A transfer learning enhanced physics-informed neural network for parameter identification in soft materials

Soft materials,with the sensitivity to various external stimuli,exhibit high flexibility and stretchability.Accurate prediction of their mechanical behaviors requires advanced hyperelastic constitutive models incorporating multiple parameters.However,identifying multiple parameters under complex deformations remains a challenge,especially with limited observed data.In this study,we develop a physics-informed neural network(PINN)framework to identify material parameters and predict mechanical fields,focusing on compressible Neo-Hookean materials and hydrogels.To improve accuracy,we utilize scaling techniques to normalize network outputs and material parameters.This framework effectively solves forward and inverse problems,extrapolating continuous mechanical fields from sparse boundary data and identifying unknown mechanical properties.We explore different approaches for imposing boundary conditions(BCs)to assess their impacts on accuracy.To enhance efficiency and generalization,we propose a transfer learning enhanced PINN(TL-PINN),allowing pre-trained networks to quickly adapt to new scenarios.The TL-PINN significantly reduces computational costs while maintaining accuracy.This work holds promise in addressing practical challenges in soft material science,and provides insights into soft material mechanics with state-of-the-art experimental methods.

Identification of dynamic systems using support vector regression neural networks

A novel adaptive support vector regression neural network （SVR-NN） is proposed, which combines respectively merits of support vector machines and a neural network. First, a support vector regression approach is applied to determine the initial structure and initial weights of the SVR-NN so that the network architecture is easily determined and the hidden nodes can adaptively be constructed based on support vectors. Furthermore, an annealing robust learning algorithm is presented to adjust these hidden node parameters as well as the weights of the SVR-NN. To test the validity of the proposed method, it is demonstrated that the adaptive SVR-NN can be used effectively for the identification of nonlinear dynamic systems. Simulation results show that the identification schemes based on the SVR-NN give considerably better performance and show faster learning in comparison to the previous neural network method.

Identification of Weather Phenomena Based on Lightweight Convolutional Neural Networks

Weather phenomenon recognition plays an important role in the field of meteorology.Nowadays,weather radars and weathers sensor have been widely used for weather recognition.However,given the high cost in deploying and maintaining the devices,it is difficult to apply them to intensive weather phenomenon recognition.Moreover,advanced machine learning models such as Convolutional Neural Networks(CNNs)have shown a lot of promise in meteorology,but these models also require intensive computation and large memory,which make it difficult to use them in reality.In practice,lightweight models are often used to solve such problems.However,lightweight models often result in significant performance losses.To this end,after taking a deep dive into a large number of lightweight models and summarizing their shortcomings,we propose a novel lightweight CNNs model which is constructed based on new building blocks.The experimental results show that the model proposed in this paper has comparable performance with the mainstream non-lightweight model while also saving 25 times of memory consumption.Such memory reduction is even better than that of existing lightweight models.

NOISE IDENTIFICATION FOR HYDRAULIC AXIAL PISTON PUMP BASED ON ARTIFICIAL NEURAL NETWORKS

The noise identification model of the neural networks is established for the 63SCY14 IB hydraulic axial piston pump. Taking four kinds of different port plates as instances, the noise identification is successfully carried out for hydraulic axial piston pump based on experiments with the MATLAB and the toolbox of neural networks, The operating pressure, the flow rate of hydraulic axial piston pump, the temperature of hydraulic oil, and bulk modulus of hydraulic oil are the main parameters having influences on the noise of hydraulic axial piston pump. These four parameters are used as inputs of neural networks, and experimental data of the noise are used as outputs of neural networks, Error of noise identification is less than 1% after the neural networks have been trained. The results show that the noise identification of hydraulic axial piston pump is feasible and reliable by using artificial neural networks. The method of noise identification with neural networks is also creative one of noise theoretical research for hydraulic axial piston pump.

Identification and Control of Dynamical Systems Using Modified Neural Networks

Aim To study the identification and control of nonlinear systems using neural networks. Methods A new type of neural network in which the dynamical error feedback is used to modify the inputs of the network was employed to reduce the inherent network approximation error. Results A new identification model constructed by the proposed network and stable filters was derived for continuous time nonlinear systems, and a stable adaptive control scheme based on the proposed networks was developed. Conclusion Theory and simulation results show that the modified neural network is feasible to control a class of nonlinear systems.

Identification of Hammerstein Model Using Hybrid Neural Networks

The identification problem of Hammerstein model with extension to the multi input multi output (MIMO) case is studied. The proposed identification method uses a hybrid neural network (HNN) which consists of a multi layer feed forward neural network (MFNN) in cascade with a linear neural network (LNN). A unified back propagation (BP) algorithm is proposed to estimate the weights and the biases of the MFNN and the LNN simultaneously. Numerical examples are provided to show the efficiency of the proposed method.

Local parameter identification with neural ordinary differential equations

The data-driven methods extract the feature information from data to build system models, which enable estimation and identification of the systems and can be utilized for prognosis and health management(PHM). However, most data-driven models are still black-box models that cannot be interpreted. In this study, we use the neural ordinary differential equations(ODEs), especially the inherent computational relationships of a system added to the loss function calculation, to approximate the governing equations. In addition, a new strategy for identifying the local parameters of the system is investigated, which can be utilized for system parameter identification and damage detection. The numerical and experimental examples presented in the paper demonstrate that the strategy has high accuracy and good local parameter identification. Moreover, the proposed method has the advantage of being interpretable. It can directly approximate the underlying governing dynamics and be a worthwhile strategy for system identification and PHM.

Nonlinear Identification and Control of Laser Welding Based on RBF Neural Networks

A laser beam is a heat source with a high energy density;this technol-ogy has been rapidly developed and applied in thefield of welding owing to its potential advantages,and supplements traditional welding techniques.An in-depth analysis of its operating process could establish a good foundation for its application in China.It is widely understood that the welding process is a highly nonlinear and multi-variable coupling process;it comprises a significant number of complex processes with random uncertain factors.Because of their nonlinear mapping and self-learning characteristics,artificial neural networks(ANNs)have certain advantages in comparison to traditional methods in thefield of welding.Laser welding is a nonlinear dynamic process;these processes still pose a major challenge in thefield of control.Therefore,establishing a stable model is a pre-requisite for achieving accurate control.In this study,the identification and con-trol of radial basis function neural networks in laser welding processes and self-tuning PID control methods are proposed to improve weld quality.Using a MATLAB simulation,it is shown that the proposed method can obtain a good description of the level of nonlinear dynamic control,and that the algorithm iden-tification accuracy is high,practical,and effective.Using this method,the weld width quickly reaches the expected value and the system remains stable,with good robustness.Further,it ensures the stability and dynamic performance of the welding process and improves weld quality.

IDENTIFICATION OF NONLINEAR TIME VARYING SYSTEM USING FEEDFORWARD NEURAL NETWORKS

As it is well known,it is difficult to identify a nonlinear time varying system using traditional identification approaches,especially under unknown nonlinear function.Neural networks have recently emerged as a successful tool in the area of identification and control of time invariant nonlinear systems.However,it is still difficult to apply them to complicated time varying system identification.In this paper we present a learning algorithm for identification of the nonlinear time varying system using feedforward neural networks.The main idea of this approach is that we regard the weights of the network as a state of a time varying system,then use a Kalman filter to estimate the state.Thus the network implements nonlinear and time varying mapping.We derived both the global and local learning algorithms.Simulation results demonstrate the effectiveness of this approach.

Identification of Nonlinear Dynamic Systems Using Diagonal Recurrent Neural Networks

In order to apply a new dynamic neural network- Diagonal Recurrent Neural NetWork (DRNN) to the system identificationof nonlinear dynamic Systems and construct more accurate system models, the structure and learning method (DBP algorithm) of theDRNN are Present6d. Nonlinear system characteriStics can be identified by presenting a set of input / output patterns tO the DRNN andadjusting its weights with the DBP algorithm. Experimental results show that the DRNN has good performances in the identification ofnonlinear dynamic systems in comparison with BP networks.

An Improved SPSA Algorithm for System Identification Using Fuzzy Rules for Training Neural Networks

Simultaneous perturbation stochastic approximation （SPSA） belongs to the class of gradient-free optimization methods that extract gradient information from successive objective function evaluation. This paper describes an improved SPSA algorithm, which entails fuzzy adaptive gain sequences, gradient smoothing, and a step rejection procedure to enhance convergence and stability. The proposed fuzzy adaptive simultaneous perturbation approximation （FASPA） algorithm is particularly well suited to problems involving a large number of parameters such as those encountered in nonlinear system identification using neural networks （NNs）. Accordingly, a multilayer perceptron （MLP） network with popular training algorithms was used to predicate the system response. We found that an MLP trained by FASPSA had the desired accuracy that was comparable to results obtained by traditional system identification algorithms. Simulation results for typical nonlinear systems demonstrate that the proposed NN architecture trained with FASPSA yields improved system identification as measured by reduced time of convergence and a smaller identification error.

Nonlinear Time-Varying Systems Identification Using Basis Sequence Expansions Combined with Neural Networks

A new method for identifying nonlinear time varying systems with unknown structure is presented. The method extends the application area of basis sequence identification. The essential idea is to utilize the learning and nonlinear approximating ability of neural networks to model the non linearity of the system, characterize time varying dynamics of the system by the time varying parametric vector of the network, then the parametric vector of the network is approximated by a weighted sum of known basis sequences. Because of black box modeling ability of neural networks, the presented method can identify nonlinear time varying systems with unknown structure. In order to improve the real time capability of the algorithm, the neural network is trained by a simple fast learning algorithm based on local least squares presented by the authors. The effectiveness and the performance of the method are demonstrated by some simulation results.

Feature identification in complex fluid flows by convolutional neural networks

Recent advancements have established machine learning's utility in predicting nonlinear fluid dynamics,with predictive accuracy being a central motivation for employing neural networks.However,the pattern recognition central to the networks function is equally valuable for enhancing our dynamical insight into the complex fluid dynamics.In this paper,a single-layer convolutional neural network(CNN)was trained to recognize three qualitatively different subsonic buffet flows(periodic,quasi-periodic and chaotic)over a high-incidence airfoil,and a near-perfect accuracy was obtained with only a small training dataset.The convolutional kernels and corresponding feature maps,developed by the model with no temporal information provided,identified large-scale coherent structures in agreement with those known to be associated with buffet flows.Sensitivity to hyperparameters including network architecture and convolutional kernel size was also explored.The coherent structures identified by these models enhance our dynamical understanding of subsonic buffet over high-incidence airfoils over a wide range of Reynolds numbers.

Synchronization-based approach for parameter identification in delayed chaotic network

This paper introduces an adaptive procedure for the problem of synchronization and parameter identification for chaotic networks with time-varying delay by combining adaptive control and linear feedback. In particular, we consider that the equations xi（t） （for i = r＋ 1, r＋2,... ,n） can be expressed by the former xi（t） （for i=1,2,...,r）, which is not the same as the previous equation. This approach is also able to track changes in the operating parameters of chaotic networks rapidly and the speed of synchronization and parameter estimation can be adjusted. In addition, this method is quite robust against the effect of slight noise and the estimated value of a parameter fluctuates around the correct value.

THE MODEL VALIDATION OF DYNAMIC NEURAL NETWORKS

This paper investigates the problem of the model validation in identifying discrete-time-nonlinear dynamic systems by using neural networks with a single hidden layer.Based on the estimation theory,a synthetic error-index(SEI)criterion for the neural network models has been developed.By using the powerful training algorithm of recursive prediction error (RPE),two simulated non-linear systems are studied,and the results show that the synthetic error-index criterion can be used to verify the dynamic neural network models.Furthermore,the proposed technique is much simple in calculation than that of the effective correlation tests.Finally,some problems required by further study are discussed.

Modeling of Ship Maneuvering Motion Using Neural Networks

In this paper, Neural Networks （NNs） are used in the modeling of ship maneuvering motion. A nonlinear response model and a linear hydrodynamic model of ship maneuvering motion are also investigated. The maneuverability indices and linear non-dimensional hydrodynamic derivatives in the models are identified by using two-layer feed forward NNs. The stability of parametric estimation is confirmed. Then, the ship maneuvering motion is predicted based on the obtained models. A comparison between the predicted results and the model test results demonstrates the validity of the proposed modeling method.

Effective data sampling strategies and boundary condition constraints of physics-informed neural networks for identifying material properties in solid mechanics

Material identification is critical for understanding the relationship between mechanical properties and the associated mechanical functions.However,material identification is a challenging task,especially when the characteristic of the material is highly nonlinear in nature,as is common in biological tissue.In this work,we identify unknown material properties in continuum solid mechanics via physics-informed neural networks(PINNs).To improve the accuracy and efficiency of PINNs,we develop efficient strategies to nonuniformly sample observational data.We also investigate different approaches to enforce Dirichlet-type boundary conditions(BCs)as soft or hard constraints.Finally,we apply the proposed methods to a diverse set of time-dependent and time-independent solid mechanic examples that span linear elastic and hyperelastic material space.The estimated material parameters achieve relative errors of less than 1%.As such,this work is relevant to diverse applications,including optimizing structural integrity and developing novel materials.

Individual Minke Whale Recognition Using Deep Learning Convolutional Neural Networks

The only known predictable aggregation of dwarf minke whales (Balaenoptera acutorostrata subsp.) occurs in the Australian offshore waters of the northern Great Barrier Reef in May-August each year. The identification of individual whales is required for research on the whales’ population characteristics and for monitoring the potential impacts of tourism activities, including commercial swims with the whales. At present, it is not cost-effective for researchers to manually process and analyze the tens of thousands of underwater images collated after each observation/tourist season, and a large data base of historical non-identified imagery exists. This study reports the first proof of concept for recognizing individual dwarf minke whales using the Deep Learning Convolutional Neural Networks (CNN).The “off-the-shelf” Image net-trained VGG16 CNN was used as the feature-encoder of the perpixel sematic segmentation Automatic Minke Whale Recognizer (AMWR). The most frequently photographed whale in a sample of 76 individual whales (MW1020) was identified in 179 images out of the total 1320 images provid-ed. Training and image augmentation procedures were developed to compen-sate for the small number of available images. The trained AMWR achieved 93% prediction accuracy on the testing subset of 36 positive/MW1020 and 228 negative/not-MW1020 images, where each negative image contained at least one of the other 75 whales. Furthermore on the test subset, AMWR achieved 74% precision, 80% recall, and 4% false-positive rate, making the presented approach comparable or better to other state-of-the-art individual animal recognition results.

Modelling missile motion system using neural networks

The models of noallnear systems are idendried by recmeive pedctive ermrs(RPE) methed based on thelayered neural networks. To improve the identification precision, gain callcient and arentUm factor are itheucedinto the algorithm for the data are dids by noses and vny suddnly. this lerthm is applied to the twcmedeiling of rolling and pitchng angles of ndssiles. Simulation results shoW tha the proposed algurithm is sultable forthe modelling of nodrinear systems.

Adaptive Control by Using Neural Networks

ＡｄａｐｔｉｖｅＣｏｎｔｒｏｌｂｙＵｓｉｎｇＮｅｕｒａｌＮｅｔｗｏｒｋｓ￥（郝继红）（吕强）（段运波）（许耀铭）ＨＡＯＪｉｈｏｎｇ；ＬＵＱｉａｎｇ；ＤＵＡＮＹｕｎｂｏ；ＸＵＹａｏｍｉｎｇ（Ｄｅｐｔ．ｏｆＰｏｗｅｒＥｎｇｉｎｅｅｒｉｎｇ，Ｈａｒｂｉｎｉ...