Mean Impact Value Research Articles

Fault diagnosis of wind turbine gears based on OCSSA-VMD and WOA-CNN-BiLSTM

Abstract The accuracy of wind turbine gearbox fault diagnosis will be compromised if the fault feature data is not adequately extracted during operation. To enhance fault identification efficiency and mitigate human interference in parameter setting, this paper introduces an optimized mode decomposition algorithm OCSSA-VMD, derived from variational mode decomposition (VMD) and further optimized by osprey-Cauchy-sparrow search algorithm (OCSSA). This algorithm offers two key advantages: (1) automatic optimization of parameters such as the number of modes k and penalty factor α; (2) reduction of feature dimensionality through mean impact value (MIV) algorithm based on minimum envelope entropy principle, resulting in a multi-fault feature vector set from 13 time-domain features in the intrinsic mode function (IMF) optimal component of wind turbine gearbox vibration data. Additionally, a fault diagnosis model WOA-CNN-BiLSTM is proposed based on whale optimization algorithm (WOA) and convolutional neural network-bidirectional long-short-term-memory (CNN-BiLSTM), which demonstrates improved fault classification accuracy to 98.3333% and diagnosis accuracy to 98.3853% under conditions of insufficient data when compared with other models.

Algae content prediction based on transfer learning and mean impact value

To improve the prediction accuracies of algae contents in different water bodies, this paper proposes a chlorophyll-A prediction model method based on transfer learning(TL) and mean impact value(MIV) algorithm. Firstly, we preprocess the data collected from the Huai River, including remove the missing data and standardize the preserving data. Then, the MIV algorithm is used to reduce the dimensionality of the data and determine the input variables of the model. Based on the selected input variables, the TL algorithm is introduced to establish the chlorophyll-A prediction model. The developed method can effectively enhance the prediction accuracy, especially when the number of samples is small. The simulation results verify the effectiveness and feasibility of the proposed prediction model.

Predicting ignitability classification of thermally thick solids using hybrid GA-BPNN and PSO-BPNN algorithms

Two hybrid binary classification models combining the merits of GA (genetic algorithm) and PSO (particle swarm optimization) with BPNN (backpropagation neural network) are proposed to estimate the ignitability of thermally thick solids. A 1D numerical model verified by analytical correlation and experimental measurements is employed to yield training, validation and testing datasets. Surface absorptivity (ε), density (ρ), specific heat (Cp), thermal conductivity (k), critical temperature (Tcri), and incident heat flux (HF) which are highly related to solid ignition are selected as inputs, and ignitability serves as output. A one-hidden-layer BPNN is first constructed, and then GA and PSO are encoded to form GA-BPNN and PSO-BPNN where connection weights and biases are optimized by GA/PSO and the predicted error serves as objective function of GA/PSO. Results show that the optimal neuron number in hidden layer is 34. Compared to BPNN, GA-BPNN and PSO-BPNN feature higher accuracy but more training time. Accuracy and convergence efficiency of PSO-BPNN are higher than GA-BPNN, nevertheless GA-BPNN exhibits better robustness. Predictive accuracies of BPNN, GA-BPNN, and PSO-BPNN on testing dataset are 99.05%, 99.55%, and 99.55%, respectively. ROC (receiver operating characteristic) curves are plotted to rank the performance of the three models, revealing 0.5 is an appropriate threshold to classify ignitability. Feature importance of the models is analyzed using PI (permutation importance) and MIV (mean impact value) methods. It is found HF and Tcri are the most important two inputs followed by ε, while ρ, Cp, and k show least and approximately identical impact. Reliability of the three models is verified by predicting critical heat flux of ignition of three polymers, and good agreement with literature is observed.

Comfort weight analysis for optimising ergonomic cabin design of a drilling rig machine using three-dimensional human simulation

Ergonomics in product design enhance user comfort, correlating with increased efficiency and usability between the user and the product. Anthropometry is an important part of creating ergonomic design that correlates with human body size. By utilising anthropometry data, this research aims to analyse the cabin's comfort in drilling rig machine by creating 3D simulations for human-machine interaction. The comfort values will be assessed using Jack software. An experimental orthogonal design is applied to generate 81 optimal combination samples. The sample with the optimal comfort value can also be obtained. Following that, the extreme learning machine and mean impact value (ELM-MIV) algorithm is employed to evaluate the comfort weight analysis of each influencing factor. The accuracy value of the prediction model assessed using mean squared error (MSE) is 0.004, and the squared correlation coefficient (R2 ) value is 0.996. It can be inferred that the prediction error is apparently minimal, indicating the reliability of ELM implementation in data training. It will optimise the redesign of a drilling rig machine cabin to solve work-related health issues and improve operator comfort and efficiency.

Mineralized carbon sequestration evaluation of coal-based solid waste consolidated backfill: A novel data-driven approach

The coal mining industry and its byproduct utilization are confronted with challenges such as the accumulation of coal-based solid waste and the emission of CO2, which seriously jeopardize environmental protection. A lucrative way of mitigating these problems is CO2 mineralization storage technology of coal-based solid waste consolidated backfill. Its successful realization stringy depends on the CO2 mineralization sealing stock and requires accurate account of the carbon sequestration rate of cemented backfill. Therefore, this study proposes a novel hybrid intelligent model combining the adaptive enhanced whale optimization algorithm and the support vector regression (A-E-WOA-SVR) to forecast the carbon sequestration performance of cemented backfill. The respective data set of cemented backfill was obtained through laboratory tests under different values of seven factors influencing the carbon sequestration rate, including water–solid ratio, cement ratio, fly ash ratio, slag ratio, curing pressure, curing temperature, and curing time. The results exhibit that the adaptive enhanced whale optimization algorithm can effectively optimize the hyperparameters of the support vector regression. The A-E-WOA-SVR hybrid intelligent model proposed in this paper accurately predicted the carbon sequestration rate of cemented backfill. Coefficient of determination, mean absolute error, root mean square error, and other indices were used to evaluate the performance of the intelligent prediction model. The obtained values of these indices implied small errors. The mean impact value sensitivity analysis revealed that water–solid ratio, cement content, curing pressure, and curing time were the key sensitive factors controlling the carbon sequestration performance of cemented backfill, which should mainly considered in the control of cemented backfill mineralization carbon sequestration performance. The research results provide a theoretical reference which enhance the CO2 mineralization storage performance of coal-based solid waste consolidated backfill.

Quantitative analysis of soil potassium by near-infrared (NIR) spectroscopy combined with a three-step progressive hybrid variable selection strategy

Soil potassium is a crucial nutrient element necessary for crop growth, and its efficient measurement has become essential for developing rational fertilization plans and optimizing crop growth benefits. At present, data mining technology based on near-infrared (NIR) spectroscopy analysis has proven to be a powerful tool for real-time monitoring of soil potassium content. However, as technology and instruments improve, the curse of the dimensionality problem also increases accordingly. Therefore, it is urgent to develop efficient variable selection methods suitable for NIR spectroscopy analysis techniques. In this study, we proposed a three-step progressive hybrid variable selection strategy, which fully leveraged the respective strengths of several high-performance variable selection methods. By sequentially equipping synergy interval partial least squares (SiPLS), the random forest variable importance measurement (RF(VIM)), and the improved mean impact value algorithm (IMIV) into a fusion framework, a soil important potassium variable selection method was proposed, termed as SiPLS-RF(VIM)-IMIV. Finally, the optimized variables were fitted into a partial least squares (PLS) model. Experimental results demonstrated that the PLS model embedded with the hybrid strategy effectively improved the prediction performance while reducing the model complexity. The RMSET and RT on the test set were 0.01181% and 0.88246, respectively, better than the RMSET and RT of the full spectrum PLS, SiPLS, and SiPLS-RF(VIM) methods. This study demonstrated that the hybrid strategy established based on the combination of NIR spectroscopy data and the SiPLS-RF(VIM)-IMIV method could quantitatively analyze soil potassium content levels and potentially solve other issues of data-driven soil dynamic monitoring.

CFRP-RC fracture strength prediction: A novel approach using deep learning

Externally bonded carbon fiber-reinforced polymer (CFRP) composites have been widely adopted for strengthening and repairing aging concrete structures. However, premature fracture at the CFRP-concrete interface remains a significant concern, necessitating a better understanding of the interfacial bond behavior and fracture mechanisms. Traditional experimental studies and numerical simulations have limitations in accurately capturing the complex nonlinear factors influencing this fracture behavior. This paper explores the novel application of machine learning (ML), specifically artificial neural networks (ANNs), for predicting the fracture strength of CFRP-reinforced concrete (CFRP-RC) members. ANNs enable mapping the intricate relationships between input parameters (e.g., CFRP/concrete properties, geometric configurations) and fracture responses through iterative training on experimental data. Key aspects include comprehensive data collection, preprocessing techniques, feature selection methods like mean impact value (MIV) analysis, and neural network architecture design. The paper highlights successful ANN applications in predicting CFRP-RC bond strength, shear capacity, and overall fracture behavior. A systematic approach is proposed for developing robust ANN models tailored to CFRP-RC fracture prediction, encompassing data curation, input variable screening, network training/validation, and model interpretability analyses. By leveraging ML’s ability to handle multifaceted nonlinearities, this data-driven framework offers a powerful alternative to traditional methods, potentially enhancing the design, analysis, and performance evaluation of CFRP-strengthened concrete structures.

Energy consumption prediction of coal-fired unit boiler system based on different operating states

ABSTRACT The energy consumption of the coal-fired unit’s boiler system varies significantly when accommodating flexible peak shaving demands. To aid staff in comprehending the boiler’s operational status and optimize its performance, a prediction model of the energy consumption of the boiler system was established based on the different states of the unit operation. First, a dataset of boiler energy consumption under variable load was established based on theory of fuel-specific consumption, and the Mean Impact Value (MIV) algorithm was used to simplify the input features of the model. Second, the Aquila Optimizer (AO) with tent map, adaptive t-distribution, and opposites learning mechanism was introduced to determine the parameters in the prediction model. On this basis, the sliding-window method was used to classify the operating states based on the load of the unit, and the original dataset without operating state distinction, the steady state operating data, the load uplink data, and the load downlink data were used to establish Models 1–4, respectively. The result shows that Model 1 outperforms Model 2 with 24.45% and 18.22% lower aMAE and aRMSE, respectively. compared to Model 3, it shows a decrease of 24.07% and 16.98%. Compared to Model 1, Model 4 shows a reduction of 20.52% and 18.91% in aMAE and aRMSE, respectively. This indicates that distinguishing different operating states to establish boiler energy consumption prediction models can obtain better prediction accuracy.

Early identification of Parkinson's disease with anxiety based on combined clinical and MRI features.

To identify cortical and subcortical volume, thickness and cortical area features and the networks they constituted related to anxiety in Parkinson's disease (PD) using structural magnetic resonance imaging (sMRI), and to integrate multimodal features based on machine learning to identify PD-related anxiety. A total of 219 patients with PD were retrospectively enrolled in the study. 291 sMRI features including cortical volume, subcortical volume, cortical thickness, and cortical area, as well as 17 clinical features, were extracted. Graph theory analysis was used to explore structural networks. A support vector machine (SVM) combination model, which used both sMRI and clinical features to identify participants with PD-related anxiety, was developed and evaluated. The performance of SVM models were evaluated. The mean impact value (MIV) of the feature importance evaluation algorithm was used to rank the relative importance of sMRI features and clinical features within the model. 17 significant sMRI variables associated with PD-related anxiety was used to build a brain structural network. And seven sMRI and 5 clinical features with statistically significant differences were incorporated into the SVM model. The comprehensive model achieved higher performance than clinical features or sMRI features did alone, with an accuracy of 0.88, a precision of 0.86, a sensitivity of 0.81, an F1-Score of 0.83, a macro-average of 0.85, a weighted-average of 0.92, an AUC of 0.88, and a result of 10-fold cross-validation of 0.91 in test set. The sMRI feature right medialorbitofrontal thickness had the highest impact on the prediction model. We identified the brain structural features and networks related to anxiety in PD, and developed and internally validated a comprehensive model with multimodal features in identifying.

Prediction of Energy Consumption in a Coal-Fired Boiler Based on MIV-ISAO-LSSVM

Aiming at the problem that the energy consumption of the boiler system varies greatly under the flexible peaking requirements of coal-fired units, an energy consumption prediction model for the boiler system is established based on a Least-Squares Support Vector Machine (LSSVM). First, the Mean Impact Value (MIV) algorithm is used to simplify the input characteristics of the model and determine the key operating parameters that affect energy consumption. Secondly, the Snow Ablation Optimizer (SAO) with tent map, adaptive t-distribution, and the opposites learning mechanism is introduced to determine the parameters in the prediction model. On this basis, based on the operation data of an ultra-supercritical coal-fired unit in Xinjiang, China, the boiler energy consumption dataset under variable load is established based on the theory of fuel specific consumption. The proposed prediction model is used to predict and analyze the boiler energy consumption, and a comparison is made with other common prediction methods. The results show that compared with the LSSVM, BP, and ELM prediction models, the average Relative Root Mean Squared Errors (aRRMSE) of the LSSVM model using ISAO are reduced by 2.13%, 18.12%, and 40.3%, respectively. The prediction model established in this paper has good accuracy. It can predict the energy consumption distribution of the boiler system of the ultra-supercritical coal-fired unit under variable load more accurately.

A Soft Measurement Method for the Tail Diameter in the Growing Process of Czochralski Silicon Single Crystals

In the Czochralski silicon single crystal growth process, the tail diameter is a key parameter that cannot be directly measured. In this paper, we propose a real-time soft measurement method that combines a deep belief network (DBN) and a support vector regression (SVR) network based on system identification to accurately predict the crystal diameter. The main steps of the proposed method are as follows: First, we address the delay problem of the effects of the temperature and crystal pulling speed on the tail diameter growth by using a back propagation (BP) neural network based on the mean impact value (MIV) method to determine the optimal delay time. Second, we construct a prediction model of the tail diameter by using the DBN network with the temperature and crystal pulling speed as input variables in the crystal growth process. Third, we improve the DBN network by using the SVR network to enhance its linear regression capability. We also employ the ant colony optimization (ACO) algorithm to obtain the optimal parameters of the SVR network. Finally, we compare the performance of the DBN-ACO-SVR network based on system identification with the DBN and SVR networks, and the results show that our method can effectively deal with the delay problem and achieve the accurate prediction of the tail diameter in the Czochralski silicon single crystal growth process.

Application of Northern Goshawk Back-Propagation Artificial Neural Network in the Prediction of Monohydroxycarbazepine Concentration in Patients with Epilepsy.

A northern goshawk back-propagation artificial neural network (NGO-BPANN) model was established to predict monohydroxycarbazepine (MHD) concentration in patients with epilepsy. The data were collected from 108 Han Chinese patients with epilepsy on oxcarbazepine monotherapy. The results of 14 genotype variates were selected as the input layer in the first BPANN model, and the variables that had a more significant impact on the plasma concentration of MHD were retained. With demographic characteristics and clinical laboratory test results, the genotypes of SCN1A rs2298771 and SCN2A rs17183814 were used to construct the BPANN model. The BPANN model was comprehensively validated and used to predict the MHD plasma concentration of five patients with epilepsy in our hospital. The model demonstrated favorable fitness metrics, including a mean squared error of 0.00662, a gradient magnitude of 0.00753, an absence of validation tests amounting to zero, and a correlation coefficient of 0.980. Sex, BMI, and the genotype SCN1A rs2298771 were ranked highest by the absolute mean impact value (MIV), which is primarily associated with the concentration of MHD. The test group exhibited a range of - 20.84% to 31.03% bias between the predicted and measured values, with a correlation coefficient of 0.941 between the two. With BPANN, the MHD nadir concentration could be predicted precisely. The NGO-BPANN model exhibits exceptional predictive capability and can be a practical instrument for forecasting MHD concentration in patients with epilepsy. www.chiCTR-OOC-17012141 .

Mechanical properties evaluation of waste gangue-based cemented backfill materials based on an improved response surface model.

Traditional mining methods damage the cultivated land and produce gangue waste that often contaminates the environment. Yet, these problems can be mitigated by transforming the waste into gangue-based cemented backfill material (GCBM), whose mechanical properties are crucial for surface protection. Therefore, in this study, an intelligent model based on laboratory tests was developed to evaluate the GCBM's mechanical properties. The strength tests and polynomial response surface model (PRSM) were used to analyze the non-linear correlation between the influencing factors and the uniaxial compressive strength (UCS). Meanwhile, the importance of multidimensional factors was analyzed by the mean impact value, revealing that concentration and gangue proportion are the most sensitive factors. In addition, an intelligent response surface model (IRSM) based on support vector regression model was constructed by enhancing an optimization algorithm with chaotic mapping and adaptive methods. The performance of the traditional PRSM and the novel IRSM was compared, and the IRSM was validated. The IRSM can predict UCS more efficiently and effectively than the traditional PRSM under high-dimensional factors, with R2 of 0.96 and MBE of 0.05. This indicated that the IRSM has the potential to promote coal mine waste reduction and environmental protection.

An investigation of the density of nano-confined subcritical/supercritical water

In various applications such as supercritical water gasification, oil and gas production, and energy harvesting and storage, subcritical/supercritical water is often confined within material pores. Investigating the density and critical parameters of high-temperature and high-pressure water in confined spaces can help us better understand the behavior of water within the pore space. In this study, a topological model consisting of two baths and a carbon nanotube (CNT) is built to examine the effect of temperature (300 K & 600–1173 K), pressure (1 atm & 20–30 MPa), and tube diameter (9.49–50.17Å) on confined density, and used machine learning (ML) to develop a predictive application (APP). The ML model demonstrates excellent predictive performance, achieving an R2 of 0.9962 on the test set. Furthermore, the mean impact value (MIV) is used to evaluate the impact of independent variables on confined density, and find that temperature has the most significant effect. The results indicate that the critical temperature and pressure of water confined within different CNTs are not significantly different from those of bulk water, but the confined critical density is slightly lower than the bulk critical density.

Downscaling of GPM satellite precipitation products based on machine learning method in complex terrain and limited observation area

Precipitation products with high spatial and temporal resolutions are crucial in hydrological monitoring, meteorological forecasting, and disaster warning. However, obtaining such products in regions with complex terrain and limited observation conditions is a challenging task. To address this issue, a statistical downscaling model for satellite precipitation products using an optimized Back Propagation (BP) neural network was developed. The model employed key environmental variables selected by the Mean Impact Value (MIV) index, including enhanced vegetation (EVI), land surface temperature (LST_D, LST_N), evapotranspiration (ET), digital elevation model (DEM), slope, and latitude and longitude (Lon, Lat). The downscaled precipitation products were corrected twice using a combination of the model error correction and observation data merging methods. Finally, the satellite precipitation products with a resolution of 0.1° (∼10 km) were downscaled to 1 km. A comprehensive evaluation of the results showed that: (1) the accuracy of the precipitation products obtained using this method was better than that of the original satellite precipitation products; (2) the method effectively supplemented precipitation data in areas with few ground stations, with better results in areas with a dense distribution of ground stations; (3) this method demonstrated the efficacy of satellite precipitation products for downscaling in areas with complex terrain.

A machine learning method for HTLCF life prediction of titanium aluminum alloys with consideration of manufacturing processes

Most conventional methods only consider the effects of materials and loading conditions when predicting the high-temperature low-cycle fatigue life of titanium aluminum alloys. However, the effects of manufacturing processes are not considered. To address this limitation, this paper proposes a machine learning method. First, the loading conditions are preliminarily filtered by physics knowledge. Second, the manufacturing processes and loading conditions are analyzed by using the average value of multiple mean impact values. Then, the variables that have little contribution to the output are filtered out, and the remaining variables are used as inputs. Finally, an optimized genetic algorithm-back propagation artificial neural network is established to predict the low-cycle fatigue life of the materials. The optimization methods are Levy flight and an adaptive adjustment mechanism of probability. Min-Max normalization is used to normalize and denormalize the data in the proposed method. A set of experimental data for Ti-685 is used to validate the proposed method. Moreover, the results show that the proposed method has better prediction accuracy than other methods.

A Flight Parameter-Based Aircraft Structural Load Monitoring Method Using a Genetic Algorithm Enhanced Extreme Learning Machine

High-precision operational flight loads are essential for monitoring fatigue of individual aircraft and are usually determined by flight parameters. To tackle the nonlinear relationship between flight loads and flight parameters for more accurate prediction of flight loads, artificial neural networks have been widely studied. However, there are still two major problems, namely the training strategy and sensitivity analysis of the flight parameters. For the first problem, the gradient descent method is usually used, which is time-consuming and can easily converge to a local solution. To solve this problem, an extreme learning machine is proposed to determine the weights based on a Moore–Penrose generalized inverse. Moreover, a genetic algorithm method is proposed to optimize the weights between the input and hidden layers. For the second problem, a mean impact value (MIV) method is proposed to measure the sensitivity of the flight parameters, and the neuron number in the hidden layer is also optimized. Finally, based on the measured dataset of an aircraft, the proposed flight load prediction method is verified to be effective and efficient. In addition, a comparison is made with some well-known neural networks to demonstrate the advantages of the proposed method.

Time-varying interval prediction and decision-making for short-term wind power using convolutional gated recurrent unit and multi-objective elephant clan optimization

Wind power (WP) interval prediction has attracted more and more attention in recent years due to WP's intermittency and uncertainty. However, traditional interval prediction models suffer from data distribution assumptions, fixed interval widths, etc. This paper proposes a hybrid WP interval prediction method to eliminate these constraints. First, the mean impact value is applied to select the optimal inputs from meteorological factors, which are considered together with the WP data. Then, we propose a time-varying interval optimization strategy to construct prediction intervals (PIs) and avoid the restrictive condition of data distribution, which can provide a time-varying interval width simultaneously. Meanwhile a convolutional gated recurrent unit is performed to extract the spatial-temporal features and generates the prediction results. Based on these results, the final PIs are generated by the proposed multi-objective elephant clan optimization, in which three objectives are optimized simultaneously. To evaluate the performance of the proposed model, two WP datasets in Ningxia, China, are used. Finally, the obtained PIs are applied for decision-making to offer planned productions in the future and estimate the operational costs. The comparison results indicate that the proposed model can provide high-quality PIs and achieve lower operational costs than the benchmark models in decision-making.

Accurate identification of inflammation in blood based on laser-induced breakdown spectroscopy using chemometric methods

Diagnosis of inflammation in the blood requires multiple medical examinations that rely heavily on doctors' experiences, which offer a large room for error. Thus, diagnosis becomes complex and time consuming. Herein, we proposed the use of laser-induced breakdown spectroscopy (LIBS) and chemometric methods to rapidly and accurately diagnose inflammation in blood. Serum samples were collected from 10 healthy people and 10 patients suffering from inflammation in blood. The training and test sets were divided according to each individual in a ratio of 7:3. After excluding considerably different divisions of training and test sets (DTTs) using the Wilcoxon test, 10 DTTs were randomly selected. With these 10 DTTs, backpropagation neural network (BPNN) models were built for substrate optimization, and glass slides exhibited the best performance with an average accuracy of 80.87%. Using glass slides and a multiplicative scatter correction–mean impact value–backpropagation neural network (MSC–MIV–BPNN) model, the accuracy of the best DTT was improved to 93.00%. For the identification effect validation of the improved model, the same features were selected from other DTTs to build new MSC–MIV–BPNN models. The accuracies of all the DTTs were increased by 4.67%–16.33% compared to the original BPNN models. Furthermore, the validation time of a single DTT was ∼0.7 s. These results demonstrated that LIBS combined with the MSC–MIV–BPNN model could accurately and rapidly identify samples with inflammation in blood from healthy blood samples for emergency applications.

Flush Airdata System on a Flying Wing Based on Machine Learning Algorithms

By using an array of pressure sensors distributed on the surface of an aircraft to measure the pressure of each port, the flush airdata sensing (FADS) system is widely applied in many modern aircraft and unmanned aerial vehicles (UAVs). Normally, the pressure transducers of the FADS system should be mounted on the leading edge of the aircraft, where they are sensitive to changes in pressure. For UAVs, however, the leading edge of the nose and wing may not be available for pressure transducers. In addition, the number of transducers is limited to 8–10, making it difficult to maintain accuracy in the normal method for FADS systems. An FADS system model for an unmanned flying wing was developed, and the pressure transducers were all located outside the regions of the leading edge areas. The locations of the transducers were selected by using the mean impact value (MIV), and ensemble neural networks were developed to predict the airdata with a very limited number of transducers. Furthermore, an error detection method was also developed based on artificial neural networks and random forests. The FADS system model can accurately detect the malfunctioning port and use the correct pressure combination to predict the Mach number, angle of attack, and angle of sideslip with high accuracy.