Tree peach hardness inversion method based on finite element simulation and transfer learning

Abstract

The invention discloses a tree peach hardness inversion method based on finite element simulation and transfer learning, and the method comprises the following steps: 1, collecting vibration signals of a tree peach in different growth stages through a laser Doppler vibration meter, and carrying out the preprocessing of the vibration signals, and taking the vibration signals as the input of a model; using a texture analyzer to measure a peach fruit hardness reference value as the output of the model, and constructing an experimental data set; step 2, establishing a peach vibration finite element model with a high bionic degree and calculating simulation vibration response; 3, material attributes of the finite element model in the step 2 are changed to obtain vibration responses of peaches with different hardness, and a simulation data set is constructed; and 4, constructing a domain adversarial neural network, and realizing domain migration and hardness inversion through adversarial training. According to the method, simulation vibration data is produced through a finite element method, the domain adversarial neural network is constructed for feature migration, and the inversion accuracy of the hardness of the peach fruits on the tree is improved under the condition of limited samples.

Description

Technical Field

[0001] The invention relates to the field of fruit quality detection, and in particular to an on-tree peach fruit hardness inversion method based on finite element simulation and transfer learning. Background Art

[0002] Hardness is a key quality indicator of peaches, which is related to their taste, maturity, and storage stability. The demand for hardness measurement runs through the entire peach industry chain. Peaches harvested within a specific hardness range usually have higher resistance to damage, longer shelf life, and better taste after fully softening. Therefore, pre-harvest hardness monitoring is important for determining the optimal time to harvest peaches.

[0003] Traditional fruit hardness testing methods are destructive and cannot meet the needs of large-scale testing. The acoustic vibration method analyzes the vibration response of vibrating peach fruits, extracts vibration features, inverts the mechanical parameters of peach fruits, and then obtains the hardness of peach fruits, which can reduce the mechanical damage of peach fruits. However, in pre-harvest applications, due to the interference of natural wind, the vibration response of peach fruits is full of noise, and even workers with prior knowledge find it difficult to accurately extract vibration features from the signal. At present, feature extraction methods based on deep learning have good performance in vibration signal processing. They can extract features related to target tasks from a large number of signals without supervision, and are therefore widely used in mechanical fault diagnosis, electrocardiogram analysis, agricultural product quality testing and other fields. However, traditional deep learning methods require a large number of data samples and assume that training and test data have the same feature distribution, which puts high demands on the quantity and quality of the data. Collecting more samples not only increases the investment of manpower, material resources and funds, but also causes various deviations due to fatigue of workers due to a large number of experiments. Especially in agricultural field applications, it is almost impossible to obtain so many high-quality and evenly distributed samples. Numerical simulation provides an effective solution to this problem. Through numerical simulation technology, vibration simulation of objects can be performed, and a large amount of simulation data can be obtained. Finite element analysis method is a commonly used numerical simulation method. However, because the shape and structure of fruits are complex and the material properties are difficult to determine, the shape, internal structure or material properties of existing fruit finite element models are overly simplified, so that there is a large difference between the simulation data and the experimental data of the finite element model. Constructing an accurate finite element model can improve the similarity between simulation data and experimental data, but the field measurement environment is complex and changeable, and the size and shape of fruits are different, which inevitably leads to certain differences in the characteristic distribution of simulation data and experimental data, which will reduce the prediction accuracy of the deep learning prediction model. Therefore, how to achieve accurate inversion of peach fruit pre-harvest hardness with a small sample size is a problem to be solved. Summary of the invention

[0004] The purpose of the present invention is to address the above-mentioned shortcomings and propose a method for inverting the hardness of peach fruit on the tree based on finite element simulation and transfer learning. It solves the problem of low precision of results caused by over-simplification of traditional fruit finite element models, overcomes the problems of small number of data set samples and large differences in feature distribution, and provides an effective solution for accurately inverting the hardness of peach fruit before harvest.

[0005] In order to solve the above technical problems, the technical solution proposed in the present invention is: a method for inverting peach fruit hardness on a tree based on finite element simulation and transfer learning, comprising the following steps:

[0006] Step 1: Use a laser Doppler vibrometer to collect vibration signals of peach fruits at different growth stages on the tree, and use them as input of the model after preprocessing. Use a texture analyzer to measure the peach fruit hardness reference value as the output of the model to construct an experimental data set;

[0007] Step 2, establishing a peach fruit vibration finite element model with a high bionic degree and calculating the simulated vibration response;

[0008] Step 2.1, using a handheld laser 3D scanner to obtain a 3D point cloud of the outer surface of the peach fruit, the pit, and the kernel, and constructing a 3D geometric model with an accurate shape structure of the peach fruit through reverse modeling;

[0009] Step 2.2, using a texture analyzer and a universal mechanical testing machine to test the compressive elastic modulus of peach pulp, pit, and kernel and the tensile elastic modulus of peach peel respectively as material properties of the finite element model;

[0010] Step 2.3, establishing a peach fruit vibration finite element model with a high bionic degree according to the three-dimensional geometric model of the peach fruit, the material properties measured in step 2.2, the experimental excitation and the fruit constraint conditions, and simulating and calculating the simulated vibration response of the response point;

[0011] Step 3, changing the material properties of the finite element model in step 2 to obtain simulated vibration responses of peaches with different hardness;

[0012] Step 4: construct a domain adversarial neural network, use simulation data with hardness values ​​as the source domain and experimental data without hardness values ​​as the target domain for training, and achieve domain migration and hardness inversion through adversarial training;

[0013] Step 4.1, construct a feature extraction network based on multi-scale convolution and channel attention mechanism to achieve adaptive feature extraction;

[0014] Step 4.2, build a predictor and predict the hardness of the features through the fully connected layer. And choose the mean square error (MSE) as the loss function of the predictor:

[0015]

[0016] In the formula, is the loss function of the predictor; N is the number of samples; y i is the hardness value; To predict the hardness value.

[0017] Step 4.3, build a domain discriminator. This step uses a gradient reversal layer to automatically reverse the gradient direction during the back propagation process, maximize the domain classification loss, and confuse the target domain data with the source domain data. The cross entropy loss is used as the loss function of the domain discriminator:

[0018]

[0019] Where, is the loss function of the predictor; N is the number of samples; y i is the hardness value; To predict the hardness value.

[0020] In step 4.4, the network loss function is composed of the predictor loss function and the domain discriminator loss function:

[0021] L=L p -λL d

[0022] Where L is the total loss function; λ is the parameter for adjusting the strength of the adversarial attack.

[0023] As a further improvement of the present invention, a bandpass filter is used for filtering during signal preprocessing, and the power spectrum density of the vibration response is calculated as a model input.

[0024] As a further improvement of the present invention, in step 1, a force-displacement curve of the puncture process is obtained through a puncture experiment, and the initial slope of the curve is used as a reference value for peach fruit hardness.

[0025] As a further improvement of the present invention, in step 2.1, the peach fruit point cloud is denoised and surfaced in Geomagic software, and then imported into Solidworks software to combine various parts according to the physiological structure of the peach fruit to construct a complete peach fruit three-dimensional model.

[0026] As a further improvement of the present invention, in step 2.2, the pulp is prepared into a 15×15×15 mm cubic sample, and a compression test is performed using a texture analyzer. After the force-displacement curve is obtained, the elastic modulus is calculated according to the following formula:

[0027]

[0028] Where E is the elastic modulus, σ is the stress, ε is the strain, F is the compression force, L is the initial length of the specimen, A is the cross-sectional area of ​​the specimen, and ΔL is the deformation.

[0029] As a further improvement of the present invention, in step 2.2, the complete fruit core and kernel are placed on a texture analyzer for compression test, and after the force-displacement curve is obtained, the elastic modulus is calculated according to the following formula:

[0030]

[0031] Where E is the elastic modulus, F is the force, D is the deformation, and K is U and K L is a constant determined by the curvature of the contact point between the upper and lower surfaces, R U and R′ U are the maximum and minimum radii of curvature of the upper surface contact points, R L and R′ L are the maximum and minimum radii of curvature of the lower surface at the contact point.

[0032] As a further improvement of the present invention, in step 2.2, the peel is prepared into a rectangular sample, and a tensile test is performed on the peel using a universal mechanical testing machine, and its elastic modulus is calculated according to the following formula:

[0033]

[0034] Where E is the elastic modulus, σ is the stress, ε is the strain, F is the compression force, L is the initial length of the specimen, A is the cross-sectional area of ​​the specimen, and ΔL is the deformation.

[0035] As a further improvement of the present invention, in step 2.3, a fixed constraint is set at the fruit stalk, an exciting force is applied at the equator, all modes within 2000 Hz are calculated, and the vibration response output is obtained through transient analysis.

[0036] Compared with the prior art, the advantages of the present invention are:

[0037] The bionic peach fruit vibration finite element model of the present invention fully considers the complex appearance, internal structure and material properties of peach fruit, constructs an accurate three-dimensional geometric model of peach fruit through three-dimensional scanning and reverse modeling methods, and experimentally determines the elastic modulus of the peach fruit peel, flesh, core and kernel as the material property of the finite element to improve the accuracy of finite element simulation. The present invention obtains simulation data sets through the finite element simulation method for transfer learning, and can realize the hardness inversion of peach fruit on the tree based on the acoustic vibration method with a small sample size. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a schematic diagram of a specific implementation of the present invention.

[0039] Figure 2 This is a simplified diagram of the domain adversarial neural network structure.

[0040] Figure 3 This is a simplified diagram of the network structure for extracting peach fruit vibration response features.

[0041] Figure 4 Feature visualization for different network outputs. DETAILED DESCRIPTION

[0042] The present invention will be further described below in conjunction with the accompanying drawings.

[0043] Reference Figure 1 to Figure 4 , a method for inversion of peach fruit hardness on a tree based on finite element simulation and transfer learning, the method comprising the following steps:

[0044] Step 1, collect vibration response data of peach fruits on the tree, measure hardness, and construct an experimental data set;

[0045] Step 1.1, using a laser Doppler vibrometer to collect vibration signals of peach fruits at different growth stages on the tree to obtain vibration response data of peach fruits of different hardness and size, performing noise reduction through a bandpass filter, setting the cutoff frequency to 5-2000 Hz, and using an autoregressive model method to calculate the power spectral density of the vibration response as a model input;

[0046] Step 1.2, using a texture analyzer to perform a puncture test on peach fruit, the diameter of the probe is 5 mm, the loading speed is set to 0.5 mm / s, the loading distance is 8 mm, and the initial slope of the force-displacement curve is calculated to obtain a hardness reference value as the output of the model;

[0047] Step 2, establishing a peach fruit vibration finite element model with a high bionic degree and calculating the simulated vibration response;

[0048] Step 2.1, using a handheld laser 3D scanner to obtain 3D point clouds of the outer surfaces of 10 different peach fruits, pits, and kernels, denoising and surfacing the point clouds of each part of the peach fruit in Geomagic software, and then importing them into Solidworks software to combine various parts according to the physiological structure of the peach fruit to construct a complete 3D model of the peach fruit;

[0049] Step 2.2, select 15 peaches at different growth stages, prepare the pulp into 15×15×15 mm cubic samples, and use a texture analyzer to perform a compression test. Select a cylindrical probe with a diameter of 100 mm, set the loading speed to 0.1 mm / s, and the loading distance to 8 mm. After obtaining the force-displacement curve, calculate its elastic modulus according to the following formula:

[0050]

[0051] Where E is the elastic modulus, σ is the stress, ε is the strain, F is the compression force, L is the initial length of the specimen, A is the cross-sectional area of ​​the specimen, and ΔL is the deformation.

[0052] Place the complete fruit core and kernel on the texture analyzer for compression test. Select a cylindrical probe with a diameter of 100 mm, set the loading speed to 0.1 mm / s, and the loading distance to 3 mm. After obtaining the force-displacement curve, calculate its elastic modulus according to the following formula:

[0053]

[0054] Where E is the elastic modulus, F is the force, D is the deformation, and K is U and K L is a constant determined by the curvature of the contact point between the upper and lower surfaces, R U and R′ U are the maximum and minimum radii of curvature of the upper surface contact points, R L and R′ L are the maximum and minimum radii of curvature of the contact points on the lower surface. The radii of curvature of the core and kernel vertices are given by the three-dimensional model.

[0055] The peel was prepared into a rectangular sample and subjected to a tensile test using a universal mechanical testing machine. Its elastic modulus was calculated according to the following formula:

[0056]

[0057] Where E is the elastic modulus, σ is the stress, ε is the strain, F is the compression force, L is the initial length of the specimen, A is the cross-sectional area of ​​the specimen, and ΔL is the deformation.

[0058] Step 2.3, a peach fruit finite element model with a high degree of bionics is established in the ANSYS finite element simulation software according to the three-dimensional geometric model of the peach fruit, the material properties measured in step 2.2, the experimental excitation and the fruit constraint conditions, a fixed constraint is set at the fruit stem to simulate the external constraint of the peach fruit, and all modes within 2000 Hz are calculated; an exciting force of 0.5 N is applied at the equator to simulate the gas exciting force during the experiment, and the vibration response output is obtained through transient analysis;

[0059] Step 3, changing the material properties of the pulp of the finite element model in step 2, and selecting 100 values ​​evenly in the range of 0.5 MPa to 2.5 MPa as the elastic modulus of the pulp according to the range of the elastic modulus of the pulp measured in the experiment, so as to obtain the simulated vibration response of peaches with different hardness;

[0060] Step 4, such as Figure 2As shown in the figure, a domain adversarial neural network (DANN) is constructed, which mainly includes a feature extraction network, a hardness predictor, a domain discriminator and a gradient reversal layer. The gradient reversal layer automatically reverses the gradient of the domain discriminator to maximize the domain classification error and extract domain invariant features. In the experiment, simulation data with hardness values ​​are used as the source domain, and experimental data without hardness values ​​are used as the target domain for training. Domain migration and hardness inversion are achieved through adversarial training;

[0061] Step 4.1, based on multi-scale convolution and channel attention mechanism, construct Figure 3 The feature extraction network shown in the figure realizes multi-scale feature extraction. It mainly includes two convolutional layers, an Inception module, a Squeeze-and-Excitation (SE) module, and a Dropout layer. BatchNormalization layer, ReLU activation function and maximum pooling layer are added after each convolutional layer to speed up the convergence speed and improve the nonlinear ability of the network.

[0062] Step 4.2, build a predictor and predict the hardness of the features through the fully connected layer. And choose the mean square error (MSE) as the loss function of the predictor:

[0063]

[0064] In the formula, is the loss function of the predictor; N is the number of samples; y i is the hardness value; To predict the hardness value.

[0065] Step 4.3, build a domain discriminator. This step uses a gradient reversal layer to automatically reverse the gradient direction during the back propagation process, maximize the domain classification loss, and confuse the target domain data with the source domain data. The cross entropy loss is used as the loss function of the domain discriminator:

[0066]

[0067] Where, is the loss function of the predictor; N is the number of samples; y i is the hardness value; To predict the hardness value.

[0068] In step 4.4, the network loss function is composed of the predictor loss function and the domain discriminator loss function:

[0069] L=L p -λL d

[0070] Where L is the total loss function; λ is the parameter for adjusting the strength of the adversarial attack.

[0071] The 1000 vibration response data obtained by simulation are used as the source domain, and the vibration response data of 300 peach fruits measured in the experiment are used as the target domain for training. The learning rate is set to 0.001, the penalty parameter λ is set to 1, the number of iterations is 100, and the batch size is 64 for training.

[0072] In order to verify the effectiveness of the present invention, the Inception-SE network and the Inception-SE+DANN network with the same network structure are selected for comparison. The results of feature visualization using t-SNE are shown in the figure below. Figure 4 As shown in (a) and (b), the results show that the Inception-SE+DANN network in the present invention can effectively extract domain-invariant features. The root mean square error (RMSE) and the coefficient of determination (R 2 ) as the evaluation index to evaluate the effect of the method, and the results are shown in Table 1. From the comparison results, it can be seen that the feature extraction network proposed by the method of the present invention can effectively extract the features related to peach fruit hardness, and the method of obtaining simulated vibration data through the finite element method and performing transfer learning can improve the accuracy of peach fruit hardness inversion on the tree with a limited sample size.

[0073] Table 1

[0074]

Claims

1. A method for inversion of peach fruit hardness on trees based on finite element simulation and transfer learning, characterized in that: The method comprises the following steps: Step 1: Use a laser Doppler vibrometer to collect vibration signals of peach fruits at different growth stages on the tree, use them as input of the model after preprocessing, and use a texture analyzer to measure the reference value of peach fruit hardness to construct an experimental data set; Step 2, establishing a peach fruit vibration finite element model with bionic degree and calculating the simulated vibration response; Step 3, changing the material properties of the peach fruit vibration finite element model with bionic degree obtained in step 2 to obtain the vibration response of peach fruits with different hardness and construct a simulation data set; Step 4, constructing a domain adversarial neural network, using the simulation data set obtained in step 3 as the source domain and the experimental data set obtained in step 1 as the target domain for training, and obtaining a peach fruit hardness inversion model through adversarial training; Step 5, input the vibration response of peach fruits on the tree into the peach fruit hardness inversion model to obtain the peach fruit hardness value to guide fruit picking.

2. The method for inversion of peach fruit hardness on a tree based on finite element simulation and transfer learning according to claim 1, characterized in that: In step 1, the preprocessing method uses bandpass filtering and power spectral density estimation.

3. The method for inversion of peach fruit hardness on a tree based on finite element simulation and transfer learning according to claim 1, characterized in that: In step 2, a bionic peach fruit vibration finite element model is established and the simulated vibration response is calculated, specifically including: Step 2.1, using a handheld laser 3D scanner to obtain a 3D point cloud of the outer surface of the peach fruit, the pit, and the kernel, and constructing a 3D geometric model with an accurate shape structure of the peach fruit through reverse modeling; Step 2.2, using a texture analyzer and a universal mechanical testing machine to test the compressive elastic modulus of peach pulp, pit, and kernel and the tensile elastic modulus of peach peel as material properties; Step 2.3, establish a peach fruit vibration finite element model with bionic degree based on the three-dimensional geometric model with the accurate shape structure of the peach fruit and the material properties measured in step 2.2, and use the peach fruit vibration finite element model with bionic degree to simulate and calculate the simulated vibration response of the response point under the conditions of experimental excitation and fruit constraints.

4. The method for inversion of peach fruit hardness on a tree based on finite element simulation and transfer learning according to claim 3, characterized in that: In step 2.3, the experimental excitation is the gas excitation force applied to the peach fruit during the experiment.

5. The method for inversion of peach fruit hardness on a tree based on finite element simulation and transfer learning according to claim 3, characterized in that: In step 2.3, the fruit constraint condition is that the peach fruit is subject to constraint force at the stalk.

6. The method for inversion of peach fruit hardness on a tree based on finite element simulation and transfer learning according to claim 1, characterized in that: In step 4, a domain adversarial neural network is constructed, which includes: Step 4.1, construct a feature extraction network based on multi-scale convolution and channel attention mechanism; Step 4.2, build a predictor, predict the hardness of the features through the fully connected layer, and select the mean square error MSE as the loss function of the predictor: In the formula, is the loss function of the predictor; N p is the number of samples; y p is the hardness value; To predict the hardness value; Step 4.3, construct a domain discriminator, use a gradient reversal layer to automatically reverse the gradient direction during back propagation, and use the cross entropy loss as the loss function of the domain discriminator: Where, L d is the loss function of the discriminator; N d is the number of samples; y d is the hardness value; To predict the hardness value; In step 4.4, the network loss function is composed of the loss function of the predictor and the loss function of the domain discriminator: L=L p -λL d Where L is the total loss function; λ is the parameter for adjusting the strength of the adversarial attack.

Images