A remote control system for hydraulic gates

Abstract

The present invention relates to the field of water conservancy and hydropower, and specifically discloses a remote control system for a water conservancy gate, which comprises a data acquisition hardware module, a data acquisition module, a data transmission module, a data preprocessing module, a multimodal data module, an adaptive adjustment module, and a gate adjustment module. The remote control system for a water conservancy gate proposed in the present invention monitors water conservancy facilities by installing monitoring equipment on the water conservancy gate, decomposes and fuses the collected multimodal data through a proposed data reconstruction processing algorithm, and then proposes an adaptive control algorithm, constructs an adjustment target function, optimizes the control coefficient, obtains a water conservancy gate control optimization method, and realizes adaptive control of the water conservancy gate.

Description

Technical Field

[0001] The invention relates to the field of water conservancy and hydropower, and in particular to a remote control system for a water conservancy gate. Background Art

[0002] With the rapid development of information technology, the field of water conservancy engineering is also constantly facing new opportunities and challenges. Traditional water conservancy gate control methods are often limited to manual operation or fixed automation systems. These methods have problems such as low efficiency, slow response speed, and difficulty in dealing with complex water flow conditions. In order to solve these challenges, remote monitoring and control technology has gradually become a hot direction in the field of water conservancy engineering in recent years. Through the application of emerging technologies such as the Internet, sensor technology, and data processing algorithms, remote real-time monitoring and control of water conservancy facilities has become more feasible. Although the automation system based on fixed strategies can achieve a certain degree of automation control, it lacks flexibility and intelligence and is difficult to adapt to complex and changeable water flow conditions. These traditional methods seem to be unable to cope with flood disasters, water resources management, and water conservancy project scheduling. In this context, remote monitoring and control technology has gradually become the mainstream trend in the field of water conservancy engineering. Therefore, a remote control system for water conservancy gates is proposed. Summary of the invention

[0003] The object of the present invention is to provide a remote control system for a water conservancy gate, aiming to solve the problems mentioned in the above background.

[0004] In order to achieve the above-mentioned purpose, the present invention proposes a remote control system for a water conservancy gate, comprising a data acquisition hardware module, a data acquisition module, a data transmission module, a data preprocessing module, a multimodal data module, an adaptive adjustment module, and a gate adjustment module; the data acquisition hardware module comprises equipment for monitoring around the water conservancy gate; the data acquisition module collects river data through the monitoring equipment; the data transmission module transmits the data collected by the data acquisition module to a control server; the data preprocessing module converts the received data into multimodal vector data; the multimodal data module processes the multimodal vector data through a data reconstruction processing algorithm; the adaptive adjustment module proposes an adaptive control algorithm to obtain an adjustment method for the water conservancy gate; the gate adjustment module adjusts the water conservancy gate through the adjustment method output by the adaptive adjustment module.

[0005] Furthermore, the monitoring equipment includes ordinary cameras and infrared cameras, which are installed around the same water conservancy gate and are a physical component in the system to monitor the river in real time.

[0006] Furthermore, the data acquisition module is tasked with monitoring the same position of the water conservancy gate through the same set of ordinary cameras and infrared cameras, receiving the data stream transmitted from the monitoring equipment, receiving and storing it through a data receiver, and obtaining a set of monitoring data.

[0007] Furthermore, the data transmission module is equipped with communication equipment and communication protocols, including Ethernet interface, Wi-Fi module, GSM module, and control server, which transmits the river data collected to the control server, supports real-time monitoring and remote control of the system, meets the data transmission requirements in different environments, ensures the efficiency and security of data transmission, and has flexible data transmission control functions. It can adjust the frequency, priority and flow limit of data transmission according to actual conditions, and ensure the stability and reliability of data transmission.

[0008] Furthermore, the data preprocessing module processes and converts the raw data obtained from the data acquisition module, and converts the data into multimodal vector data through data cleaning and data conversion, thereby providing a data basis for subsequent analysis and control.

[0009] Furthermore, the multimodal data module proposes a data reconstruction processing algorithm to decompose and fuse the multimodal data by constructing a decomposition matrix.

[0010] Furthermore, the decomposition matrix is ​​as follows:

[0011] For each initial data vector, construct a combination vector , expressed as:

[0012] ,

[0013] in, They represent the first initial data vector, the second initial data vector, the ith initial data vector, and the nth initial data vector respectively. For each initial data vector, it is expressed as:

[0014] ,

[0015] in, Represent the initial data vectors The first data value, initial data vector The second data value, initial data vector The i-th data value, initial data vector The mth data value of Represents the transpose of the local vector. First, the initial data vector is decomposed to construct the decomposition matrix , which is expressed as follows:

[0016] ,

[0017] in, They represent the value of the 1st row and 1st column of the decomposition matrix, the value of the 1st row and mth column of the decomposition matrix, the value of the mth row and 1st column of the decomposition matrix, the value of the kth row and jth column of the decomposition matrix, and the value of the mth row and mth column of the decomposition matrix. For each value in the decomposition matrix, the calculation formula is as follows:

[0018] ,

[0019] in, , , Represent the initial data vectors The jth data value, initial data vector The jth data value, initial data vector No. data values, Represented as the initial data vector No. data values, Represented as the kth row of the decomposition matrix The value of the column is decomposed based on the decomposition matrix to obtain the characteristic data vector. The calculation formula is as follows:

[0020] ,

[0021] in, Represents the initial data vector Based on the characteristic data vector, the multimodal data is fused to obtain a fused data vector , the formula is as follows:

[0022] ,

[0023] Where n represents the number of vectors, represents the 1-norm, Represents 2-norm. The data reconstruction processing algorithm proposed in the present invention first decomposes the initial data vector by constructing a decomposition matrix, obtains the characteristic data vector corresponding to the initial data vector based on the decomposed data vector, and then fuses the data vector based on the characteristic data vector by the norm of each vector. The data reconstruction processing algorithm proposed in the present invention fuses multimodal data to improve the accuracy of the data, thereby improving the accuracy of the monitoring data.

[0024] Furthermore, the adaptive control algorithm constructs a control objective function, optimizes the control coefficient, establishes a node transfer function, obtains a control optimization method, extracts gate control adjustment related parameters from the processed fusion data vector, and constructs the extracted adjustment related parameters into a related parameter matrix , expressed as:

[0025] ,

[0026] in They are respectively represented as the first related parameter, the second related parameter, the tth related parameter, and the nth related parameter. The adaptive control algorithm is modified and optimized according to the control results to construct the adjustment objective function ,as follows:

[0027] ,

[0028] in, represents the control coefficient of the tth related parameter, Represents the expected output. The adjustment of the adaptive control algorithm is achieved by optimizing the control coefficient. For the optimization of the control coefficient, first build the control coefficient optimization library , expressed as:

[0029] ,

[0030] in, They represent the first control coefficient library, the second control coefficient library, the i-th control coefficient library, and the n-th control coefficient library respectively, and a control optimization network is constructed. Each node in the network represents a control coefficient library. The control coefficient library in the control coefficient optimization library is searched to find a control coefficient library that better meets the objective function. In the process of searching the control coefficient library, the forgetting degree is defined to eliminate the corresponding nodes. Nodes with large forgetting degrees are less likely to be searched. During the node search process, the node forgetting degree will be updated. The update function is as follows:

[0031] ,

[0032] in, , They represent the forgetting degree of node i in stage k and the forgetting degree of node i in stage k+1 respectively. represents the forgetting coefficient, represents the abstract distance between node i and node j in the regulation optimization network, Indicates that node j searches for node i. Due to different distributions of nodes, different node importances are caused. Therefore, the distribution of each control coefficient library in the network nodes is different. In order to expand the search degree, the distribution of the control coefficient library is dynamically changing. The probability density function of the distribution of each control coefficient library is for:

[0033] ,

[0034] in, Indicates the position of the i-th control coefficient library at the node, Represents the neighboring coefficient of node i. Based on the node forgetting degree, the transfer rules between nodes are constructed as follows:

[0035] ,

[0036] in Expressing hope, Represents the forgetting factor, r represents the distance factor, and through the transfer rule, the transfer search method between nodes is defined, and the node that maximizes the above formula is made the next transfer node to find the optimal control coefficient that meets the objective function. The adaptive control algorithm proposed in the present invention optimizes the control method of the control optimization coefficient, constructs the objective function, and constructs the control optimization network based on the control coefficient optimization library. By proposing transfer rules, the search is performed in the control optimization network. The adaptive control algorithm proposed in the present invention can traverse the optimal control coefficient and optimize the water conservancy gate control method. The introduction of the forgetting degree improves the search speed.

[0037] Furthermore, the gate adjustment module is equipped with an actuator with load-bearing capacity and adjustment accuracy, including a hydraulic cylinder and an electric actuator, which are used to realize the opening, closing and adjustment operations of the water conservancy gate. Through the output results of the adaptive adjustment module, the water conservancy gate is specifically adjusted and controlled to achieve the adjustment and control of the water flow.

[0038] The beneficial effects of the present invention are as follows:

[0039] 1. A remote control system for a water conservancy gate of the present invention proposes a data reconstruction processing algorithm to process multimodal data. First, the initial data vector is decomposed by constructing a decomposition matrix. Based on the decomposed data vector, a characteristic data vector corresponding to the initial data vector is obtained. Then, the data vector is fused based on the characteristic data vector through the norm of each vector. The data reconstruction processing algorithm proposed by the present invention fuses multimodal data to improve the accuracy of the data, thereby improving the accuracy of the monitoring data;

[0040] 2. The adaptive adjustment module of the present invention proposes an adaptive control algorithm, optimizes the control method of the control optimization coefficient, constructs the objective function, constructs the control optimization network based on the control coefficient optimization library, and searches in the control optimization network by proposing transfer rules. The adaptive control algorithm proposed by the present invention can traverse the optimal control coefficient and optimize the control method of the water conservancy gate. The forgetting degree is proposed to improve the search speed;

[0041] 3. Compared with the traditional manual operation method, the remote control system for the hydraulic gate proposed in the present invention can reduce the dependence on human resources and reduce labor costs. Operators do not need to operate on site, and can complete the monitoring and adjustment of the hydraulic gate through the remote control center, saving human resources. The remote control system can replace manual operation in dangerous environments, thereby improving the safety of water conservancy projects. For example, during floods or in severe weather conditions, operators can safely monitor and adjust through the remote control center, avoiding the risks that personnel may face in on-site operations, and can achieve precise adjustment and remote monitoring of water flow, making the operation of water conservancy projects more efficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings in the following description are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0043] Figure 1 It is a system schematic diagram of the present invention. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] like Figure 1 As shown, a remote control system for a water conservancy gate of the present invention includes a data acquisition hardware module, a data acquisition module, a data transmission module, a data preprocessing module, a multimodal data module, an adaptive adjustment module, and a gate adjustment module; the data acquisition hardware module includes equipment for monitoring around the water conservancy gate; the data acquisition module collects river data through the monitoring equipment; the data transmission module transmits the data collected by the data acquisition module to the control server; the data preprocessing module converts the received data into multimodal vector data; the multimodal data module processes the multimodal vector data through a data reconstruction processing algorithm; the adaptive adjustment module proposes an adaptive control algorithm to obtain an adjustment method for the water conservancy gate; the gate adjustment module specifically adjusts the water conservancy gate through the adjustment method output by the adaptive adjustment module.

[0046] Specifically, the monitoring equipment includes ordinary cameras and infrared cameras, which are installed around the same water conservancy gate. It is a physical component in the system and monitors the river in real time.

[0047] Specifically, the data acquisition module uses a group of ordinary cameras and infrared cameras to monitor the same position of the water conservancy gate, receives the data stream from the monitoring transmission, receives and stores it through a data receiver, and obtains a group of monitoring data.

[0048] Specifically, the data transmission module is equipped with communication equipment and communication protocols, including Ethernet interface, Wi-Fi module, GSM module, and control server, which transmits the river data collected to the control server, supports real-time monitoring and remote control of the system, meets the data transmission requirements in different environments, ensures the efficiency and security of data transmission, and has flexible data transmission control functions. It can adjust the frequency, priority and flow limit of data transmission according to actual conditions, and ensure the stability and reliability of data transmission.

[0049] Specifically, the data preprocessing module preprocesses the received monitoring data, processes and converts the original data obtained from the data acquisition module, and converts the data into multimodal vector data through data cleaning and data conversion, thereby providing a data basis for subsequent analysis and control.

[0050] Specifically, the multimodal data module proposes a data reconstruction processing algorithm, which decomposes and fuses the multimodal data by constructing a decomposition matrix. The detailed process is as follows:

[0051] For each initial data vector, construct a combination vector , expressed as:

[0052] ,

[0053] in, They represent the first initial data vector, the second initial data vector, the ith initial data vector, and the nth initial data vector respectively. For each initial data vector, it is expressed as:

[0054] ,

[0055] in, Represent the initial data vectors The first data value, initial data vector The second data value, initial data vector The i-th data value, initial data vector The mth data value of Represents the transpose of the local vector. First, the initial data vector is decomposed to construct the decomposition matrix , which is expressed as follows:

[0056] ,

[0057] in, They represent the value of the 1st row and 1st column of the decomposition matrix, the value of the 1st row and mth column of the decomposition matrix, the value of the mth row and 1st column of the decomposition matrix, the value of the kth row and jth column of the decomposition matrix, and the value of the mth row and mth column of the decomposition matrix. For each value in the decomposition matrix, the calculation formula is as follows:

[0058] ,

[0059] in, , , Represent the initial data vectors The jth data value, initial data vector The jth data value, initial data vector No. data values, Represented as the initial data vector No. data values, Represented as the kth row of the decomposition matrix The value of the column is decomposed based on the decomposition matrix to obtain the characteristic data vector. The calculation formula is as follows:

[0060] ,

[0061] in, Represents the initial data vector Based on the characteristic data vector, the multimodal data is fused to obtain a fused data vector , the formula is as follows:

[0062] ,

[0063] Where n represents the number of vectors, represents the 1-norm, represents the 2-norm.

[0064] Specifically, the adaptive control algorithm constructs an adjustment objective function, optimizes the adjustment coefficient, establishes a node transfer function, obtains an adjustment optimization method, extracts gate control adjustment related parameters from the processed fusion data vector, and constructs the extracted adjustment related parameters into a related parameter matrix , expressed as:

[0065] ,

[0066] in They are respectively represented as the first related parameter, the second related parameter, the tth related parameter, and the nth related parameter. The adaptive control algorithm is modified and optimized according to the control results to construct the adjustment objective function ,as follows:

[0067] ,

[0068] in, represents the control coefficient of the tth related parameter, Represents the expected output. The adjustment of the adaptive control algorithm is achieved by optimizing the control coefficient. For the optimization of the control coefficient, first build the control coefficient optimization library , expressed as:

[0069] ,

[0070] in, They represent the first control coefficient library, the second control coefficient library, the i-th control coefficient library, and the n-th control coefficient library respectively, and a control optimization network is constructed. Each node in the network represents a control coefficient library. The control coefficient library in the control coefficient optimization library is searched to find a control coefficient library that better meets the objective function. In the process of searching the control coefficient library, the forgetting degree is defined to eliminate the corresponding nodes. Nodes with large forgetting degrees are less likely to be searched. During the node search process, the node forgetting degree will be updated. The update function is as follows:

[0071] ,

[0072] in, , They represent the forgetting degree of node i in stage k and the forgetting degree of node i in stage k+1 respectively. represents the forgetting coefficient, represents the abstract distance between node i and node j in the regulation optimization network, Indicates that node j searches for node i. Due to different distributions of nodes, different node importances are caused. Therefore, the distribution of each control coefficient library in the network nodes is different. In order to expand the search degree, the distribution of the control coefficient library is dynamically changing. The probability density function of the distribution of each control coefficient library is for:

[0073] ,

[0074] in, Indicates the position of the i-th control coefficient library at the node, Represents the neighboring coefficient of node i. Based on the node forgetting degree, the transfer rules between nodes are constructed as follows:

[0075] ,

[0076] in Expressing hope, Represents the forgetting factor, r represents the distance factor. Through the transfer rule, the transfer search method between nodes is defined, and the node that maximizes the above formula is made the next transfer node to find the optimal control coefficient that satisfies the objective function.

[0077] Specifically, the gate adjustment module is equipped with an actuator with load-bearing capacity and adjustment accuracy, including a hydraulic cylinder and an electric actuator, which are used to realize the opening, closing and adjustment operations of the water conservancy gate. Through the output results of the adaptive adjustment module, the water conservancy gate is specifically adjusted and controlled to achieve the adjustment and control of the water flow.

[0078] In a specific embodiment, first, the user installs ordinary cameras and infrared cameras at the same position around the water conservancy gate to monitor the river in real time; then, through the Ethernet interface, Wi-Fi module, GSM module, and control server, a data transmission channel is realized to receive and store the data stream transmitted from the monitoring equipment to obtain monitoring data; then, the received monitoring data is converted into multimodal vector data through data cleaning and data conversion; based on this, through the data reconstruction processing algorithm, the multimodal data is decomposed and fused by constructing a decomposition matrix to improve the accuracy of the monitoring data; then, the adaptive control algorithm is used to construct an adjustment objective function, optimize the control coefficient, and extract the gate control adjustment related parameters based on the processed fusion data vector, find the optimal control coefficient that meets the objective function, and obtain the control optimization method; finally, equipped with hydraulic cylinders and electric actuators with load-bearing capacity and adjustment accuracy, the water conservancy gate is adjusted and controlled to achieve water flow adjustment and control.

[0079] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0080] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0081] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A remote control system for a hydraulic gate, characterized in that: It includes data acquisition hardware module, data collection module, data transmission module, data preprocessing module, multimodal data module, adaptive adjustment module and gate adjustment module; the data acquisition hardware module includes equipment for monitoring around the water conservancy gate; The data acquisition module collects river data through monitoring equipment; the data transmission module transmits the data collected by the data acquisition module to the control server; The data preprocessing module converts the received data into multimodal vector data; the multimodal data module processes the multimodal vector data through a data reconstruction processing algorithm; The adaptive regulation module proposes an adaptive control algorithm to obtain the regulation mode of the water conservancy gate; the gate regulation module regulates the water conservancy gate through the regulation mode output by the adaptive regulation module; The multimodal data module proposes a data reconstruction processing algorithm to decompose and fuse the multimodal data by constructing a decomposition matrix; The data reconstruction processing algorithm is specifically as follows: First, decompose the initial data vector and construct the decomposition matrix H. The calculation formula for each value in the decomposition matrix is ​​as follows: Among them, b i,j 、b k,j 、b i,l Represent the initial data vector b i The jth data value, initial data vector b k The jth data value, initial data vector b i The lth data value, b k,l Represented as the initial data vector b k The lth data value, h k,l It is represented by the value of the kth row and lth column of the decomposition matrix. Based on the decomposition matrix, each initial data vector is decomposed to obtain the characteristic data vector. The calculation formula is as follows: b′ i =b i -H×b i , Among them, b′ i Represents the initial data vector b i Based on the characteristic data vector, the multimodal data is fused to obtain a fused data vector The formula is as follows: Where n represents the number of vectors, ||·||1 represents the 1-norm, and ||·||2 represents the 2-norm; The adaptive control algorithm obtains a control optimization method by constructing a control objective function, optimizing the control coefficient, and establishing a node transfer function; The control optimization method is obtained by constructing a control objective function, optimizing the control coefficient, and establishing a node transfer function. Specifically, the method includes: extracting gate control control related parameters from the processed fusion data vector, constructing the extracted control related parameters into a related parameter matrix X, and performing correction and optimization on the adaptive control algorithm according to the control result to construct a control objective function f, as follows: Among them, x t represents the tth related parameter, w t Represents the control coefficient of the t-th related parameter, Y represents the expected output, and the adjustment of the adaptive control algorithm is achieved by optimizing the control coefficient. First, the control coefficient optimization library δ is constructed, and then the control optimization network is constructed. The nodes in the network represent the control coefficient library. The control coefficient library in the control coefficient optimization library is searched to find the control coefficient library that better meets the objective function. In the process of searching the control coefficient library, the forgetting degree is defined to eliminate the corresponding nodes. The nodes with large forgetting degrees are less likely to be searched. The node forgetting degree is updated during the node search process. The update function is as follows: Among them, μ i (k), μ i (k+1) represents the forgetting degree of node i in stage k and the forgetting degree of node i in stage k+1, c represents the forgetting coefficient, τ i,j represents the abstract distance between node i and node j in the control optimization network, j→i means node j searches for node i, and the distribution of each control coefficient library in the network nodes is different. The probability density function p(y i )for: Among them, y i represents the position of the i-th control coefficient library at the node, ξ i Represents the neighboring coefficient of node i. Based on the node forgetting degree, the transfer rules between nodes are constructed as follows: Where E(·) represents the expectation, α represents the forgetting factor, and r represents the distance factor. Based on the transfer rule, the node transfer search method is defined to find the optimal control coefficient that satisfies the objective function.

2. A remote control system for a hydraulic gate according to claim 1, characterized in that: The monitoring equipment includes an ordinary camera and an infrared camera. The ordinary camera and the infrared camera are installed around the same water conservancy gate to monitor the river in real time.

3. A remote control system for water conservancy gates according to claim 1, characterized in that: In the data acquisition module, the same group of ordinary cameras and infrared cameras monitor the same position of the water conservancy gate, receive the data stream transmitted from the monitoring equipment, receive and store it through the data receiver, and obtain a group of monitoring data.

4. A remote control system for a hydraulic gate according to claim 1, characterized in that: The data transmission module is equipped with communication equipment and communication protocols, including Ethernet interface, Wi-Fi module, GSM module, and control server, which transmits the river data collected through data collection to the control server and adjusts the frequency, priority and flow limit of data transmission according to actual conditions.

5. A remote control system for a hydraulic gate according to claim 1, characterized in that: The data conversion is to convert the original data acquired by the data acquisition module into multi-modal vector data through data cleaning and data conversion.

6. A remote control system for a hydraulic gate according to claim 1, characterized in that: The hydraulic gate adjustment is controlled by equipping an actuator with load-bearing capacity and adjustment accuracy, including a hydraulic cylinder and an electric actuator. The hydraulic gate is specifically adjusted and controlled through the output of the adaptive adjustment module.

Images