BP Model Research Articles

Thermal displacement prediction of variable preload motorized spindles based on speed reduction experiments and IABC-BP optimization models

The thermal error caused during the high-speed operation of a high-speed motorized spindle has a significant impact on machine tool precision. In this paper, we firstly built, constructed an experimental platform for variable voltage preloaded motorized spindle, used the natural deceleration experimental method to ascertain the spindle's thermal displacement and temperature information when bearing preload is 1400 N, 1450 N, 1550 N and 1700 N, and combined with the thermoelasticity theoretical analysis, the thermal displacement of affected by the heat generation of motor and bearing was separated, and a new artificial bee colony algorithm-optimized BP neural network-based thermal error prediction model has been presented. The thermal displacements of the spindles are separated and a BP neural network optimization of a novel thermal error prediction model based on Improved Artificial Bee Colony Algorithm (IABC-BP) is proposed for transformer preloaded spindles. Combined with the experimental data of bearing preload of 1400 N, the thermal displacements of the spindle at preloads of 1450 N, 1550 N and 1700 N are predicted, and the evaluation indexes obtained from the simulation of the BP, ABC-BP, and IABC-BP models are compared. absolute error (MAE) and root-mean-square error (RMSE), higher goodness-of-fit (R2), and 20.37 % lower mean absolute error and 26.83 % lower root-mean-square error compared with the traditional thermal error prediction model. The IABC-BP prediction model proposed in this paper provides a more accurate compensation method for transformer preloaded spindles.

Optimizing Back-Propagation Neural Network to Retrieve Sea Surface Temperature Based on Improved Sparrow Search Algorithm

Sea surface temperature (SST) constitutes a pivotal physical parameter in the investigation of atmospheric, oceanic, and air–sea exchange processes. The retrieval of SST through satellite passive microwave (PMW) technology effectively mitigates the interference posed by cloud cover, addressing a longstanding challenge. Nevertheless, conventional functional representations often fall short in capturing the intricate interplay of factors influencing SST. Leveraging neural networks (NNs), known for their adeptness in tackling nonlinear and intricate problems, holds great promise in SST retrieval. Nonetheless, NNs exhibit a high sensitivity to initial weights and thresholds, rendering them susceptible to local optimization issues. In this study, we present a novel machine learning (ML) approach for SST retrieval using PMW measurements, drawing from the Sparrow Search Algorithm (SSA) and Back-Propagation neural network (BPNN) methodologies. The core premise involves the optimization of the BP neural network’s initial weights and thresholds through an enhanced SSA algorithm employing various optimization strategies. This optimization aims to provide superior parameters for the training of the BP neural network. Employing AMSR2 brightness temperature data, sea surface wind speed data, and buoy SST measurements, we construct the ISSA-BP model for sea surface temperature retrieval. The validation of the ISSA-BP model against the test data is conducted and compared against the multiple linear regression (MLR) model, an unoptimized BP model, and an unimproved SSA-BP model. The results manifest an impressive R-squared (R2) value of 0.9918 and a root-mean-square error (RMSE) of 0.8268 °C for the ISSA-BP model, attesting to its superior accuracy. Furthermore, the ISSA-BP model was applied to retrieve global sea surface temperatures on 15 July 2022, yielding an R2 of 0.9926 and an RMSE of 0.7673 °C for the OISST product on the same day, underscoring its excellent concordance. The results indicate that SST can be efficiently and accurately retrieved using the model proposed in this paper, based on satellite PMW measurements. This finding underscores the potential of employing machine learning algorithms for SST retrieval and offers a valuable reference for future studies focusing on the retrieval of other sea surface parameters.

قياس العلاقة التوازنية بين متغيّرات IS-LM-BP ومؤشّرات الاستقرار الاقتصادي في نيجيريا

The concept of economic balance occupies great importance in most of the world's economies, as it is the axis around which the discussion of economic thought revolves in various economic schools. Economic thought is in a state of continuous development and works to provide a model through which the general balance in the overall economy can be determined despite the difficulty of finding common relationships between all... Markets and the possibility of describing them in an integrated applied model that allows determining the equilibrium at the same time. Therefore, this study came to clarify the possibility of determining the total equilibrium through the IS-LM model, which works on equilibrium by combining the commodity market IS on the one hand and the money market LM on the other hand. The BP model was also added, which works to achieve balance in the external sector. Therefore, in this study, we can achieve balance internally and externally through the IS-LM-BP model, as the study addressed the impact of this balance that can be achieved on some indicators of economic stability. By determining an equilibrium interest rate and income, which is the final result of a set of economic relations.

Thermal error modeling of servo axis based on optimized LSSVM with gray wolf optimizer algorithm

Thermal error of a CNC machine tool has a serious effect on its machining accuracy. In order to reduce the thermal error, establishing an accurate and robust thermal error model is necessary. A new data-driven thermal error model is proposed based on gray wolf optimizer (GWO) and least squares support vector machine (LSSVM). While, three temperature-sensitivity points (TSPs) were picked by grouping search method. With optimizing the hyperparameters γ and σ2 by GWO algorithm, LSSVM is applied to thermal error modeling, which has advantages in dealing with small samples and nonlinear data. The experiments were conducted, and the results showed that the error prediction model constructed by GWO-LSSVM achieved an accuracy of 94.39 % meeting the requirements for error compensation. Then, the stability of the proposed error model is verified. Finally, the LSSVM model is compared with MLR and BP models commonly used in error modeling, and the advantages and applicable occasions are analyzed through experiments.

Aboveground Forest Biomass Estimation Using Tent Mapping Atom Search Optimized Backpropagation Neural Network with Landsat 8 and Sentinel-1A Data

Accurate forest biomass estimation serves as the foundation of forest management and holds critical significance for a comprehensive understanding of forest carbon storage and balance. This study aimed to integrate Landsat 8 OLI and Sentinel-1A SAR satellite image data and selected a portion of the Shanxia Experimental Forest in Jiangxi Province as the study area to establish a biomass estimation model by screening influencing factors. Firstly, we extracted spectral information, vegetation indices, principal component features, and texture features within 3 × 3-pixel neighborhoods from Landsat 8 OLI. Moreover, we incorporated Sentinel-1’s VV (vertical transmit–vertical receive) and VH (vertical transmit–horizontal receive) polarizations. We proposed an ensemble AGB (aboveground biomass) model based on a neural network. In addition to the neural network model, namely the tent mapping atom search optimized BP neural network (Tent_ASO_BP) model, partial least squares regression (PLSR), support vector machine (SVR), and random forest (RF) regression prediction techniques were also employed to establish the relationship between multisource remote sensing data and forest biomass. Optical variables (Landsat 8 OLI), SAR variables (Sentinel-1A), and their combinations were input into the four prediction models. The results indicate that Tent_ ASO_ BP model can better estimate forest biomass. Compared to pure optical or single microwave data, the Tent_ASO_BP model with the optimal combination of optical and microwave input features achieved the highest accuracy. Its R2 was 0.74, root mean square error (RMSE) was 11.54 Mg/ha, and mean absolute error (MAE) was 9.06 Mg/ha. Following this, the RF model (R2 = 0.54, RMSE = 21.33 Mg/ha, MAE = 17.35 Mg/ha), SVR (R2 = 0.52, RMSE = 17.66 Mg/ha, MAE = 15.11 Mg/ha), and PLSR (R2 = 0.50, RMSE = 16.52 Mg/ha, MAE = 12.15 Mg/ha) models were employed. In conclusion, the BP neural network model improved by tent mapping atom search optimization algorithm significantly enhanced the accuracy of AGB estimation in biomass studies. This will provide a new avenue for large-scale forest resource surveys.

Spatial-temporal high-order rotated-staggered-grid finite-difference scheme of elastic wave equations for TTI medium

In the finite-difference (FD) solution of the elastic wave equation for TTI medium, the traditional FD scheme can improve the computational accuracy of the spatial derivatives. However, the difference discretization on the temporal partial derivatives still uses the FD scheme of second-order accuracy, which cannot guarantee the computational accuracy of the temporal partial derivatives and often causes the temporal dispersion problem. The temporal high-order FD scheme can improve the computational accuracy of the temporal partial derivatives. Nevertheless, due to the complexity of the elastic wave equation in TTI medium, using the conventional staggered-grid technique to solve the elastic wave equation, some spatial derivatives need to be approximated by spatial interpolation, which will become new error and reduce the accuracy of the solution of the equations. Therefore, the currently commonly used temporal high-order FD method for the elastic wave equation in isotropic medium cannot be directly applied to the simulation of anisotropic medium. To solve the above problems, we propose a new temporal high-order rotated-staggered-grid FD stencil and derive a new temporal high-order FD scheme under this new stencil for the TTI medium elastic wave equation. Then we estimated the FD coefficients of the new stencil using Taylor series expansions (TE) and optimized the FD coefficients based on least squares (LS). Numerical experiments of the homogeneous TTI medium model and the modified BP model demonstrate that the TE + LS-based temporal high-order rotated-staggered-grid FD scheme can well solve the temporal dispersion in the numerical simulation of TTI medium.

Backpropagation Neural Network Application in Predicting The Stock Price of PT Bank Rakyat Indonesia Tbk

Investors often make mistakes when making stock transactions even though having chosen good company stocks. The thing that needs to be considered in making stock transactions is to see the movement of stock prices. The movement of the stock price in PT Bank Rakyat Indonesia Tbk has changed in the form of a decrease or increase. An increasing stock price will provide benefits for investors by selling stocks. But, investors actually decide to make stock purchases. The existence of stock purchase transactions causes investors to take a high risk because stock prices fluctuate. To anticipate the occurrence of high risk to investor, stock price predictions are made using a Backpropagation Neural Network (BPNN). BPNN can adapt quickly and is able to predict nonlinear data such as stock prices and produce a high level of accuracy. The results of this study obtained the best BPNN model, namely the BP(5,3,1) model with a Mean Absolute Percentage Error (MAPE) of 0,8193%. These results show that the model has good network performance so that it can predict stock prices well because it gets a small prediction error.

Prediction model of goaf coal temperature based on PSO-GRU deep neural network

The accurate determination of coal temperature in hidden space such as goaf has always been a worldwide problem that needs to be solved. The research of coal temperature prediction model has important practical significance for the accurate detection of loose coal temperature. Based on the coal natural ignition experiment and coal spontaneous combustion gas characterization index as the initial data set GRU neurons are used to mine the nonlinear relationship between the index gas and temperature, and the GRU model parameters are optimized by PSO to obtain the predicted value of coal body temperature. The results show that the predicted MAE value of the PSO-GRU model is 1.37 °C, 6.51 °C, 11.40 °C, 15.90 °C, 20.20 °C lower than that of the PSO-SVM, PSO-BP, BP, RF and SVM prediction models respectively. The RMSE value decreased by 0.45 °C, 4.44 °C, 10.33 °C, 15.71 °C and 24.24 °C respectively. The judgment coefficient R2 on the test set and the training set of the PSO-GRU model is 0.99, and the generalization, prediction accuracy and robustness are all good. The experimental results show that the inversion temperature error of the model is within the range of 3.87 %, the maximum temperature difference is 5.69 °C, and the average temperature difference is 2.83 °C, which can meet the accuracy requirements of the field temperature measurement.

Coal and gas outburst prediction model based on principal component analysis and improved support vector machine

In order to predict the coal outburst risk quickly and accurately, a PCA-FA-SVM based coal and gas outburst risk prediction model was designed. Principal component analysis (PCA) was used to pre-process the original data samples, extract the principal components of the samples, use firefly algorithm (FA) to improve the support vector machine model, and compare and analyze the prediction results of PCA-FA-SVM model with BP model, FA-SVM model, FA-BP model and SVM model. Accuracy rate, recall rate, Macro-F1 and model prediction time were used as evaluation indexes. The results show that: Principal component analysis improves the prediction efficiency and accuracy of FA-SVM model. The accuracy rate of PCA-FA-SVM model predicting coal and gas outburst risk is 0.962, recall rate is 0.955, Macro-F1 is 0.957, and model prediction time is 0.312s. Compared with other models, The comprehensive performance of PCA-FA-SVM model is better.

Spatiotemporal Changes and the Prediction of Drought Characteristics in a Major Grain-Producing Area of China

Understanding variations in drought characteristics is of great importance for water resource planning and agriculture risk management. Despite increasing interest in exploring spatiotemporal drought patterns, long-term drought event characteristics and their future changes are unclear in major grain-producing areas in China. In this study, we applied Run theory, Sen’s slope, the modified Mann–Kendall method, wavelet analysis, and three machine learning models to systematically examine drought variation patterns, their future trends, and agricultural exposure in Henan Province, China, from 1961 to 2019. The results indicated that the SPEI-12 showed a significant increase at a rate of 0.0017/month during 1961–1999, but this has gradually changed to a drying trend since the 21st century. Drought event characteristics shifted markedly during these two periods, with drought duration and severity gradually shifting from east to west. The BO-LSTM model performed better than the LSTM and BP models, indicating that the drought frequency, higher drought duration, and drought peak would greatly increase 1.28–3.40-fold and cropland exposure is predicted to increase 1.61-fold in the near future compared to the first two decades of the 21st century. This finding not only helps developing meteorological drought predicting models, but also provides the scientific groundwork for drought disaster prevention and mitigation in Henan Province.

Bullous pemphigoid induced by IgG targeting type XVII collagen non-NC16A/NC15A extracellular domains is driven by Fc gamma receptor- and complement-mediated effector mechanisms and is ameliorated by neonatal Fc receptor blockade.

Bullous pemphigoid (BP) is an autoimmune blistering disease characterized by autoantibodies targeting type XVII collagen (Col17) with the noncollagenous 16A (NC16A) ectodomain representing the immunodominant site. The role of additional extracellular targets of Col17 outside NC16A has not been unequivocally demonstrated. In this study, we showed that Col17 ectodomain-reactive patient sera depleted in NC16A IgG induced dermal-epidermal separation in a cryosection model indicating the pathogenic potential of anti-Col17 non-NC16A extracellular IgG. Moreover, injection of IgG targeting the murine Col17 NC14-1 domains (downstream of NC15A, the murine homologue of human NC16A) into C57BL/6J mice resulted in erythematous skin lesions and erosions. Clinical findings were accompanied by IgG/C3 deposits along the basement membrane and subepidermal blistering with inflammatory infiltrates. Disease development was significantly reduced in either Fc-gamma receptor (FcγR)- or complement-5a receptor-1 (C5aR1)-deficient mice. Inhibition of the neonatal FcR (FcRn), an atypical FcγR regulating IgG homeostasis, with the murine Fc fragment IgG2c-ABDEG, a derivative of efgartigimod, reduced anti-NC14-1 IgG levels, resulting in ameliorated skin inflammation compared with isotype-treated controls. These data demonstrate that the pathogenic effects of IgG targeting the Col17 domain outside human NC16A/murine NC15A are partly attributable to antibody-mediated FcγR- and C5aR1 effector mechanisms while pharmacological inhibition of the FcRn represents a promising treatment for BP. The mouse model of BP will be instrumental in further investigating the role of Col17 non-NC16A/NC15A extracellular epitopes and validating new therapies for this disease. © 2023 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

Data-driven prediction of the equivalent sand-grain roughness

Surface roughness affects the near-wall fluid velocity profile and surface drag, and is commonly quantified by the equivalent sand-grain roughness {k}_{s}. It is essential to estimate {k}_{s} for accurate fluid dynamic problem modeling. While numerous roughness correlation formulas have been proposed to predict {k}_{s} in the fully rough regime, most of them are restricted to certain roughness types, with various geometric parameters considered in each case, leading to ongoing disagreements regarding its parameterization and lack of universality. In this study, a Particle Swarm Optimized Backpropagation (PSO-BP) method is proposed to predict {k}_{s} based on the selected surface parameters from previous DNS, LES, and experimental results for flow behavior over various surface roughness. The PSO-BP model’s ability to predict {k}_{s} in the fully rough region is evaluated and compared with both the existing roughness correction formulas as well as the traditional BP model. An optimized polynomial function is also proposed to serve as a ‘white box’ for predicting {k}_{s}. It turns out that the PSO-BP method has better performance in the evaluation metrics compared to other methods, yielding a Mean Absolute Error (MAE) of 0.0390, a Mean Squared Error (MSE) of 0.0026 and a Mean Absolute Percentage Error (MAPE) of 28.12%. This novel approach for estimating {k}_{s} has practical applicability and holds promise for improving the precision and efficiency of calculations related to equivalent sand-grain roughness, and thus provides more accurate and effective solutions for CFD and other engineering applications.

BP neural network-based prediction and optimal control of thermoelectric output of distributed solar PV/T systems

Abstract This study employs An evolutionary algorithm to set up a multilayer BP neural network. The goal is to solve the issue that BP neural systems converge slowly and readily fall into local optimal solutions. The genetic algorithm reaches an initial set of evolutionary generations and outputs a BP neural network’s most appropriate starting weights and thresholds. In the GA-BP model, the fitness value is calculated as the sum of the total errors between the network’s output and the desired output. A communication protocol device was used to gather performance information for the global solar PV/T system, and the GA-BP neural network model parameters were adjusted. The GA-BP model had a mean absolute error of 0.7% lower than the BP model’s for the forecast of electrical efficiency. The GA-BP model has an average relative error of 0.21 in forecasting heating power.

Prediction for permeability index of blast furnace based on VMD–PSO–BP model

Prediction for permeability index of blast furnace based on VMD–PSO–BP model

A Petri Net Approach for Business Process Modeling and Simulation

A business process is a set of activities executed in a specific sequence involving various actors. This relationship between actors, activities, and sequence is crucial for achieving the goals and objectives of organizations. Business process modeling involves determining the actors, activities, and execution sequence necessary to accomplish the organization’s objectives, permitting analysis of the overall process in order to identify and rectify potential failures, improve operations, or eliminate activities that do not generate value. In this study, Petri nets have been selected as the modeling tool due to their ability to provide graphical and mathematical representations of business processes, which offers a significant advantage over other tools. The objective of this research is to develop a BP modeling algorithm using Petri nets. It aims to simulate the behavior of each activity within a case study in which the mathematical representation of Petri nets is utilized to measure process performance. Additionally, a software artifact is created to assess the algorithm’s functionality and compare the performance of two different business process that share the same goal.

Industrial carbon emission efficiency prediction and carbon emission reduction strategies based on multi-objective particle swarm optimization-backpropagation: A perspective from regional clustering

Against the backdrop of global climate change, industrial carbon emission reduction has become an important pathway to for global low-carbon development. This study constructs a framework of geographic spatial constraints regionalization and multi-objective machine learning to predict future industrial carbon emission efficiency (ICEE) and explore strategies for carbon emission reduction. Firstly, the ICEE of 285 Chinese cities were calculated by the super-efficiency slacks-based measure. Secondly, the cities were classified into four ICEE level regions through the spatially constrained multivariate clustering. Next, the multi-objective particle swarm optimization-BP (MOPSO-BP) model was constructed to predict the future trends of ICEE in the four regions. Finally, the geographical detector and multi-scale geographically weighted regression were employed for exploring driving force and carbon emission reduction strategies in different regions. The results show that most cities had low or medium ICEE, while super efficiency cities were mainly distributed in the east coastal areas. The prediction performance of the MOPSO-BP model for the four regions was better than the ordinary particle swarm optimization-BP and traditional BP model. Except for the Agricultural Production Region, there is considerable room for improving the ICEE of other regions over the next decade. Macroeconomic and microeconomic development have a global effect in promoting regional ICEE improvement, urban construction shows a promoting or inhibiting effect in different regions, and information technology has significant spatial heterogeneity in its influence within each region. The analysis framework developed in the study is a reliable solution for managing and planning ICEE and provides constructive suggestions for future regional low-carbon development.

Classification and rapid non-destructive quality evaluation of different processed products of Cyperus rotundus based on near-infrared spectroscopy combined with deep learning

The quality of traditional Chinese medicine is very important for human health, but the traditional quality control method is very tedious, which leads to the substandard quality of many traditional Chinese medicine. In order to solve the problem of time-consuming and laborious traditional quality control methods, this study takes traditional Chinese medicine Cyperus rotundus as an example, a comprehensive strategy of near-infrared (NIR) spectroscopy combined with One-dimensional convolutional neural network (1D-CNN) and chaotic map dung beetle optimization (CDBO) algorithm combined with BP neural network (BPNN) is proposed. This strategy has the advantages of fast and non-destructive. It can not only qualitatively distinguish Cyperus rotundus and various processed products, but also quantitatively predict two bioactive components. In classification, 1D-CNN successfully distinguished four kinds of processed products of Cyperus rotundus with 100 % accuracy. Quantitatively, a CDBO algorithm is proposed to optimize the performance of the BPNN quantitative model of two terpenoids, and compared with the BP, whale optimization algorithm (WOA)-BP, sparrow optimization algorithm (SSA)-BP, grey wolf optimization (GWO)-BP and particle swarm optimization (PSO)-BP models. The results show that the CDBO-BPNN model has the smallest error and has a significant advantage in predicting the content of active components in different processed products. To sum up, it is feasible to use near infrared spectroscopy to quickly evaluate the effect of processing methods on the quality of Cyperus rotundus, which provides a meaningful reference for the quality control of traditional Chinese medicine with many other processing methods.

Remaining Useful Life Prediction Method for High Temperature Blades of Gas Turbines Based on 3D Reconstruction and Machine Learning Techniques

Turbine blades are crucial components exposed to harsh conditions, such as high temperatures, high pressures, and high rotational speeds. It is of great significance to accurately predict the life of blades for reducing maintenance cost and improving the reliability of gas turbine systems. A rapid and accurate blade life assessment method holds significant importance in the maintenance plan of gas turbine engines. In this paper, a novel on-line remaining useful life (RUL) prediction method for high-temperature blades is proposed based on 3D reconstruction technology and data-driven surrogate mode. Firstly, the 3D reconstruction technology was employed to establish the geometric model of real turbine blades, and the fluid–thermal–solid analysis under actual operational conditions was carried out in ANSYS software. Six checkpoints were selected to estimate the RUL according to the stress–strain distribution of the blade surface. The maximum equivalent stress was 1481.51 MPa and the highest temperature was 1393.42 K. Moreover, the fatigue-creep lifetime was calculated according to the parameters of the selected checkpoints. The RUL error between the simulation model and commercial software (Control and Engine Health Management (CEHM)) was less than 0.986%. Secondly, different data-driven surrogate models (BP, DNN, and LSTM algorithms) were developed according to the results from numerical simulation. The maximum relative errors of BP, DNN, and LSTM models were 0.030%, 0.019%, and 0.014%. LSTM demonstrated the best performance in predicting the RUL of turbine blades with time-series characteristics. Finally, the LSTM model was utilized for predicting the RUL within a gas turbine real operational process that involved five start–stop cycles.

Forecasting crude oil futures price using machine learning methods: Evidence from China

Crude oil is an indispensable energy resource. With the establishment of the local crude oil futures market in China, providing accurate forecasts for crude oil futures price is urgent. To cope with this challenge, this paper introduces artificial intelligence methods to evaluate the optimal forecasting strategy for China's crude oil futures price. We use machine learning to process historical information, volatility and non-linear features. Using daily data from March 26, 2018 to February 28, 2023, we estimate the forecasting effects of RNN, LSTM, GRU, SVR, MLP, CNN and BP models on China crude oil futures, respectively. With a series of evaluation tests, we demonstrate that the GRU model outperforms other models in terms of forecast accuracy and performance for China's crude oil futures price. Taking multiple influencing factors into account, the forecasting accuracy of proposed models is improved by including influential factors. Therefore, these findings effectively explore the forecasting of China's crude oil futures prices, contributing to the improvement of the emerging crude oil futures market and the management of energy price risks.

A Discriminative Model for Early Detection of Anthracnose in Strawberry Plants Based on Hyperspectral Imaging Technology

Strawberry anthracnose, caused by Colletotrichum spp., is a major disease that causes tremendous damage to cultivated strawberry plants (Fragaria × ananassa Duch.). Examining and distinguishing plants potentially carrying the pathogen is one of the most effective ways to prevent and control strawberry anthracnose disease. Herein, we used this method on Colletotrichum gloeosporioides at the crown site on indoor strawberry plants and established a classification and distinguishing model based on measurement of the spectral and textural characteristics of the disease-free zone near the disease center. The results, based on the successive projection algorithm (SPA), competitive adaptive reweighted sampling (CARS), and interval random frog (IRF), extracted 5, 14, and 11 characteristic wavelengths, respectively. The SPA extracted fewer effective characteristic wavelengths, while IRF covered more information. A total of 12 dimensional texture features (TFs) were extracted from the first three minimum noise fraction (MNF) images using a grayscale co-occurrence matrix (GLCM). The combined dataset modeling of spectral and TFs performed better than single-feature modeling. The accuracy rates of the IRF + TF + BP model test set for healthy, asymptomatic, and symptomatic samples were 99.1%, 93.5%, and 94.5%, the recall rates were 100%, 94%, and 93%, and the F1 scores were 0.9955, 0.9375, and 0.9374, respectively. The total modeling time was 10.9 s, meaning that this model demonstrated the best comprehensive performance of all the constructed models. The model lays a technical foundation for the early, non-destructive detection of strawberry anthracnose.