CN104714408B - The acquisition methods and device of lag-lead-corrector structural parameters - Google Patents

Abstract

The present invention provides a kind of acquisition methods and device of lag-lead-corrector structural parameters, and the method includes：A) the transmission function structure and the desired frequency domain characteristic of system of automatic control system controlled device and lag-lead-corrector are determined；B) ssystem transfer function structure and desired frequency domain characteristic for determined by, construct corresponding neutral net；C) multiple data samples of the system are gathered；D) data sample for being collected is input in neutral net, the neutral net is trained；E) structural parameters of the corrector are obtained.During so that obtaining the structural parameters of lag-lead-corrector using the method and device, desired frequency domain performance parameter γ, ω of system after structural parameter K, α, β and the introducing lag-lead-corrector of user input systems controlled device is needed only, the structural parameters of the corrector are calculated rapidly can, so as to enormously simplify the acquisition process of lag-lead-corrector structural parameters, therefore, it can shorten the design time of lag-lead-corrector.

Description

The acquisition methods and device of lag-lead-corrector structural parameters

Technical field

The invention belongs to automation field, and in particular to a kind of lag-lead-corrector structure based on artificial intelligence is joined Several acquisition methods and device.

Background technology

Automatically control and refer to the working condition that controlled device (such as motor, liquid level control system, lathe etc.) is made using control device Run by predetermined rule.Fig. 1 is block diagram, shows a naive model of automatic control system.In the automatic control shown in Fig. 1 In system processed, during beginning, reference signal input control device, control device are entered to controlled device according to the reference signal of input Row control, makes controlled device produce output signal, and the output signal Jing feedback element feeds back to control device input, and with ginseng Examine signal to be compared, then, control device adjusts its control to controlled device further according to comparative result, under so circulating Go, finally make controlled device produce the output signal for matching with reference signal or being consistent.Fig. 2 is block diagram, in showing Fig. 1 The frequency-domain structure of automatic control system model.As shown in Fig. 2 from the point of view of frequency domain, controlled device is G_p(s), and feedback element is H S (), reference signal are R (s), output signal is C (s).

The index for weighing automatic control system performance includes stability, steady-state behaviour index (such as open-loop gain K etc.), dynamic Performance indications (such as phase margin, shearing frequency etc.).In general, the systematic function being only made up of controlled device is poor, and Under many circumstances, the parameter for adjusting system controlled device can not make the property indices of system reach requirement.Now, lead to Some attachment devices are introduced in systems often, to change the performance of system, are allowed to meet engine request.These attachment devices are referred to as Corrector.

The type of corrector has various, and the conventional corrector of a class is lag-lead-corrector.Fig. 3 is block diagram, is illustrated Introduce the frequency-domain structure of the automatic control system after lag-lead-corrector.As shown in figure 3, lag-lead-corrector G_c(s) It is connected in the forward path of system.The lag-lead-corrector of series connection has the characteristics of correction or lag and anticipatory control concurrently, its profit The stable state accuracy of system is improved with the amplitude attenuation feature of the lagging portion in frequency characteristic, using in frequency characteristic The phase angular advance characteristic of look-ahead portion improve the Phase margin of system, it is adaptable to need to improve stable state and dynamic property simultaneously is The correction of system.

Specifically, for the common controlled device of a class, its transmission function structure can be expressed as：

Wherein, K, α, β can be considered as the structural parameters of the controlled device.And the transmission letter of the lag-lead-corrector for introducing Table structure can be expressed as：

Wherein, T_a、T_b、αT_a、For the structural parameters of the lag-lead-corrector.Introduce system after lag-lead-corrector Desired frequency domain performance parameter then include phase margin γ and shearing frequency ω.

In the acquisition process of the structural parameters of existing lag-lead-corrector, principle step is generally utilized, according to Strict mathematical derivation (such as classical frequency-domain analysiss and method for designing) is from the structural parameter K of controlled device, α, β and introduces stagnant Afterwards after Lead-Corrector desired frequency domain performance parameter γ, ω of system obtaining the structural parameters T of corrector_a、T_b、αT_a、

Using principle step according to strict mathematical derivation obtaining the mistake of the structural parameters of lag-lead-corrector Cheng Zhong, is difficult to calculate due to unskilled, counting loss, high-order, the numeral excessively many reasons such as complexity, can cause delayed advanced school The acquisition of the structural parameters of positive device is excessively difficult for some designers, thus is easily caused lag-lead-corrector and sets Delay in meter and wrong appearance.

The content of the invention

The present invention is made to solve above-mentioned technical problem present in prior art, its object is to provide a kind of The acquisition methods and device of lag-lead-corrector structural parameters so that obtain lag-lead-corrector using the method and device Structural parameters when, only need the structural parameter K of user input controlled device, α, β and introduce the system phase after lag-lead-corrector Frequency domain performance parameter γ, ω of prestige, so that it may calculate rapidly the structural parameters of the lag-lead-corrector, so as to avoid complexity Mathematical derivation.

To achieve these goals, in one aspect of the invention, there is provided a kind of lag-lead-corrector structural parameters Acquisition methods, the method include：

A) determine transmission function structure G of automatic control system controlled device_pS () is：

Wherein, K, α, β are the structural parameters of the automatic control system controlled device；Determine the transmission of lag-lead-corrector Function structure G_cS () is：

Wherein, T_a、T_b、αT_a、For the structural parameters of the lag-lead-corrector；And determine the introducing delayed advanced school After positive device, the desired frequency domain performance parameter of system is phase margin γ and shearing frequency ω；

B) lag-lead-corrector determined according to the automatic control system controlled device determined by (1) formula, by (2) formula with And desired frequency domain performance parameter, corresponding neutral net is constructed, the neutral net includes input layer, hidden layer and output layer, Wherein, the input of input layer is structural parameter K, α, β and the desired frequency domain of the automatic control system controlled device Energy parameter γ, ω, exports the structural parameters T that node layer is output as the lag-lead-corrector_a、T_b、αT_a、And the K, α, β, γ, ω and the T_a、T_b、αT_a、Contact as follows by hidden layer node：

Wherein, k=1,2,3,4, O₁=T_a, O₂=T_b,O₃=α T_a, O₄=T_b/ α, 1≤i≤n, n=5, x₁=K, x₂=α, x₃=β, x₄=γ, x₅=ω, 1≤j≤l, l are node in hidden layer, w1_ijRepresent the i-th node of input layer to hidden layer jth section The weights of point, b1_jRepresent input layer to the threshold value of j-th node of hidden layer, w2_jkRepresent hidden layer jth node to output layer kth The weights of node, b2_kHidden layer is represented to the threshold value of output layer kth node, f is tansig functions；

C) multiple existing data samples are gathered, each existing data sample includes that the automatic control system is controlled right The structural parameter K of elephant, α, β；The structural parameters T of the lag-lead-corrector of introducing_a、T_b、αT_a、And to introduce this delayed super Frequency domain performance parameter γ, ω of system after front corrector；

D) data sample for being collected is input in the neutral net expressed by above-mentioned (3) formula, the neutral net is entered Row training；

E), in the neutral net that will be trained described in K, α, β, γ, ω value input outside the data with existing sample, obtain Take the structural parameters T of lag-lead-corrector corresponding with K, α, β, γ, the ω_a、T_b、αT_a、

Preferably, during being trained to the neutral net, the nerve can be obtained using heuristic algorithm The nodes l of network hidden layer.

Furthermore it is preferred that the step of being trained to the neutral net can include：

The first step：The neutral net is initialized, w1, w2, b1 and b2 initial value is arbitrarily given, wherein, w1=[w1_ij], W2=[w2_jk], b1=[b1_j], b2=[b2_k]；

Second step：K, α, β, γ, the ω's being input in the plurality of data sample untapped data sample Value；

3rd step：According to the value of K, α, β, γ, ω of input, the output valve of the neutral net is calculated forward；

4th step：Calculate the output valve and the T in the untapped data sample_a、T_b、αT_a、Between error, and sentence Whether the error of breaking is less than predetermined value, if it is less, the 7th step is gone to, if it is not, then performing the 5th step；

5th step：The partial gradient of neutral net described in backwards calculation；

6th step：According to calculating partial gradient amendment w1, w2, b1, b2 value, and the 3rd step is performed to the 4th step；

7th step：Judge whether to train the neutral net using all data samples, if the judgment is No, Second step is then returned, the training of the neutral net if the judgment is Yes, is then completed.

In another aspect of this invention, there is provided a kind of acquisition device of lag-lead-corrector structural parameters, which includes：Pass Delivery function structure determination unit, neutral net unit, data sample storehouse, neural metwork training unit, lag-lead-corrector knot Structure parameter acquiring unit, wherein,

The transmission function structure determination unit determines transmission function structure G of automatic control system controlled device_p(s) For：

Wherein, K, α, β are the structural parameters of the automatic control system controlled device；Determine the transmission of lag-lead-corrector Function structure G_cS () is：

Wherein, T_a、T_b、αT_a、For the structural parameters of the lag-lead-corrector；And determine the introducing delayed advanced school After positive device, the desired frequency domain performance parameter of system is phase margin γ and shearing frequency ω；

The neutral net unit according to the automatic control system controlled device determined by (1) formula, by (2) formula determine it is stagnant Lead-Corrector and desired frequency domain performance parameter afterwards, construct corresponding neutral net, and the neutral net includes input layer, hidden Containing layer and output layer, wherein, the input of input layer is the structural parameter K of the automatic control system controlled device, α, β and Desired frequency domain performance parameter γ, ω, exports the structural parameters T that node layer is output as the lag-lead-corrector_a、T_b、αT_a、And K, α, β, γ, the ω and the T_a、T_b、αT_a、Contact as follows by hidden layer node：

Wherein, k=1,2,3,4, O₁=T_a, O₂=T_b,O₃=α T_a, O₄=T_b/ α, 1≤i≤n, n=5, x₁=K, x₂=α, x₃=β, x₄=γ, x₅=ω, 1≤j≤l, l are node in hidden layer, w1_ijRepresent the i-th node of input layer to hidden layer jth section The weights of point, b1_jRepresent input layer to the threshold value of j-th node of hidden layer, w2_jkRepresent hidden layer jth node to output layer kth The weights of node, b2_kHidden layer is represented to the threshold value of output layer kth node, f is tansig functions；

The data sample storehouse gathers multiple existing data samples, and each existing data sample includes the automatic control The structural parameter K of system controlled device processed, α, β；The structural parameters T of the lag-lead-corrector of introducing_a、T_b、αT_a、And Introduce frequency domain performance parameter γ, ω of system after the lag-lead-corrector；

The data sample for being collected is input into the neutral net expressed by above-mentioned (3) formula by the neural metwork training unit In, the neutral net is trained；

The lag-lead-corrector structural parameters acquiring unit is by K, α, β, γ, the ω outside the data with existing sample In the neutral net trained described in value input, the structure ginseng of lag-lead-corrector corresponding with K, α, β, γ, the ω is obtained Number T_a、T_b、αT_a、

Given specific embodiment can see that the present invention utilizes neural network algorithm by above description and below To obtain the coefficient T in the transmission function structure of the structural parameters of lag-lead-corrector, i.e. lag-lead-corrector_a、T_b、α T_a、The principle for abandoning complexity is calculated, and only needs structural parameter K, α, β and the introducing of user input systems controlled device delayed Desired frequency domain performance parameter γ, ω of system after Lead-Corrector, so that it may calculate rapidly the structure of the lag-lead-corrector Parameter T_a、T_b、αT_a、So as to enormously simplify the process for obtaining lag-lead-corrector structural parameters, therefore, it can shorten The design time of lag-lead-corrector.

Description of the drawings

Fig. 1 is block diagram, shows a naive model of automatic control system；

Fig. 2 is block diagram, shows the frequency-domain structure of the automatic control system model in Fig. 1；

Fig. 3 is block diagram, shows the frequency-domain structure of the automatic control system after introducing lag-lead-corrector；

Fig. 4 is flow chart, shows obtaining for the lag-lead-corrector structural parameters described in one embodiment of the present of invention Take method；

Fig. 5 is schematic diagram, shows the neutral net described in one embodiment of the present of invention；

Fig. 6 is flow chart, shows the method being trained to neutral net described in one embodiment of the present of invention；

Fig. 7 is curve chart, show the present invention an example in introduce lag-lead-corrector after system step Response curve；

Fig. 8 is curve chart, shows the pulse respond of the system in Fig. 7 examples；

Fig. 9 is curve chart, shows the amplitude-frequency Bode diagram and phase frequency Bode diagram of system in Fig. 7 examples；

Figure 10 is block diagram, shows obtaining for the lag-lead-corrector structural parameters described in one embodiment of the present of invention Take device.

Specific embodiment

In the following description, for purposes of illustration, in order to provide the comprehensive understanding to one or more embodiments, explain Many details are stated.It may be evident, however, that these embodiments can also be realized in the case where not having these details. In other examples, for the ease of describing one or more embodiments, known structure and equipment are illustrated in block form an.

Fig. 4 is flow chart, shows obtaining for the lag-lead-corrector structural parameters described in one embodiment of the present of invention Take method.As shown in figure 1, the acquisition methods of lag-lead-corrector structural parameters of the present invention comprise the steps：

First, in step slo, determine transmission function structure G of automatic control system controlled device_pS () is：

Wherein, K, α, β are the structural parameters of the automatic control system controlled device；Determine the transmission of lag-lead-corrector Function structure G_cS () is：

Wherein, T_a、T_b、αT_a、For the structural parameters of the lag-lead-corrector；And determine the introducing delayed advanced school After positive device, the desired frequency domain performance parameter of system is phase margin γ and shearing frequency ω.

Then, in step S20, determine according to the automatic control system controlled device determined by (1) formula, by (2) formula Lag-lead-corrector and desired frequency domain performance parameter, construct corresponding neutral net.Fig. 5 is schematic diagram, shows this The structure of the neutral net described in one embodiment of invention.As shown in figure 5, the neutral net in the present embodiment includes input Layer, hidden layer and output layer, wherein, the input of input layer is the structural parameter K of the automatic control system controlled device, α, β and desired frequency domain performance parameter γ, ω, export the structural parameters T that node layer is output as the lag-lead-corrector_a、 T_b、αT_a、And K, α, β, γ, the ω and the T_a、T_b、αT_a、Contact as follows by hidden layer node：

Wherein, k=1,2,3,4, O₁=T_a, O₂=T_b,O₃=α T_a, O₄=T_b/ α, 1≤i≤n, n=5, x₁=K, x₂=α, x₃=β, x₄=γ, x₅=ω, 1≤j≤l, l are node in hidden layer, w1_ijRepresent the i-th node of input layer to hidden layer jth section The weights of point, b1_jRepresent input layer to the threshold value of j-th node of hidden layer, w2_jkRepresent hidden layer jth node to output layer kth The weights of node, b2_kHidden layer is represented to the threshold value of output layer kth node, f is tansig functions.

Subsequently, in step s 30, gather multiple existing data samples, each existing data sample include it is described from The structural parameter K of autocontrol system controlled device, α, β；The structural parameters T of the lag-lead-corrector of introducing_a、T_b、αT_a、 And introduce frequency domain performance parameter γ, ω of system after the lag-lead-corrector.Table 1 shows existing 4 groups for collecting K、α、β、γ、ω、T_a、T_b、αT_a、Value.In practice, more data samples can also be gathered.

Table 1

Then, in step s 40, the data sample for being collected is input in the neutral net expressed by above-mentioned (3) formula, The neutral net is trained.

Fig. 6 is flow chart, shows the method being trained to neutral net described in one embodiment of the present of invention.Such as Shown in Fig. 6, according to one embodiment of present invention, the step of being trained to the neutral net can include：

The first step, in step S41, initializes the neutral net, arbitrarily gives w1, w2, b1 and b2 initial value, its In, w1=[w1_ij], w2=[w2_jk], b1=[b1_j], b2=[b2_k]。

Second step, in step S42, K in a untapped data sample being input in the plurality of data sample, The value of α, β, γ, ω.

3rd step, in step S43, according to the value of K, α, β, γ, ω of input, calculates forward the defeated of the neutral net Go out value.

4th step, in step S44, calculates the output valve and the T in the untapped data sample_a、T_b、αT_a、It Between error, and judge the error whether less than predetermined value, if it is less, go to the 7th step (S47 described later), such as Fruit is not less than, then perform the 5th step, i.e. step S45.

5th step, in step S45, the partial gradient of neutral net described in backwards calculation.

6th step, in step S46, according to calculating partial gradient amendment w1, w2, b1, b2 value, and performs the 3rd step extremely 4th step (i.e. step S43-S44, actually iterative process).

7th step, in step S47, judges whether to train the neutral net using all data samples, If the judgment is No, then second step (S42) is returned, if the judgment is Yes, then completes the training of the neutral net.

Fig. 4 is returned, finally, in step s 50, by K, α, β, γ, ω value input institute outside the data with existing sample State in the neutral net for training, obtain the structural parameters T of lag-lead-corrector corresponding with K, α, β, γ, the ω_a、T_b、α T_a、

Preferably, during being trained to the neutral net, the nerve can be obtained using heuristic algorithm The nodes l of network hidden layer.In neutral net design, node in hidden layer decides the quality of neutral net performance, is Difficult point in neutral net design, here using heuristic algorithm determining the nodes of hidden layer.Rule of thumb can also come really Determine the nodes of hidden layer.

An example of the present invention is detailed below.

For lag-lead-corrector involved in the present invention, neutral net hidden layer node is determined according to said method Number is 12, and neural network parameter w1, b1, w2, b2 are respectively (represent in the matrix form)：

W2=

Automatic control system involved by this example is rotor winding machine system, and the system requirements after correction has following property Energy：Static velocity error coefficient K_v≥15s^-1, Phase margin γ >=60 °, adjustment time t_s≤3s.According to the rotor after correction around The design requirement of line machine system, the input quantity of the neutral net for obtaining is：X1=K=15, x2=α=0.2, x3=β=0.1, X4=γ=60, x5=ω=2.4.

The output of neutral net obtained by above-mentioned steps is：T_a=1.1520, T_b=3.4625, α T_a= 66.1270, T_bThe transmission function of/α=0.0332, i.e. lag-lead-corrector is：G_c(s)=(1+1.1520s) (1+ 3.4625s)/(1+66.1270s)(1+0.0332s)。

Fig. 7-Fig. 9 respectively illustrate introduce the step response curve of system after lag-lead-corrector, pulse respond, Amplitude-frequency Bode diagram and phase frequency Bode diagram (wherein, γ=111.6778, ω=1.5279).

The acquisition methods of lag-lead-corrector structural parameters of the present invention are described above with reference to Fig. 1-Fig. 9.This The acquisition methods of the described lag-lead-corrector structural parameters of invention, can be realized using software, it would however also be possible to employ hardware reality It is existing, or realized by the way of software and hardware combination.

Figure 10 is block diagram, shows obtaining for the lag-lead-corrector structural parameters described in one embodiment of the present of invention Take device.As shown in Figure 10, the acquisition device 1000 of lag-lead-corrector structural parameters of the present invention includes：Transmission letter It is table structure determining unit 100, neutral net unit 200, data sample storehouse 300, neural metwork training unit 400, delayed advanced Corrector structural parameters acquiring unit 500, wherein,

Transmission function structure determination unit 100 determines transmission function structure G of automatic control system controlled device_pS () is：

Wherein, K, α, β are the structural parameters of the automatic control system controlled device；Determine the transmission of lag-lead-corrector Function structure G_cS () is：

Wherein, T_a、T_b、αT_a、For the structural parameters of the lag-lead-corrector；And determine the introducing delayed advanced school After positive device, the desired frequency domain performance parameter of system is phase margin γ and shearing frequency ω；

Neutral net unit 200 according to the automatic control system controlled device determined by (1) formula, by (2) formula determine it is stagnant Lead-Corrector and desired frequency domain performance parameter afterwards, construct corresponding neutral net, and the neutral net includes input layer, hidden Containing layer and output layer, wherein, the input of input layer is the structural parameter K of the automatic control system controlled device, α, β and Desired frequency domain performance parameter γ, ω, exports the structural parameters T that node layer is output as the lag-lead-corrector_a、T_b、αT_a、And K, α, β, γ, the ω and the T_a、T_b、αT_a、Contact as follows by hidden layer node：

Wherein, k=1,2,3,4, O₁=T_a, O₂=T_b,O₃=α T_a, O₄=T_b/ α, 1≤i≤n, n=5, x₁=K, x₂=α, x₃=β, x₄=γ, x₅=ω, 1≤j≤l, l are node in hidden layer, w1_ijRepresent the i-th node of input layer to hidden layer jth section The weights of point, b1_jRepresent input layer to the threshold value of j-th node of hidden layer, w2_jkRepresent hidden layer jth node to output layer kth The weights of node, b2_kHidden layer is represented to the threshold value of output layer kth node, f is tansig functions；

Data sample storehouse 300 gathers multiple existing data samples, and each existing data sample includes the automatic control The structural parameter K of system controlled device processed, α, β；The structural parameters T of the lag-lead-corrector of introducing_a、T_b、αT_a、And Introduce frequency domain performance parameter γ, ω of system after the lag-lead-corrector；

The data sample for being collected is input into the neutral net expressed by above-mentioned (3) formula by neural metwork training unit 400 In, the neutral net is trained；

Lag-lead-corrector structural parameters acquiring unit 500 is by K, α, β, γ, the ω outside the data with existing sample In the neutral net trained described in value input, the structure ginseng of lag-lead-corrector corresponding with K, α, β, γ, the ω is obtained Number T_a、T_b、αT_a、

Although disclosing the present invention, those skilled in the art already in connection with the preferred embodiment being shown specifically and describe It should be appreciated that the acquisition methods and device of the lag-lead-corrector structural parameters proposed for the invention described above, can be with Various improvement are made on the basis of without departing from present invention.Therefore, protection scope of the present invention should be by appended right The content of claim determines.

Claims (4)

1. a kind of acquisition methods of lag-lead-corrector structural parameters, including：

A) determine transmission function structure G of automatic control system controlled device_pS () is：

$G_P\left(s\right)=\frac{K}{s(\mathrm{\αs}+1)(\mathrm{\βs}+1)}---\left(1\right)$

Wherein, K, α, β are the structural parameters of the automatic control system controlled device；Determine the transmission function of lag-lead-corrector Structure G_cS () is：

$G_c\left(s\right)=\frac{(T_{a}s+1)(T_{b}s+1)}{(\mathrm{\α}{T}_{a}s+1)(\frac{T_b}{\mathrm{\α}}s+1)}---\left(2\right)$

Wherein, T_a、T_b、αT_a、For the structural parameters of the lag-lead-corrector；And determine and introduce the lag-lead-corrector The desired frequency domain performance parameter of system is phase margin γ and shearing frequency ω afterwards；

B) according to by (1) formula automatic control system controlled device for determining, the lag-lead-corrector determined by (2) formula and phase The frequency domain performance parameter of prestige, constructs corresponding neutral net, and the neutral net includes input layer, hidden layer and output layer, wherein, The input of input layer is structural parameter K, α, β and the desired frequency domain performance parameter of the automatic control system controlled device γ, ω, export the structural parameters T that node layer is output as the lag-lead-corrector_a、T_b、αT_a、And the K, α, β, γ, ω and the T_a、T_b、αT_a、Contact as follows by hidden layer node：

$O_k=\underset{j=1}{\overset{l}{\mathrm{\Σ}}}\left(f(\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{w1}_{\mathrm{ij}}{x}_i-{b1}_j)\right){w2}_{\mathrm{jk}}-{b2}_k---\left(3\right)$

Wherein, k=1,2,3,4, O₁=T_a, O₂=T_b,O₃=α T_a, O₄=T_b/ α, 1≤i≤n, n=5, x₁=K, x₂=α, x₃= β, x₄=γ, x₅=ω, 1≤j≤l, l are node in hidden layer, w1_ijRepresent the i-th node of input layer to hidden layer jth node Weights, b1_jRepresent input layer to the threshold value of j-th node of hidden layer, w2_jkRepresent hidden layer jth node to output layer kth node Weights, b2_kHidden layer is represented to the threshold value of output layer kth node, f is tansig functions；

C) multiple existing data samples are gathered, each existing data sample includes the automatic control system controlled device Structural parameter K, α, β；The structural parameters T of the lag-lead-corrector of introducing_a、T_b、αT_a、And introduce the delayed advanced school Frequency domain performance parameter γ, ω of system after positive device；

D) data sample for being collected is input in the neutral net expressed by above-mentioned (3) formula, the neutral net is instructed Practice；

E) in K, α, β, γ, ω value input neutral net for training outside the data with existing sample, will obtain and The structural parameters T of the corresponding lag-lead-corrector of K, α, β, γ, the ω_a、T_b、αT_a、

2. acquisition methods of lag-lead-corrector structural parameters according to claim 1, wherein, to the nerve net During network is trained, the nodes l of the neutral net hidden layer is obtained using heuristic algorithm.

3. acquisition methods of lag-lead-corrector structural parameters according to claim 1, wherein, to the neutral net The step of being trained includes：

The first step：The neutral net is initialized, w1, w2, b1 and b2 initial value is arbitrarily given, wherein, w1=[w1_ij], w2= [w2_jk], b1=[b1_j], b2=[b2_k]；

Second step：The value of K, α, β, γ, ω for being input in the plurality of data sample untapped data sample；

3rd step：According to the value of K, α, β, γ, ω of input, the output valve of the neutral net is calculated forward；

4th step：Calculate the output valve and the T in the untapped data sample_a、T_b、αT_a、Between error, and judge should Whether error is less than predetermined value, if it is less, the 7th step is gone to, if it is not, then performing the 5th step；

5th step：The partial gradient of neutral net described in backwards calculation；

6th step：According to calculating partial gradient amendment w1, w2, b1, b2 value, and the 3rd step is performed to the 4th step；

7th step：Judge whether to train the neutral net using all data samples, if the judgment is No, then return Second step is returned, the training of the neutral net if the judgment is Yes, is then completed.

4. a kind of acquisition device of lag-lead-corrector structural parameters, including：Transmission function structure determination unit, neutral net Unit, data sample storehouse, neural metwork training unit, lag-lead-corrector structural parameters acquiring unit, wherein,

The transmission function structure determination unit determines transmission function structure G of automatic control system controlled device_pS () is：

$G_P\left(s\right)=\frac{K}{s(\mathrm{\αs}+1)(\mathrm{\βs}+1)}---\left(1\right)$

Wherein, K, α, β are the structural parameters of the automatic control system controlled device；Determine the transmission function of lag-lead-corrector Structure G_cS () is：

$G_c\left(s\right)=\frac{(T_{a}s+1)(T_{b}s+1)}{(\mathrm{\α}{T}_{a}s+1)(\frac{T_b}{\mathrm{\α}}s+1)}---\left(2\right)$

Wherein, T_a、T_b、αT_a、For the structural parameters of the lag-lead-corrector；And determine and introduce the lag-lead-corrector The desired frequency domain performance parameter of system is phase margin γ and shearing frequency ω afterwards；

The neutral net unit according to the automatic control system controlled device determined by (1) formula, by (2) formula determine it is delayed super Front corrector and desired frequency domain performance parameter, construct corresponding neutral net, and the neutral net includes input layer, hidden layer And output layer, wherein, the input of input layer is structural parameter K, α, β and the expectation of the automatic control system controlled device Frequency domain performance parameter γ, ω, export node layer and be output as the structural parameters T of the lag-lead-corrector_a、T_b、αT_a、 And K, α, β, γ, the ω and the T_a、T_b、αT_a、Contact as follows by hidden layer node：

$O_k=\underset{j=1}{\overset{l}{\mathrm{\Σ}}}\left(f(\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{w1}_{\mathrm{ij}}{x}_i-{b1}_j)\right){w2}_{\mathrm{jk}}-{b2}_k---\left(3\right)$

Wherein, k=1,2,3,4, O₁=T_a, O₂=T_b,O₃=α T_a, O₄=T_b/ α, 1≤i≤n, n=5, x₁=K, x₂=α, x₃= β, x₄=γ, x₅=ω, 1≤j≤l, l are node in hidden layer, w1_ijRepresent the i-th node of input layer to hidden layer jth node Weights, b1_jRepresent input layer to the threshold value of j-th node of hidden layer, w2_jkRepresent hidden layer jth node to output layer kth node Weights, b2_kHidden layer is represented to the threshold value of output layer kth node, f is tansig functions；

The data sample storehouse gathers multiple existing data samples, and each existing data sample includes that described automatically controlling is The structural parameter K of system controlled device, α, β；The structural parameters T of the lag-lead-corrector of introducing_a、T_b、αT_a、And introduce Frequency domain performance parameter γ, ω of system after the lag-lead-corrector；

The neural metwork training unit is input into the data sample for being collected in the neutral net expressed by above-mentioned (3) formula, The neutral net is trained；

The lag-lead-corrector structural parameters acquiring unit will be K, α, β, γ, ω value outside the data with existing sample defeated Enter in the neutral net for training, obtain the structural parameters T of lag-lead-corrector corresponding with K, α, β, γ, the ω_a、 T_b、αT_a、