-phase friction factors are determined only using the Reynolds number and two geometrical parameters). Therefore, the latter procedures notably reduce the complexity of the model, while providing a higher accuracy (MARD of 6.72% and 7.05% on the training and test sets respectively) compared to the one achieved using the most promising available physical model (MARD of 15.21%). Finally, through implementing the forward feature combination strategy on the optimal pipeline, the contribution of each feature to the achieved accuracy is shown and the trade-off between the model's complexity (number of features) and the obtained accuracy is presented. Thus, the latter step provides the possibility of utilizing an even inferior number of features, while achieving an acceptable accuracy. Moreover, since these pipelines will be made publicly accessible, the implemented models also offer a higher reproducibility and ease of use.

A Tactile Method for Rice Plant Recognition Based on Machine Learning.

Accurate and real-time recognition of rice plants is the premise underlying the implementation of precise weed control. However, achieving desired results in paddy fields using the traditional visual method is difficult due to the occlusion of rice leaves and the interference of weeds. The objective of this study was to develop a novel rice plant recognition sensor based on a tactile method which acquires tactile information through physical touch. The tactile sensor would be mounted on the paddy field weeder to provide identification information for the actuator. First, a flexible gasbag filled with air was developed, where vibration features produced by tactile and sliding feedback were acquired when this apparatus touched rice plants or weeds, allowing the subtle vibration data with identification features to be reflected through the voltage value of an air-pressured sensor mounted inside the gasbag. Second, voltage data were preprocessed by three algorithms to optimize recognition features, including dimensional feature, dimensionless feature, and fractal dimension. The three types of features were used to train and test a neural network classifier. To maximize classification accuracy, an optimum set of features (b (variance), f (kurtosis), h (waveform factor), l (box dimension), and m (Hurst exponent)) were selected using a genetic algorithm. Finally, the feature-optimized classifier was trained, and the actual performances of the sensor at different contact positions were tested. Experimental results showed that the recognition rates of the end, middle, and root of the sensor were 90.67%, 98%, and 96% respectively. A tactile-based method with intelligence could produce high accuracy for rice plant recognition, as demonstrated in this study.