Intelligent tower crane control system and method

The fuzzy logic control system handles the load and wind speed input of the intelligent tower crane, which solves the problems of the existing system's robustness and insufficient response time in complex environments, and achieves more efficient and safe handling.

CN118723800BInactive Publication Date: 2024-11-26CHENGDU THIRD ARCHITECTURAL ENG CO
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411226060.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-03
Publication Date
2024-11-26
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

When handling complex nonlinear systems and uncertain environments, the existing intelligent tower crane control system lacks robustness and anti-interference capabilities, and the calculation speed and response time are difficult to meet real-time control requirements.

Method used

The fuzzy logic control system is adopted, and the load and wind speed are received through the input layer. The fuzzy layer converts the precise data into a fuzzy set. The rule layer uses fuzzy rules to map the output. The normalization layer calculates the activation intensity, and the output layer calculates the angle adjustment of the lifting arm. , realize the processing of nonlinear relationships and uncertainties.

Benefits of technology

It improves the robustness and real-time response capabilities of the system, enhances the safety and efficiency of operations, simplifies computing logic, and improves the operability and maintenance of the system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118723800B_ABST
    Figure CN118723800B_ABST
Patent Text Reader

Abstract

The present invention belongs to the field of intelligent control, and provides an intelligent tower crane control system and method, including: an input layer, the input layer receives input variables, and the input variables include load #imgabs0# and wind speed #imgabs1#; a fuzzification layer, the fuzzification layer converts the precise input variables load #imgabs2# and wind speed #imgabs3# into fuzzy sets, and each variable can be divided into three fuzzy sets; a rule layer, the rule layer maps the fuzzy set of the input variable to the fuzzy set of the output variable; a normalization layer, the normalization layer includes an inference mechanism, and the inference mechanism applies fuzzy control rules to map the fuzzy input to the fuzzy output; the normalization layer also includes a normalization rule, and the activation strength is calculated according to the normalization rule, so that the sum of the activation strength is 1; and an output layer, the output layer calculates the final output angle adjustment amount of the crane arm. The present invention can accurately control the tower crane.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of intelligent control, and in particular relates to an intelligent tower crane control system and method. Background Art

[0002] Tower crane, also known as tower crane for short, is a large-scale construction machinery, mainly used for lifting and horizontal transportation of materials in high-rise building construction. Tower crane is named because of its tower-like shape, and is widely used in construction sites, port terminals, bridge construction and other places.

[0003] The control of traditional tower cranes mainly relies on manual operation and automatic control systems based on PID (proportional-integral-differential) controllers. Although PID control has been widely used in many industrial control systems, its performance and flexibility are limited when dealing with complex nonlinear systems and uncertain environments.

[0004] In recent years, with the development of sensor technology, computer technology and artificial intelligence technology, intelligent tower cranes have gradually emerged. These intelligent systems have achieved automated and intelligent control by integrating advanced sensor networks, data processing technology and intelligent control algorithms. However, the existing intelligent control technology still faces some challenges and problems in practical applications, which limits its wide application and performance improvement.

[0005] For example, the existing system lacks robustness and anti-interference capabilities to environmental uncertainties (such as wind speed changes, load changes), and the calculation speed and response time of the existing control system are difficult to meet the requirements of real-time control. Summary of the invention

[0006] In order to solve the problems in the prior art, the present invention provides an intelligent tower crane control system, comprising the following modules:

[0007] An input layer receives input variables, including load and wind speed ;

[0008] The fuzzification layer converts the exact input variable load and wind speed Converted into fuzzy sets, each variable can be divided into three fuzzy sets;

[0009] a rule layer that maps the fuzzy set of input variables to the fuzzy set of output variables;

[0010] A normalization layer, the normalization layer comprising an inference mechanism, the inference mechanism applying a fuzzy control rule to map a fuzzified input to a fuzzified output; the normalization layer further comprising a normalization rule, the activation strength is calculated according to the normalization rule so that the sum of the activation strengths is 1;

[0011] The output layer calculates the final output angle adjustment of the boom.

[0012] On the other hand, the present invention also provides an intelligent tower crane control system, which uses the aforementioned intelligent tower crane control system to realize the control of the intelligent tower crane.

[0013] The present invention can produce the following beneficial effects through the above technical solution:

[0014] Through fuzzy logic, precise input variables are converted into fuzzy sets, and fuzzy rules are used to handle the nonlinear relationship between input and output, while being able to handle uncertainty and noise in the input data.

[0015] It is highly robust to uncertainty and noise in the input data and can work stably under various environmental conditions.

[0016] The calculation logic is simple, with high real-time response capability, and can quickly respond to environmental changes, improving the safety and efficiency of operations.

[0017] At the same time, the form of fuzzy rules is simple and clear, and operators can adjust and optimize the rules according to specific needs, which improves the operability and maintainability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 It is a framework diagram of the system of the present invention. DETAILED DESCRIPTION

[0020] Below, the invention is preferably described in conjunction with the accompanying drawings and specific implementation methods.

[0021] This embodiment solves the above problem through the following steps:

[0022] In one embodiment, reference Figure 1 The present invention provides an intelligent tower crane control system, comprising the following modules:

[0023] An input layer receives input variables, including load and wind speed .

[0024] The input layer is the first layer of the system in this embodiment, responsible for receiving external input variables and passing them to the subsequent layers of the system. The main input variables received by the input layer include load and wind speed .

[0025] load Represents the weight of the object currently being hoisted by the crane, usually in tons. Load is a key variable because different weights can have a significant impact on the stability and operation of the crane. Load measurement is usually done by force sensors installed on the hook or boom, which can detect the weight of the hoisted object in real time and transmit data to the input layer.

[0026] Wind speed Represents the wind speed in the current environment, and its unit is usually meters per second (m / s). Wind speed is another important input variable, because strong winds may threaten the stability of the crane, especially when working at high altitudes. The measurement of wind speed is usually completed by wind speed sensors installed on the top of the crane. These sensors can detect the changes in wind speed in the environment in real time and transmit data to the input layer.

[0027] The fuzzification layer converts the exact input variable load and wind speed Converted into fuzzy sets, each variable is divided into three fuzzy sets.

[0028] The fuzzification layer is the second layer of the system in this embodiment, which is responsible for converting the precise input variable load and wind speed Convert to fuzzy sets. The main purpose of the fuzzification process is to convert the actual measured precise data into fuzzy sets so that the system can handle uncertainty and nonlinear problems. The two input variables, load and wind speed, will be divided into several fuzzy sets, each representing a different degree of fuzziness.

[0029] The load 𝐿 represents the weight of the object currently hoisted by the crane. For fuzzification, the load is divided into three fuzzy sets: Low, ), Medium, ), High (High, ).

[0030] Used to indicate the degree to which different load values ​​belong to a fuzzy set.

[0031] Specifically:

[0032] ,

[0033] ,

[0034] ,

[0035] in:

[0036] Indicates load Membership to low fuzzy sets;

[0037] Indicates load The degree of membership belongs to the medium fuzzy set;

[0038] Indicates load The degree of membership belongs to a high fuzzy set.

[0039] It is the parameter of the membership function, which determines the range and shape of the fuzzy set.

[0040] Wind speed Represents the wind speed in the current environment. Similar to load, wind speed is also divided into three fuzzy sets: Low, ), Medium, ), High (High, ).

[0041] Specifically:

[0042] ,

[0043] ,

[0044] ,

[0045] in:

[0046] Indicates wind speed Membership to low fuzzy sets;

[0047] Indicates wind speed Membership degree of fuzzy set

[0048] Indicates wind speed The degree of membership belongs to a high fuzzy set.

[0049] It is the parameter of the membership function, which determines the range and shape of the fuzzy set.

[0050] A rule layer that maps fuzzy sets of input variables to fuzzy sets of output variables.

[0051] The rule layer is responsible for mapping the fuzzy sets of input variables to the fuzzy sets of output variables. By applying predefined fuzzy rules, the rule layer combines the fuzzified results of input variables to generate the corresponding fuzzified results of output variables.

[0052] Specifically, this embodiment has nine fuzzy rules:

[0053] If the load is low and wind speed If it is low, the angle adjustment amount It is small;

[0054] If the load is low and wind speed If the angle is adjusted It is in the middle;

[0055] If the load is low and wind speed is high, then the angle adjustment amount It is big;

[0056] If the load Medium wind speed If it is low, the angle adjustment amount It is in the middle;

[0057] If the load Medium wind speed If the angle is adjusted It is big;

[0058] If the load Medium wind speed is high, then the angle adjustment amount It is big;

[0059] If the load Is high and wind speed If it is low, the angle adjustment amount It is big;

[0060] If the load Is high and wind speed If the angle is adjusted It is big;

[0061] If the load Is high and wind speed is high, then the angle adjustment amount It is big.

[0062] Furthermore, these rules are expressed in the form of fuzzy control rules:

[0063] ,

[0064] ,

[0065] ,

[0066] in Indicates load, Indicates low load, Indicates wind speed, Indicates low wind speed, Indicates medium wind speed, Indicates high wind speed, Indicates the angle adjustment amount, Indicates the amount of small angle adjustment, Indicates the amount of mid-angle adjustment, Indicates large angle adjustment.

[0067] A normalization layer, wherein the normalization layer includes an inference mechanism, wherein the inference mechanism applies a fuzzy control rule to map the fuzzy input to the fuzzy output; the normalization layer also includes a normalization rule, wherein the activation strength is calculated according to the normalization rule so that the sum of the activation strengths is 1.

[0068] The normalization layer includes the reasoning mechanism and the normalization rules. The main function of this layer is to apply the fuzzy control rules to the fuzzy input, map it to the fuzzy output, and calculate the activation strength of each rule according to the normalization rules so that the sum of the activation strengths is 1. The normalization layer ensures that the contribution of each fuzzy rule to the output is reasonable and effective.

[0069] The inference mechanism is the process of applying fuzzy control rules to map fuzzified input to fuzzified output.

[0070] ,

[0071] in:

[0072] Indicates The activation strength of the rule.

[0073] and The load and wind speed The degree of membership to the corresponding fuzzy set.

[0074] Normalize the regular activation intensities so that the sum of the activation intensities is 1:

[0075] ,

[0076] in

[0077] is the normalized activation strength;

[0078] is the total number of fuzzy rules.

[0079] The output layer calculates the final output angle adjustment of the boom.

[0080] This example assumes that the output is a linear function

[0081] ,

[0082] The final output is a weighted sum of normalized activation intensities:

[0083] ,

[0084] Right now

[0085] ,

[0086] in:

[0087] It is Output parameters of the rule;

[0088] It is The output value of the rule.

[0089] Furthermore, for the above model, the training process is as follows:

[0090] During the training process, the parameters of the membership function and the output function are adjusted by minimizing the error function:

[0091] ,

[0092] in:

[0093] is the error function.

[0094] It is The actual output of each sample.

[0095] It is The predicted output for each sample.

[0096] 𝑀 is the number of training samples.

[0097] Update the parameters using gradient descent to minimize the error:

[0098] ,

[0099] in is the learning rate.

[0100] It is The output parameters of the rule are the parameters that need to be adjusted during the training process.

[0101] Specific examples

[0102] Assuming the current load Tons (Medium) and wind speed m / s (height), the membership function is obtained through the fuzzification step:

[0103] ,

[0104] ,

[0105] Calculate activation strength based on fuzzy rules:

[0106] ,

[0107] ,

[0108] Normalized activation strength:

[0109] ,

[0110] Assume that the output function parameters are

[0111] ,

[0112] and

[0113] ,

[0114] Then there is

[0115] ,

[0116] ,

[0117] Final output:

[0118] ,

[0119] Therefore, the angle adjustment of the boom The angle of the crane is 8.92 degrees. This method can achieve more precise control and improve the operating efficiency and safety of the intelligent tower crane.

[0120] On the other hand, the present invention also provides an intelligent tower crane control system, which uses the aforementioned intelligent tower crane control system to realize the control of the intelligent tower crane.

[0121] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

[0122] The present invention does not particularly specify the structure of some modules, which shall be subject to the contents recorded in the prior art. The prior art mentioned in the above background technology section and the specific embodiment section of the present invention can be used as part of the present invention to understand the meaning of some technical features or parameters. The scope of protection of the present invention shall be subject to the contents actually recorded in the claims.

Claims

1. An intelligent tower crane control system, It is characterized in that The system includes the following modules: An input layer, wherein the input layer receives input variables, wherein the input variables include a load L and a wind speed W; A fuzzification layer, which converts the precise input variables load L and wind speed W into fuzzy sets, each variable being divided into three fuzzy sets; a rule layer that maps the fuzzy set of input variables to the fuzzy set of output variables; A normalization layer, the normalization layer comprising an inference mechanism, the inference mechanism applying a fuzzy control rule to map a fuzzified input to a fuzzified output; the normalization layer further comprising a normalization rule, the activation strength is calculated according to the normalization rule so that the sum of the activation strengths is 1; An output layer, wherein the output layer calculates and outputs a final angle adjustment of the boom; The specific implementation of the fuzzification layer is as follows: The load is divided into three fuzzy sets: in Indicates that the load L belongs to the low fuzzy set membership; Indicates that the load L belongs to the membership of the medium fuzzy set; Indicates that the load L belongs to the high fuzzy set membership; a 1 ,a 2 ,b 1 ,b 2 ,b 3 ,c 1 ,c 2 is the parameter of the membership function, which determines the scope and shape of the fuzzy set; Wind speed is divided into three fuzzy sets: in Indicates that the wind speed W belongs to the low fuzzy set membership; Indicates that the wind speed W belongs to the membership of the medium fuzzy set; Indicates that the wind speed W belongs to the high fuzzy set membership; d 1 ,d 2 ,e 1 ,e 2 ,e 3 ,f 1 ,f 2 is the parameter of the membership function, which determines the scope and shape of the fuzzy set; The fuzzy rules of the rule layer are as follows: If the load L is low and the wind speed W is low, the angle adjustment amount Δθ is small; If the load L is low and the wind speed W is medium, the angle adjustment amount Δθ is medium; If the load L is low and the wind speed W is high, the angle adjustment amount Δθ is large; If the load L is medium and the wind speed W is low, the angle adjustment amount Δθ is medium; If the load L is medium and the wind speed W is medium, the angle adjustment amount Δθ is large; If the load L is medium and the wind speed W is high, the angle adjustment amount Δθ is large; If the load L is high and the wind speed W is low, the angle adjustment amount Δθ is large; If the load L is high and the wind speed W is medium, the angle adjustment amount Δθ is large; If the load L is high and the wind speed W is high, the angle adjustment amount Δθ is large; The fuzzy control rule is further expressed as: Rule 1:IFLisL L ANDWisW L THEN△θis△θ S Rule 2:IFLisL L ANDWisW M THEN△θis△θ M Rule 3:IFLisL L ANDWisW H THEN△θis△θ L Where L represents the load, L L Indicates low load, W indicates wind speed, W L Indicates low wind speed, W M Indicates medium wind speed, W H Indicates high wind speed, △θ indicates angle adjustment, △θ s Indicates the small angle adjustment, △θ M Indicates the mid-angle adjustment, △θ H Indicates the amount of large angle adjustment; The activation intensity calculation method of the normalized layer is: in: ω i represents the activation strength of the i-th rule; and are the membership of the load L and wind speed W to the corresponding fuzzy set respectively; the normalization method of the normalization layer is: in is the normalized activation strength; N is the total number of fuzzy rules; The output layer is specifically implemented as follows: Assume the output is a linear function △θ i =p i L+q i W+r i The final output is a weighted sum of normalized activation intensities: Right now in: p i ,q i ,r i is the output parameter of the i-th rule; △θ i is the output value of the i-th rule; The training process of the output parameters is as follows: The parameters of the membership function and the output function are adjusted by minimizing the error function: in: E is the error function; is the actual output of the kth sample; is the predicted output of the kth sample; M is the number of training samples; Update the parameters using gradient descent to minimize the error: Where η is the learning rate; p i ,q i ,r i is the output parameter of the ith rule, which is the parameter that needs to be adjusted during the training process; the load is measured by a force sensor installed on the hook or the boom; The wind speed is measured by a wind speed sensor installed on the top of the crane.

2. A method for controlling an intelligent tower crane, It is characterized in that The system as claimed in claim 1 is used for intelligent tower crane operation.