CN105045091A - Dredging process intelligent decision analysis method based on fuzzy neural control system - Google Patents

Abstract

The invention discloses a dredging process intelligent decision analysis method based on a fuzzy neural control system. The method comprises the steps that 1, data influencing related decision parameters of a dredging construction technology are collected; 2, a matlab principal component analysis method is used to find out the feature thresholds of several decision parameters with the maximum contribution rate; 3, a knowledge base is established; 4, a fuzzy neural control system mechanism is selected and artificial neurons are established, and the number of hidden layers of a neural network is determined according to the dredging complexity; and 5, the fuzzy neural control system is established to carry out assisted decision on dredging construction. According to the invention, the space complexity of the neural network and fuzzy control time complexity are fused, so that the degree of dredging automation is high.

Description

Intelligent decision-making analysis method for dredging process based on fuzzy neural control system

technical field

The invention relates to an intelligent decision-making analysis method for dredging technology based on a fuzzy neural control system, which belongs to the field of dredging engineering.

Background technique

As an underwater operation, dredging has many process control parameters, and at present, the degree of automation of dredging in China is not high, and manual operation is still the main method. Even for experienced operators, due to the complex factors affecting the mud flow state, such as mud concentration, mud flow velocity, sediment particle size, sedimentation velocity of different sediments and pipeline performance, etc., and the interaction of various factors makes qualitative testing relatively difficult . As a result, dredging production has been in a state of low production, low efficiency, high energy consumption and high emissions. Therefore, it is particularly urgent to improve the degree of dredging automation.

In 1965, Z.A. Zadeh, an American automatic control scholar, proposed the concept of fuzzy sets and pioneered fuzzy set theory, which is used to describe phenomena without clear boundaries and fuzzy extensions. In 1943, French psychologists W.S.McCuloch and W.Pitts proposed the neuron model. The space complexity of neural network is used to fuse the time complexity of fuzzy control, and the combination of the two creates a fuzzy neural control system. The fuzzy neural control system provides us with a new way of thinking.

Contents of the invention

The invention realizes an intelligent decision-making analysis method for dredging technology based on a fuzzy neural control system, integrates the time complexity of fuzzy control through the space complexity of the neural network, and makes the dredging operation more automatic.

In order to achieve the above object, the technical scheme adopted in the present invention is:

An intelligent decision-making analysis method for dredging technology based on a fuzzy neural control system, including the following steps,

Step 1, collecting data related to decision-making parameters affecting the construction process of dredging operations;

Step two, apply the matlab principal component analysis method to find out the characteristic thresholds of several decision parameters with the largest contribution rate;

Step 3, establishing a knowledge base; the knowledge base includes a fuzzy rule base and a fuzzy database;

Fuzzy rules are defined in the fuzzy rule base; membership functions used in the fuzzy rules are defined in the fuzzy database;

Step 4, select the mechanism of the fuzzy neural control system, establish artificial neurons, and determine the number of hidden layers of the neural network according to the complexity of the dredging operation;

Step 5: Establish a fuzzy neural control system to assist in decision-making for dredging operations.

The relevant decision-making parameters affecting the construction process of dredging operations include mud concentration, reamer speed, mud pump speed, pipeline flow rate, reamer traverse speed, reamer cutting mud thickness, reamer advance distance, reamer depth, trolley travel, pipe Road-average concentration and outlet velocity.

The decision parameters with the largest contribution rate include mud concentration, reamer speed, mud pump speed, reamer traversing speed and reamer advance distance.

The membership function is calculated by the rule of thirds, and the specific process is as follows:

1) Define space Ω, divide Ω into three subspaces A ₁ , A ₂ and A ₃ ;

2) define the boundary point/face of A ₁ and A ₂ as ξ, define the boundary point/face of A ₂ and A ₃ as η;

3) The formula for calculating the membership function using the random partition method is as follows,

Let (ξ, η) be a set of continuous random vectors satisfying P(ξ, η)=1, and let each value of (ξ, η) correspond to a mapping e, we have

e(ξ, η):Ω→U＝{A ₁ ,A ₂ ,A ₃ }

That is to say, three corresponding subspaces can be obtained every time the boundary is determined

and

$\mathrm{<span\; class="notranslate">\; e</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; \&xi;</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; \&eta;</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\left\{\begin{array}{cc}{\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}& \mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; \&le;</span>\mathrm{<span\; class="notranslate">\; \&xi;</span>}\\ {\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}& \mathrm{<span\; class="notranslate">\; \&xi;</span>}<span\; class="notranslate">\; <</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; \&le;</span>\mathrm{<span\; class="notranslate">\; \&eta;</span>}\\ {\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}& \mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ></span>\mathrm{<span\; class="notranslate">\; \&eta;</span>}\end{array}\right.$

Among them: U is the complete set including three subsets A ₁ , A ₂ , A ₃ ; e(ξ, η) means that each value of (ξ, η) corresponds to a mapping e; e(ξ, η)(x) Indicates the value range of A ₁ , A ₂ , and A ₃ when ξ and η are determined;

Then the three membership functions corresponding to the three fuzzy subsets and for,

${\mathrm{<span\; class="notranslate">\; \&mu;</span>}}_{{\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>{<span\; class="notranslate">\; \&Integral;</span>}_{\mathrm{<span\; class="notranslate">\; x</span>}}^{\mathrm{<span\; class="notranslate">\; \&infin;</span>}}{\mathrm{<span\; class="notranslate">\; P</span>}}_{\mathrm{<span\; class="notranslate">\; \&xi;</span>}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; u</span>}<span\; class="notranslate">\; )</span>\mathrm{<span\; class="notranslate">\; d</span>}\mathrm{<span\; class="notranslate">\; u</span>}$

${\mathrm{<span\; class="notranslate">\; \&mu;</span>}}_{{\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; \&mu;</span>}}_{\mathrm{<span\; class="notranslate">\; A</span>}\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; \&mu;</span>}}_{\mathrm{<span\; class="notranslate">\; A</span>}\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span>$

${\mathrm{<span\; class="notranslate">\; \&mu;</span>}}_{{\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>{<span\; class="notranslate">\; \&Integral;</span>}_{\mathrm{<span\; class="notranslate">\; x</span>}}^{\mathrm{<span\; class="notranslate">\; \&infin;</span>}}{\mathrm{<span\; class="notranslate">\; P</span>}}_{\mathrm{<span\; class="notranslate">\; \&eta;</span>}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; u</span>}<span\; class="notranslate">\; )</span>\mathrm{<span\; class="notranslate">\; d</span>}\mathrm{<span\; class="notranslate">\; u</span>}$

Among them, P _ξ (u) and P _η (u) are the marginal distribution density functions of ξ and η, respectively.

The BP algorithm is used to establish artificial neurons, and the number of hidden layers of the neural network is determined according to the complexity of the dredging operation.

The fuzzy rule base is used as the hidden layer node, and the fuzzy neural control system is established, and the output error is reduced to the allowable level through continuous learning and training.

The beneficial effects achieved by the present invention: the present invention fuses the time complexity of fuzzy control through the space complexity of neural network, and the fuzzy neural control has strong adaptability and robustness. The simulation results show that the static and dynamic performance And anti-jamming performance are superior to conventional PID and conventional fuzzy control, which can make dredging operations more automated.

Description of drawings

Fig. 1 is a flowchart of the present invention.

Figure 2 is a basic structural diagram of the fuzzy neural control system.

detailed description

The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.

As shown in Figure 1, the intelligent decision analysis method for dredging process based on fuzzy neural control system includes the following steps:

Step 1, collecting data on relevant decision-making parameters affecting the construction process of dredging operations.

The relevant decision-making parameters affecting the construction process of dredging operations need to be obtained based on construction experience. The decision-making parameters collected here include mud concentration, reamer speed, mud pump speed, pipeline flow rate, reamer traverse speed, reamer cutting mud thickness, reamer Knife advance distance, reamer depth, trolley travel, pipeline average concentration and outlet flow rate.

The second step is to use the matlab principal component analysis method to find out the characteristic thresholds of several decision parameters with the largest contribution rate.

Apply the matlab principal component analysis method to study the contribution rate and cumulative contribution rate of each decision-making parameter to output and energy consumption, and obtain the principal components and characteristic thresholds that affect output and energy consumption. The decision-making parameter regulation provides a reasonable and feasible value range to reduce the complexity of dredging process decision-making.

Here, the principal components that affect output and energy consumption, that is, the decision parameters with the largest contribution rate include mud concentration, reamer speed, mud pump speed, reamer traverse speed and reamer advance distance.

Step three, build a knowledge base.

Knowledge base includes fuzzy rule base and fuzzy database; fuzzy rules are defined in fuzzy rule base; membership functions used in fuzzy rules are defined in fuzzy database.

The membership function is calculated by the method of thirds, and the specific process is as follows:

A1) Define space Ω, divide Ω into three subspaces A ₁ , A ₂ and A ₃ ;

A2) define the boundary point/face _of A1 and A2 as _ξ , define the boundary point/face _of A2 and A3 as η _;

3) The formula for calculating the membership function using the random partition method is as follows,

Let (ξ, η) be a set of continuous random vectors satisfying P(ξ, η)=1, and let each value of (ξ, η) correspond to a mapping e;

e(ξ, η):Ω→U＝{A ₁ ,A ₂ ,A ₃ }

That is to say, three corresponding subspaces can be obtained every time the boundary is determined.

and

$\mathrm{<span\; class="notranslate">\; e</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; \&xi;</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; \&eta;</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\left\{\begin{array}{cc}{\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}& \mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; \&le;</span>\mathrm{<span\; class="notranslate">\; \&xi;</span>}\\ {\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}& \mathrm{<span\; class="notranslate">\; \&xi;</span>}<span\; class="notranslate">\; <</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; \&le;</span>\mathrm{<span\; class="notranslate">\; \&eta;</span>}\\ {\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}& \mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ></span>\mathrm{<span\; class="notranslate">\; \&eta;</span>}\end{array}\right.$

Among them: U is the complete set including three subsets A ₁ , A ₂ , A ₃ ; e(ξ, η) means that each value of (ξ, η) corresponds to a mapping e; e(ξ, η)(x) Indicates the value range of A ₁ , A ₂ , and A ₃ when ξ and η are determined;

Then the three membership functions corresponding to the three fuzzy subsets and for,

${\mathrm{<span\; class="notranslate">\; \&mu;</span>}}_{{\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>{<span\; class="notranslate">\; \&Integral;</span>}_{\mathrm{<span\; class="notranslate">\; x</span>}}^{\mathrm{<span\; class="notranslate">\; \&infin;</span>}}{\mathrm{<span\; class="notranslate">\; P</span>}}_{\mathrm{<span\; class="notranslate">\; \&xi;</span>}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; u</span>}<span\; class="notranslate">\; )</span>\mathrm{<span\; class="notranslate">\; d</span>}\mathrm{<span\; class="notranslate">\; u</span>}$

${\mathrm{<span\; class="notranslate">\; \&mu;</span>}}_{{\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; \&mu;</span>}}_{\mathrm{<span\; class="notranslate">\; A</span>}\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; \&mu;</span>}}_{\mathrm{<span\; class="notranslate">\; A</span>}\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span>$

${\mathrm{<span\; class="notranslate">\; \&mu;</span>}}_{{\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>{<span\; class="notranslate">\; \&Integral;</span>}_{\mathrm{<span\; class="notranslate">\; x</span>}}^{\mathrm{<span\; class="notranslate">\; \&infin;</span>}}{\mathrm{<span\; class="notranslate">\; P</span>}}_{\mathrm{<span\; class="notranslate">\; \&eta;</span>}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; u</span>}<span\; class="notranslate">\; )</span>\mathrm{<span\; class="notranslate">\; d</span>}\mathrm{<span\; class="notranslate">\; u</span>}$

Among them, P _ξ (u) and P _η (u) are the marginal distribution density functions of ξ and η, respectively.

Therefore, several main input parameters are divided into three levels: A ₁ , A ₂ , and A ₃ :

Mud concentration: small, medium, large;

Reamer speed: slow, medium, fast;

Dredge pump speed: slow, medium, fast;

Reamer traverse speed: slow, medium, fast;

Reamer advance distance: small, medium, large;

For example, for mud concentration, input the set concentration value at the beginning. When the output concentration value is less than the input value, the mud concentration is considered small. When the output value is exactly equal to the input value, it is medium. When the output value is greater than the input value, it is considered high. The other parameters are the same.

The specific membership function can be obtained from the values of the required parameters.

Step 4: Select the mechanism of the fuzzy neural control system, use the BP algorithm to establish artificial neurons, and determine the number of hidden layers of the neural network according to the complexity of the dredging operation.

Step 5: Establish a fuzzy neural control system to assist in decision-making for dredging operations.

In this fuzzy neural control system, the fuzzy rule library is used as the hidden layer node, and the fuzzy neural control system is established. Through continuous learning and training, the output error is reduced to the allowable level.

The establishment of a fuzzy neural control system is shown in Figure 2, where x ₁ , x ₂ , x ₃ ... x _n are input parameters, y ₁ , y ₂ , y ₃ ... y _n are output parameters, and the number of hidden layers is one layer. The layer node corresponds to the fuzzy rule base.

Let n=5, that is, x ₁ , x ₂ , x ₃ ... x ₅ are mud concentration, reamer speed, mud pump speed, reamer traverse speed and reamer advance distance respectively, y ₁ , y ₂ , y ₃ ... y ₅ is the actual output parameter. Before the dredging operation, the concentration value of the high output and the values of other parameters under this concentration value will be set. When the mud concentration is higher or lower than the set concentration value, other The parameter will also automatically adjust its output to maintain the mud concentration at or close to the set value.

The above-mentioned intelligent decision-making analysis method for dredging process based on fuzzy neural control system integrates the time complexity of fuzzy control through the space complexity of neural network, so that the degree of automation of dredging operations is higher.

The above is only a preferred embodiment of the present invention, and it should be pointed out that for those of ordinary skill in the art, without departing from the technical principle of the present invention, some improvements and modifications can also be made. It should also be regarded as the protection scope of the present invention.

Claims (6)

1. The dredging technology intelligent decision-making analysis method based on fuzzy neural control system, is characterized in that: comprise the following steps, Step 1, collecting data related to decision-making parameters affecting the construction process of dredging operations; Step two, apply the matlab principal component analysis method to find out the characteristic thresholds of several decision parameters with the largest contribution rate; Step 3, establishing a knowledge base; the knowledge base includes a fuzzy rule base and a fuzzy database; Fuzzy rules are defined in the fuzzy rule base; membership functions used in the fuzzy rules are defined in the fuzzy database; Step 4, select the mechanism of the fuzzy neural control system, establish artificial neurons, and determine the number of hidden layers of the neural network according to the complexity of the dredging operation; Step 5: Establish a fuzzy neural control system to assist in decision-making for dredging operations. 2. The intelligent decision-making analysis method for dredging technology based on fuzzy neural control system according to claim 1, characterized in that: the relevant decision-making parameters affecting the dredging operation construction technology include mud concentration, reamer speed, mud pump speed, pipeline flow rate, Reamer traverse speed, reamer cutting mud thickness, reamer forward distance, reamer depth, trolley travel, pipeline average concentration and outlet flow rate. 3. the dredging technology intelligent decision-making analysis method based on fuzzy neural control system according to claim 2, is characterized in that: the decision-making parameter that contribution rate is maximum comprises mud concentration, reamer rotating speed, mud pump rotating speed, reamer traverse speed and Reamer forward distance. 4. The intelligent decision-making analysis method for dredging technology based on fuzzy neural control system according to claim 1, characterized in that: said membership function is calculated and obtained by the rule of thirds, and the specific process is, 1) Define space Ω, divide Ω into three subspaces A ₁ , A ₂ and A ₃ ; 2) define the boundary point/face of A ₁ and A ₂ as ξ, define the boundary point/face of A ₂ and A ₃ as η; 3) The formula for calculating the membership function using the random partition method is as follows, Let (ξ, η) be a group of continuous random vectors satisfying P(ξ, η)=1, and assume that each value of (ξ, η) corresponds to a mapping e with e(ξ, η):Ω→U＝{A ₁ ,A ₂ ,A ₃ } That is to say, three corresponding subspaces can be obtained every time the boundary is determined and $\mathrm{<span\; class="notranslate">\; e</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; \&xi;</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; \&eta;</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\left\{\begin{array}{cc}{\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}& \mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; \&le;</span>\mathrm{<span\; class="notranslate">\; \&xi;</span>}\\ {\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}& \mathrm{<span\; class="notranslate">\; \&xi;</span>}<span\; class="notranslate">\; <</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; \&le;</span>\mathrm{<span\; class="notranslate">\; \&eta;</span>}\\ {\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}& \mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ></span>\mathrm{<span\; class="notranslate">\; \&eta;</span>}\end{array}\right.$ Among them: U is the complete set including three subsets A ₁ , A ₂ , A ₃ ; e(ξ, η) means that each value of (ξ, η) corresponds to a mapping e; e(ξ, η)(x) Indicates the value range of A ₁ , A ₂ , and A ₃ when ξ and η are determined; Then the three membership functions corresponding to the three fuzzy subsets and for, ${\mathrm{<span\; class="notranslate">\; \&mu;</span>}}_{{\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>{<span\; class="notranslate">\; \&Integral;</span>}_{\mathrm{<span\; class="notranslate">\; x</span>}}^{\mathrm{<span\; class="notranslate">\; \&infin;</span>}}{\mathrm{<span\; class="notranslate">\; P</span>}}_{\mathrm{<span\; class="notranslate">\; \&xi;</span>}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; u</span>}<span\; class="notranslate">\; )</span>\mathrm{<span\; class="notranslate">\; d</span>}\mathrm{<span\; class="notranslate">\; u</span>}$ ${\mathrm{<span\; class="notranslate">\; \&mu;</span>}}_{{\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; \&mu;</span>}}_{\mathrm{<span\; class="notranslate">\; A</span>}\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; \&mu;</span>}}_{\mathrm{<span\; class="notranslate">\; A</span>}\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span>$ ${\mathrm{<span\; class="notranslate">\; \&mu;</span>}}_{{\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>{<span\; class="notranslate">\; \&Integral;</span>}_{\mathrm{<span\; class="notranslate">\; x</span>}}^{\mathrm{<span\; class="notranslate">\; \&infin;</span>}}{\mathrm{<span\; class="notranslate">\; P</span>}}_{\mathrm{<span\; class="notranslate">\; \&eta;</span>}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; u</span>}<span\; class="notranslate">\; )</span>\mathrm{<span\; class="notranslate">\; d</span>}\mathrm{<span\; class="notranslate">\; u</span>}$ Among them, P _ξ (u) and P _η (u) are the marginal distribution density functions of ξ and η, respectively. 5. The intelligent decision analysis method for dredging technology based on fuzzy neural control system according to claim 1, characterized in that: adopt BP algorithm to set up artificial neuron, and determine the number of hidden layers of neural network according to the dredging operation complexity. 6. The intelligent decision-making analysis method for dredging technology based on fuzzy neural control system according to claim 1, characterized in that: the fuzzy rule library is used as hidden layer nodes to set up a fuzzy neural control system, and through continuous learning and training until the output error reduced to allowable levels.