Eliminating Stick-Slip Vibrations in Drill-Strings with a Dual-Loop Control Strategy Optimised by the CRO-SL Algorithm

Pérez-Aracil, Jorge; Camacho-Gómez, Carlos; Pereira, Emiliano; Vaziri, Vahid; Aphale, Sumeet S.; Salcedo‐Sanz, Sancho

doi:10.3390/math9131526

Cited by 10 publications

(5 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are three main types of ant colonies in polymorphic ant colony algorithms: Reconnaissance ants, search ants, and worker ants. Among them, the task of the worker ant colony is only responsible for feeding back from the confirmed optimal path, and the author did not consider it when designing the cloud database path optimization algorithm [4]; Reconnaissance ants are mainly responsible for local reconnaissance, searching around each node in the cloud database and leaving reconnaissance results (reconnaissance elements) to provide assistance for searching ants; Search ants 1) Reconnaissance ants place m reconnaissance ants on n nodes, with each reconnaissance ant scouting n-1 other nodes centered around its node. The reconnaissance results are combined with existing MAXPC (prior knowledge) to form reconnaissance elements, denoted as s [i] [j], marked on the path from node i to j, the search ant colony can calculate the state transition probability P k ij and adjust the amount of information on each path based on the marked detection elements and existing pheromones [5].…”

Section: Basic Polymorphic Ant Colony Algorithm Modelmentioning

confidence: 99%

Dynamic Security Rule Optimization Based on Deep Learning and Adaptive Algorithms

Hang,

Xie,

Zhang

et al. 2024

SCPE

View full text Add to dashboard Cite

Compared with traditional computer network security identification techniques, deep learning algorithms are based on their own distributed network structure for storage, processing, classification, comparison, and automatic identification functions. The distribution and dynamism of cloud databases increase the difficulty of route prediction and recognition in the cloud, affecting the efficiency of cloud computing. In response to the above issues, the author proposes a dynamic path optimization process for cloud databases based on adaptive immune grouping polymorphic ant colony algorithm. By setting up two states of ant colony, reconnaissance ant and search ant, and introducing an adaptive polymorphic ant colony competition strategy, the defect of general ant colony algorithms being prone to falling into local optima is improved; On this basis, an artificial immune algorithm with fast global search capability is further integrated to improve the search ant path optimization process, improving search speed and accuracy. Simulation experiments show that the IPANT algorithm outperforms the other three algorithms, maintaining a throughput of 1000 kbps and relatively stable; The data of OSPF, SPF, and FR are not significantly different, significantly lower than IPANT. The immune polymorphic ant colony algorithm (IPANT) has the lowest time delay for packet routing and performs better than the other three algorithms, with FR and SPF having higher latency. It has been proven that this algorithm can better solve convergence speed and global optimization problems, and can quickly and reasonably find the database to be accessed in the cloud.

show abstract

Section: Basic Polymorphic Ant Colony Algorithm Modelmentioning

confidence: 99%

Dynamic Security Rule Optimization Based on Deep Learning and Adaptive Algorithms

Hang,

Xie,

Zhang

et al. 2024

SCPE

View full text Add to dashboard Cite

show abstract

“…Recently, a multi-method ensemble known as coral reef optimization with substrate layers (CRO-SL) was proposed [27][28][29] and successfully applied to very different optimization problems in science and engineering, such as energy grid and microgrid design [30][31][32], mechanical and structural design [33][34][35][36][37], and electrical engineering [38][39][40]. The CRO-SL is a low-level, evolutionary-based multi-method ensemble which combines different types of search operators within a single population (reef) by dividing it in different zones (substrates), in which a different operator is applied.…”

Section: Contribution and Structurementioning

confidence: 99%

New Probabilistic, Dynamic Multi-Method Ensembles for Optimization Based on the CRO-SL

et al. 2023

Self Cite

View full text Add to dashboard Cite

In this paper, new probabilistic and dynamic (adaptive) strategies for creating multi-method ensembles based on the coral reef optimization with substrate layers (CRO-SL) algorithm are proposed. CRO-SL is an evolutionary-based ensemble approach that is able to combine different search procedures for a single population. In this work, two different probabilistic strategies to improve the algorithm are analyzed. First, the probabilistic CRO-SL (PCRO-SL) is presented, which substitutes the substrates in the CRO-SL population with tags associated with each individual. Each tag represents a different operator which will modify the individual in the reproduction phase. In each generation of the algorithm, the tags are randomly assigned to the individuals with similar probabilities, obtaining this way an ensemble that sees more intense changes with the application of different operators to a given individual than CRO-SL. Second, the dynamic probabilistic CRO-SL (DPCRO-SL) is presented, in which the probability of tag assignment is modified during the evolution of the algorithm, depending on the quality of the solutions generated in each substrate. Thus, the best substrates in the search process will be assigned higher probabilities than those which showed worse performance during the search. The performances of the proposed probabilistic and dynamic ensembles were tested for different optimization problems, including benchmark functions and a real application of wind-turbine-layout optimization, comparing the results obtained with those of existing algorithms in the literature.

show abstract

“…In the above research, the characteristics of multi-objective optimization of machine learning algorithm and the advantages of overcoming the sensitivity of initial parameter values of simplex method were utilized to optimize controller parameters [24,25]. In this paper, machine learning algorithms [26] are used to optimize the controller parameters, improve the robustness of the control system, increase the control accuracy, and suppress the drill string stick-slip vibration to the greatest extent.…”

Section: Introductionsmentioning

confidence: 99%

Research on Stick-Slip Vibration Suppression Method of Drill String Based on Machine Learning Optimization

Su,

Wei,

et al. 2023

Sound&Vibration

View full text Add to dashboard Cite

During the drilling process, stick-slip vibration of the drill string is mainly caused by the nonlinear friction generated by the contact between the drill bit and the rock. To eliminate the fatigue wear of downhole drilling tools caused by stick-slip vibrations, the Fractional-Order Proportional-Integral-Derivative (FOPID) controller is used to suppress stick-slip vibrations in the drill string. Although the FOPID controller can effectively suppress the drill string stick-slip vibration, its structure is flexible and parameter setting is complicated, so it needs to use the corresponding machine learning algorithm for parameter optimization. Based on the principle of torsional vibration, a simplified model of multi-degree-of-freedom drill string is established and its block diagram is designed. The continuous nonlinear friction generated by cutting rock is described by the LuGre friction model. The adaptive learning strategy of genetic algorithm (GA), particle swarm optimization (PSO) and particle swarm optimization improved (IPSO) by arithmetic optimization (AOA) is used to optimize and adjust the controller parameters, and the drill string stick-slip vibration is suppressed to the greatest extent. The results show that: When slight drill string stick-slip vibration occurs, the FOPID controller optimized by machine learning algorithm has a good effect on suppressing drill string stick-slip vibration. However, the FOPID controller cannot get the drill string system which has fallen into serious stick-slip vibration (stuck pipe) out of trouble, and the machine learning algorithm is required to mark a large amount of data on adjacent Wells to train the model. Set a reasonable range of drilling parameters (weight on bit/drive torque) in advance to avoid severe stick-slip vibration (stuck pipe) in the drill string system. KEYWORDSStick-slip vibration; machine learning; fractional order proportional integral derivative (FOPID) control; optimization algorithm Nomenclature C pb Drill bit viscous damping [(N • m • s)/rad] C rs Viscous damping coefficient of the turn table [(N • m • s)/rad] J zp , J zg , J BH , J zt Rotational inertias of the turn table, drill pipe, BHA, and drill bit, respectively [kg • m 2 ] K Pg , K gB , K Bt Torsional stiffness of the springs between the turn table and drill pipe, drill pipe and BHA, and BHA and drill bit, respectively [(N • m)/rad] N pg , N gB , N Bt Torsional damping of the springs between the turn table and drill pipe, drill pipe and BHA, and BHA and drill bit, respectively [(N • m • s)/rad]

show abstract

Eliminating Stick-Slip Vibrations in Drill-Strings with a Dual-Loop Control Strategy Optimised by the CRO-SL Algorithm

Cited by 10 publications

References 61 publications

Dynamic Security Rule Optimization Based on Deep Learning and Adaptive Algorithms

Dynamic Security Rule Optimization Based on Deep Learning and Adaptive Algorithms

New Probabilistic, Dynamic Multi-Method Ensembles for Optimization Based on the CRO-SL

Research on Stick-Slip Vibration Suppression Method of Drill String Based on Machine Learning Optimization

Contact Info

Product

Resources

About