In Rayleigh wave exploration,the inversion of dispersion curves is a crucial step for obtaining subsurface stratigraphic information,characterized by its multi-parameter and multi-extremum nature.Local optimization al...In Rayleigh wave exploration,the inversion of dispersion curves is a crucial step for obtaining subsurface stratigraphic information,characterized by its multi-parameter and multi-extremum nature.Local optimization algorithms used in dispersion curve inversion are highly dependent on the initial model and are prone to being trapped in local optima,while classical global optimization algorithms often suffer from slow convergence and low solution accuracy.To address these issues,this study introduces the Osprey Optimization Algorithm(OOA),known for its strong global search and local exploitation capabilities,into the inversion of dispersion curves to enhance inversion performance.In noiseless theoretical models,the OOA demonstrates excellent inversion accuracy and stability,accurately recovering model parameters.Even in noisy models,OOA maintains robust performance,achieving high inversion precision under high-noise conditions.In multimode dispersion curve tests,OOA effectively handles higher modes due to its efficient global and local search capabilities,and the inversion results show high consistency with theoretical values.Field data from the Wyoming region in the United States and a landfill site in Italy further verify the practical applicability of the OOA.Comprehensive test results indicate that the OOA outperforms the Particle Swarm Optimization(PSO)algorithm,providing a highly accurate and reliable inversion strategy for dispersion curve inversion.展开更多
Rock physics inversion is to use seismic elastic properties of underground strata for predicting reservoir petrophysical parameters.The Markov chain Monte Carlo(MCMC)algorithm is commonly used to solve rock physics in...Rock physics inversion is to use seismic elastic properties of underground strata for predicting reservoir petrophysical parameters.The Markov chain Monte Carlo(MCMC)algorithm is commonly used to solve rock physics inverse problems.However,all the parameters to be inverted are iterated simultaneously in the conventional MCMC algorithm.What is obtained is an optimal solution of combining the petrophysical parameters with being inverted.This study introduces the alternating direction(AD)method into the MCMC algorithm(i.e.the optimized MCMC algorithm)to ensure that each petrophysical parameter can get the optimal solution and improve the convergence of the inversion.Firstly,the Gassmann equations and Xu-White model are used to model shaly sandstone,and the theoretical relationship between seismic elastic properties and reservoir petrophysical parameters is established.Then,in the framework of Bayesian theory,the optimized MCMC algorithm is used to generate a Markov chain to obtain the optimal solution of each physical parameter to be inverted and obtain the maximum posterior density of the physical parameter.The proposed method is applied to actual logging and seismic data and the results show that the method can obtain more accurate porosity,saturation,and clay volume.展开更多
Local and global optimization methods are widely used in geophysical inversion but each has its own advantages and disadvantages. The combination of the two methods will make it possible to overcome their weaknesses. ...Local and global optimization methods are widely used in geophysical inversion but each has its own advantages and disadvantages. The combination of the two methods will make it possible to overcome their weaknesses. Based on the simulated annealing genetic algorithm （SAGA） and the simplex algorithm, an efficient and robust 2-D nonlinear method for seismic travel-time inversion is presented in this paper. First we do a global search over a large range by SAGA and then do a rapid local search using the simplex method. A multi-scale tomography method is adopted in order to reduce non-uniqueness. The velocity field is divided into different spatial scales and velocities at the grid nodes are taken as unknown parameters. The model is parameterized by a bi-cubic spline function. The finite-difference method is used to solve the forward problem while the hybrid method combining multi-scale SAGA and simplex algorithms is applied to the inverse problem. The algorithm has been applied to a numerical test and a travel-time perturbation test using an anomalous low-velocity body. For a practical example, it is used in the study of upper crustal velocity structure of the A＇nyemaqen suture zone at the north-east edge of the Qinghai-Tibet Plateau. The model test and practical application both prove that the method is effective and robust.展开更多
For density inversion of gravity anomaly data, once the inversion method is determined, the main factors affecting the inversion result are the inversion parameters and subdivision scheme. A set of reasonable inversio...For density inversion of gravity anomaly data, once the inversion method is determined, the main factors affecting the inversion result are the inversion parameters and subdivision scheme. A set of reasonable inversion parameters and subdivision scheme can, not only improve the inversion process efficiency, but also ensure inversion result accuracy. The gravity inversion method based on correlation searching and the golden section algorithm is an effective potential field inversion method. It can be used to invert 2D and 3D physical properties with potential data observed on flat or rough surfaces. In this paper, we introduce in detail the density inversion principles based on correlation searching and the golden section algorithm. Considering that the gold section algorithm is not globally optimized. we present a heuristic method to ensure the inversion result is globally optimized. With a series of model tests, we systematically compare and analyze the inversion result efficiency and accuracy with different parameters. Based on the model test results, we conclude the selection principles for each inversion parameter with which the inversion accuracy can be obviously improved.展开更多
The inversions of complex geophysical data always solve multi-parameter, nonlinear, and multimodal optimization problems. Searching for the optimal inversion solutions is similar to the social behavior observed in swa...The inversions of complex geophysical data always solve multi-parameter, nonlinear, and multimodal optimization problems. Searching for the optimal inversion solutions is similar to the social behavior observed in swarms such as birds and ants when searching for food. In this article, first the particle swarm optimization algorithm was described in detail, and ant colony algorithm improved. Then the methods were applied to three different kinds of geophysical inversion problems： （1） a linear problem which is sensitive to noise, （2） a synchronous inversion of linear and nonlinear problems, and （3） a nonlinear problem. The results validate their feasibility and efficiency. Compared with the conventional genetic algorithm and simulated annealing, they have the advantages of higher convergence speed and accuracy. Compared with the quasi-Newton method and Levenberg-Marquardt method, they work better with the ability to overcome the locally optimal solutions.展开更多
Prticle swarm optimization(PSO)is adopted to invert the self-potential anomalies of simple geometry.Taking the vertical semi-infinite cylinder model as an example,the model parameters are first inverted using standard...Prticle swarm optimization(PSO)is adopted to invert the self-potential anomalies of simple geometry.Taking the vertical semi-infinite cylinder model as an example,the model parameters are first inverted using standard particle swarm optimization(SPSO),and then the searching behavior of the particle swarm is discussed and the change of the particles’distribution during the iteration process is studied.The existence of different particle behaviors enables the particle swarm to explore the searching space more comprehensively,thus PSO achieves remarkable results in the inversion of SP anomalies.Finally,six improved PSOs aiming at improving the inversion accuracy and the convergence speed by changing the update of particle positions,inertia weights and learning factors are introduced for the inversion of the cylinder model,and the effectiveness of these algorithms is verified by numerical experiments.The inversion results show that these improved PSOs successfully give the model parameters which are very close to the theoretical value,and simultaneously provide guidance when determining which strategy is suitable for the inversion of the regular polarized bodies and similar geophysical problems.展开更多
In order to interpret the vertical electrical sounding data more reliably and effectively in the case of lacking proper priori information, two inverse schemes are proposed to invert combined re- sistivity and induced...In order to interpret the vertical electrical sounding data more reliably and effectively in the case of lacking proper priori information, two inverse schemes are proposed to invert combined re- sistivity and induced polarization data by using particle swarm optimization technique. Based on the computational formula of induced polarization, the inversion for chargeability/polarizability data can be transformed into inverting equivalent resistivity data. Then, the inversion for combined data can be decomposed into two procedures： inverting resistivity data and inverting equivalent resistivity data. A sequential inversion scheme is presented to run the two procedures sequentially. Contrast to the se- quential scheme, a simultaneous one is proposed to invert resistivity and induced polarization data si- multaneously. Both the sequential and simultaneous schemes are performed via centered-progressive particle swarm optimization algorithm for more exploratory purpose. Numerical experiments show that both the designed inversion algorithms can invert resistivity and induced polarization data suc- cessfully with fast convergence and high accuracy, even performed in a large search space. The inverse results are comparable to the results from generalized linear method. As an approximate importance sampler, the particle swarm optimization based algorithm can provide posterior analysis conveniently. We employ the posterior probability distributions of inverted model parameters to evaluate the per- formance and uncertainty of inversion. The posterior analysis and further field data testing show that the proposed inversion algorithms perform good sampling of the equivalence region and make sure that the global optimum can locate in the high probability areas.展开更多
A new prestack AVA simultaneous inversion using particle swarm optimization algorithm is proposed, which can obtain the elastic parameters such as P-wave and S-wave impedance from P-wave reflection data simultaneously...A new prestack AVA simultaneous inversion using particle swarm optimization algorithm is proposed, which can obtain the elastic parameters such as P-wave and S-wave impedance from P-wave reflection data simultaneously. Compared with the conventional AVA inversion based on generalized linear technique, this method does not depend on the initial model and can reach the global minimum. In order to increase the stability of the inversion, low-frequency trends of P-wave and S-wave impedances are built into the inversion. This method has been successfully applied to synthetic and field data. The estimated P-wave and S-wave impedances can be combined to derive other elastic parameters, which are sensitive for lithology identification and fluid prediction.展开更多
The practical application of 3D inversion of gravity data requires a lot of computation time and storage space.To solve this problem,we present an integrated optimization algorithm with the following components:(1)tar...The practical application of 3D inversion of gravity data requires a lot of computation time and storage space.To solve this problem,we present an integrated optimization algorithm with the following components:(1)targeting high accuracy in the space domain and fast computation in the wavenumber domain,we design a fast 3D forward algorithm with high precision;and(2)taking advantage of the symmetry of the inversion matrix,the main calculation in gravity conjugate gradient inversion is decomposed into two forward calculations,thus optimizing the computational efficiency of 3D gravity inversion.We verify the calculation accuracy and efficiency of the optimization algorithm by testing various grid-number models through numerical simulation experiments.展开更多
In order to improve the fine structure inversion ability of igneous rocks for the exploration of underlying strata, based on particle swarm optimization(PSO), we have developed a method for seismic wave impedance inve...In order to improve the fine structure inversion ability of igneous rocks for the exploration of underlying strata, based on particle swarm optimization(PSO), we have developed a method for seismic wave impedance inversion. Through numerical simulation, we tested the effects of different algorithm parameters and different model parameterization methods on PSO wave impedance inversion, and analyzed the characteristics of PSO method. Under the conclusions drawn from numerical simulation, we propose the scheme of combining a cross-moving strategy based on a divided block model and high-frequency filtering technology for PSO inversion. By analyzing the inversion results of a wedge model of a pitchout coal seam and a coal coking model with igneous rock intrusion, we discuss the vertical and horizontal resolution, stability and reliability of PSO inversion. Based on the actual seismic and logging data from an igneous area, by taking a seismic profile through wells as an example, we discuss the characteristics of three inversion methods, including model-based wave impedance inversion, multi-attribute seismic inversion based on probabilistic neural network(PNN) and wave impedance inversion based on PSO.And we draw the conclusion that the inversion based on PSO method has a better result for this igneous area.展开更多
For geophysical inversion problems,deterministic inversion methods can easily fall into local optimal solutions,while stochastic optimization methods can theoretically converge to global optimal solutions.These proble...For geophysical inversion problems,deterministic inversion methods can easily fall into local optimal solutions,while stochastic optimization methods can theoretically converge to global optimal solutions.These problems have always been a concern for researchers.Among many stochastic optimization methods,particle swarm optimization(PSO)has been applied to solve geophysical inversion problems due to its simple principle and the fact that only a few parameters require adjustment.To overcome the nonuniqueness of inversion,model constraints can be added to PSO optimization.However,using fixed regularization parameters in PSO iteration is equivalent to keeping the default model constraint at a certain level,yielding an inversion result that is considerably affected by the model constraint.This study proposes a hybrid method that combines the regularized least squares method(RLSM)with the PSO method.The RLSM is used to improve the global optimal particle and accelerate convergence,while the adaptive regularization strategy is used to update the regularization parameters to avoid the influence of model constraints on the inversion results.Further,the inversion results of the RLSM and hybrid algorithm are compared and analyzed by considering the audio magnetotelluric synthesis and field data as examples.Experiments show that the proposed hybrid method is superior to the RLSM.Furthermore,compared with the standard PSO algorithm,the hybrid algorithm needs a broader model space but a smaller particle swarm and fewer iteration steps,thus reducing the prior conditions and the computational cost used in the inversion.展开更多
Conventional pit excavation engineering methods often struggle to manage the complex deformation patterns associated with asymmetric excavations,resulting in significant safety risks and increased project costs.These ...Conventional pit excavation engineering methods often struggle to manage the complex deformation patterns associated with asymmetric excavations,resulting in significant safety risks and increased project costs.These challenges highlight the need for more precise and efficient design methodologies to ensure structural stability and economic feasibility.This research proposes an innovative automatic optimization inverse design method(AOIDM)that integrates an enhanced genetic algorithm(EGA)with a multiobjective optimization model.By combining advanced computational techniques with engineering principles,this approach improves search efficiency by 30%and enhances deformation control accuracy by 25%.Additionally,the approach exhibits potential for reducing carbon emissions to align with sustainable engineering goals.The effectiveness of this approach was validated through comprehensive data analysis and practical case studies,demonstrating its ability to optimize retaining structure designs under complex asymmetric loading conditions.This research establishes a new standard for precision and efficiency in automated excavation design,with accompanying improvements in safety and cost-effectiveness.Furthermore,it lays the foundation for future geotechnical engineering advancements,offering a robust solution to one of the most challenging aspects of modern excavation projects.展开更多
Inverse reinforcement learning optimal control is under the framework of learner-expert.The learner system can imitate the expert system's demonstrated behaviors and does not require the predefined cost function,s...Inverse reinforcement learning optimal control is under the framework of learner-expert.The learner system can imitate the expert system's demonstrated behaviors and does not require the predefined cost function,so it can handle optimal control problems effectively.This paper proposes an inverse reinforcement learning optimal control method for Takagi-Sugeno(T-S)fuzzy systems.Based on learner systems,an expert system is constructed,where the learner system only knows the expert system's optimal control policy.To reconstruct the unknown cost function,we firstly develop a model-based inverse reinforcement learning algorithm for the case that systems dynamics are known.The developed model-based learning algorithm is consists of two learning stages:an inner reinforcement learning loop and an outer inverse optimal control loop.The inner loop desires to obtain optimal control policy via learner's cost function and the outer loop aims to update learner's state-penalty matrices via only using expert's optimal control policy.Then,to eliminate the requirement that the system dynamics must be known,a data-driven integral learning algorithm is presented.It is proved that the presented two algorithms are convergent and the developed inverse reinforcement learning optimal control scheme can ensure the controlled fuzzy learner systems to be asymptotically stable.Finally,we apply the proposed fuzzy optimal control to the truck-trailer system,and the computer simulation results verify the effectiveness of the presented approach.展开更多
This paper investigates the problem of fuzzy adaptive finite-time inverse optimal control for active suspension systems(ASSs).The fuzzy logic systems(FLSs)are utilized to learn the unknown non-linear dynamics and an a...This paper investigates the problem of fuzzy adaptive finite-time inverse optimal control for active suspension systems(ASSs).The fuzzy logic systems(FLSs)are utilized to learn the unknown non-linear dynamics and an auxiliary system is established.Based on the finite-time stability theory and inverse optimal theory,a fuzzy adaptive inverse finite-time inverse optimal control method is proposed.It is proven that the formulated control approach guarantees the stability of the controlled systems,while ensuring that errors converge to a small neighborhood of zero within finite time.Moreover,the optimized control performance can be achieved.Eventually,the simulation results demonstrate the effectiveness of the proposed fuzzy adaptive finite-time inverse optimal control scheme.展开更多
Traditional inverse neural network(INN)approaches for inverse design typically require auxiliary feedforward networks,leading to increased computational complexity and architectural dependencies.This study introduces ...Traditional inverse neural network(INN)approaches for inverse design typically require auxiliary feedforward networks,leading to increased computational complexity and architectural dependencies.This study introduces a standalone INN methodology that eliminates the need for feedforward networks while maintaining high reconstruction accuracy.The approach integrates Principal Component Analysis(PCA)and Partial Least Squares(PLS)for optimized feature space learning,enabling the standalone INN to effectively capture bidirectionalmappings between geometric parameters and mechanical properties.Validation using established numerical datasets demonstrates that the standalone INN architecture achieves reconstruction accuracy equal or better than traditional tandem approaches while completely eliminating the workload and training time required for Feedforward Neural Networks(FNN).These findings contribute to AI methodology development by proving that standalone invertible architectures can achieve comparable performance to complex hybrid systems with significantly improved computational efficiency.展开更多
Global optimization is an essential approach to any inversion problem.Recently,the grey wolf optimizer(GWO)has been proposed to optimize the global minimum,which has been quickly used in a variety of inv-ersion proble...Global optimization is an essential approach to any inversion problem.Recently,the grey wolf optimizer(GWO)has been proposed to optimize the global minimum,which has been quickly used in a variety of inv-ersion problems.In this study,we proposed a parameter-shifted grey wolf optimizer(psGWO)based on the conven-tional GWO algorithm to obtain the global minimum.Com-pared with GWO,the novel psGWO can effectively search targets toward objects without being trapped within the local minimum of the zero value.We confirmed the effectiveness of the new method in searching for uniform and random objectives by using mathematical functions released by the Congress on Evolutionary Computation.The psGWO alg-orithm was validated using up to 10,000 parameters to dem-onstrate its robustness in a large-scale optimization problem.We successfully applied psGWO in two-dimensional(2D)synthetic earthquake dynamic rupture inversion to obtain the frictional coefficients of the fault and critical slip-weakening distance using a homogeneous model.Furthermore,this alg-orithm was applied in inversions with heterogeneous dist-ributions of dynamic rupture parameters.This implementation can be efficiently applied in 3D cases and even in actual earthquake inversion and would deepen the understanding of the physics of natural earthquakes in the future.展开更多
In this study,we implement forward modeling and inversion based on deep-learning strategies using an optimal nearly analytic discrete(ONAD)method.The forward-modeling method combines the ONAD method with recurrent neu...In this study,we implement forward modeling and inversion based on deep-learning strategies using an optimal nearly analytic discrete(ONAD)method.The forward-modeling method combines the ONAD method with recurrent neural network(RNN)for the fi rst time.RNN is a type of neural network that is suitable for sequential data,which uses information from both previous and current times to obtain output information.We express the ONAD method using an RNN framework to advance the time iteration of an acoustic equation.This process can simplify programming using RNN and convolution kernels.Next,we use deep learning based on the proposed forward-modeling method to study full waveform-inversion problems.Because the main purpose of inversion is to minimize the error between real and synthetic data,inversion is essentially an optimization problem.Many new optimizers are available in the framework of deep learning,such as the Adam and Nadam optimizers,which are used for optimizing velocity model in the inversion process.We perform six numerical experiments.The first two experiments demonstrate the forward-modeling results,which indicate that the forward-modeling method can effectively suppress numerical dispersion and improve computational effi ciency.The other four experiments demonstrate the inversion results,which show that the method proposed in this paper can eff ectively realize inversion imaging.We compare several optimizers used in deep learning and find that the Nadam optimizer has faster convergence and better effectiveness based on the ONAD method combined with RNN.展开更多
The non-linear inversion of rock mechanics parameters based on genetic algorithm is presented. The principIe and step of genetic algorithm is also given. A brief discussion of this method and an application example is...The non-linear inversion of rock mechanics parameters based on genetic algorithm is presented. The principIe and step of genetic algorithm is also given. A brief discussion of this method and an application example is presented at the end of this paper. From the satisfied result, quick, convenient and practical new approach is developed to solve this kind of problems.展开更多
Wavelet estimation is an important part of high-resolution seismic data processing.However,itis difficult to preserve the lateral continuity of geological structures and eff ectively recover weak geologicalbodies usin...Wavelet estimation is an important part of high-resolution seismic data processing.However,itis difficult to preserve the lateral continuity of geological structures and eff ectively recover weak geologicalbodies using conventional deterministic wavelet inversion methods,which are based on the joint inversionof wells with seismic data.In this study,starting from a single well,on the basis of the theory of single-welland multi-trace convolution,we propose a steady-state seismic wavelet extraction method for synchronizedinversion using spatial multi-well and multi-well-side seismic data.The proposed method uses a spatiallyvariable weighting function and wavelet invariant constraint conditions with particle swarm optimization toextract the optimal spatial seismic wavelet from multi-well and multi-well-side seismic data to improve thespatial adaptability of the extracted wavelet and inversion stability.The simulated data demonstrate that thewavelet extracted using the proposed method is very stable and accurate.Even at a low signal-to-noise ratio,the proposed method can extract satisfactory seismic wavelets that refl ect lateral changes in structures andweak eff ective geological bodies.The processing results for the field data show that the deconvolution resultsimprove the vertical resolution and distinguish between weak oil and water thin layers and that the horizontaldistribution characteristics are consistent with the log response characteristics.展开更多
Conventional gradient-based full waveform inversion (FWI) is a local optimization, which is highly dependent on the initial model and prone to trapping in local minima. Globally optimal FWI that can overcome this limi...Conventional gradient-based full waveform inversion (FWI) is a local optimization, which is highly dependent on the initial model and prone to trapping in local minima. Globally optimal FWI that can overcome this limitation is particularly attractive, but is currently limited by the huge amount of calculation. In this paper, we propose a globally optimal FWI framework based on GPU parallel computing, which greatly improves the efficiency, and is expected to make globally optimal FWI more widely used. In this framework, we simplify and recombine the model parameters, and optimize the model iteratively. Each iteration contains hundreds of individuals, each individual is independent of the other, and each individual contains forward modeling and cost function calculation. The framework is suitable for a variety of globally optimal algorithms, and we test the framework with particle swarm optimization algorithm for example. Both the synthetic and field examples achieve good results, indicating the effectiveness of the framework. .展开更多
基金sponsored by China Geological Survey Project(DD20243193 and DD20230206508).
文摘In Rayleigh wave exploration,the inversion of dispersion curves is a crucial step for obtaining subsurface stratigraphic information,characterized by its multi-parameter and multi-extremum nature.Local optimization algorithms used in dispersion curve inversion are highly dependent on the initial model and are prone to being trapped in local optima,while classical global optimization algorithms often suffer from slow convergence and low solution accuracy.To address these issues,this study introduces the Osprey Optimization Algorithm(OOA),known for its strong global search and local exploitation capabilities,into the inversion of dispersion curves to enhance inversion performance.In noiseless theoretical models,the OOA demonstrates excellent inversion accuracy and stability,accurately recovering model parameters.Even in noisy models,OOA maintains robust performance,achieving high inversion precision under high-noise conditions.In multimode dispersion curve tests,OOA effectively handles higher modes due to its efficient global and local search capabilities,and the inversion results show high consistency with theoretical values.Field data from the Wyoming region in the United States and a landfill site in Italy further verify the practical applicability of the OOA.Comprehensive test results indicate that the OOA outperforms the Particle Swarm Optimization(PSO)algorithm,providing a highly accurate and reliable inversion strategy for dispersion curve inversion.
基金supported by the National Natural Science Foundation of China(No.42174146)CNPC major forwardlooking basic science and technology projects(No.2021DJ0204).
文摘Rock physics inversion is to use seismic elastic properties of underground strata for predicting reservoir petrophysical parameters.The Markov chain Monte Carlo(MCMC)algorithm is commonly used to solve rock physics inverse problems.However,all the parameters to be inverted are iterated simultaneously in the conventional MCMC algorithm.What is obtained is an optimal solution of combining the petrophysical parameters with being inverted.This study introduces the alternating direction(AD)method into the MCMC algorithm(i.e.the optimized MCMC algorithm)to ensure that each petrophysical parameter can get the optimal solution and improve the convergence of the inversion.Firstly,the Gassmann equations and Xu-White model are used to model shaly sandstone,and the theoretical relationship between seismic elastic properties and reservoir petrophysical parameters is established.Then,in the framework of Bayesian theory,the optimized MCMC algorithm is used to generate a Markov chain to obtain the optimal solution of each physical parameter to be inverted and obtain the maximum posterior density of the physical parameter.The proposed method is applied to actual logging and seismic data and the results show that the method can obtain more accurate porosity,saturation,and clay volume.
基金supported by the National Natural Science Foundation of China (Grant Nos.40334040 and 40974033)the Promoting Foundation for Advanced Persons of Talent of NCWU
文摘Local and global optimization methods are widely used in geophysical inversion but each has its own advantages and disadvantages. The combination of the two methods will make it possible to overcome their weaknesses. Based on the simulated annealing genetic algorithm （SAGA） and the simplex algorithm, an efficient and robust 2-D nonlinear method for seismic travel-time inversion is presented in this paper. First we do a global search over a large range by SAGA and then do a rapid local search using the simplex method. A multi-scale tomography method is adopted in order to reduce non-uniqueness. The velocity field is divided into different spatial scales and velocities at the grid nodes are taken as unknown parameters. The model is parameterized by a bi-cubic spline function. The finite-difference method is used to solve the forward problem while the hybrid method combining multi-scale SAGA and simplex algorithms is applied to the inverse problem. The algorithm has been applied to a numerical test and a travel-time perturbation test using an anomalous low-velocity body. For a practical example, it is used in the study of upper crustal velocity structure of the A＇nyemaqen suture zone at the north-east edge of the Qinghai-Tibet Plateau. The model test and practical application both prove that the method is effective and robust.
基金supported by Specialized Research Fund for the Doctoral Program of Higher Education of China(20110022120004)the Fundamental Research Funds for the Central Universities
文摘For density inversion of gravity anomaly data, once the inversion method is determined, the main factors affecting the inversion result are the inversion parameters and subdivision scheme. A set of reasonable inversion parameters and subdivision scheme can, not only improve the inversion process efficiency, but also ensure inversion result accuracy. The gravity inversion method based on correlation searching and the golden section algorithm is an effective potential field inversion method. It can be used to invert 2D and 3D physical properties with potential data observed on flat or rough surfaces. In this paper, we introduce in detail the density inversion principles based on correlation searching and the golden section algorithm. Considering that the gold section algorithm is not globally optimized. we present a heuristic method to ensure the inversion result is globally optimized. With a series of model tests, we systematically compare and analyze the inversion result efficiency and accuracy with different parameters. Based on the model test results, we conclude the selection principles for each inversion parameter with which the inversion accuracy can be obviously improved.
基金supported by the 973 Program(Grant No 2007CB209600)Open Fund(No.GDL0706) of the Key Laboratory of Geo-detection(China University of Geosciences,Beijing),Ministry of Education
文摘The inversions of complex geophysical data always solve multi-parameter, nonlinear, and multimodal optimization problems. Searching for the optimal inversion solutions is similar to the social behavior observed in swarms such as birds and ants when searching for food. In this article, first the particle swarm optimization algorithm was described in detail, and ant colony algorithm improved. Then the methods were applied to three different kinds of geophysical inversion problems： （1） a linear problem which is sensitive to noise, （2） a synchronous inversion of linear and nonlinear problems, and （3） a nonlinear problem. The results validate their feasibility and efficiency. Compared with the conventional genetic algorithm and simulated annealing, they have the advantages of higher convergence speed and accuracy. Compared with the quasi-Newton method and Levenberg-Marquardt method, they work better with the ability to overcome the locally optimal solutions.
基金Projects(41874145,72088101)supported by the National Natural Science Foundation of China。
文摘Prticle swarm optimization(PSO)is adopted to invert the self-potential anomalies of simple geometry.Taking the vertical semi-infinite cylinder model as an example,the model parameters are first inverted using standard particle swarm optimization(SPSO),and then the searching behavior of the particle swarm is discussed and the change of the particles’distribution during the iteration process is studied.The existence of different particle behaviors enables the particle swarm to explore the searching space more comprehensively,thus PSO achieves remarkable results in the inversion of SP anomalies.Finally,six improved PSOs aiming at improving the inversion accuracy and the convergence speed by changing the update of particle positions,inertia weights and learning factors are introduced for the inversion of the cylinder model,and the effectiveness of these algorithms is verified by numerical experiments.The inversion results show that these improved PSOs successfully give the model parameters which are very close to the theoretical value,and simultaneously provide guidance when determining which strategy is suitable for the inversion of the regular polarized bodies and similar geophysical problems.
基金supported by the National Natural Science Foundation of China(No.41574123)
文摘In order to interpret the vertical electrical sounding data more reliably and effectively in the case of lacking proper priori information, two inverse schemes are proposed to invert combined re- sistivity and induced polarization data by using particle swarm optimization technique. Based on the computational formula of induced polarization, the inversion for chargeability/polarizability data can be transformed into inverting equivalent resistivity data. Then, the inversion for combined data can be decomposed into two procedures： inverting resistivity data and inverting equivalent resistivity data. A sequential inversion scheme is presented to run the two procedures sequentially. Contrast to the se- quential scheme, a simultaneous one is proposed to invert resistivity and induced polarization data si- multaneously. Both the sequential and simultaneous schemes are performed via centered-progressive particle swarm optimization algorithm for more exploratory purpose. Numerical experiments show that both the designed inversion algorithms can invert resistivity and induced polarization data suc- cessfully with fast convergence and high accuracy, even performed in a large search space. The inverse results are comparable to the results from generalized linear method. As an approximate importance sampler, the particle swarm optimization based algorithm can provide posterior analysis conveniently. We employ the posterior probability distributions of inverted model parameters to evaluate the per- formance and uncertainty of inversion. The posterior analysis and further field data testing show that the proposed inversion algorithms perform good sampling of the equivalence region and make sure that the global optimum can locate in the high probability areas.
基金supported by the National Natural Science Foundation of China(Nos.41004096 and 41230318)
文摘A new prestack AVA simultaneous inversion using particle swarm optimization algorithm is proposed, which can obtain the elastic parameters such as P-wave and S-wave impedance from P-wave reflection data simultaneously. Compared with the conventional AVA inversion based on generalized linear technique, this method does not depend on the initial model and can reach the global minimum. In order to increase the stability of the inversion, low-frequency trends of P-wave and S-wave impedances are built into the inversion. This method has been successfully applied to synthetic and field data. The estimated P-wave and S-wave impedances can be combined to derive other elastic parameters, which are sensitive for lithology identification and fluid prediction.
基金Financial support by the China Geological Survey Project(Nos.DD20190030,DD20190032)
文摘The practical application of 3D inversion of gravity data requires a lot of computation time and storage space.To solve this problem,we present an integrated optimization algorithm with the following components:(1)targeting high accuracy in the space domain and fast computation in the wavenumber domain,we design a fast 3D forward algorithm with high precision;and(2)taking advantage of the symmetry of the inversion matrix,the main calculation in gravity conjugate gradient inversion is decomposed into two forward calculations,thus optimizing the computational efficiency of 3D gravity inversion.We verify the calculation accuracy and efficiency of the optimization algorithm by testing various grid-number models through numerical simulation experiments.
基金provided by the National Science and Technology Major Project(No.2011ZX05004-004)China National Petroleum Corporation Key Projects(No.2014E2105)the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)
文摘In order to improve the fine structure inversion ability of igneous rocks for the exploration of underlying strata, based on particle swarm optimization(PSO), we have developed a method for seismic wave impedance inversion. Through numerical simulation, we tested the effects of different algorithm parameters and different model parameterization methods on PSO wave impedance inversion, and analyzed the characteristics of PSO method. Under the conclusions drawn from numerical simulation, we propose the scheme of combining a cross-moving strategy based on a divided block model and high-frequency filtering technology for PSO inversion. By analyzing the inversion results of a wedge model of a pitchout coal seam and a coal coking model with igneous rock intrusion, we discuss the vertical and horizontal resolution, stability and reliability of PSO inversion. Based on the actual seismic and logging data from an igneous area, by taking a seismic profile through wells as an example, we discuss the characteristics of three inversion methods, including model-based wave impedance inversion, multi-attribute seismic inversion based on probabilistic neural network(PNN) and wave impedance inversion based on PSO.And we draw the conclusion that the inversion based on PSO method has a better result for this igneous area.
基金supported by the National Natural Science Foundation of China(NSFC)[grant number 41374133]
文摘For geophysical inversion problems,deterministic inversion methods can easily fall into local optimal solutions,while stochastic optimization methods can theoretically converge to global optimal solutions.These problems have always been a concern for researchers.Among many stochastic optimization methods,particle swarm optimization(PSO)has been applied to solve geophysical inversion problems due to its simple principle and the fact that only a few parameters require adjustment.To overcome the nonuniqueness of inversion,model constraints can be added to PSO optimization.However,using fixed regularization parameters in PSO iteration is equivalent to keeping the default model constraint at a certain level,yielding an inversion result that is considerably affected by the model constraint.This study proposes a hybrid method that combines the regularized least squares method(RLSM)with the PSO method.The RLSM is used to improve the global optimal particle and accelerate convergence,while the adaptive regularization strategy is used to update the regularization parameters to avoid the influence of model constraints on the inversion results.Further,the inversion results of the RLSM and hybrid algorithm are compared and analyzed by considering the audio magnetotelluric synthesis and field data as examples.Experiments show that the proposed hybrid method is superior to the RLSM.Furthermore,compared with the standard PSO algorithm,the hybrid algorithm needs a broader model space but a smaller particle swarm and fewer iteration steps,thus reducing the prior conditions and the computational cost used in the inversion.
基金supported by the National Key R&D Program of China(Grant No.2023YFC3009400)the National Natural Science Foundation of China(Grant Nos.52238009 and 52208344).
文摘Conventional pit excavation engineering methods often struggle to manage the complex deformation patterns associated with asymmetric excavations,resulting in significant safety risks and increased project costs.These challenges highlight the need for more precise and efficient design methodologies to ensure structural stability and economic feasibility.This research proposes an innovative automatic optimization inverse design method(AOIDM)that integrates an enhanced genetic algorithm(EGA)with a multiobjective optimization model.By combining advanced computational techniques with engineering principles,this approach improves search efficiency by 30%and enhances deformation control accuracy by 25%.Additionally,the approach exhibits potential for reducing carbon emissions to align with sustainable engineering goals.The effectiveness of this approach was validated through comprehensive data analysis and practical case studies,demonstrating its ability to optimize retaining structure designs under complex asymmetric loading conditions.This research establishes a new standard for precision and efficiency in automated excavation design,with accompanying improvements in safety and cost-effectiveness.Furthermore,it lays the foundation for future geotechnical engineering advancements,offering a robust solution to one of the most challenging aspects of modern excavation projects.
基金The National Natural Science Foundation of China(62173172).
文摘Inverse reinforcement learning optimal control is under the framework of learner-expert.The learner system can imitate the expert system's demonstrated behaviors and does not require the predefined cost function,so it can handle optimal control problems effectively.This paper proposes an inverse reinforcement learning optimal control method for Takagi-Sugeno(T-S)fuzzy systems.Based on learner systems,an expert system is constructed,where the learner system only knows the expert system's optimal control policy.To reconstruct the unknown cost function,we firstly develop a model-based inverse reinforcement learning algorithm for the case that systems dynamics are known.The developed model-based learning algorithm is consists of two learning stages:an inner reinforcement learning loop and an outer inverse optimal control loop.The inner loop desires to obtain optimal control policy via learner's cost function and the outer loop aims to update learner's state-penalty matrices via only using expert's optimal control policy.Then,to eliminate the requirement that the system dynamics must be known,a data-driven integral learning algorithm is presented.It is proved that the presented two algorithms are convergent and the developed inverse reinforcement learning optimal control scheme can ensure the controlled fuzzy learner systems to be asymptotically stable.Finally,we apply the proposed fuzzy optimal control to the truck-trailer system,and the computer simulation results verify the effectiveness of the presented approach.
基金supported by the National Natural Science Foundation of China under 62173172。
文摘This paper investigates the problem of fuzzy adaptive finite-time inverse optimal control for active suspension systems(ASSs).The fuzzy logic systems(FLSs)are utilized to learn the unknown non-linear dynamics and an auxiliary system is established.Based on the finite-time stability theory and inverse optimal theory,a fuzzy adaptive inverse finite-time inverse optimal control method is proposed.It is proven that the formulated control approach guarantees the stability of the controlled systems,while ensuring that errors converge to a small neighborhood of zero within finite time.Moreover,the optimized control performance can be achieved.Eventually,the simulation results demonstrate the effectiveness of the proposed fuzzy adaptive finite-time inverse optimal control scheme.
基金funding by the Deutsche Forschungsgemeinschaft under Germany’s Excellence Strategy within the Cluster of Excellence PhoenixD(EXC 2122,Project ID 390833453).
文摘Traditional inverse neural network(INN)approaches for inverse design typically require auxiliary feedforward networks,leading to increased computational complexity and architectural dependencies.This study introduces a standalone INN methodology that eliminates the need for feedforward networks while maintaining high reconstruction accuracy.The approach integrates Principal Component Analysis(PCA)and Partial Least Squares(PLS)for optimized feature space learning,enabling the standalone INN to effectively capture bidirectionalmappings between geometric parameters and mechanical properties.Validation using established numerical datasets demonstrates that the standalone INN architecture achieves reconstruction accuracy equal or better than traditional tandem approaches while completely eliminating the workload and training time required for Feedforward Neural Networks(FNN).These findings contribute to AI methodology development by proving that standalone invertible architectures can achieve comparable performance to complex hybrid systems with significantly improved computational efficiency.
基金This study is supported by the National Natural Science Foundation of China(Nos.41922024 and 42174057)Shenzhen Key Laboratory of Deep Offshore Oil and Gas Exploration Technology(No.ZDS-YS20190902093007855)Shenzhen Science and Technology Program(No.KQTD20170810111725321).
文摘Global optimization is an essential approach to any inversion problem.Recently,the grey wolf optimizer(GWO)has been proposed to optimize the global minimum,which has been quickly used in a variety of inv-ersion problems.In this study,we proposed a parameter-shifted grey wolf optimizer(psGWO)based on the conven-tional GWO algorithm to obtain the global minimum.Com-pared with GWO,the novel psGWO can effectively search targets toward objects without being trapped within the local minimum of the zero value.We confirmed the effectiveness of the new method in searching for uniform and random objectives by using mathematical functions released by the Congress on Evolutionary Computation.The psGWO alg-orithm was validated using up to 10,000 parameters to dem-onstrate its robustness in a large-scale optimization problem.We successfully applied psGWO in two-dimensional(2D)synthetic earthquake dynamic rupture inversion to obtain the frictional coefficients of the fault and critical slip-weakening distance using a homogeneous model.Furthermore,this alg-orithm was applied in inversions with heterogeneous dist-ributions of dynamic rupture parameters.This implementation can be efficiently applied in 3D cases and even in actual earthquake inversion and would deepen the understanding of the physics of natural earthquakes in the future.
基金supported by the National Key Research and Development Project of China (No. 2017YFC1500301)the Joint Earthquake Research Program of the National Natural Science Foundation and the China Earthquake Administration (No. U1839206)the National Natural Science Foundation of China (No. 41974114)
文摘In this study,we implement forward modeling and inversion based on deep-learning strategies using an optimal nearly analytic discrete(ONAD)method.The forward-modeling method combines the ONAD method with recurrent neural network(RNN)for the fi rst time.RNN is a type of neural network that is suitable for sequential data,which uses information from both previous and current times to obtain output information.We express the ONAD method using an RNN framework to advance the time iteration of an acoustic equation.This process can simplify programming using RNN and convolution kernels.Next,we use deep learning based on the proposed forward-modeling method to study full waveform-inversion problems.Because the main purpose of inversion is to minimize the error between real and synthetic data,inversion is essentially an optimization problem.Many new optimizers are available in the framework of deep learning,such as the Adam and Nadam optimizers,which are used for optimizing velocity model in the inversion process.We perform six numerical experiments.The first two experiments demonstrate the forward-modeling results,which indicate that the forward-modeling method can effectively suppress numerical dispersion and improve computational effi ciency.The other four experiments demonstrate the inversion results,which show that the method proposed in this paper can eff ectively realize inversion imaging.We compare several optimizers used in deep learning and find that the Nadam optimizer has faster convergence and better effectiveness based on the ONAD method combined with RNN.
文摘The non-linear inversion of rock mechanics parameters based on genetic algorithm is presented. The principIe and step of genetic algorithm is also given. A brief discussion of this method and an application example is presented at the end of this paper. From the satisfied result, quick, convenient and practical new approach is developed to solve this kind of problems.
文摘Wavelet estimation is an important part of high-resolution seismic data processing.However,itis difficult to preserve the lateral continuity of geological structures and eff ectively recover weak geologicalbodies using conventional deterministic wavelet inversion methods,which are based on the joint inversionof wells with seismic data.In this study,starting from a single well,on the basis of the theory of single-welland multi-trace convolution,we propose a steady-state seismic wavelet extraction method for synchronizedinversion using spatial multi-well and multi-well-side seismic data.The proposed method uses a spatiallyvariable weighting function and wavelet invariant constraint conditions with particle swarm optimization toextract the optimal spatial seismic wavelet from multi-well and multi-well-side seismic data to improve thespatial adaptability of the extracted wavelet and inversion stability.The simulated data demonstrate that thewavelet extracted using the proposed method is very stable and accurate.Even at a low signal-to-noise ratio,the proposed method can extract satisfactory seismic wavelets that refl ect lateral changes in structures andweak eff ective geological bodies.The processing results for the field data show that the deconvolution resultsimprove the vertical resolution and distinguish between weak oil and water thin layers and that the horizontaldistribution characteristics are consistent with the log response characteristics.
文摘Conventional gradient-based full waveform inversion (FWI) is a local optimization, which is highly dependent on the initial model and prone to trapping in local minima. Globally optimal FWI that can overcome this limitation is particularly attractive, but is currently limited by the huge amount of calculation. In this paper, we propose a globally optimal FWI framework based on GPU parallel computing, which greatly improves the efficiency, and is expected to make globally optimal FWI more widely used. In this framework, we simplify and recombine the model parameters, and optimize the model iteratively. Each iteration contains hundreds of individuals, each individual is independent of the other, and each individual contains forward modeling and cost function calculation. The framework is suitable for a variety of globally optimal algorithms, and we test the framework with particle swarm optimization algorithm for example. Both the synthetic and field examples achieve good results, indicating the effectiveness of the framework. .
