Hybrid Intelligent Algorithm Research Articles

Design of logistics operation management algorithm based on information technology on internet

Aiming at the problems of slow convergence, high cost and low efficiency when ant colony algorithm is used to solve the distribution path optimisation problem in logistics operation management, a logistics operation management algorithm based on hybrid intelligent optimisation algorithm is proposed. Based on the establishment of the optimisation model and its constraints, the initial solution of the model was obtained by artificial fish swarm algorithm in the early stage, and the updating strategy of ant pheromone concentration was selected to improve the transition probability of ant state. In the later stage, the concept of crowding degree is introduced to improve the basic ant colony algorithm and improve the ability of ant colony optimisation. The optimal solution is obtained by analysing the parameters that affect the performance. The results show that the algorithm is superior to the basic ant colony algorithm in optimisation efficiency, convergence speed and distribution cost.

Hybrid machine learning algorithms to enhance lost-circulation prediction and management in the Marun oil field

Drilling fluid loss of circulation is a challenging issue to resolve for many oil and gas wells as drilling progresses. It imposes enormous expenses on drilling industry. One of the common practices to solve this problem or make it less severe is introducing various loss circulation materials (LCM) into the circulating drilling fluid. The ability to predict the amount of mud loss before drilling a particular formation would provide engineers with invaluable information to assist them in selecting appropriate LCM properties such as particle size distribution. In this study, a number of heuristic search algorithms including genetic algorithm (GA), particle swarm size (PSO), and cuckoo search algorithm (COA) are combined with two machine-learning techniques namely multilayer perception (MLP) neural network and least square support vector machine (LSSVM) to present different hybrid algorithms in prediction of lost circulation. The established database consists of 2820 cases (datasets) extracted from available drilling reports of 305 drilled wells in the Marun oil field. These datasets are associated with drilling operation variables, formation specifications, and drilling mud characteristics which totally include 18 input variables and 1 output. Pre-processing of data involves filtering with Savitzky-Golay (SG) filter and ranking features using wrapper method. Results show that hybrid intelligent models are highly capable of predicting lost circulation before drilling a certain formation. Furthermore, LSSVM-COA and LSSVM-PSO achieve coefficients of determination of 0.9424 and 0.9391, respectively, making them the two most accurate models. GA cannot match the prediction performance of the other two algorithms in enhancing machine-learning techniques for this purpose. MLP-GA with a coefficient of determination (R2) and RMSE of 0.9304 and 25.26 (bbl/hr), respectively, yields the weakest prediction performance. Hybrid intelligent models, coupling optimizers and machine learning algorithms show themselves to be superior to applying standalone machine-learning methodologies for predicting loss of circulation.

Research on role modeling and behavior control of virtual reality animation interactive system in Internet of Things

To solve the problems of poor real-time collision accuracy and low efficiency of modeling in the virtual reality environment, we propounded a depth image-based 3D modeling system and a hybrid intelligent collision detection algorithm. With the development of the 3D animation interactive system as an example, this paper uses 3D modeling technology based on depth images to build single role models, then reorganizes and merges the models to form 3D scenes. The hybrid intelligent collision detection algorithm, which combines the quantum behavior particle swarm optimization algorithm and the differential algorithm, improves the collision detection efficiency and accuracy and realizes behavior control of the characters in the interactive system. The experimental result shows that the 3D modeling technology based on depth images has greatly improved the accuracy and quantity of model texture and motion rate. By comparing the hybrid intelligent collision detection algorithm, the QPSO algorithm, and the FDH bounding box for collision detection, we conclude that the algorithm used in this paper has a shorter average collision time, more stable role behavior control, and better robustness.

A new hybrid algorithm model for prediction of internal corrosion rate of multiphase pipeline

Pipeline plays an important role in the oil and gas transportation industry. In recent years, more and more pipeline damages and breakdowns are caused by corrosion, which hurts the normal operation. Accurate prediction of the pipeline's corrosion rate is of great significance for the pipeline to operate safely and soundly. In this study, a hybrid intelligent algorithm method is proposed to predict the corrosion rate of the multiphase flow pipeline. The proposed model combines support vector regression (SVR), principal component analysis (PCA), and chaos particle swarm optimization (CPSO), named PCA-CPSO-SVR. PCA can reduce the data dimension and screen out the main variables of corrosion influencing factors. CPSO is utilized to optimize the hyperfine parameters in SVR, thus improving the prediction accuracy of the prediction model. The mean absolute error of the proposed model is 0.083, which is 18.6% lower than that of SVR. Compared with five benchmark models including linear regression (LR), artificial neural network (ANN), PCA-genetic algorithm-SVR, PCA-PSO-SVR, and De warred95(OLGA), the proposed model has higher prediction accuracy. According to the above results, PCA-CPSO-SVR has a good performance in the prediction of the corrosion rate of the multiphase flow pipeline.

Cultural Emperor Penguin Optimizer and Its Application for Face Recognition

Face recognition is an important technology with practical application prospect. One of the most popular classifiers for face recognition is support vector machine (SVM). However, selection of penalty parameter and kernel parameter determines the performance of SVM, which is the major challenge for SVM to solve classification problems. In this paper, with a view to obtaining the optimal SVM model for face recognition, a new hybrid intelligent algorithm is proposed for multiparameter optimization problem of SVM, which is a fusion of cultural algorithm (CA) and emperor penguin optimizer (EPO), namely, cultural emperor penguin optimizer (CEPO). The key aim of CEPO is to enhance the exploitation capability of EPO with the help of cultural algorithm basic framework. The performance of CEPO is evaluated by six well-known benchmark test functions compared with eight state-of-the-art algorithms. To verify the performance of CEPO-SVM, particle swarm optimization-based SVM (PSO-SVM), genetic algorithm-based SVM (GA-SVM), CA-SVM, and EPO-SVM, moth-flame optimization-based SVM (MFO-SVM), grey wolf optimizer-based SVM (GWO-SVM), cultural firework algorithm-based SVM (CFA-SVM), and emperor penguin and social engineering optimizer-based SVM (EPSEO-SVM) are used for the comparison experiments. The experimental results confirm that the parameters optimized by CEPO are more instructive to make the classification performance of SVM better in terms of accuracy, convergence rate, stability, robustness, and run time.

An algorithm for solving FEVM problem based on SPSO algorithm

To solve fuzzy expected value model problem that widely exists in fuzzy programming field, a new hybrid intelligence algorithm based on Stochastic Particle Swarm Optimization (SPSO) algorithm is put forward in this article. Fuzzy simulation is used to get training samples for multi-layer (BP) Back Propagation artificial neural networks and multi-layer BP artificial neural networks is used to approximate fuzzy expected value function when SPSO algorithm is used to find the optimal value, the trained multi-layer BP artificial neural networks is used to calculate fuzzy expected function’s fitness value and detail steps are designed. Compared with the hybrid intelligence algorithm based on the classical Genetic Algorithm, the proposed algorithm overcomes some defects, such as taking a long time, computing complexity, easy being immersed in local extremum. The results are justified with the help of two numerical illustrations for fuzzy expected value model problem, the effectiveness of our new approach is demonstrated and it has determinate practical value.

Optimization of load sharing for parallel compressors using a novel hybrid intelligent algorithm

AbstractCompressor stations, which usually consist of multiple compressors in parallel, are installed to power natural gas travel in pipelines. Compressor station optimization, which should be expressed as a mixed integer nonlinear programming (MINLP) problem, makes economic sense for the entire gas transmission system. However, it has often been simplified as a nonlinear programming (NLP) or mixed integer linear programming (MILP) problem in previous research. Most of existing solutions are based on discretization and a genetic algorithm (GA). This paper addresses the general MINLP problem for compressor station optimization without simplification; a novel hybrid intelligent algorithm is proposed to solve this problem. The proposed algorithm, DWOA, leverages advantages of the whale optimization algorithm (WOA) and differential evolution (DE). The proposed algorithm can balance exploration and exploitation to find the global optimal solution. An approach to handling constraints is also presented, where the original problem model is reformulated to be continuous by expanding the flow rate range of the compressor. A case study is performed to illustrate the performance of this approach. Results show that the continuous reformulated model is easier to solve, and DWOA produces a satisfactory solution that differs from theoretical results by only 1.61%. In addition, DWOA demonstrates better accuracy and stability than WOA, DE, and DE‐WOA, another hybrid algorithm. Therefore, this solution has the potential to promote comprehensive compressor station optimization.

Designing Hybrid Intelligence based Recommendation Algorithms: An Experience through Machine Learning Metaphor

This article presents a summarization of the doctoral thesis which proposes efficient hybrid intelligent algorithms in recommendation systems. Development of effective recommendation algorithms for ensuring quality recommendation in timely manner is a tricky task. Moreover, traditional recommendation system is inadequate to cope up with the new technological trends. In order to overcome these issues, a batch of sophisticated recommendation systems has been discovered e.g. contextual recommendation, group recommendation, and social recommendation. The research work, investigates and analyzes new genres of recommenders using nature inspired algorithms, evolutionary algorithms, swarm intelligence algorithms, and machine learning techniques. The algorithms resolve some crucial problems of these recommenders. As a result, more precise personalized recommendation is ensured.

Dynamic reactive power optimisation of UHVDC converter station considering coordination of synchronous condenser and system filtering requirements

The reactive power compensation of large-capacity synchronous condensers in a ultrahigh-voltage direct current (UHVDC) converter station is not yet fully utilised, and there is no method for achieving effective coordination between synchronous condensers and DC systems. To realise their coordinated control of reactive power and voltage, a dynamic reactive power optimisation model that considers the coordination of synchronous condenser and filtering requirements of system is proposed in this study. The model considers the constraints of the variable steady reactive power capacity of synchronous condenser by taking into account its dynamic reserve demand, the minimum filter capacity of the system, and the switching sequence of AC filters and shunt capacitors. The model is solved by a two-stage hybrid intelligent algorithm based on the interior point method and the differential evolution algorithm. Further, the effectiveness of the proposed method is verified by the example of a UHVDC sending converter station in Northeast China. The simulation results show that the proposed model can greatly reduce the number of times discrete devices enter operation in a converter station under satisfying the dynamic reactive power reserve of the synchronous condenser, providing a basis for the coordinated optimal control of synchronous condensers and DC systems.

Saddle point equilibrium model for uncertain discrete systems

Uncertainty theory is a newly founded mathematical tool for modeling subjective indeterminacy. This type of indeterminate events is described as uncertain events and measured by belief degrees. In this paper, a saddle point equilibrium game model is studied for an uncertain discrete system, where the system is disturbed by an uncertain event at each stage. Applying Bellman’s dynamic programming approach, recurrence equations for this model are presented. The explicit solution of a bang–bang game model for the uncertain discrete system is obtained. Furthermore, for general cases, a hybrid intelligent algorithm is provided to approximate the solution numerically. Finally, a discrete game of duopoly is discussed to show the effectiveness of our results.

Fuzzy Random Chance-Constrained Programming Model for the Vehicle Routing Problem of Hazardous Materials Transportation

As an indispensable necessity in daily routine of citizens, hazardous materials (Hazmat) not only plays an increasingly important role, but also brings a series of transportation uncertainty phenomena, the most prominent of which is a safety problem. When it attempts to find the best vehicle route scheme that can possess the lowest risk attribute in a fuzzy random environment for a single warehouse, the influence of cost should also be taken into account. In this study, a new mathematical theory was conducted in the modeling process. To take a full consideration of uncertainty, vehicle travel distance and population density along the road segment were assumed to be fuzzy variables. Meanwhile, accident probability and vehicle speed were set to be stochastic. Furthermore, based on the assumptions, authors established three chance constrained programming models according to the uncertain theory. Model I was used to seek the achievement of minimum risk of the vehicle route scheme, using traditional risk model; the goal of Model II was to obtain the lowest total cost, including the green cost, and the main purpose of Model III was to establish a balance between cost and risk. To settle the above models, a hybrid intelligent algorithm was designed, which was a combination of genetic algorithm and fuzzy random simulation algorithm, which simultaneously proved its convergence. At last, two experiments were designed to illustrate the feasibility of the proposed models and algorithms.

Hybrid Intelligence Assisted Sample Average Approximation Method for Chance Constrained Dynamic Optimization

Realistic industrial process is usually a dynamic process with uncertainty. Chance constraints are applicable to industrial process modeling under uncertain conditions, where constraints cannot be strictly met, or need not be fully met. Therefore, chance constrained dynamic optimization (CCDO) formulation is available to address realistic industrial process issues. Because of the dynamic and uncertainty, chance constrained dynamic optimization problems (CCDOPs) arising from practical industries are hard to cope with. In this article, a novel CCDO method is proposed to resolve this issue, where an adaptive sample average approximation method, a control vector parameterization method, and a state constraint handling strategy are integrated. Specially, a hybrid intelligent optimization algorithm is introduced to realize a global and efficient optimization performance. The proposed method is applied to CCDOPs modified by dynamic optimization standard test functions and industrial experiments to demonstrate its effectiveness. The experimental results show that the proposed method has good performance in solving CCDOPs.

A Prediction of Grain Yield Based on Hybrid Intelligent Algorithm

The prediction is most important goals in economic quantitative studies, it basis in design and plan future economic policies properly process over forecasting accuracy. This paper is aiming at the problem salp swarm algorithm (SSA) for predicting grain yield is prone to fall into the local optimal problem. An improved SSA is proposed with combine with back propagation neural network. Using the different advantages of SSA algorithm in global search capabilities, combining the two for further optimize the weight, improve the accuracy and robustness of the grain yield prediction model. The specific implementation is selected from 1963 to 2013.These methods are used to define agricultural datasets that supports crop growth decision for grain product and its influencing factors were tested as a data set.The results show that, the improved salp swarm optimization can be classified as a good predict tool for the domestic food production trend in recent years compared with the SSA. This paper briefly introduces three artificial methods BP neural networks, SSA and improved SSA optimization algorithm. The natural behavior of salp, barrel-shaped plankton that are mostly water by weight optimization and combined with mixed-group of intelligent algorithm are simulated. The simulation results of grain production prediction illustrate that the predict precision of the improved SSA is much higher than of both conventional BPNN and SSA techniques and it’s very efficient and practicable.

Analysis of a class of dynamic programming models for multi-stage uncertain systems

Uncertainty theory is a new branch of mathematics concerned with the analysis of subjective indeterminacy. This paper deals with the optimal control problem for a multi-stage dynamic system in an indeterminate environment. Firstly, we formulate a practical uncertain control model based on the critical value criterion and present recursion equations for this model based on Bellman’s Principle. A special linear model is shown to illustrate how the recursion equations operate to obtain the analytical solution. Furthermore, we demonstrate a hybrid intelligent algorithm to evaluate and approximate the optimal solutions of more general cases. Finally, a discrete version of the production-inventory problem is discussed and numerically analyzed to illuminate the effectiveness of the methodology.

A chance-constrained programming approach for a zinc hydrometallurgy blending problem under uncertainty

Considering the low qualified rate in the blending of zinc concentrate caused by uncertainty of zinc concentrate composition in individual warehouses, we proposed a nonlinear stochastic optimization framework to handle uncertainties in the zinc concentrate blending problem. First, we obtained the distribution characteristics of uncertainty of zinc concentrate. Second, to minimize the pessimistic value of the objective function, we transformed the nonlinear stochastic optimization model into a nonlinear MiniMin chance-constrained programming model, which was easy to handle. Then, we used a hybrid intelligent optimization algorithm to solve the problem effectively. Finally, we verified the validity of the method using the actual production data of a zinc smelter's batching process. Compared with the deterministic optimization method, the model not only gave the probability that each component of the mixed zinc concentrate met the requirements but also achieved a higher qualified rate under the same conditions.

A Multiperiod Multiobjective Portfolio Selection Model With Fuzzy Random Returns for Large Scale Securities Data

It is agreed that portfolio selection models are of great importance for the financial market. In this article, a constrained multiperiod multiobjective portfolio model is established. This model introduces several constraints to reflect the trading restrictions and quantifies future security returns by fuzzy random variables to capture fuzzy and random uncertainties in the financial market. Meanwhile, it considers terminal wealth, conditional value at risk (CVaR), and skewness as tricriteria for decision making. Obviously, the proposed model is computationally challenging. This situation gets worse when investors are interested in a larger financial market since the data they need to analyze may constitute typical big data. Whereafter, a novel intelligent hybrid algorithm is devised to solve the presented model. In this algorithm, the uncertain objectives of the model are approximated by a simulated annealing resilient back propagation (SARPROP) neural network which is trained on the data provided by fuzzy random simulation. An improved imperialist competitive algorithm, named IFMOICA, is designed to search the solution space. The intelligent hybrid algorithm is compared with the one obtained by combining NSGA-II, SARPROP neural network, and fuzzy random simulation. The results demonstrate that the proposed algorithm significantly outperforms the compared one not only in the running time but also in the quality of obtained Pareto frontier. To improve the computational efficiency and handle the large scale securities data, the algorithm is parallelized using MPI. The conducted experiments illustrate that the parallel algorithm is scalable and can solve the model with the size of securities more than 400 in an acceptable time.

Fluid typing in tight sandstone from wireline logs using classification committee machine

Owing to the low porosity and low permeability of tight sandstone reservoirs, the geophysical log responses to different fluids are unclear, and it is difficult to identify the fluid types of some layers from wireline logs. The committee machine is a recently developed hybrid intelligent algorithm that combines expert networks and makes the final judgment through a decision mechanism. Fluid identification by log interpretation is a classification problem in machine learning; thus, we construct a classification committee machine (CCM). It is composed of a back-propagation neural network, a probabilistic neural network, and a decision tree classifier, and the final result is decided by voting. The processing flow of fluid identification from wireline logs is summarized, and the expert networks are optimized. Fluid typing for a gas reservoir and an oil reservoir in the Ordos Basin is conducted and analyzed in detail, and logs that are sensitive to the fluids in layers are chosen as input for the CCM. The prediction results from the CCM are compared with those of the three expert networks. Case studies from the gas field and oilfield show that the CCM can effectively combine intelligent algorithms through a decision-making mechanism and provide more accurate results.

Optimal arrangement of structural sensors in soft rock tunnels based industrial IoT applications

In recent years, with the rapid development of China’s economy, many civil engineering structures such as high-rise buildings, bridges, dams and tunnel have increased rapidly. Sensor optimization layout, as an important technology of Structural Health Monitoring (SHM), has become one of the research hotspots in related fields and disciplines. Due to the limitations of civil engineering structures and real economic conditions, it is not possible to place sensors on all structural degrees of freedom. Therefore, it is of great theoretical and practical significance to study the optimal layout of sensors for civil engineering. The optimal layout of the sensor is to evaluate and monitor the civil engineering structure through a reasonably arranged limited sensor, which is a combinatorial optimization problem. At present, the algorithms for solving this problem are traditional optimization algorithms, sequence methods and intelligent optimization algorithms. Both traditional optimization algorithms and sequence methods can only obtain suboptimal solutions, which cannot guarantee the accuracy of sensor placement. In view of this, this paper proposes a sensor optimization arrangement based on the intelligent algorithm emerging in recent years. This paper introduces several common intelligent optimization algorithms, and proposes a hybrid intelligent algorithm combining Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) algorithm. By comparing and analyzing the convergence of each algorithm, the results show that the hybrid algorithm has certain advantages over the single intelligent algorithm. In this paper, the hybrid intelligent algorithm is used to optimize the arrangement of the sensor. The experimental results show that the optimal layout of the sensor has certain rationality and feasibility.

Hybrid meta-heuristic and machine learning algorithms for tunneling-induced settlement prediction: A comparative study

Machine learning (ML) algorithms have been gradually used in predicting tunneling-induced settlement, but there is no uniform process for establishing ML models and even obviously exists deficiency in the existing settlement prediction ML models. This study systematically demonstrates the process of application of machine learning (ML) algorithms in predicting tunneling-induced settlement. The whole process can be categorized into four phases: the selection of ML algorithms, the determination of optimum-hyper-parameters, the improvement in model robustness and sensitivity analysis. The prediction performance of five commonly used ML algorithms back-propagation (BPNN), general regression neural network (GRNN), extreme learning machine (ELM), support vector machine (SVM) and random forest (RF) was comprehensively compared. The results indicate that proposed hybrid intelligent algorithm with the integration of the meta-heuristic algorithm particle swarm optimization (PSO) and ML can effectively determine the global optimum hyper-parameters of ML algorithms. The mean prediction error of k-fold cross-validation sets defined as the fitness function of the PSO algorithm can improve the robustness of ML models. RF algorithm outperforms the remaining four ML algorithms in recognizing the evolution of tunneling-induced settlement. BPNN shows great extrapolation capability, so it is recommended to establish settlement prediction model if the existing datasets are small. Sensitivity analysis indicates the geological and geometric parameters are the most influential variables for the settlement.

Cloud-based robotic system for crowd control in smart cities using hybrid intelligent generic algorithm

In recent years, cloud robotics in smart cities emerged with the technology of cloud computing and robotic enabled services such as ubiquitous computing based on internet resources, wireless sensor network, communication technologies, and large scale storage system for smart systems. The Internet of things is a complement to generate an enhanced system where robots offload the pervasive cloud to ensure the quality of the service from the data-intensive computation. In general the robots offloading is a crucial issue because of their skill learning, decision-making capabilities, a unique feature of mobility, and data collection. In this paper, a cloud-based robotic system for the crowd control system in smart cities using the hybrid intelligent generic algorithm has been proposed for smart crowd management. The cloud enhanced robots are employed to execute the essential task while taking into consideration of different complexity in a smart city. Furthermore, the integrated framework has been introduced to handling the task offloading and task completion through the robotics movement with minimum time and energy. The experimental results shows that the proposed system achieves powerful computation, storage, energy-efficient and reduce the cost with the help of cloud computing for smart city management.