Learning Vector Quantization Neural Network Research Articles

Research on Tractor Condition Recognition Based on Neural Networks

Tractor condition recognition has important research value in helping to understand the operating status of tractors and the trend of tillage depth changes in the field. Therefore, this article presents a method for recognizing tractor conditions, providing the basis for establishing the relationship between tractor conditions and the tillage depth of the attached agricultural machinery. This study designed a tractor condition recognition method based on neural networks. Using real-world vehicle data to establish a data set, K-means clustering analysis was used to label the data set based on four conditions: “accelerated start”, “constant speed”, “decelerated stop” and “turning”. The learning vector quantization (LVQ) neural network and the VGG-16 model of a CNN were selected for use recognizing the tractor conditions. The results showed that both the neural networks had good recognition effects. The average accuracy rates of the VGG-16 model of CNN and LVQ neural network were 90.25% and 79.7%, respectively, indicating that these models could be applied to tractor condition recognition and provide theoretical support for the correction of angle detection errors.

Hybrid Architecture Model of Genetic Algorithm and Learning Vector Quantization Neural Network for Early Identification of Ear, Nose, and Throat Diseases

Background: In 2020, the World Health Organization (WHO) estimated that 466 million people worldwide are affected by hearing loss, with 34 million of them being children. Indonesia is identified as one of the four Asian countries with a high prevalence of hearing loss, specifically at 4.6%. Previous research was conducted to identify diseases related to the Ear, Nose, and Throat, utilizing the certainty factor method with a test accuracy rate of 46.54%. The novelty of this research lies in the combination of two methods, the use of genetic algorithms for optimization and learning vector quantization to improve the level of accuracy for early identification of Ear, Nose, and Throat diseases. Objective: This research aims to produce a hybrid model between the genetic algorithm and the learning vector quantization neural network to be able to identify Ear, Nose, and Throat diseases with mild symptoms to improve accuracy. Methods: Implementing a 90:10 ratio means that 90% (186 data) of the data from the initial sequence is assigned for training purposes, while the remaining 10% (21 data) is allocated for testing. The procedural stages of genetic algorithm-learning vector quantization are population initialization, crossover, mutation, evaluation, selection elitism, and learning vector quantization training. Results The optimum hybrid genetic algorithm-learning vector quantization model for early identification of Ear, Nose, and Throat diseases was obtained with an accuracy of 82.12%. The parameter values with the population size 10, cr 0.9, mr 0.1, maximum epoch of 5000, error goal of 0.01, and learning rate (alpha) of 0.5. Better accuracy was obtained compared to backpropagation (64%), certainty factor 46.54%), and radial basic function (72%). Conclusion: Experiments in this research, successed identifying models by combining genetic algorithm-learning vector quantization to perform the early identification of Ear, Nose, and Throat diseases. For further research, it's very challenging to develop a model that automatically adapts the bandwidth parameters of the weighting functions during trainin Keywords: Early Identification, Ear-Nose-Throat Diseases, Genetic Algorithm, Learning Vector Quantization

Damage Detection of Gantry Crane with a Moving Mass Using Artificial Neural Network

Gantry cranes play a pivotal role in various industrial applications, and their reliable operation is paramount. While routine inspections are standard practice, certain defects, particularly in less accessible components, remain challenging to detect early. In this study, first a finite element model is presented, and the damage is introduced using random changes in the stiffness of different parts of the structure. Contrary to the assumption of inherent reliability, undetected defects in crucial structural elements can lead to catastrophic failures. Then, the vibration equations of healthy and damaged models are analyzed to find the displacement, velocity, and acceleration of the different crane parts. The learning vector quantization neural network is used to train and detect the defects. The output is the location of the damage and the damage severity. Noisy data are then used to evaluate the network performance robustness. This research also addresses the limitations of traditional inspection methods, providing early detection and classification of defects in gantry cranes. The study’s relevance lies in the need for a comprehensive and efficient damage detection method, especially for components not easily accessible during routine inspections.

A comprehensive performance evaluation algorithm for substation secondary equipment: An improved analytic hierarchy process entropy weight and learning vector quantization neural network approach

AbstractThis paper introduces a comprehensive performance evaluation algorithm explicitly designed for secondary equipment in substations, specifically targeting the relay protection system. In contrast to the current evaluation systems, this novel method navigates the complex internal interconnections and mechanisms inherent within secondary system equipment. Such complications have previously impeded the accuracy and breadth of evaluations, thereby limiting the degree of precision and innovation attainable within substations. The proposed approach effectively integrates the improved Analytic Hierarchy Process entropy weight (IAHP‐EW) method with the Learning Vector Quantization (LVQ) neural network. Initially, the IAHP‐EW method identified the comprehensive evaluation indicators and their corresponding weights for relay protection devices. Following weight allocation, these evaluation indicators are scrutinized and computed utilizing the multivariate regression analysis algorithm, resulting in performance evaluation outcomes for the relay protection system. These outcomes are subsequently classified and utilized in training the LVQ neural network, promoting the network's capacity to autonomously evaluate the performance status of the relay protection system. To corroborate the viability and effectiveness of this proposed performance evaluation and prediction algorithm, empirical operating data from a local substation is used. The results suggest a significant improvement in the evaluation accuracy of secondary equipment performance, indicating potential for practical application and a valuable contribution to the field through the introduction of a novel approach to performance assessment of substation relay protection systems.

Detecting loss of excitation condition of synchronous generator in the presence of unified power flow controller based on data mining method

Loss-of-excitation (LOE) conditions may cause devastating effects on both the generator and power system. If LOE is not meticulously detected, two dangerous events may emerge: 1. unnecessary trip signal, 2. not detecting this abnormal condition or detecting it with time delay. Both mentioned flaws have considerable harmful consequences on the generator and power system. Conventional techniques for detecting LOE conditions are based on impedance measurement. The presence of flexible alternating current transmission (FACT) system devices can considerably affect the impedance characteristic of the system and as a result, the operation of impedance-based relays. This paper simulates LOE and stable power swing (SPS) conditions causing failures and errors in the LOE protection in the presence or absence of a unified power flow compensator (UPFC), and parameters with different behaviors are determined. Then, the most sensitive parameters are combined using an intelligent method. The single parameter, achieved from a combination of features in the previous process, is applied to a learning vector quantization (LVQ) neural network. The LVQ is a type of artificial neural network that is based on a prototype supervised learning classification algorithm and trained its network through a competitive learning algorithm. The simulation results show that, in a single machine infinitive bus (SMIB) test system, R-X directional scheme has 2 mal-operations and the proposed algorithm has no mal-operation without UPFC in the system. With UPFC in the system, the R-X directional scheme has four mal-operations and the proposed algorithm has no mal-operation. In the IEEE 9-bus test system, the R-X directional scheme has five mal-operations and the proposed algorithm has no mal-operation. Moreover, applying the proposed algorithm, LOE is detected very quickly in the presence or absence of the UPFC in the system and this approach prevents electrical and mechanical stresses enforced to the machine and power system. © 2017 Elsevier Inc. All rights reserved.

Application of the Learning Vector Quantization Algorithm for Classification of Students with the Potential to Drop Out

Universities, as providers of academic education services, are required to provide an optimal educational process for students to produce a generation of quality human beings. Student learning success is seen as the success of universities in implementing the higher education process. One of the problems universities face in maintaining the quality of education is student dropout. The high dropout rate in universities can impact accreditation assessments. As a result, it will affect the level of public trust. The number of dropouts in higher education can be minimized from an early age by analyzing the factors that cause student dropouts using data on students who graduated and those who dropped out. This data can be used to determine student dropout patterns by classifying them using the artificial neural network learning vector quantization (LVQ) approach. The data used in this research was 4053, consisting of 3840 graduate student data and 213 dropout student data. This data is considered unbalanced, an unbalanced dataset can cause errors because the model tends to classify the majority class with a high classification and pays less attention to the minority class. So, it is necessary to apply oversampling techniques to overcome this problem. The research results show that the application of the LVQ method to unbalanced data produces an accuracy value of 95.53%, a precision value of 100%, a recall value of 15.02% and an f1-score of 0.26, while the application of the LVQ method to data that has undergone resampling resulting in an accuracy value of 94.66%, a precision value of 92.22%, a recall value of 97.55%, and an f1-score value of 0.95. The LVQ method can be used to classify dropout students with excellent results.

An energy active regulation management strategy based on driving mode recognition for electro-hydraulic hybrid vehicles

Electro-hydraulic hybrid vehicles(EHHVs) have shown astonishing advantages in energy utilization and recovery. However, the key factor affecting the energy efficiency lies in the selection and switching conditions of driving modes. This paper introduces the structure and working principle of an electro-hydraulic hybrid vehicle that combines planetary gear mechanism. And an energy active regulation management strategy combined with driving mode recognition(DMR) and fuzzy control strategy is proposed. Firstly, a driving mode feature parameter evaluation is presented based on the collected speed and the principal component analysis(PCA). Secondly, K-means clustering algorithm is applied to identify offline driving modes through the extraction of driving short cycles. Then, combined with the PCA results, a Learning Vector Quantization neural network(LVQ) is constructed to recognize driving modes. Simultaneously, a fuzzy controller is added to allocate torque ratio. Finally, the DMR and fuzzy controller are combined to realize the energy active regulation of motors and hydraulic pump/motor. Experimental results indicate that energy management strategies based on DMR and fuzzy controller can realize optimal switching between modes according to condition recognition. It improves the utilization rate of the accumulator, and reduces battery energy consumption compared with traditional strategies.

A transient stability enhancement framework based on rapid fault-type identification for virtual synchronous generators

The virtual synchronous generator (VSG) control, widely used for voltage source inverters, is prone to the loss of synchronization (LOS) under large disturbances such as grid voltage sags. Despite the significant amount of research that has been conducted on the transient stability of VSGs, the existing conclusions on the influence of virtual inertia under different fault conditions remain controversial. In this paper, the conflicting effect of virtual inertia on VSG transient stability under different severities of grid voltage sag is comprehensively investigated. Faults, like grid voltage sags, are classified into two types in this paper: transient tolerable faults and transient intolerable faults. Moreover, a unified control framework for rapid fault-type identification and transient stability improvement is proposed. The Learning vector quantization (LVQ) neural networks are used to distinguish fault types within 5 ms. Based on the fault-type identification results, the proposed control strategies are applied to enhance the transient stability of VSG. Finally, simulations and control-hardware-in-loop experimental validations are carried out to demonstrate the effectiveness of the proposed framework.

Toward improving the performance of learning by joining feature selection and ensemble classification techniques: an application for cancer diagnosis.

Breast cancer is known as the most common type of cancer in women, and this has raised the importance of its diagnosis in medical science as one of the most important issues. In addition to reducing costs, the diagnosis of benign or malignant breast cancer is very important in determining the treatment method. The purpose of this paper is to present a model based on data mining techniques including feature selection and ensemble classification that can accurately predict breast cancer patients in the early stages. The proposed breast cancer detection model is developed by joining Adaptive Differential Evolution (ADE) algorithm for feature selection and Learning Vector Quantization (LVQ) neural network for classification. Our proposed model as ADE-LVQ has the ability to automatically and quickly diagnose breast cancer patients into two classes, benign and malignant. As a new evolutionary approach, ADE performs optimal configuration for LVQ neural network in addition to selecting effective features from breast cancer data. Meanwhile, we configure an ensemble classification technique based on LVQ, which significantly improves the prediction performance. ADE-LVQ has been analyzed from different perspectives on different datasets from Wisconsin breast cancer database. We apply different approaches to handle missing values and improve data quality on this database. The results of the simulations showed that the ADE-LVQ model is more successful than the equivalent and state-of-the-art models in diagnosing breast cancer patients. Also, ADE-LVQ provides better performance with less complexity, considering feature selection and ensemble learning. In particular, ADE-LVQ improves accuracy (up to 3.4%) and runtime (up to 2.3%) on average compared to the existing best method. Combined methods based on data mining techniques for breast cancer diagnosis can help doctors in making better decisions for disease treatment.

A twin delayed deep deterministic policy gradient-based energy management strategy for a battery-ultracapacitor electric vehicle considering driving condition recognition with learning vector quantization neural network

Deep reinforcement learning algorithms have been widely applied in the energy management of hybrid energy storage systems. However, these deep reinforcement learning algorithms, such as DQN and DDPG, have the problem of discontinuous action space and consistently overestimated Q values. To address this issue, a novel energy management strategy based on a twin delayed deep deterministic policy gradient (TD3) algorithm is proposed for the battery-ultracapacitor electric vehicles in this study. In addition, the driving condition recognition method is integrated into the energy management strategy framework to reduce the training time of the TD3 agent. The detailed implementation steps are as follows. At first, dynamic experiments were performed to establish high-precision models of the battery and ultracapacitor. Secondly, learning vector quantization neural networks are applied to classify driving conditions, namely, urban, suburban and highway conditions. Furthermore, three parallel TD3 agents are trained for urban, suburban and highway conditions, respectively. Finally, the proposed strategy is evaluated under standard driving cycles. The simulation results indicate that compared with the TD3-based strategy, the proposed strategy improves the economy by 1 % and reduces the training time by 34 %, and the economic gap with the dynamic programming-based energy management strategy is narrowed down to 3 %.

A novel coal-rock cutting state identification model based on the Internet of Things

The sudden change in the interface between coal-rock mass can lead to the increased abrasion of picks and the failure rate of mining machinery. The safe and efficient coal-rock identification technology is the key to realize the intelligent control of coal mining machinery. To realize the real-time perception and accurate recognition of coal-rock cutting state information, a novel coal-rock cutting state identification model based on the Internet of Things (IoT) is explored. Specifically, by using the virtual prototype technology, multi-source heterogeneous data from acquisition, processing and identification of coal-rock cutting state information are fused and analyzed. First, the paper analyzes the physical and mechanical characteristics of coal-rock mass, and takes the cutting drum of bolter miner as the research object to theoretically analyze its load, which provides a foundation for the research on coal-rock cutting state identification. Second, a rigid-flexible coupling virtual prototype model of the cutting drum and coal-rock models under different cutting conditions are established. The simulation process is implemented by employing the discrete element method (DEM) to ensure the real-time transmission of motion information and state characteristic signals. Ultimately, the dynamic information of drum load during the coal-rock cutting process is obtained. Finally, LVQ (Learning Vector Quantization) and PSO-BP (Particle Swarm Optimization-Back Propagation) neural networks are created, and the variation coefficient, waveform factor, and peak factor of load curves of cutting drums in the coal-rock mass with different firmness coefficients are input into the neural networks as feature vectors for state recognition. The experimental results show that LVQ and PSO-BP neural networks can be used for coal-rock cutting state identification, and PSO-BP network has faster convergence speed and higher recognition efficiency, which provides a new scheme for coal-rock cutting state identification to improve the safety and efficiency of coal mining machinery.

Transfer Deep Reinforcement Learning-Based Energy Management Strategy for Plug-In Hybrid Electric Heavy-Duty Trucks under Segmented Usage Scenarios

Energy management strategy (EMS) is a way to reduce the energy consumption of hybrid power systems. This article proposes a unique deep reinforcement learning- (DRL-) based EMS for plug-in hybrid electric heavy-duty trucks (PHETs), combining driving cycle pattern recognition (DPR) and deep transfer learning (DTL). The proposed EMS can cope well with the complex usage scenarios of PHETs and the difficulty of generating EMS. While ensuring the minimum overall driving cost, the strategy can improve the convergence speed of the DRL method and the generalizability under segmented usage scenarios. Firstly, representative driving cycles that reflect different usage scenarios are constructed based on a naturalistic data-driven method. Secondly, a plug-in hybrid electric heavy-duty truck (PHET) driving pattern recognizer based on a learning vector quantization neural network (LVQ) is built. Thirdly, the deep deterministic policy gradient (DDPG) algorithm is innovatively combined with the DTL algorithm. The pretrained neural network in the corresponding usage scenarios is transferred to the natural driving cycles based on DTL. Moreover, the proposed EMS gives an emphasized consciousness on the battery degradation cost. Finally, the strategy is tested under natural driving cycles in different usage scenarios and proven through comparison with the current state-of-the-art techniques, deep reinforcement learning-based strategy, and dynamic programming (DP). The results show that the proposed strategy outperforms existing cutting-edge deep reinforcement learning techniques in terms of convergence speed, battery life extension, fuel consumption, and overall driving cost reduction. The proposed control strategy can improve the convergence speed by nearly 50%, while effectively extending the battery life and reducing the overall driving cost compared to the existing state-of-the-art strategies. The battery degradation rate is reduced by 48.46%, 57.95%, and 36.99%, and the driving cost is reduced by 17.76%, 8.51%, and 7.12%, respectively, under each usage scenario.

A Novel Energy Management Strategy Integrating Deep Reinforcement Learning and Rule Based on Condition Identification

In order to reduce the driving cost of plug-in hybrid electric vehicles, a novel energy management strategy integrating deep reinforcement learning and rule based on condition identification is proposed. Firstly, principal component analysis is used to reduce the dimension of kinematic sequences features, and fuzzy clustering is used to classify the kinematics sequences, and then the working conditions are reorganized according to the classification results to obtain the three kinds of training conditions, and learning vector quantization neural network is used to train and identify the type of working conditions. Then, the rule taking engine torque, state of charge, and motor torque as control variables and driving mode as output is designed, which is integrated into the agent of deep reinforcement learning. Combined with the designed energy management strategy trained under three working conditions, the numerical simulation is carried out under the verification working condition based on condition identification, the simulation results are systematically analyzed to show the effectiveness of the designed energy management strategy.

Dynamic Scheduling Optimization of Production Workshops Based on Digital Twin

Production scheduling is the key to manufacturing process decision support, which directly affects the efficiency and competitiveness of enterprises. The production process of discrete workshops is complex and changeable, and it is usually difficult to make adjustments quickly and accurately in response to disturbance events. In this paper, a workshop production scheduling method based on digital twin is proposed and applied to the manufacturing workshop of an aerospace factory. Combined with the advantages of real-time virtual real interaction fusion of digital twin technology, the dynamic scheduling problem under fault disturbance factors is studied. A high-fidelity digital twin workshop is established to realize the mapping and interaction between the real production and the virtual factory. Based on the vibration data of machine tool spindle, a fault prediction method of learning vector quantization neural network is proposed. The dynamic scheduling strategy of workshop production based on digital twin is constructed and compared with the scheduling results without digital twin under fault disturbance. The results show that the scheduling method based on digital twin can effectively deal with disturbances and improve workshop productivity. This study can be used for the application of digital twin and production scheduling in practical factories.

Reliability-driven time series data analysis in multiple-level deep Learning methods utilizing soft computing methods

This paper introduces a novel method for mining data & information retrieval using series data for the duration. A multi-resolution S transformis viewed as a stage-adjusted transform of wavelet/a parameter window low period. Fourier-transform is used to recover significant characteristics from nonstationary duration series data with electricity-network disruptions. In pattern classification of disturbance waveform information, and incorporated Learning Vector Quantization neural-network & different feed-forward neural-network designs were employed afterwardextending required characteristics from the period of series-data.A fuzzy Multilayer perceptron accepts other connectionist systems and therefore is utilized in the final phase of encoding information inside the linking weights to produce fuzzy disturbance rules pattern inference. With energy signal time series data, a pattern classification performance of 99% was attained. Utilizing the new measurement processes, the data-driven information retrieval was displayed. A method proposed in this research is generically used to mine for information similarities in either duration of the series data pattern.

Online power management strategy for plug-in hybrid electric vehicles based on deep reinforcement learning and driving cycle reconstruction

This paper proposes a novel power management strategy for plug-in hybrid electric vehicles based on deep reinforcement learning algorithm. Three parallel soft actor-critic (SAC) networks are trained for high speed, medium speed, and low-speed conditions respectively; the reward function is designed as minimizing the cost of energy cost and battery aging. During operation, the driving condition is recognized at each moment for the algorithm invoking based on the learning vector quantization (LVQ) neural network. On top of that, a driving cycle reconstruction algorithm is proposed. The historical speed segments that were recorded during the operation are reconstructed into the three categories of high speed, medium speed, and low speed, based on which the algorithms are online updated. The SAC-based control strategy is evaluated based on the standard driving cycles and Shenyang practical data. The results indicate the presented method can obtain the effect close to dynamic programming and can be further improved by up to 6.38% after the online update for uncertain driving conditions.

Deep Q-learning network based trip pattern adaptive battery longevity-conscious strategy of plug-in fuel cell hybrid electric vehicle

The driving trip pattern is of great significance in hydrogen consumption and battery Longevity of the plug-in fuel cell hybrid electric vehicles (PFCHEV). However, the traditional energy management strategy failed to consider the uncertainty of driving patterns. To overcome this drawback, a deep Q-learning network based trip pattern adaptive (DQN-TPA) battery longevity-conscious strategy is proposed in this study. To begin with, the trip pattern recognition based Learning Vector Quantization Neural Network is devised for pattern identification, and the adaptive-equivalent consumption minimizes strategy (A-ECMS) is conducted to improve the hydrogen consumption. Then, a TPA longevity-conscious strategy is developed and compared with the conventional multi-criteria (MC) optimization strategy to investigate the discrepancy brought by the pattern adaptation. And finally, in combination with the above efforts, an improved DQN-TPA based battery longevity-conscious strategy has been established accordingly. The advances are confirmed by the validation results that, the A-ECMS makes an 11.76% promotion in fuel economy by taking the deviation among different driving patterns into concern. The TPA strategy shows more adaptiveness than the MC optimization strategy in which, the effective Ah-throughput is 5.17% lower than MC-based while keeping the same economy. Further improvement can be achieved by the modified DQN-TPA based approach by remedying the imperfection of TPA-based recognition delay and performing the economy and durability conscious actions with 5.87% further reduction of effective Ah-throughput without observably sacrificing the fuel economy. Furthermore, the effectiveness and adaptiveness of the proposed strategy are validated by the Hardware-in-the-Loop experiments. Both the numerical validation and semi-physical validation results indicate that the DQN-TPA based approach made it possible to develop the battery longevity-conscious strategy capable of significantly adapting various driving patterns and improving the hydrogen consumption and battery durability performance of the PFCHEV.

A Novel Recognition Method of Aging Stage of Transformer Oil-Paper Insulation Using Raman Spectroscopic Recurrence Plots

Timely identification of the aging stage of the transformer can effectively ensure the safe operation of the transformer and prevent the aging fault of the transformer. This work proposes the aging diagnosis of transformer using the Raman spectroscopic recurrence plot combined with learning vector quantization (LVQ) neural network. Oil-paper insulation samples at different aging stages are obtained by accelerated thermal aging tests. Acquisition of Raman spectra of insulating oil is from 800 to 3000 cm <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">−1</sup> and converts to the Raman spectroscopic recurrence plot. The gray-level cooccurrence matrix (GLCM) is used to extract the characteristic information of the Raman spectroscopic recurrence plot. The optimal number of neurons in competitive layer of LVQ neural network is determined by the experimental method. A transformer aging diagnosis model based on the Raman spectroscopic recurrence plot is established. The results show that the diagnostic accuracy of the proposed diagnostic model reached 95%. The Raman spectroscopic recurrence plot has more abundant aging “fingerprint” characteristic information and the proposed diagnostic method shows potential for monitoring oil-paper insulation.

Fault Diagnosis for PEMFC Water Management Subsystem Based on Learning Vector Quantization Neural Network and Kernel Principal Component Analysis

To solve the problem of water management subsystem fault diagnosis in a proton exchange membrane fuel cell (PEMFC) system, a novel approach based on learning vector quantization neural network (LVQNN) and kernel principal component analysis (KPCA) is proposed. In the proposed approach, the KPCA method is used for processing strongly coupled fault data with a high dimension to reduce the data dimension and to extract new low-dimensional fault feature data. The LVQNN method is used to carry out fault recognition using the fault feature data. The effectiveness of the proposed fault detection method is validated using the experimental data of the PEMFC power system. Results show that the proposed method can quickly and accurately diagnose the three health states: normal state, water flooding failure and membrane dry failure, and the recognition accuracy can reach 96.93%. Therefore, the method proposed in this paper is suitable for processing the fault data with a high dimension and abundant quantities, and provides a reference for the application of water management subsystem fault diagnosis of PEMFC.

Overview of Algorithms for Using Particle Morphology in Pre-Detonation Nuclear Forensics

A major goal in pre-detonation nuclear forensics is to infer the processing conditions and/or facility type that produced radiological material. This review paper focuses on analyses of particle size, shape, texture (“morphology”) signatures that could provide information on the provenance of interdicted materials. For example, uranium ore concentrates (UOC or yellowcake) include ammonium diuranate (ADU), ammonium uranyl carbonate (AUC), sodium diuranate (SDU), magnesium diuranate (MDU), and others, each prepared using different salts to precipitate U from solution. Once precipitated, UOCs are often dried and calcined to remove adsorbed water. The products can be allowed to react further, forming uranium oxides UO3, U3O8, or UO2 powders, whose surface morphology can be indicative of precipitation and/or calcination conditions used in their production. This review paper describes statistical issues and approaches in using quantitative analyses of measurements such as particle size and shape to infer production conditions. Statistical topics include multivariate t tests (Hotelling’s T2), design of experiments, and several machine learning (ML) options including decision trees, learning vector quantization neural networks, mixture discriminant analysis, and approximate Bayesian computation (ABC). ABC is emphasized as an attractive option to include the effects of model uncertainty in the selected and fitted forward model used for inferring processing conditions.