CN104965941A - Magnetic flux leakage testing defect reconstruction method based on improved artificial bee colony algorithm - Google Patents
Magnetic flux leakage testing defect reconstruction method based on improved artificial bee colony algorithm Download PDFInfo
- Publication number
- CN104965941A CN104965941A CN201510295609.0A CN201510295609A CN104965941A CN 104965941 A CN104965941 A CN 104965941A CN 201510295609 A CN201510295609 A CN 201510295609A CN 104965941 A CN104965941 A CN 104965941A
- Authority
- CN
- China
- Prior art keywords
- nectar source
- value
- leakage signal
- magnetic leakage
- magnetic flux
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The invention relates to a magnetic flux leakage testing defect reconstruction method based on an improved artificial bee colony algorithm. According to the method, a radial basis function neural network is used as a forward model, and an error square sum of a magnetic flux leakage signal predicted by the forward model and an actually measured magnetic flux leakage signal is used as a target function to improve the artificial bee colony algorithm; a current individual optimal solution and a global optimal solution are introduced to accelerate algorithm convergence speed; the improved artificial bee colony algorithm is used as an iterative algorithm to solve a reconstruction problem, and the finally obtained global optimal solution is a reconstructed defect outline. The magnetic flux leakage testing defect reconstruction method based on the improved artificial bee colony algorithm improves speed and precision of magnetic flux leakage testing defect reconstruction.
Description
Technical field
The present invention relates to a kind of Magnetic Flux Leakage Inspecting technology, particularly a kind of Magnetic Flux Leakage Inspecting Root cause analysis method of the artificial bee colony algorithm based on improving.
Background technology
Magnetic Flux Leakage Inspecting is one of lossless detection method that ferromagnetic material is conventional, have that principle is simple, on-line checkingi ability by force, not by advantages such as material surface greasy dirt and other non-magnetic covertures affect.Magnetic Flux Leakage Inspecting comprises forward and inverse problem two aspects, and the reconstruct of pipeline magnetic flux leakage defect profile refers to by the magnetic leakage signal reconstruction defect profile detected or geometric parameter, is the key of carrying out Magnetic Flux Leakage Inspecting and assessment.The domestic and international research to leakage field inverse problem at present mainly contains neural network and optimization method.Neural network has Nonlinear Mapping and self-learning capability, can realize inputting magnetic leakage signal and exporting approaching of crack shape nonlinear relationship.But neural network is large to training sample dependence, and to noise-sensitive.Optimization sets up an objective function, makes the value of objective function minimum by various optimized algorithm, and therefore suitable optimized algorithm is the key of optimization method inverting.
Artificial bee colony (Artificial Bee Colony Algorithm, ABC) algorithm principle is simple, parameter is few, be easy to realize, simultaneously, the algorithm optimized algorithm that oneself knows relative to other can be explored and ability of searching optimum the local preferably in balance optimizing process, may be used for solving high-dimensional optimization.But when solving practical problems, due to the complex nature of the problem, basic ABC algorithm is not easily restrained, and iteration time is long, therefore need to find a kind of energy Fast Convergent and the improvement ABC algorithm ensureing precision.
Summary of the invention
The present invention be directed to and how to improve artificial bee colony algorithm and the problem being applied to pipeline magnetic flux leakage defect reconstruct, propose a kind of Magnetic Flux Leakage Inspecting Root cause analysis method of the artificial bee colony algorithm based on improving, in the ABC algorithm that current optimum solution pbest and globally optimal solution gbest is incorporated into, and by the ABC algorithm application of improvement in the Root cause analysis of Magnetic Flux Leakage Inspecting, the algorithm after improvement can improve reconstruction accuracy and reduce computing time.
Technical scheme of the present invention is: a kind of Magnetic Flux Leakage Inspecting Root cause analysis method of the artificial bee colony algorithm based on improving, is characterized in that, specifically comprise the steps:
1) initialization algorithm parameter and position, nectar source, and set greatest iteration number, initial nectar source is set, produces F at random
nindividual initial nectar source
Rand in formula is the random value of [0,1], x
ijbe the value of the jth dimension in i-th nectar source,
be respectively maximal value and the minimum value of j dimension, D represents dimension;
2) setting current iteration number of times is 1;
3) calculate the fitness value in each nectar source, adopt the position of artificial bee colony algorithm to nectar source of improving to upgrade, specifically comprise:
301) corresponding fitness fitness value is calculated as follows to nectar source:
Wherein f (x
i) be error sum of squares between the magnetic leakage signal predicted of the magnetic leakage signal measured and RBFNN be objective function:
In formula, D is the dimension of magnetic leakage signal, Z=[Z
1, Z
2..., Z
d] be actual measurement magnetic leakage signal, Y=[Y
1, Y
2..., Y
d] be the magnetic leakage signal that RBFNN predicts, Z
jwith Y
jbe respectively jth dimension actual measurement magnetic leakage signal and prediction magnetic leakage signal;
302) by comparing the size of fitness value, current individual optimum solution pbest is obtained
iwith globally optimal solution gbest, current individual optimum solution pbest
ibe the maximum solution of i-th nectar source fitness value in iteration, globally optimal solution gbest is the maximum solution of all nectar sources fitness value in iteration;
303) gathering honey honeybee is by the following formula search nectar source of improving, and calculates fitness, if nectar source quality improves, then upgrades nectar source current location, pbest
iwith the value of gbest, and by counting variable counter
iset to 0, otherwise gathering honey honeybee current location is constant, and by counter
iadd 1,
Wherein t is current iteration number of times; J ∈ 1,2 ..., D}, k ∈ 1,2 ... F
n, j, k are the random value in its codomain, and k1i; x
kjfor the value that the jth in a kth nectar source is tieed up;
for obeying equally distributed random number;
304) P is calculated
i,
if P
ibe greater than a random value, then observe honeybee and be converted into gathering honey honeybee, search for nectar source by following formula and calculate fitness, if nectar source quality improves, then upgrade nectar source current location, pbest
iwith the value of gbest, and by counting variable counter
iset to 0, otherwise the current location in nectar source is constant, and by counter
iadd 1;
305) if counter
i>limit, then abandon this nectar source, and gathering honey honeybee is converted to investigation honeybee, the new nectar source of random selecting, and wherein limit is the maximum times allowing exploitation;
4) judge whether to reach maximum iteration time, if so, then iterations, as the reconstruct profile of magnetic leakage signal, if not, is then added 1 by globally optimal solution, and with the initial position of position, current nectar source as particle, and return step 3).
The magnetic leakage signal of described RBFNN prediction is by radial ba-sis function network forward model prediction gained.
Beneficial effect of the present invention is: the Magnetic Flux Leakage Inspecting Root cause analysis method that the present invention is based on the artificial bee colony algorithm of improvement, and compared with basic ABC, the present invention can improve the precision of leakage field reconstruct.
Accompanying drawing explanation
Fig. 1 is existing iterative inversion frame principles schematic diagram;
Fig. 2 is Characterization of Real Defects Outlines in defect 1 situation, reconstruct profile based on basic ABC algorithm and the present invention compare schematic diagram;
Fig. 3 is Characterization of Real Defects Outlines in defect 2 situation, reconstruct profile based on basic ABC algorithm and the present invention compare schematic diagram;
Fig. 4 is Characterization of Real Defects Outlines in defect 3 situation, reconstruct profile based on basic ABC algorithm and the present invention compare schematic diagram;
Fig. 5 is Characterization of Real Defects Outlines in defect 4 situation, reconstruct profile based on basic ABC algorithm and the present invention compare schematic diagram;
Fig. 6 is the experimental provision principle schematic that the embodiment of the present invention adopts;
Fig. 7 be in defect 5 situation Characterization of Real Defects Outlines, reconstruct the comparison diagram of profile based on basic ABC algorithm and the present invention;
Fig. 8 be in defect 6 situation Characterization of Real Defects Outlines, reconstruct the comparison diagram of profile based on basic ABC algorithm and the present invention.
Embodiment
The present invention adopts radial basis function neural network as forward model, using the magnetic leakage signal of forward direction model prediction with actual measurement magnetic leakage signal error sum of squares as objective function, using improvement ABC as the iterative algorithm solving reconstruction, the globally optimal solution finally obtained is the defect profile of reconstruct.
Current optimum solution pbest and globally optimal solution gbest introduces in ABC algorithm by the present invention, and is applied to pipeline magnetic flux leakage defect reconstructing method.To set forth from improvement ABC algorithm technical scheme of the present invention below.
(1) ABC algorithm is improved
To look for food by nature honeybee the inspiration of labor division in process between bee colony individuality and self-organization behavior, the Karaboga of Ai Erjiyesi university of Turkey proposed the artificial bee colony algorithm (Artificial Bee Colony Algorithm, ABC) based on bee colony foraging behavior first in 2005.In basic ABC algorithm, artificial bee colony is divided into three kinds by the division of labor: gathering honey honeybee, observation honeybee and investigation honeybee.Wherein, gathering honey honeybee and observation honeybee respectively account for half, and only there is a gathering honey honeybee job in each nectar source, and namely the quantity of gathering honey honeybee is equal with nectar source quantity, uses F
nrepresent.By (1) formula stochastic generation F during algorithm initialization
nindividual D ties up initial solution and calculates corresponding fitness value to each nectar source by (2) formula.
Rand in above formula is the random value of [0,1], x
ijbe the value of the jth dimension in i-th nectar source,
be respectively maximal value and the minimum value of j dimension.Search procedure is as follows:
1) in the gathering honey honeybee stage: implement Local Search to each nectar source near its neighborhood, the quality of assessment Search Results, upgrades nectar source according to greedy algorithm;
2) observe the honeybee stage: according to the quality of nectar source fitness value, observe honeybee and choose containing the relatively high nectar source of honey amount, change gathering honey honeybee into and continue to perform above-mentioned search renewal process;
3) the search bee stage: eliminate one and measure the nectar source (this nectar source still cannot be improved through repeatedly searching for its earning rate in other words) be about to totally containing honey from whole nectar source, and then the gathering honey honeybee of correspondence transfers search bee to, continue in whole search volume, select new potential high-quality nectar source randomly.
Start to search for by above process bee colony, may separate for one in each nectar source representing optimized problem in algorithm, the quality in nectar source correspond to the quality of solution, represents by fitness fitness value:
Wherein f (x
i) represent the target function value of correspondence problem, be error sum of squares between the magnetic leakage signal predicted of the magnetic leakage signal measured and RBFNN in this problem be objective function.Each gathering honey honeybee searches for formula near its nectar source neighborhood:
Wherein t is current iteration number of times; J ∈ 1,2 ..., D}, k ∈ 1,2 ... F
n, j, k are the random value in its codomain, and k1i; x
kjthe value of the jth dimension in a kth nectar source;
for obeying equally distributed random number.After gathering honey honeybee completes search, observe honeybee with way selection nectar source of roulette:
P
ithe nectar source of high person can attract more to observe honeybee and go to gathering honey, after " being recruited ", observing honeybee and changes gathering honey honeybee into, adopt the local searching strategy shown in formula (3) to exploit.When a nectar source is gathering honey honeybee with observe the honeybee stage after the exploitation of certain number of times, its quality of separating still can not get improving, to be abandoned in this nectar source, gathering honey honeybee changes investigation honeybee into, and then the nectar source new according to (1) formula random selecting, represent the maximum times allowing exploitation with limit, use counter
ithe exploitation number of times in record i-th nectar source.
Easily be absorbed in the shortcoming of locally optimal solution to overcome basic ABC algorithm, Hu Ke etc. propose a kind of ABC algorithm of improvement.The present invention introduces current individual optimum solution pbest on this basis
ibe used for accelerating algorithm the convergence speed with globally optimal solution gbest.Current individual optimum solution pbest
ibe the maximum individuality of i-th nectar source fitness value in current iteration, globally optimal solution gbest is the individuality that in all iteration before current iteration, fitness value is maximum.The gathering honey honeybee of improving ABC algorithm and the neighborhood search formula observing honeybee are respectively formula (5), formula (6).
J, k in upper two formulas and
value mode identical with (3) formula.After improving, algorithm steps is as follows:
Step 1: arrange initial parameter, obtains initial solution according to (1) formula, calculates fitness fitness value, obtain current individual optimum solution pbest by the size comparing fitness value by (2) formula
iwith the value of globally optimal solution gbest;
Step 2: gathering honey honeybee calculates fitness by (5) formula search nectar source, if nectar source quality improves, then upgrades nectar source current location, pbest
iwith the value of gbest and by counting variable counter
iset to 0, otherwise nectar source current location is constant, and by counter
iadd 1;
Step 3: calculate P
iif, P
ibe greater than a random value, then observe honeybee and be converted into gathering honey honeybee, calculate fitness according to (6) formula search nectar source, if nectar source quality improves, then upgrade nectar source current location, pbest
iwith the value of gbest, and by counting variable counter
iset to 0, otherwise nectar source current location is constant, and by counter
iadd 1;
Step 4: if counter
i>limit, then abandon this nectar source, and gathering honey honeybee is converted into investigation honeybee, chooses new nectar source by (1) formula;
Step 5: if reach maximum iteration time, Output rusults; Otherwise return step 2, enter next iteration.
(2) the present invention is based on the pipeline magnetic flux leakage defect reconstructing method improving ABC algorithm
According to the algorithm proposed in (1), be applied to the refutation process in pipeline magnetic flux leakage defect reconstructing method, reconstruction accuracy can be improved preferably.
Process flow diagram of the present invention as shown in Figure 1, the profile of the positional representation defect of the bee colony in algorithm, the magnetic leakage signal of defect is predicted by radial basis function neural network (radial-basis function neural network, RBFNN) forward model.Square error between the magnetic leakage signal predicted with the magnetic leakage signal measured and RBFNN, for objective function, is carried out iteration with the ABC algorithm improved, is drawn final profile.Objective function is:
In formula, D is the dimension of magnetic leakage signal, Z=[Z
1, Z
2..., Z
d] be actual measurement magnetic leakage signal, Y=[Y
1, Y
2..., Y
d] be the magnetic leakage signal that RBFNN predicts, Z
jwith Y
jbe respectively jth dimension actual measurement magnetic leakage signal and prediction magnetic leakage signal.Formula (7) is objective function f (x) in (2) formula.Due to by the magnetic flux leakage data of 100 sampled points as emulated data, so set the dimension of bee colony as 100.Position, nectar source is as input, and obtain magnetic leakage signal Y by RBFNN prediction, try to achieve target function value by (7) formula, (2) formula of substitution obtains fitness function fitness value.Through type (4), (5), (6) upgrade position, nectar source again, namely upgrade defect profile, complete an iteration.When iterations reaches maximal value, globally optimal solution is required defect profile.
(3) reconstitution experiments of the present invention and interpretation of result
The present invention uses emulation magnetic leakage signal and actual measurement magnetic leakage signal to verify validity of the present invention respectively, simulate signal is that finite element analysis software ANSYS emulates the 2 dimension defect profile-signal datas pair obtained, comprise 240 2 dimension defect sample, crack width is from 2.54 centimetres to 17.78 centimetres, and the degree of depth is not from 0.381 centimetre to 4.699 centimetres etc.240 sample centerings, 210 for training RBFNN, 30 are reconstructed defect for adopting the present invention.Actual measurement magnetic leakage signal by experiment device records.Because defect profile and magnetic leakage signal are 100 sampled points, so be also all 100 as the input layer of the radial basis function neural network of forward model and output layer nodes.The dispersion constant (spread) of neural network is 10
-8.
Bee colony quantity is set to 100 (gathering honey honeybee and observation honeybee quantity are respectively 50), limit value is 100, and solution space scope is [-2.159,0.254] centimetre, improving ABC algorithm maximum iteration time is 5000, and basic ABC algorithm maximum iteration time is 10000.Table 1 gives comparing of the error sum of squares of defect profile and the actual profile adopting the basic ABC algorithm of improvement ABC algorithm to reconstruct under different defect condition.
Table 1
As shown in Figures 2 to 5, wherein solid line represents real profile to one 2 dimension defect sample example, and dotted line is the reconstruct profile based on basic ABC algorithm, and dot-and-dash line is the reconstruct profile based on improving ABC algorithm.Upper as can be seen from figure, the algorithm after improvement can obtain defect profile more accurately.
In order to verify the performance of this patent institute extracting method further, actual measurement magnetic leakage signal is used to verify.The experimental provision that this example adopts as shown in Figure 6.
Experimental provision mainly comprises rotation platform, field coil, sensor, signal conditioning circuit, data collector.Wherein, disk diameter is 0.8494m, and different defect has been engraved in the periphery of rotating disk.Exciting current is 0.87A, and data sampling frequency is 120kHz, and sensor lift-off value is 1mm.。Defect is distributed in the edge surface of rotation platform.The yoke of excitation excitation is adopted to produce magnetic field.Hall element probe is positioned at the centre position of yoke two magnetic pole of distance side 0.5mm, for obtaining magnetic leakage signal.After signal conditioning circuit regulates, magnetic leakage signal is sent to data collector.In addition, the speed of rotation platform is controlled by motor.
The material type of rotation platform upper surface is U71Mn.The defect distribution of different size is at the upper surface of rotation platform, and actual speed scope is 2 ~ 50m/s.The type of hall effect sensor and data collecting card is respectively UGN3503 and ADLINK DAQ 2204.Amplitude due to Analysis of Magnetic Flux Leakage Testing Signals is millivolt level, and the voltage range of data collecting card is volt level, therefore, adopts AD620 instrumentation amplifier to carry out the differential amplifier circuit that Design enlargement coefficient is 100.In addition, for avoiding pick-up unit remagnetization rotation platform, also design with the addition of demagnetizer.
Different from emulating the simulation magnetic leakage signal obtained, the true magnetic leakage signal that actual measurement obtains, owing to being collected by Hall element, comprises certain noise signal.Respectively the algorithm application improving front and back is carried out profile estimation to actual measurement magnetic leakage signal.Use iterations, error amount and be put in table 2 respectively computing time, Fig. 7 and Fig. 8 gives the result of reconstruct.Reconstructing method that this patent is carried as can be seen from Table 2, for survey magnetic leakage signal carry out profile reconstruct time, can when keep precision reduce computing time significantly.
Table 2
By the experiment of emulation magnetic leakage signal and the experiment of actual measurement magnetic leakage signal, can find out, the ABC algorithm of improvement can improve reconstruction accuracy when computing time is substantially identical for emulation magnetic leakage signal, and for actual measurement magnetic leakage signal, when ensureing reconstruction accuracy, computing time can be reduced significantly.
Claims (2)
1., based on a Magnetic Flux Leakage Inspecting Root cause analysis method for the artificial bee colony algorithm improved, it is characterized in that, specifically comprise the steps:
1) initialization algorithm parameter and position, nectar source, and set greatest iteration number, initial nectar source is set, produces F at random
nindividual initial nectar source
Rand in formula is the random value of [0,1], x
ijbe the value of the jth dimension in i-th nectar source,
be respectively maximal value and the minimum value of j dimension, D represents dimension;
2) setting current iteration number of times is 1;
3) calculate the fitness value in each nectar source, adopt the position of artificial bee colony algorithm to nectar source of improving to upgrade, specifically comprise:
301) corresponding fitness fitness value is calculated as follows to nectar source:
Wherein f (x
i) be error sum of squares between the magnetic leakage signal predicted of the magnetic leakage signal measured and RBFNN be objective function:
In formula, D is the dimension of magnetic leakage signal, Z=[Z
1, Z
2..., Z
d] be actual measurement magnetic leakage signal, Y=[Y
1, Y
2..., Y
d] be the magnetic leakage signal that RBFNN predicts, Z
jwith Y
jbe respectively jth dimension actual measurement magnetic leakage signal and prediction magnetic leakage signal; 302) by comparing the size of fitness value, current individual optimum solution pbest is obtained
iwith globally optimal solution gbest, current individual optimum solution pbest
ibe the maximum solution of i-th nectar source fitness value in iteration, globally optimal solution gbest is the maximum solution of all nectar sources fitness value in iteration;
303) gathering honey honeybee is by the following formula search nectar source of improving, and calculates fitness, if nectar source quality improves, upgrades nectar source current location, pbest
iwith the value of gbest and by counting variable counter
iset to 0, otherwise gathering honey honeybee current location is constant by counter
iadd 1,
Wherein t is current iteration number of times; J ∈ 1,2 ..., D}, k ∈ 1,2 ... F
n, j, k are the random value in its codomain, and k1i; x
kjfor the value that the jth in a kth nectar source is tieed up;
for obeying equally distributed random number; 304) P is calculated
i,
if P
ibe greater than a random value, then observe honeybee and be converted into gathering honey honeybee, search for nectar source by following formula and calculate fitness, if nectar source quality improves, then upgrade nectar source current location, pbest
iwith the value of gbest, and by counting variable counter
iset to 0, otherwise the current location in nectar source is constant, and by counter
iadd 1;
305) if counter
i>limit, then abandon this nectar source, and gathering honey honeybee is converted to investigation honeybee, the new nectar source of random selecting, and wherein limit is the maximum times allowing exploitation;
4) judge whether to reach maximum iteration time, if so, then iterations, as the reconstruct profile of magnetic leakage signal, if not, is then added 1 by globally optimal solution, and with the initial position of position, current nectar source as particle, and return step 3).
2. according to claim 1 based on the Magnetic Flux Leakage Inspecting Root cause analysis method of the artificial bee colony algorithm improved, it is characterized in that, the magnetic leakage signal of described RBFNN prediction is by radial ba-sis function network forward model prediction gained.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510295609.0A CN104965941A (en) | 2015-06-02 | 2015-06-02 | Magnetic flux leakage testing defect reconstruction method based on improved artificial bee colony algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510295609.0A CN104965941A (en) | 2015-06-02 | 2015-06-02 | Magnetic flux leakage testing defect reconstruction method based on improved artificial bee colony algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104965941A true CN104965941A (en) | 2015-10-07 |
Family
ID=54219978
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510295609.0A Pending CN104965941A (en) | 2015-06-02 | 2015-06-02 | Magnetic flux leakage testing defect reconstruction method based on improved artificial bee colony algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104965941A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105704729A (en) * | 2016-01-22 | 2016-06-22 | 南京大学 | Wireless sensor deployment method employing improved artificial bee colony algorithm |
CN106018545A (en) * | 2016-06-29 | 2016-10-12 | 东北大学 | Pipeline defect magnetic flux leakage inversion method based on Adaboost-RBF synergy |
CN106595661A (en) * | 2016-11-16 | 2017-04-26 | 桂林电子科技大学 | Reconstruction method of inertial sensor signal |
CN106628097A (en) * | 2016-11-22 | 2017-05-10 | 南京航空航天大学 | Ship equipment fault diagnosis method based on improved radial basis function neutral network |
JP2018054375A (en) * | 2016-09-27 | 2018-04-05 | 日本電気株式会社 | Image inspection device, image inspection method and image inspection program |
CN110399928A (en) * | 2019-07-29 | 2019-11-01 | 集美大学 | Voltage of solid oxide fuel cell prediction technique, terminal device and storage medium |
CN111399370A (en) * | 2020-03-12 | 2020-07-10 | 四川长虹电器股份有限公司 | Artificial bee colony PI control method of off-grid inverter |
CN112995075A (en) * | 2021-02-15 | 2021-06-18 | 青岛科技大学 | Acoustic channel equalization method based on championship selection chaotic artificial bee colony algorithm |
CN113365282A (en) * | 2021-06-22 | 2021-09-07 | 成都信息工程大学 | WSN obstacle area covering deployment method adopting artificial bee colony algorithm of problem features |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102982008A (en) * | 2012-11-01 | 2013-03-20 | 山东大学 | Complicated function maximum and minimum solving method by means of parallel artificial bee colony algorithm based on computer cluster |
-
2015
- 2015-06-02 CN CN201510295609.0A patent/CN104965941A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102982008A (en) * | 2012-11-01 | 2013-03-20 | 山东大学 | Complicated function maximum and minimum solving method by means of parallel artificial bee colony algorithm based on computer cluster |
Non-Patent Citations (3)
Title |
---|
胡珂 等: "改进的人工蜂群算法性能", 《计算机应用》 * |
邱剑锋 等: "基于交叉突变算子的人工蜂群算法及其应用", 《计算机应用研究》 * |
韩文花 等: "自学习粒子群与梯度下降混杂的漏磁反演方法", 《火力与指挥控制》 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105704729A (en) * | 2016-01-22 | 2016-06-22 | 南京大学 | Wireless sensor deployment method employing improved artificial bee colony algorithm |
CN105704729B (en) * | 2016-01-22 | 2019-03-08 | 南京大学 | A kind of wireless sensor dispositions method using improved artificial bee colony algorithm |
CN106018545A (en) * | 2016-06-29 | 2016-10-12 | 东北大学 | Pipeline defect magnetic flux leakage inversion method based on Adaboost-RBF synergy |
CN106018545B (en) * | 2016-06-29 | 2019-05-14 | 东北大学 | A kind of pipeline defect and magnetic leakage inversion method based on Adaboost-RBF collaboration |
JP2018054375A (en) * | 2016-09-27 | 2018-04-05 | 日本電気株式会社 | Image inspection device, image inspection method and image inspection program |
CN106595661A (en) * | 2016-11-16 | 2017-04-26 | 桂林电子科技大学 | Reconstruction method of inertial sensor signal |
CN106628097A (en) * | 2016-11-22 | 2017-05-10 | 南京航空航天大学 | Ship equipment fault diagnosis method based on improved radial basis function neutral network |
CN110399928A (en) * | 2019-07-29 | 2019-11-01 | 集美大学 | Voltage of solid oxide fuel cell prediction technique, terminal device and storage medium |
CN111399370A (en) * | 2020-03-12 | 2020-07-10 | 四川长虹电器股份有限公司 | Artificial bee colony PI control method of off-grid inverter |
CN111399370B (en) * | 2020-03-12 | 2022-08-16 | 四川长虹电器股份有限公司 | Artificial bee colony PI control method of off-grid inverter |
CN112995075A (en) * | 2021-02-15 | 2021-06-18 | 青岛科技大学 | Acoustic channel equalization method based on championship selection chaotic artificial bee colony algorithm |
CN113365282A (en) * | 2021-06-22 | 2021-09-07 | 成都信息工程大学 | WSN obstacle area covering deployment method adopting artificial bee colony algorithm of problem features |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104965941A (en) | Magnetic flux leakage testing defect reconstruction method based on improved artificial bee colony algorithm | |
CN104897769B (en) | Magnetic Flux Leakage Inspecting Root cause analysis method based on improved particle swarm optimization algorithm | |
CN104299033A (en) | Magnetic flux leakage defect reconstruction method based on cuckoo searching and particle filter hybrid algorithm | |
Biswas et al. | Scales and locations of time stability of soil water storage in a hummocky landscape | |
CN105093278B (en) | Full waveform inversion gradient operator extracting method based on the main energy-optimised algorithm of excitation | |
CN113568055B (en) | Aviation transient electromagnetic data inversion method based on LSTM network | |
CN104614718A (en) | Method for decomposing laser radar waveform data based on particle swarm optimization | |
CN114970315A (en) | Urban accumulated water simulation and rapid prediction method based on spatial dynamic characteristic deep learning | |
CN105425611B (en) | A kind of turbine-generator units Excitation System Parameter Identification of Synchronous method | |
Song et al. | An implementation of differential search algorithm (DSA) for inversion of surface wave data | |
CN104899440B (en) | A kind of pipeline magnetic flux leakage defect reconstructing method based on gravitation searching algorithm | |
CN116523129A (en) | Road surface anti-skid performance prediction method based on XGBOOST and fractal dimension | |
Curk et al. | Perspectives of hydrologic modeling in agricultural research | |
Qin et al. | Estimating parameters for the Van Genuchten model from soil physical-chemical properties of undisturbed loess-soil | |
CN110098610B (en) | Real-time identification method and system for oscillation leading mode of power system under fault disturbance | |
Hou et al. | A Target-Focusing Optimization Method for 3D Profile Reconstruction of Defects using MFL Measurements | |
CN115049800A (en) | Electrical impedance imaging method based on wolf optimization and radial basis function neural network | |
CN114330917A (en) | Tree root diameter and depth prediction method and prediction system based on deep learning | |
CN113009107A (en) | Method for detecting unfrozen water content of frozen soil | |
CN111126782A (en) | Method for evaluating environmental flow of river reach in river source area based on carbon metabolism rate | |
Chang et al. | Intelligent diagnosis model of traction seat of urban rail vehicle based on harris hawks optimization | |
Li et al. | Image reconstruction of electrical impedance tomography based on deep learning | |
Huang et al. | Magnetic flux leakage testing | |
CN115565611B (en) | Biological regression prediction method, device, equipment and storage medium | |
Du et al. | Stress wave tomography of wood internal defects based on deep learning and contour constraint under sparse sampling |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20151007 |
|
WD01 | Invention patent application deemed withdrawn after publication |