CN101837165A - Walking aid electrostimulation fine control method based on genetic-ant colony fusion fuzzy controller - Google Patents

Abstract

The invention relates to the rehabilitation training field and aims to optimize the quantifying factor and scale factor of a fuzzy controller and the fuzzy control rules, then control the current mode of an FES system accurately, stably and instantly and effectively improve the accuracy and stability of the FES system. The technical scheme adopted by the invention is as follows: the walking aid electrostimulation fine control method based on genetic-ant colony fusion fuzzy controller comprises the following steps: firstly, converting the selection of fuzzy control decision variable to the combinational optimization problem adapting to the genetic-ant colony algorithm, coding the decision variable, randomly generating a chromosome composed of n-numbered individuals; secondly, using the genetic algorithm to generate the initial pheromone distribution of the ant algorithm, utilizing the ant colony algorithm to randomly search and optimize the membership function, quantifying factor and scale factor of the fuzzy controller; and performing repeated self-learning and self-regulating according to the system output, and finally using the processes in the FES system. The invention is mainly used for rehabilitation training.

Description

Merge the walk help electricity irritation precision control method of fuzzy controller based on genetic-ant colony

Technical field

The present invention relates to the rehabilitation training field, especially walker stand under load force measurement specifically relates to the walk help electricity irritation precision control method that merges fuzzy controller based on genetic-ant colony.

Background technology

(Functional Electrical Stimulation is to stimulate limb motion muscle group and peripheral nervous thereof by current pulse sequence FES) to functional electric stimulation, recovers or rebuild the technology of the componental movement function of paralytic patient effectively.At present, because the spinal cord regeneration ability is faint, at the spinal cord injury paralysed patient, Shang Weiyou can directly repair effective treatment method of damage, and implementing function rehabilitation training is effective measures.According to statistics, spinal cord injury paralysed patient number increases year by year, and function rehabilitation training is a technology of demanding demand urgently.The sixties in 20th century, Liberson successfully utilizes the electricity irritation peroneal nerve to correct the gait of hemiplegic patient's drop foot first, has started the new way that functional electric stimulation is used to move and Sensory rehabilitation is treated.At present, FES has become the componental movement function of recovering or rebuilding paralytic patient, is important rehabilitation means.Yet how accurate triggering sequential and the pulse current intensity of controlling FES can accurately be finished the key problem in technology that the intended function action is still FES with assurance electricity irritation action effect.According to statistics, the mode of the triggering of FES control is at present studied still few, and according to action effect and predetermined action deviation, automatically adjust FES stimulus intensity and time sequence parameter with closed loop control, thereby improved real-time, accuracy and the stability of FES system greatly, but now effective control method is still among exploring.

Fuzzy controller is a kind of method by fuzzy logic and approximate resoning, people's experience formalization, modelling, become computer acceptable controlling models, allow computer generation replace the people to control the high-level policy and the novel technical method of controlled device in real time, can improve the controllability of control algolithm effectively, adaptability and reasonability, especially at complicated and be difficult to modeling and have enrich manual empirical problem and have peculiar advantage with math equation, and human muscle's complexity and time variation operating environment make it set up its mathematical model, cause traditional control method to be difficult to adapt to the strict demand in FES field, fuzzy controller provides new departure for the precision control of FES.The fuzzy controller core technology is exactly to determine the factors such as method of structure, the fuzzy rule that is adopted, compositional rule of inference algorithm and the fuzzy decision of fuzzy controller, and the key that fuzzy control will obtain optimum control effect is to adjust to fuzzy controller quantizing factor, scale factor and fuzzy control rule are isoparametric.In the FES field, system stability is required very strictness, so select also particularly important to Fuzzy Controller Parameters.This patent propose based on the adjust method of the accurate control of fuzzy Control functional electric stimulation of genetic algorithm, can obtain good effect at the FES system power aspect horizontal.

Genetic algorithm belongs to artificial bio-membrane's evolution algorithm, be a kind of biosphere natural selection and natural genetic mechanism of being referred from, main feature is the information exchange between the individuality in colony's search strategy and the colony, does not rely on gradient information, is particularly suitable for the nonlinear problem optimizing to complexity.But the utilization for the feedback information in the system is powerless, causes often to do a large amount of unable redundant iteration when finding the solution certain limit, asks exact solution efficient low.Formica fusca in the ant group algorithm simulation biological world seeks under without any prompting by ant cave to the foraging behavior of the shortest path of food source and proposes simulated evolutionary algorithm based on population, has stronger adaptability, distributed parallel calculates, be easy to the integrated advantage of other algorithms, but initial stage pheromone scarcity, it is slow to find the solution speed.That genetic algorithm and ant group algorithm all have is applied widely, highly versatile or the like advantage, is widely used in discrete optimization problem, and genetic algorithm and ant group algorithm have complementarity and organically merge, and can overcome shortcoming separately, bring into play advantage separately.

Summary of the invention

For overcoming the deficiencies in the prior art, the objective of the invention is to, the precision control method of a kind of new FES is proposed, fusion by genetic algorithm and ant group algorithm, have complementary advantages, optimize quantizing factor, scale factor and the fuzzy control rule of fuzzy controller, the accurately stable then current-mode of controlling the FES system in real time, and can improve FES system accuracy and stability effectively, and obtain considerable social benefit and economic benefit.For achieving the above object, the technical solution used in the present invention is: the walk help electricity irritation precision control method based on genetic-ant colony fusion fuzzy controller comprises the following steps:

At first the selection of 12 decision variable kfuzz of quantizing factor, scale factor and the membership function parameter of fuzzy control is converted into the combinatorial optimization problem that heredity and ant group algorithm are suitable for, and these 12 kfuzz are carried out binary coding, produce n the individual initial population P (0) that forms afterwards at random, wherein kfuzz is the vector of n * 12;

Next sets up rational actual joint angles and the corresponding relation object function of muscle model output joint angles and the parameter setting of definite ant group algorithm, the initial information element that utilizes genetic algorithm to produce in the ant group algorithm distributes, utilize the Formica fusca random search to optimize membership function and the quantizing factor and the scale factor of fuzzy controller, and call the fuzzy controller of having adjusted, whether checking reaches goal-selling, do not repeat above operation if having, restrain or reach predetermined index up to parameter, the number of times of the decision variable of output fuzzy control and ant group operation;

According to the decision variable of aforementioned output fuzzy control under fuzzy controller computing system output and with the deviation of muscle model after enter next step again self study and self-adjusting, this process repeatedly, the final self adaptation on-line tuning of realizing Fuzzy Controller Parameters, and be used for the FES system.

Described fuzzy controller is a two-dimensional fuzzy controller, two actual respectively error e (k) and error change rate ec (k) that export joint angles and expectation joint degree of input variable, domain is FE=[-E, E], FEC=[-EC, EC], the stimulating current intensity u (k) of output, its domain is FU=[-U, U];

The quantification domain of error is X={-n ,-n+1 ... 0 ..., n-1, n}; (1)

The quantification domain of error rate is X ₁=m ,-m+1 ... 0 ..., m-1, m}; (2)

The quantification domain of controlled quentity controlled variable is Y={-k ,-k+1 ... 0 ..., k-1, k}; (3)

Quantizing factor is respectively

K _e＝n/X _e；(4)

K _ec＝m/X _ec；(5)

Scale factor is

K _u＝k/Y _u；(6)

The opinion domain of error: { 3-2-10 12 3}; The domain of error rate is the { domain of 3-2-1 012 3} output valves { 3-2-1 012 3}.Control law is: if E1 and EC1 then U1, if E2 and EC2 then U2 ... Ep and ECp be Up then;

Its total fuzzy control rule is

R＝(E _i×CE _i) ^T1оC _i (8)

E wherein ₁=(a _1iA _Ni), EC ₁=(b _1iB _Mi), U ₁=(c _1iC _Ti) (i=1 ... p)

The reverse gelatinizing method that adopts is a weighted mean method

$u_c=\left(\underset{i=-s}{\overset{s}{\mathrm{\Σ}}}{\mathrm{ik}}_i\right)/\left(\underset{i=-s}{\overset{s}{\mathrm{\Σ}}}{u}_i\right)---\left(9\right)$

For each concrete observed value deviation E ^*With its error rate EC ^*, use quantizing factor formula separately to become the element that quantizes in the domain more respectively, again its fuzzy E that turns to ^*And EC ^*,

E wherein ^*=(e ₁E _n), EC ^*=(f ₁F _m)

Ask the accurate amount of output by formula (8).

The selection of 12 decision variables of described quantizing factor with fuzzy control, scale factor and membership function parameter is converted into heredity and the combinatorial optimization problem that ant group algorithm is suitable for, and is to be undertaken by following formula:

K _e1＝kfuzzi(1)*K _e (18)

K _c1＝kfuzzi(2)*K _c (19)

K _u1＝kfuzzi(3)*K _u (20)

To the membership function of error adjust promptly to the domain of error domain adjust into:

{ 3-kfuzzi (4) ,-2-kfuzzi (5) ,-1-kfuzzi (6), 0,1+kfuzzi (6), 2+kfuzzi (5), 3+kfuzzi (4) } to the membership function of error rate adjust promptly to the domain of error rate adjust into:

The membership function of { 3-kfuzzi (7) ,-2-kfuzzi (8) ,-1-kfuzzi (9), 0,1+kfuzzi (9), 2+kfuzzi (8), 3+kfuzzi (7) } output current adjust promptly to the domain of the membership function of output current adjust into:

{ 3-kfuzzi (10),-2-kfuzzi (11) ,-1-kfuzzi (12), 0,1+kfuzzi (12), 2+kfuzzi (11), 3+kfuzzi (10) } described plain distribution of utilizing in the genetic algorithm generation ant group algorithm of initial information, utilize the Formica fusca random search to optimize membership function and the quantizing factor and the scale factor of fuzzy controller, aforementioned kfuzzi is a chromosomal coding in the genetic algorithm, be again the coding in city in the ant group algorithm, the length of the two coding should equate, according to

n _i＜1og ₂[(x _imax-x _imin)×10 ^m]-1 (21)

n _i≥1og ₂[(x _imax-x _imin)×10 ^m+1] (22)

The kfuzzi code length

The pairing real number of each parameter can be decoded and be obtained, and then Dui Ying decoding formula is

$\mathrm{kfuzzi}\left(i\right)=x_{i\min }+(\underset{j=0}{\overset{l_i}{\mathrm{\Σ}}}{b}_j\×2^{j-1})\×\frac{x_{i\max }-x_{i\min }}{2^{l-1}}---\left(23\right)$

Wherein kfuzzi (i) is the variable quantity of the fuzzy controller adjusted, l _iThe length of the coding of parameter for this reason, b ∈ [0,1], x _ImaxAnd x _IminBe respectively the maximum and the minima of decision content.

Described concrete steps are refined as:

At first be the definition and the setting of genetic algorithm:

Step1: initialization genetic algorithm control parameter (population scale, hybridization probability, variation probability);

Step2: the genetic algorithm termination condition is set comprises: minimum genetic iteration number of times, maximum genetic iteration number of times, minimum evolution rate, subsequent iteration number of times;

Step3: treating deals with problems carries out binary coding, random initializtion population X (0)=(x ₁, x ₂... x _n).

Step4: to each individual x among the current X of colony (t) _i, its fitness F (x is calculated in decoding _i).

Step5: determine the probability that each is individual according to individual fitness and roulette wheel selection strategy, two individualities that probability is high are genetic directly to the next generation, and algorithm is carried out intersection, mutation operation according to intersecting, making a variation.

Step6: upgrade the individual adaptive value of a new generation.Repeat Step5.

Step7: select the strong individuality of adaptive capacity, put into set, gather as optimal solution.To optimizing each concentrated individuality, genetic algorithm result is set to ant group algorithm initial information element.

The improvement of ant group algorithm in the genetic-ant colony blending algorithm once more, genetic algorithm is connected mutually then, and with this blending algorithm Fuzzy Controller Parameters of adjusting:

Step8: the initial value setting of pheromone: τ _S=τ _C+ τ _G, wherein, τ _CBe a constant, i.e. minimal information element in the MMAS algorithm, τ _GIt is the pheromone value that the genetic algorithm for solving result transforms;

Step9: parameter initialization: make time t=0 and cycle-index N _Max=0, maximum cycle N is set _Cmax, m Formica fusca placed starting point.Formica fusca number and cycle-index are set;

Step10: the Formica fusca random search, after the end of once creeping, determine the actual input variable of the selected conduct of which characteristic variable, revise the taboo list index, after promptly choosing Formica fusca is moved to new element, and this element is moved the taboo of this Formica fusca individuality

In the table;

Step11: calculate fitness function and membership function, the probability that Formica fusca individual state transition probability formula calculates is selected element;

Step12: the information of utilizing training sample to provide produces the condition of fuzzy rule, the accuracy of check fuzzy model;

Step13:, change Step10, otherwise be Step12 if the Formica fusca element has not traveled through;

Step14: the pheromone concentration that the plain concentration of lastest imformation is divided the high characteristic variable of accuracy is enhanced, and next time can be selected with bigger probability when searching for;

Step15: satisfy and finish to regulate the end of adjusting.

Its characteristics of the present invention are: at first with the current-mode of fuzzy control according to the variation Real Time Control Function electricity irritation of knee joint angle, solved effectively because human muscle's complexity and the problem that is difficult to accurately control the electrical stimulation current pattern that time variation is brought, next utilizes the good optimizing characteristic of genetic-ant colony algorithm, adjust the quantizing factor of fuzzy controller in real time, scale factor and membership function parameter, the current-mode of more accurate then control functional electric stimulation, can finish ideal effect of stimulation, can prevent fatigue again, functional electric stimulation system is extensively promoted, and obtained considerable social benefit and economic benefit.

Description of drawings

Fig. 1 genetic-ant colony algorithm the convergence speed figure.

Fig. 2 genetic-ant colony blending algorithm structured flowchart of Fuzzy Controller Parameters of adjusting

Fig. 3 experiment scene figure.

The fuzzy controller that Fig. 4 genetic-ant colony algorithm adaptive optimization is adjusted is followed the trail of figure as a result.

The adjust relative error of the default down input joint angles of Fuzzy Controller Parameters control and actual output of Fig. 5 genetic-ant colony algorithm.

The specific embodiment

Merge based on genetic-ant colony fuzzy control the walk-aiding functional electric stimulation precision control method application structure as shown in Figure 2.Its workflow is: at first with the quantizing factor of fuzzy control, the selection of 12 decision variables of scale factor and membership function parameter is converted into the heredity combinatorial optimization problem suitable with ant group algorithm, and to its chromosome (initial population) of encoding and producing n individual composition at random, next sets up rational actual joint angles and the corresponding relation function of muscle model output joint angles and the parameter setting of definite ant group algorithm, make full use of the rapidity of genetic algorithm, randomness, global convergence, consequently produce plain distribution of initial information in the ant group algorithm, utilizing Formica fusca to search element at random makes its variable optimize membership function and the quantizing factor and the scale factor of fuzzy controller, and call the fuzzy controller of having adjusted, whether checking reaches goal-selling, then do not repeat above operation if having, restrain or reach predetermined index up to parameter; Final output promptly gets the decision variable of fuzzy control and the number of times of ant group operation.Computing system output under the new fuzzy controller and with the deviation of muscle model after enter next step again self study and self-adjusting.This process finally realizes the self adaptation on-line tuning of Fuzzy Controller Parameters repeatedly, and is used for the FES system.

1 design of fuzzy control

Because people's particularity, the FES field is to controller stability,, robustness, real-time be strict, design fuzzy controller equalization stable and real-time have been selected two-dimensional fuzzy controller, promptly two input variable difference reality are exported joint angles and the error e (k) and the error change rate ec (k) that expect the joint degree, its domain is FE=[-E, E], FEC=[-EC, EC], the stimulating current intensity u (k) of output, its domain is FU=[-U, U].

The quantification domain of error is

X＝{-n，-n+1，…0，…，n-1，n} (1)

The quantification domain of error rate is

X ₁＝{-m，-m+1，…0，…，m-1，m}； (2)

The quantification domain of controlled quentity controlled variable is

Y＝{-k，-k+1，…0，…，k-1，k} (3)

Quantizing factor is respectively

K _e＝n/X _e (4)

K _ec＝m/X _ec (5)

Scale factor is

K _u＝k/Y _u (6)

This patent adopts the opinion domain of error: { 3-2-1 012 3}; The domain of error rate is the { domain of 3-2-1 012 3} output valves { 3-2-1 012 3}.Control law is: if E1 and EC1 then U1, if E2 and EC2 then U2 ... Ep and ECp be Up then;

Its total fuzzy control rule is

R＝(E _i×CE _i) ^T1оC _i (8)

E wherein ₁=(a _1iA _Ni), EC ₁=(b _1iB _Mi), U ₁=(c _1iC _Ti) (i=1 ... p)

The reverse gelatinizing method that adopts is a weighted mean method

$u_c=\left(\underset{i=-s}{\overset{s}{\mathrm{\Σ}}}{\mathrm{ik}}_i\right)/\left(\underset{i=-s}{\overset{s}{\mathrm{\Σ}}}{u}_i\right)---\left(9\right)$

For each concrete observed value deviation E ^*With its error rate EC ^*, use quantizing factor formula separately to become the element that quantizes in the domain more respectively, again its fuzzy E that turns to ^*And EC ^*,

E wherein ^*=(e ₁E _n), EC ^*=(f ₁F _m)

Have formula 8 can in the hope of output accurate amount.

This patent angular error and error rate thereof are on [90 90], and domain is [3 3], then can use formula

$X=\left(\frac{2n}{b-a}(x^{\′}-\frac{a+b}{2})\right)---\left(11\right)$

The Fuzzy Controller Parameters 5.2 heredity and ant group blending algorithm are adjusted

Ant group algorithm is a kind of novel bionic Algorithm that comes from the Nature biological world, when finding the solution optimization problem with ant group algorithm, at first optimization problem is transformed in order to find the solution shortest route problem.Every Formica fusca is from initial contact N ₀₀Or N ₀₁Set out, N in proper order passes by ₁, N ₂, a wherein child node, up to destination node N _K0, N _K1Form path (N _0tN _1tN _Kt), t ∈ [0,1].A binary feasible solution can be represented in its path.Following feature is arranged during each Formica fusca visit city:

The state transformation rule: the state transformation rule that ant group algorithm uses is the rule of ratio at random that proposes based on the TSP problem, and it provides the probability that the Formica fusca k that is positioned at city i selects to move to city j,

τ wherein _Ij(i j) is (i, fitness j), η _Ij(i j) is the inverse of distance.α is the relative significance level of residual risk, the relative significance level that β is expected value.

In ant group algorithm, selection mode is

Wherein, q is for being evenly distributed on a random number on [0,1], q ₀Be the parameter on [0,1].

Overall situation update rule: ant algorithm has different update algorithm, the overall situation that ant group system adopts is upgraded principle, only allowing the Formica fusca release pheromone of globally optimal solution, is the neighborhood that mainly concentrates on the best path of being found out till the current circulation for the search that makes Formica fusca like this.

τ _ij(i，j)←(1-ρ)□τ _ij(i，j)+ρ·Δτ _ij(i，j) (14)

Wherein ρ is that information is counted volatility coefficient, L _GbBe the global optimum's path local updating information that finds so far: every Formica fusca is set up the renewal τ that the plain mark of the information of carrying out number is also arranged in the process of separating _Ij(i, j) ← (1-γ) τ _Ij(i, j)+γ Δ τ _Ij(i, j) (16) γ ∈ [0,1] wherein.

When utilizing the functional electric stimulation stimulated muscle to make it finish corresponding action, electric current can not be too drastic or should be made the muscle execution fast, the too drastic threshold value that surpasses the people of electric current, then can feel pain, sometimes be difficult to stand, and easily cause muscle fatigue, so the relevant parameter of the fuzzy controller of adjusting fast is even more important.So utilize genetic algorithm and ant group algorithm advantage to combine, improve optimizing efficiency, the relevant parameter of the fuzzy controller of adjusting fast.Utilizing the genetic-ant colony fuzzy controller is the distribution that utilizes the genetic-ant colony blending algorithm to adjust membership function in quantizing factor, scale factor and the fuzzy rule of fuzzy control.Shown in the following formula

K _e1＝kfuzzi(1)*K _e (18)

K _c1＝kfuzzi(2)*K _c (19)

K _u1＝kfuzzi(3)*K _u (20)

To the membership function of error adjust promptly to the domain of error domain adjust into

{ 3-kfuzzi (4) ,-2-kfuzzi (5) ,-1-kfuzzi (6), 0,1+kfuzzi (6), 2+kfuzzi (5), 3+kfuzzi (4) } to the membership function of error rate adjust promptly to the domain of error rate adjust into

The membership function of { 3-kfuzzi (7) ,-2-kfuzzi (8) ,-1-kfuzzi (9), 0,1+kfuzzi (9), 2+kfuzzi (8), 3+kfuzzi (7) } output current adjust promptly to the domain of the membership function of output current adjust into

{-3-kfuzzi(10)，-2-kfuzzi(11)，-1-kfuzzi(12)，0，1+kfuzzi(12)，2+kfuzzi(11)，3+kfuzzi(10)}

Wherein kfuzzi is a chromosomal coding in the genetic algorithm, is again the coding in city in the ant group algorithm, all adopts binary coding for the two is merged better, and kfuzzi is constant in the blending algorithm again, thus the length of the two coding should equate, should according to

n _i＜log ₂[(x _imax-x _imin)×10 ^m]-1 (21)

n _i≥log ₂[(x _imax-x _imin)×10 ^m+1] (22)

The kfuzzi code length

The pairing real number of each parameter can be decoded and be obtained, and then Dui Ying decoding formula is

$\mathrm{kfuzzi}\left(i\right)=x_{i\min }+(\underset{j=0}{\overset{l_i}{\mathrm{\Σ}}}{b}_j\×2^{j-1})\×\frac{x_{i\max }-x_{i\min }}{2^{l-1}}---\left(23\right)$

Wherein kfuzzi (i) is the variable quantity of the fuzzy controller adjusted, l _iThe length of the coding of parameter for this reason, b ∈ [0,1], xi _MaxAnd x _IminBe respectively the maximum and the minima of decision content.

At first be the definition and the setting of genetic algorithm:

Step1: initialization genetic algorithm control parameter (population scale, hybridization probability, variation probability).

Step2: genetic algorithm termination condition (minimum genetic iteration number of times, maximum genetic iteration number of times, minimum evolution rate, subsequent iteration number of times) is set.

Step3: treating deals with problems carries out binary coding, random initializtion population X (0)=(x ₁, x ₂... x _n).

Step4: to each individual x among the current X of colony (t) _i, its fitness F (x is calculated in decoding _i).

Step5: determine the probability that each is individual according to individual fitness and roulette wheel selection strategy, two individualities that probability is high are genetic directly to the next generation, and algorithm is carried out intersection, mutation operation according to intersecting, making a variation.

Step6: upgrade the individual adaptive value of a new generation.Repeat Step5.

Step7: select the strong individuality of adaptive capacity, put into set, gather as optimal solution.To optimizing each concentrated individuality, genetic algorithm result is set to ant group algorithm initial information element.

The improvement of ant group algorithm in the genetic-ant colony blending algorithm once more, genetic algorithm is connected mutually then, and with this blending algorithm Fuzzy Controller Parameters of adjusting:

Step8: the initial value setting of pheromone: τ _S=τ _C+ τ _G, wherein, τ _CBe a constant, promptly in the ant group MMAS algorithm

Little pheromone, τ _GIt is the pheromone value that the genetic algorithm for solving result transforms.

Step9: parameter initialization: make time t=0 and cycle-index N _Max=0, maximum cycle N is set _Cnmax, m Formica fusca placed starting point.Formica fusca number and cycle-index are set.

Step10: Formica fusca random search, after the end of once creeping, determine the actual input variable of the selected conduct of which characteristic variable, revise the taboo list index, after promptly choosing Formica fusca is moved to new element, and this element is moved in the taboo table of this Formica fusca individuality.

Step11: calculate fitness function and membership function, the probability that Formica fusca individual state transition probability formula calculates is selected element.

Step12: the information of utilizing training sample to provide produces the condition of fuzzy rule, the accuracy of check fuzzy model.

Step13:, change Step10, otherwise be Step12 if the Formica fusca element has not traveled through

Step14: the pheromone concentration that the plain concentration of lastest imformation is divided the high characteristic variable of accuracy is enhanced, and next time can be selected with bigger probability when searching for.

Step15: satisfy and finish to regulate the end of adjusting.

Wherein, heredity and the shared fitness function of ant group, muscle property complexity and people's ability to bear especially is limited, this requires to weigh three indexs of control system is stability, accuracy and rapidity, for control deviation is gone to zero, response speed and less overshoot are faster arranged, so fitness function should be the feedback deviation e (t) of optimum prediction and expected value, the rate of change ec (t) of deviation and the relation of controlled quentity controlled variable u (t), the optimum index J that chooses as parameter

$J={\∫}_0^t{w}_1{e}^2\left(t\right)+w_2{u}^2\left(t\right)+w_3{\left(\mathrm{ec}\left(t\right)\right)}^2\mathrm{dt}---\left(14\right)$

Wherein, w ₁, w ₂And w ₃Be weights, generally all get w ₁=100, w ₂=10, w ₃=1.

The appropriateness function is

F＝C/J (15)

Wherein, C=10 ⁿ(n is an integer), when individuality be fitness when differing big, n≤0; Differ hour n 〉=0.

2 experimental programs

Parastep functional electric stimulation walk help system and the PS-2137 of PASCO company protractor and Data Studio software that experimental provision adopts U.S. SIGMEDICS company to produce.The Parastep system comprises microprocessor and boost pulse generation circuit, contains six stimulation channels, battery powered.Experiment content is: utilize the FES system that the relevant muscle group of lower limb is stimulated, utilize the PS of PASCO company 2137 protractors to gather knee joint angle and the measured knee joint angle of Data Studio software records.Require the experimenter healthy, no lower limb muscles, skeleton illness, impassivity illness and severe cardiac pulmonary disease.The experimenter sits on the testboard during experiment, and stimulating electrode is fixed in the end positions of quadriceps femoris, and protractor is fixed on thigh and the shank, makes the joint motion point press close to knee joint moving point position.Shank does not loosen, keeps vertical vacant state when applying electricity irritation, and the FES experiment scene as shown in Figure 3.The electric stimulation pulse sequence adopts classical Lilly waveform, and pulse frequency is 25Hz, pulsewidth 150 μ s, and pulse current is adjustable in 0～120m scope.Can adjust stimulus intensity to change the knee joint angle that produces by stimulating by changing the pulse current size in the experiment.Before the experiment, set the knee joint angle movement locus of expectation, utilize the angular surveying meter to detect the knee joint subtended angle in real time in the experiment and change.The experimental data sample rate is 128Hz, and the data record duration is 60s.

Beneficial effect

Genetic-ant colony merges the Fuzzy Controller Parameters new algorithm adjust to be calculated the FES pulse current amplitude and adjusts, the knee joint angle that the FES effect is produced move the movement locus of expection.The fuzzy controller that Fig. 4 adjusts for genetic-ant colony algorithm adaptive optimization is followed the trail of the result.Red line represents that desired movement track, blue line are actual output joint angles among the figure.X-axis is the time, and Y-axis is the motion of knee joint angle.For more clearly observing the departure that this algorithm is adjusted fuzzy controller, adjust shown in the relative error of presetting input knee joint angle and actual knee joint angle under the fuzzy control as Fig. 5 genetic-ant colony blending algorithm, then error can reach accurate control all within 3% as can be seen.

Purport of the present invention is the precision control method that proposes a kind of new FES, by the genetic-ant colony blending algorithm Fuzzy Controller Parameters of adjusting, the accurately stable then current intensity of controlling the FES system in real time effectively.This invention can improve FES system real time, accuracy and stability effectively, and obtains considerable social benefit and economic benefit.Optimum implementation intends adopting patent transfer, technological cooperation or product development.

Claims (4)

1. the walk help electricity irritation precision control method based on genetic-ant colony fusion fuzzy controller is characterized in that, comprises the following steps:

At first the selection of 12 decision variable kfuzz of quantizing factor, scale factor and the membership function parameter of fuzzy control is converted into the combinatorial optimization problem that heredity and ant group algorithm are suitable for, and these 12 kfuzz are carried out binary coding, produce n the individual initial population P (0) that forms afterwards at random, wherein kfuzz is the vector of n * 12;

Next sets up rational actual joint angles and the corresponding relation object function of muscle model output joint angles and the parameter setting of definite ant group algorithm, the initial information element that utilizes genetic algorithm to produce in the ant group algorithm distributes, utilize the Formica fusca random search to optimize membership function and the quantizing factor and the scale factor of fuzzy controller, and call the fuzzy controller of having adjusted, whether checking reaches goal-selling, do not repeat above operation if having, restrain or reach predetermined index up to parameter, the number of times of the decision variable of output fuzzy control and ant group operation;

According to the decision variable of aforementioned output fuzzy control under fuzzy controller computing system output and with the deviation of muscle model after enter next step again self study and self-adjusting, this process repeatedly, the final self adaptation on-line tuning of realizing Fuzzy Controller Parameters, and be used for the FES system.

2. a kind of walk help electricity irritation precision control method that merges fuzzy controller based on genetic-ant colony according to claim 1, it is characterized in that, described fuzzy controller is a two-dimensional fuzzy controller, two actual respectively error e (k) and error change rate ec (k) that export joint angles and expectation joint degree of input variable, and domain is FE=[-E, E], FEC=[-EC, EC], the stimulating current intensity u (k) of output, its domain is FU=[-U, U];

The quantification domain of error is X={-n ,-n+1 ... 0 ..., n-1, n}; (1)

The quantification domain of error rate is X ₁=m ,-m+1 ... 0 ..., m-1, m}; (2)

The quantification domain of controlled quentity controlled variable is Y={-k ,-k+1 ... 0 ..., k-1, k}; (3)

Quantizing factor is respectively

K _e＝n/X _e； (4)

K _ec＝m/X _ex； (5)

Scale factor is

K _u＝k/Y _u； (6)

The opinion domain of error: { 3-2-1 012 3}; The domain of error rate is the { domain of 3-2-1 012 3} output valves { 3-2-1 012 3}.Control law is: if E1 and EC1 then U1, if E2 and EC2 then U2 ... Ep and ECp be Up then;

Its total fuzzy control rule is

R＝(E _i×CE _i) ^T1оC _i (8)

E wherein ₁=(a _1iA _Ni), EC ₁=(b _1iB _Mi), U ₁=(c _1iC _Ti) (i=1 ... p)

The reverse gelatinizing method that adopts is a weighted mean method

$u_c=\left(\underset{i=-s}{\overset{s}{\mathrm{\Σ}}}{\mathrm{ik}}_i\right)/\left(\underset{i=-s}{\overset{s}{\mathrm{\Σ}}}{u}_i\right)---\left(9\right)$

For each concrete observed value deviation E ^*With its error rate EC ^*, use quantizing factor formula separately to become the element that quantizes in the domain more respectively, again its fuzzy E that turns to ^*And EC ^*,

E wherein ^*=(e ₁E _n), EC ^*=(f ₁F _m)

Ask the accurate amount of output by formula (8).

3. a kind of walk help electricity irritation precision control method that merges fuzzy controller based on genetic-ant colony according to claim 1, it is characterized in that, the selection of 12 decision variables of described quantizing factor with fuzzy control, scale factor and membership function parameter is converted into heredity and the combinatorial optimization problem that ant group algorithm is suitable for, and is to be undertaken by following formula:

K _e1＝kfuzzi(1)*K _e (18)

K _c1＝kfuzzi(2)*K _c (19)

K _u1＝kfuzzi(3)*K _u (20)

To the membership function of error adjust promptly to the domain of error domain adjust into:

{-3-kfuzzi(4)，-2-kfuzzi(5)，-1-kfuzzi(6)，0，1+kfuzzi(6)，2+kfuzzi(5)，3+kfuzzi(4)}

To the membership function of error rate adjust promptly to the domain of error rate adjust into:

{-3-kfuzzi(7)，-2-kfuzzi(8)，-1-kfuzzi(9)，0，1+kfuzzi(9)，2+kfuzzi(8)，3+kfuzzi(7)}

The membership function of output current adjust promptly to the domain of the membership function of output current adjust into:

{-3-kfuzzi(10)，-2-kfuzzi(11)，-1-kfuzzi(12)，0，1+kfuzzi(12)，2+kfuzzi(11)，3+kfuzzi(10)}

The described initial information element that utilizes genetic algorithm to produce in the ant group algorithm distributes, and utilizes the optimization of Formica fusca random search fuzzy

The membership function of controller and quantizing factor and scale factor, aforementioned kfuzzi are chromosomal coding in the genetic algorithm,

Be again the coding in city in the ant group algorithm, the length of the two coding should equate, according to

n _i＜log ₂[(x _imax-x _imin)×10 ^m]-1 (21)

n _i≥log ₂[(x _imax-x _imin)×10 ^m+1] (22)

The kfuzzi code length

The pairing real number of each parameter can be decoded and be obtained, and then Dui Ying decoding formula is

$\mathrm{kfuzzi}\left(i\right)=x_{i\min }+(\underset{j=0}{\overset{l_i}{\mathrm{\Σ}}}{b}_j\×2^{j-1})\×\frac{x_{i\max }-x_{i\min }}{2^{l-1}}---\left(23\right)$

Wherein kfuzzi (i) is the variable quantity of the fuzzy controller adjusted, l _iThe length of the coding of parameter for this reason, b ∈ [0,1], x _ImaxAnd x _IminBe respectively the maximum and the minima of decision content.

4. a kind of walk help electricity irritation precision control method based on genetic-ant colony fusion fuzzy controller according to claim 1 is characterized in that described step is refined as:

At first be the definition and the setting of genetic algorithm:

Step1: initialization genetic algorithm control parameter (population scale, hybridization probability, variation probability);

Step2: the genetic algorithm termination condition is set comprises: minimum genetic iteration number of times, maximum genetic iteration number of times, minimum evolution rate, subsequent iteration number of times;

Step3: treating deals with problems carries out binary coding, random initializtion population X (0)=(x ₁, x ₂... x _n).

Step4: to each individual x among the current X of colony (t) _i, its fitness F (x is calculated in decoding _i).

Step5: determine the probability that each is individual according to individual fitness and roulette wheel selection strategy, two individualities that probability is high are genetic directly to the next generation, and algorithm is carried out intersection, mutation operation according to intersecting, making a variation.

Step6: upgrade the individual adaptive value of a new generation.Repeat Step5.

Step7: select the strong individuality of adaptive capacity, put into set, gather as optimal solution.To optimizing each concentrated individuality, genetic algorithm result is set to ant group algorithm initial information element.

The improvement of ant group algorithm in the genetic-ant colony blending algorithm once more, genetic algorithm is connected mutually then, and with this blending algorithm Fuzzy Controller Parameters of adjusting:

Step8: the initial value setting of pheromone: τ _S=τ _C+ τ _G, wherein, τ _CBe a constant, i.e. minimal information element in the MMAS algorithm, τ _GIt is the pheromone value that the genetic algorithm for solving result transforms;

Step9: parameter initialization: make time t=0 and cycle-index N _Max=0, maximum cycle N is set _Cmax, m Formica fusca placed starting point.Formica fusca number and cycle-index are set;

Step10: Formica fusca random search, after the end of once creeping, determine the actual input variable of the selected conduct of which characteristic variable, revise the taboo list index, after promptly choosing Formica fusca is moved to new element, and this element is moved in the taboo table of this Formica fusca individuality;

Step11: calculate fitness function and membership function, the probability that Formica fusca individual state transition probability formula calculates is selected element;

Step12: the information of utilizing training sample to provide produces the condition of fuzzy rule, the accuracy of check fuzzy model;

Step13:, change Step10, otherwise be Step12 if the Formica fusca element has not traveled through;

Step14: the pheromone concentration that the plain concentration of lastest imformation is divided the high characteristic variable of accuracy is enhanced, and next time can be selected with bigger probability when searching for;

Step15: satisfy and finish to regulate the end of adjusting.

Images