Back-propagation Network Model Research Articles

Machine vision-based online detection method for color characteristics of cobalt extraction solution

Cobalt, as a rare metal, plays an important role in strategic resources due to its physical, chemical, and mechanical properties in applications. In order to achieve automatic control of the cobalt extraction process, it is necessary to conduct online detection of the color characteristics of the cobalt extraction solution. Unfortunately, due to the lack of online automatic detection methods for the color of cobalt extraction solution, the automatic control of the extraction process has not yet been achieved. Currently, the color of cobalt extraction solution needs to be observed and judged by operators based on experience. This will result in significant detection errors and time lag. To change this situation, an online detection method for color features of cobalt extraction solution based on machine vision is proposed in this article. Firstly, we establish a real-time image acquisition environment for detecting object colors, and then use the Gaussian filters and K-means algorithm to denoise and segment the image. In order to correct color distortion in images caused by ambient light, we measure the color feature values of a set of standard color cards using the machine vision system and a standard spectrophotometer. Based on this test data, we establish chromaticity correction models for the extraction solution using back propagation (BP) network and radial basis function (RBF) network, respectively. The models can correct the color characteristic values of the extraction solution, overcome environmental interference, and thus obtain more accurate color characteristic values of the extraction solution. The established model can be used for online automatic color detection of cobalt extraction solution. The modeling results indicate that in the established color measurement environment, the RBF network model outperforms the BP network model in color feature detection accuracy.

Residual networks for text-independent speaker identification: Unleashing the power of residual learning

The human voice, a dynamic signal, conveys valuable information for speaker identification, encompassing gender, age, emotions, and language. In the biometrics industry, identifying voices in real-time amidst diverse accents, tones, and noisy backgrounds is a challenging task. Voice biometry, a complex aspect of speaker identification, is gaining importance in various applications, such as user authentication, attendance systems, forensics, and banking operations, as it eliminates the need for traditional credentials like cards or passwords. Recent advancements in Human–Computer Interaction technology have made conversational tasks technically feasible. Deep Neural Learning approaches, especially Convolutional Deep Neural Networks (CDNN), have emerged as a powerful tool in the field of speech processing, surpassing traditional Speaker Identification methods. This paper introduces a novel approach using 1-Dimensional Convolutional Residual Blocks for audio classification and Speaker Identification, specifically focusing on speaker recognition from spoken Hindi language. The proposed Residual architecture significantly enhances speaker identification, even in low Signal Noise Ratio environments, achieving an impressive accuracy rate of 86.02%. This outperforms traditional Gaussian Mixture Model (GMM) and Feed Forward Back-propagation Network (FFBN) model for the same set of speakers. Future research directions may explore the classification of audio and speaker identification using various acoustic features derived from speech signals.

A Data-Driven Approach Using Enhanced Bayesian-LSTM Deep Neural Networks for Picks Wear State Recognition

Picks are key components for the mechanized excavation of coal by mining machinery, with their wear state directly influencing the efficiency of the mining equipment. In response to the difficulty of determining the overall wear state of picks during coal-mining production, a data-driven wear state identification model for picks has been constructed through the enhanced optimization of Long Short-Term Memory (LSTM) networks via Bayesian algorithms. Initially, a mechanical model of pick and coal-rock interaction is established through theoretical analysis, where the stress characteristic of the pick is analyzed, and the wear mechanism of the pick is preliminarily revealed. A method is proposed that categorizes the overall wear state of picks into three types based on the statistical relation of the actual wear amount and the limited wear amount. Subsequently, the vibration signals of the cutting drum from a bolter miner that contain the wear information of picks are decomposed and denoised using wavelet packet decomposition, with the standard deviation of wavelet packet coefficients from decomposed signal nodes selected as the feature signals. These feature signals are normalized and then used to construct a feature matrix representing the vibration signals. Finally, this constructed feature matrix and classification labels are fed into the Bayesian-LSTM network for training, thus resulting in the picks wear state identification model. To validate the effectiveness of the Bayesian-LSTM deep learning algorithm in identifying the overall picks wear state of mining machinery, vibration signals from the X, Y, and Z axes of the cutting drum from a bolter miner at the C coal mine in Shaanxi, China, are collected, effectively processed, and then input into deep LSTM and Back-Propagation (BP) neural networks respectively for comparison. The results showed that the Bayesian-LSTM network achieved a recognition accuracy of 98.33% for picks wear state, showing a clear advantage over LSTM, BP network models, thus providing important references for the identification of picks wear state based on deep learning algorithms. This method only requires the processing and analysis of the equipment parameters automatically collected from bolter miners or other mining equipment, offering the advantages of simplicity, low cost, and high accuracy, and providing a basis for a proper picks replacement strategy.

Computer technology of multisensor data fusion based on FWA–BP network

Abstract Due to the diversity and complexity of data information, traditional data fusion methods cannot effectively fuse multidimensional data, which affects the effective application of data. To achieve accurate and efficient fusion of multidimensional data, this experiment used back propagation (BP) neural network and fireworks algorithm (FWA) to establish the FWA–BP multidimensional data processing model, and a case study of PM2.5 concentration prediction was carried out by using the model. In the PM2.5 concentration prediction results, the trend between the FWA–BP prediction curve and the real curve was basically consistent, and the prediction deviation was less than 10. The average mean absolute error and root mean square error of FWA–BP network model in different samples were 3.7 and 4.3%, respectively. The correlation coefficient R value of FWA–BP network model was 0.963, which is higher than other network models. The results showed that FWA–BP network model could continuously optimize when predicting PM2.5 concentration, so as to avoid falling into local optimum prematurely. At the same time, the prediction accuracy is better with the improvement in the correlation coefficient between real and predicted value, which means, in computer technology of multisensor data fusion, this method can be applied better.

Rule-Based Non-Intrusive Load Monitoring Using Steady-State Current Waveform Features.

Monitoring electricity energy usage can help to reduce power consumption considerably. Among load monitoring techniques, non-intrusive load monitoring (NILM) provides a cost-efficient solution to identify individual load consumption details from the aggregate voltage and current measurements. Existing load monitoring techniques often require large datasets or use complex algorithms to obtain acceptable performance. In this paper, a NILM technique using six non-redundant current waveform features with rule-based set theory (CRuST) is proposed. The architecture consists of an event detection stage followed by preprocessing and framing of the current signal, feature extraction, and finally, the load identification stage. During the event detection stage, a change in connected loads is ascertained using current waveform features. Once an event is detected, the aggregate current is processed and framed to obtain the event-causing load current. From the obtained load current, the six features are extracted. Furthermore, the load identification stage determines the event-causing load, utilizing the features extracted and the appliance model. The results of the CRuST NILM are evaluated using performance metrics for different scenarios, and it is observed to provide more than 96% accuracy for all test cases. The CRuST NILM is also observed to have superior performance compared to the feed-forward back-propagation network model and a few other existing NILM techniques.

BP-Model-Based Quench Detection Method for Double-Stator HTS-Excitation Field- Modulation Machine

The quench of high-temperature-superconducting (HTS)-excitation coil is one of the key issues affecting the safe and stable operation of the double-stator HTS field-modulation (DS-HTSFM) machine. At present, the conventional method for inductive voltage noise filtering from quench voltage is to adopt analog low-pass filter. However, when it encounters serious interference, the limited filtering ability of traditional low-pass filter is not enough to completely filter out the coupled inductive voltage from the quench voltage, which will increase the misjudgment of quench detection. Therefore, a back-propagation (BP) network model is innovatively introduced to further filter the inductive voltage for the second time following by the primary low-pass filter, aiming at the improvement of quench detection accuracy for the HTS-excitation coil equipped in the analyzed DS-HTSFM machine, and its validity is verified by comparison with experimental results.

Fast starting point generation method for unobscured two-mirror imaging systems with large field-of-views

The surface design methods for unobscured mirror systems have certain limitations, such as time consuming and uncertain optimization possibility. Although neural networks can efficiently improve the design speed and accuracy, the obscuration problem cannot be avoided due to the lack of obscuration judgment in the training process. This study proposes a fast method to generate the starting points for unobscured two-mirror imaging systems with large field-of-views (FOVs) based on neural networks. The design difficulty upper limit is determined to construct the training set of a backpropagation (BP) network, then an obscuration evaluation module is added in the training process. Subsequently, a BP network model of non-obscuration design starting points with a high optimization potential can be quickly generated. Experimental results show that the non-obscuration starting points generated by our method can be easily optimized, and the range of FOV is from 15° × 15 to 20° × 20°.

Prediction and Analysis of Chlorophyll-a Concentration in the Western Waters of Hong Kong Based on BP Neural Network

The Chlorophyll-a (Chl-a) concentration is an important indicator of water environmental conditions; thus, the simultaneous monitoring of large-area water bodies can be realized through the remote sensing-based retrieval of Chl-a concentrations. Together with hyperspectral remote sensing data, a BP neural network model was used to invert chlorophyll-a concentration, with remote sensing reflectance as the input factor. Given the presence of many bands in the hyperspectral data, selecting an appropriate band reflectance as the input factor is crucial to improving inversion accuracy. In this study, a Pearson correlation analysis method was proposed to select bands. A normality test was performed on the reflectance of each band of the Zhuhai-1 hyperspectral remote sensing data, and the significance index was p < 0.05. The absolute kurtosis value was less than 10, and the absolute skewness value was less than 3, indicating that the Pearson method was applicable. Pearson correlation analysis was utilised to calculate the correlation coefficient between the reflectance data and chlorophyll-a concentration. Five reflectance data with high correlation were selected as the input factors, and chlorophyll-a concentration was adopted as the output factor. An error backpropagation network model was constructed to predict chlorophyll-a concentration, and a Garson function was added to clarify the connection weights of the input factors in the model construction process. Model 12 was determined as the optimal model on the basis of the criteria of the coefficient of determination, the average relative variance, and the minimum mean square error. The chlorophyll-a concentration was predicted for July and November 2020 in the study area, and the results showed that the predicted values had a small error compared with the measured values. The root-mean-square error and mean relative error of the chlorophyll-a concentration predicted and measured values were 2.12 μg/L and 9.66%, respectively. Significant spatial differences in the Chl-a concentration were observed in the study area due to the influence of islands and land; the Chl-a concentration in July was generally higher than that in November. The results of these studies provide a reference for monitoring the water environment in the study area.

Residual storey drift estimation of the MDOF system with the weak storey under seismic excitations using the BP network

This paper focuses on estimating residual storey drifts of multi-degree-of-freedom (MDOF) systems with the weak storey due to seismic excitations. According to the distribution of yield strength coefficients, MDOF systems are categorized into two types: a uniform MDOF system and a non-uniform MDOF system. Through elasto-plastic time history analysis, typical MDOF systems were analyzed considering the P-Δ effect under 60 earthquake records free of near-fault effects. The influences of various structural parameters on distribution characteristics of residual storey drifts along the height of the MDOF systems were investigated in detail. Finally, a back propagation (BP) network model was proposed to estimate residual storey drifts of the MDOF systems with the weak storey under seismic excitations. The results indicate that the maximum residual storey drift usually occurs at the weak storey for a non-uniform MDOF system while at the bottom for a uniform MDOF system. In addition, the larger the overall yield strength coefficient, the yield strength modification factor or the post-yield stiffness coefficient, the smaller the residual storey drift of the MDOF system on the whole. Moreover, the proposed BP model can sufficiently consider the parameters affecting residual storey drifts of the MDOF system with the weak storey, while having a good accuracy and a high efficiency in estimating the residual storey drifts.

A novel fault diagnosis scheme for a ballast system

The Back Propagation (BP) neural network model is one of the neural network models suitable for model recognition and classification. However, a single BP network model cannot fully tap the feature information hiding in the data and is vulnerable to the uncertainty associated with system parameter changes and also suffers from the effects of long diagnosis times, inaccurate and undesired diagnosis results in applying a large amount of high-dimensional feature data. In addition, the standard BP algorithm has limitations in pattern recognition and classification. For example, it adopts the quadratic cost function to train the neural network, which can lead to low convergence accuracy, low convergence rate, and so on. Compared with the quadratic cost function, the cross-entropy cost function can effectively improve the convergence accuracy and the convergence rate of the neural network. The Dempster–Shafer (D–S) evidence theory is a powerful tool for handling incomplete, imprecise, and uncertain information and merging it when it derives from multiple BP networks. In order to overcome the drawbacks of a single BP network, it is necessary to divide the high-dimensional feature data into several different categories of low-dimensional feature data and to input the same dimensional feature data into the same BP network model, as well as to design the information fusion algorithms based on D–S evidence theory and multiple improved BP networks with the cross-entropy cost function. For this reason, this paper proposes a novel information fusion diagnosis approach based on D–S evidence theory and multiple improved BP networks for fault diagnosis and classification of multiple devices in a ballast system subjected to extreme environmental conditions. The proposed diagnosis approach utilizes multiple neural networks to carry out local fault diagnosis, adopts the D–S evidence theory to fuse the results of local diagnosis and derive the decision results, and introduces an improved BP algorithm based on the cross-entropy cost function into the individual neural networks to enhance the convergence rate and diagnosis accuracy of the individual neural networks. This method can overcome the deficiencies of individual BP networks in multiple BP networks in their poor diagnostic ability to handle incomplete, imprecise, and uncertain sample information. According to the design idea of the proposed diagnosis approach, a new fusion modeling for fault diagnosis of multiple devices is constructed for a ballast system. The validity of the proposed diagnosis method and model is illustrated through both simulation studies and experimental tests.

An Intelligent Near-Infrared Diffuse Reflectance Spectroscopy Scheme for the Non-Destructive Testing of the Sugar Content in Cherry Tomato Fruit

As a new non-destructive testing technology, near-infrared spectroscopy has broad application prospects in agriculture, food, and other fields. In this paper, an intelligent near-infrared diffuse reflectance spectroscopy scheme (INIS) for the non-destructive testing of the sugar contents in vegetables and fruits was proposed. The cherry tomato were taken as the research object. The applicable objects and features of the three main methods of near-infrared detection were compared. According to the advantages and disadvantages of the three near infrared (NIR) detection methods, the experiment was carried out. This experiment involved the near-infrared diffuse reflection detection method, and the back propagation (BP) network model was established to research the sugar content of the cherry tomatoes. We used smoothing and a principal component analysis (PCA) to extract the final spectrum from the experimental spectrum. Taking the preprocessed spectral data as the input of the network and the measured sugar content of the cherry tomatoes as the output, the 80-12-1 network model structure was established. The cross-validation coefficient of determination was 0.8328 and the mean absolute deviation was 0.5711. The results indicate that the BP neural network can quickly and effectively detect the sugar content in cherry tomatoes. This intelligent near-infrared diffuse reflectance spectroscopy (INIS) scheme can be extended and optimized for almost all sugar-containing fruits and vegetables in the future.

Road Segmentation and Environment Labeling for Autonomous Vehicles

In autonomous vehicles (AVs), LiDAR point cloud data are an important source to identify various obstacles present in the environment. The labeling techniques that are currently available are based on pixel-wise segmentation and bounding boxes to detect each object on the road. However, the Avs’ decision on motion control and trajectory path planning depends on the interaction among the objects on the road. The ability of the Avs to understand the moving and non-moving objects is the key to scene understanding. This paper presents a novel labeling method to combine moving and non-moving objects. This labeling technique is named relational labeling. Autoencoders are used to reduce the dimensionality of the data. A K-means model provides pseudo labels by clustering the data in the latent space. Each pseudo label is then converted into unary and binary relational labels. These relational labels are used in the supervised learning methods for labeling and segmenting the LiDAR point cloud data. A backpropagation network (BPN), along with traditional gradient descent-based learning methods, are used for labeling the data. Our study evaluated the labeling accuracy of two as well as three layers of BPN. The accuracy of the two-layer BPN model was found to be better than the three-layer BPN model. According to the experiments, our model showed competitive accuracy of 75% compared to the weakly supervised techniques in a similar area of study, i.e., the accuracy for S3DIS (Area 5) is 48.0%.

A comparison between artificial neural network algorithms and empirical equations applied to submerged weir scour evolution prediction

Estimating the time evolution of a local scour hole downstream of submerged weirs can help determine the maximum scour depth and length and is essential to designing submerged weir foundations. In the current study, artificial neural networks with a backpropagation learning algorithm were used to estimate the temporal variation of scour profiles downstream of submerged weirs under clear water conditions. Physical factors, such as the flow condition, weir size, and sediment characteristics, are general scour considerations. Two sets of data combinations, namely original and non-dimensional data, were utilized in developing the backpropagation network (BPN) model. Using the data combinations and a trial-and-error method, the appropriate number of hidden neurons in the model architecture was determined. The results indicated that using non-dimensional variables as inputs in estimating the time evolution of scour holes downstream of a submerged weir is more suitable for the BPN model. Comparisons of the prediction results of the BPN model and an empirical regression formula revealed that the BPN model was more accurate and more direct in predicting the temporal variation of the local scour hole profile. In addition, sensitivity analysis showed that the dimensionless time exerted the most significant impact on the time evolution of the non-dimensional scour hole profile.

Membrane Fouling Prediction Based on Tent-SSA-BP.

In view of the difficulty in obtaining the membrane bioreactor (MBR) membrane flux in real time, considering the disadvantage of the back propagation (BP) network in predicting MBR membrane flux, such as the local minimum value and poor generalization ability of the model, this article introduces tent chaotic mapping in the standard sparrow search algorithm (SSA), which improves the uniformity of population distribution and the searching ability of the algorithm (used to optimize the key parameters of the BP network). The tent sparrow search algorithm back propagation network (Tent-SSA-BP) membrane fouling prediction model is established to achieve accurate prediction of membrane flux; compared to the BP, genetic algorithm back propagation network (GA-BP), particle swarm optimization back propagation network (PSO-BP), sparrow search algorithm extreme learning machine(SSA-ELM), sparrow search algorithm back propagation network (SSA-BP), and Tent particle swarm optimization back propagation network (Tent–PSO-BP) models, it has unique advantages. Compared with the BP model before improvement, the improved soft sensing model reduces MAPE by 96.76%, RMSE by 99.78% and MAE by 95.61%. The prediction accuracy of the algorithm proposed in this article reaches 97.4%, which is much higher than the 48.52% of BP. It is also higher than other prediction models, and the prediction accuracy has been greatly improved, which has some engineering reference value.

Prediction of the equilibrium moisture content and specific gravity of thermally modified wood via an Aquila optimization algorithm back-propagation neural network model

The equilibrium moisture content and specific gravity of Uludag fir (Abies bornmüelleriana Mattf.) and hornbeam (Carpinus betulus L.) woods were investigated following heat treatment at different temperatures and times. Two prediction models were established based on the Aquila optimization algorithm back-propagation neural network model. To demonstrate the effectiveness and accuracy of the proposed model, it was compared with a tent sparrow search algorithm-back-propagation network model, a back-propagation network model, and an artificial neural network. The results showed that the Aquila optimization algorithm back-propagation model reduced the root mean square error value of the original back-propagation model by 87% and 97%, respectively, and the decision coefficients (R2) of the equilibrium moisture content and specific gravity were 0.99 and 0.98; as such, the model optimization effect was obvious. Therefore, this paper provides an effective method for the optimization of the process parameters (such as heat treatment time, temperature, and air pressure) in wood heat treatment and related fields.

Modeling the Mechanical Properties of Heat-Treated Mg-Zn-RE-Zr-Ca-Sr Alloys with the Artificial Neural Network and the Regression Model

In this study, an artificial neural network approach and a regression model are adopted to predict the mechanical properties of heat-treated Mg-Zn-RE-Zr-Ca-Sr magnesium alloys. The dataset for artificial neural network (ANN) modeling is generated by investigating the microhardness of heat-treated Mg-Zn-RE-Zr-Ca-Sr alloys using Vickers hardness tests. A back-propagation (BP) neural network is established using experimental data that enable the prediction of mechanical properties as a function of the composition and heat treatment process. The input variables for the BP network model are Ca and Sr contents, ageing temperature and ageing time. The output variable corresponds to the microhardness. The optimal BP network model is acquired by optimizing the number of the hidden layer nodes. The results indicate that a reliable correlation coefficient is above 0.95 for architecture (4-8-1), which has a high level of accuracy for prediction. In addition, a second-order polynomial regression model is developed based on the least squares method. The results of determination coefficients and Fisher’s criterion indicate that the regression model is capable of modeling mechanical properties as a function of composition and the ageing process. Furthermore, supplemental experiments are conducted to check the accuracy of the BP model and the regression model, suggesting that the model predictions are well in accordance with experimental results. Therefore, both the BP network and regression models have high accuracy in modeling and predicting mechanical properties of heat-treated Mg-Zn-RE-Zr-Ca-Sr alloys.

A Hybrid ANN-GA Model for an Automated Rapid Vulnerability Assessment of Existing RC Buildings

Determining the risk priorities for the building stock in highly seismic-prone regions and making the final decisions about the buildings is one of the essential precautionary measures that needs to be taken before the earthquake. This study aims to develop an Artificial Neural Network (ANN)-based model to predict risk priorities for reinforced-concrete (RC) buildings that constitute a large part of the existing building stock. For this purpose, the network parameters in the network structure have been optimized by establishing a hybrid structure with the Genetic Algorithm (GA). As a result, the ANN model can make accurate predictions with maximum efficiency. The suggested ANN model is a feedforward back-propagation network model. It aims to predict the risk priorities for 329 RC buildings in the most successful way, for which the performance score was calculated using the Turkey Rapid Evaluation Method (2013). In this paper, a GA-ANN hybrid model was implemented in which the ANN, using the most successful gene revealed by the model, produced successful results in calculating the performance score. In addition, the required input parameters for obtaining more efficient results in solving such a problem and the parameters that need to be used in establishing such an ANN network structure have been optimized. With the help of such a model, the operation process will be eliminated. The created hybrid model was 98% successful in determining the risk priority in RC buildings.

A noninvasive artificial neural network model to predict IgA nephropathy risk in Chinese population

Renal biopsy is the gold standard for Immunoglobulin A nephropathy (IgAN) but poses several problems. Thus, we aimed to establish a noninvasive model for predicting the risk probability of IgAN by analyzing routine and serological parameters. A total of 519 biopsy-diagnosed IgAN and 211 non-IgAN patients were recruited retrospectively. Artificial neural networks and logistic modeling were used. The receiver operating characteristic (ROC) curve and performance characteristics were determined to compare the diagnostic value between the two models. The training and validation sets did not differ significantly in terms of any variables. There were 19 significantly different parameters between the IgAN and non-IgAN groups. After multivariable logistic regression analysis, age, serum albumin, serum IgA, serum immunoglobulin G, estimated glomerular filtration rate, serum IgA/C3 ratio, and hematuria were found to be independently associated with the presence of IgAN. A backpropagation network model based on the above parameters was constructed and applied to the validation cohorts, revealing a sensitivity of 82.68% and a specificity of 84.78%. The area under the ROC curve for this model was higher than that for logistic regression model (0.881 vs. 0.839). The artificial neural network model based on routine markers can be a valuable noninvasive tool for predicting IgAN in screening practice.

Prediction of Mechanical Properties of Thermally Modified Wood Based on TSSA-BP Model

In order to demonstrate whether the sparrow search algorithm can show good performance in optimization, this paper improves the prediction model by this algorithm and predicts the change data of wood mechanical properties under different conditions, which better reflects the connection between the process parameters of wood heat treatment and the change of wood mechanical properties. The article takes the five main mechanical property parameters of thermally modified wood: compressive strength along the grain, flexural strength, flexural elastic modulus, radial hardness, and tangential hardness, respectively, as the objects of study and improves the sparrow search algorithm by Tenting chaotic mapping and then optimizes the Back Propagation (BP) network model by this algorithm. The results show that the number of iterations of the optimized Tent-Sparrow search algorithm-Back Propagation network model (TSSA-BP) is only one-eighth that of the original BP network model, and the convergence speed is greatly improved, the root mean square error of the TSSA-BP model is at least one-half times that of the original BP model, and the optimized model fits the original data better in terms of predicted values; thus, this article provided a feasible prediction algorithm for the field related to the mechanical property changes of wood after heat treatment.

Prediction of Burr Types in Drilling of Al-7075 Using Acoustic Emission and Convolution Neural Networks

The formation of exit burrs during the drilling of ductile metals such as aluminum is critical in precision manufacturing and manufacturing automation. Because drilling burrs are difficult to remove, methods to predict various burr types and/or implement burr minimization schemes that consider the various attributes of burrs must be devised. In this study, not only drilling process conditions, including feed, cutting speed, and drill diameter, but also an artificial neural network is implemented to predict the formation of burrs during the drilling of aluminum-7075, which is widely used in the aerospace and automobile industries. Based on the drilling conditions, the main exit burr characteristics, such as burr size and type, were classified experimentally. Three different types of exit burrs (uniform burrs, uniform burrs with caps, and transient burrs) were observed from the aluminum 7075 workpieces. The classification results were further analyzed using burr control charts and an empirical equation, which enables the understanding of the overall influence of the drilling conditions over the burr types. Moreover, acoustic emission (AE) sensor monitoring scheme was utilized to sample the sensitive time-series signals during drilling burr formation. Subsequently, burr types were predicted using artificial intelligence techniques, namely machining learning and deep learning. First, backpropagation (BP) neural networks were constructed using the drilling conditions and AE signals as input vectors. For a comparative prediction, a convolution neural network (CNN) was implemented to obtain spectrogram image inputs from the sampled AE data. The proposed scheme is useful in predicting drilling burr types by employing a sensitive sensor monitoring setup and advanced artificial intelligence techniques, where both prediction results are well matched with experimental results. In addition, the CNN model shows effectiveness for a commonly practiced manufacturing process as it predicts the burr types with better accuracy than the BP network model (0.9375 over 0.8571).