An intelligent valve control platform based on the Internet of Things

Abstract

The present invention discloses a valve intelligent management and control platform based on the Internet of Things, which relates to the field of valve intelligent control technology, identifies the current valve use scenario, matches the valve control scheme corresponding to the use scenario, executes the control scheme, and adjusts the operating state of the valve; monitors the valve operating state data, constructs a corresponding valve state data set, and constructs a difference degree from the valve state data set. If the difference degree exceeds the difference threshold, the control strategy is optimized with a trained optimization model to obtain an optimized control strategy; generates reliability from the predicted data. If the reliability exceeds the reliability threshold, it is a backup of the key components of the valve control system, and determines whether to switch the key components based on the constructed adjustment degree. Improve the reliability of the valve system and ensure that the valve can be accurately executed after entering the use state or receiving the corresponding control instruction.

Description

Technical Field

[0001] The present invention relates to the technical field of valve intelligent control, and in particular to a valve intelligent management and control platform based on the Internet of Things. Background Art

[0002] A valve control system is a system used to control fluids or gases, and is commonly used in industrial and production processes. The system can achieve functions such as flow regulation, flow direction control, and pressure regulation of fluids, and is an indispensable key technology in modern industry. The core principle of the valve control system is to regulate the flow of fluids by controlling the opening of the valve. By changing the degree of opening of the valve, the system can achieve precise flow regulation to meet the needs of different processes and techniques.

[0003] In the Chinese invention patent with application publication number CN109667973A, a high-precision flow valve control system is disclosed, which includes a precision pressure regulating valve, a flow control valve, a high-precision flow meter and a control module. The flowing medium passes through the precision pressure regulating valve, the flow control valve and the high-precision flow meter in sequence: the control module receives feedback signals from the precision pressure regulating valve, the flow control valve and the high-precision flow meter, and controls the precision pressure regulating valve and the flow control valve to form a closed-loop control system to achieve mutual feedback of signals, so as to adjust the valve and improve the control accuracy: the flow control valve realizes automatic control of the flow by controlling the opening of the valve and the frequency of opening and closing, avoiding cumbersome adjustment operations and ensuring the accuracy of flow control: the high-precision flow meter reviews the flow of the medium passing through to ensure the flow accuracy requirements.

[0004] Based on the above application documents and prior art, after the valve and installation system are installed, if there is a certain amount of communication signal interference or a communication blind spot in the area where the valve control system is located, the valve control system may not be able to effectively receive the given control instructions when in use, making it difficult for the valve to execute the corresponding control instructions as expected, thereby reducing the reliability of the valve control system. Moreover, after receiving the control instructions, due to the insufficient execution of the valve control strategy by the actuator, the valve may not achieve the expected effect when executing the control instructions.

[0005] To this end, the present invention provides a valve intelligent management and control platform based on the Internet of Things. Summary of the invention

[0006] 1. Technical issues to be resolved

[0007] In view of the deficiencies of the prior art, the present invention provides a valve intelligent management and control platform based on the Internet of Things. By identifying the current valve usage scenario and matching the valve control scheme corresponding to the usage scenario, the control scheme is executed to adjust the operating state of the valve; the valve operating state data is monitored to construct a corresponding valve state data set, and the difference is constructed from the valve state data set. If the difference exceeds the difference threshold, the control strategy is optimized with the trained optimization model to obtain the optimized control strategy; the reliability is generated from the predicted data. If the reliability exceeds the reliability threshold, it is a backup of the key components of the valve control system, and it is determined whether to switch the key components based on the constructed adjustment degree. The reliability of the valve system is improved to ensure that the valve can be accurately executed after entering the usage state or receiving the corresponding control instruction, thereby solving the problems in the background technology.

[0008] (II) Technical solution

[0009] To achieve the above objectives, the present invention is implemented through the following technical solutions: a valve intelligent management and control platform based on the Internet of Things, including a communication quality monitoring unit, which monitors the communication quality in the valve installation area and constructs a corresponding communication quality data set, and then generates a strength coefficient Dsx. If the strength coefficient Dsx does not exceed the communication quality threshold, the communication conditions in the corresponding sub-area are optimized;

[0010] A scene adaptation unit identifies the current valve usage scene, matches a valve control scheme corresponding to the usage scene, executes the control scheme, and adjusts the operating state of the valve;

[0011] A control strategy optimization unit, after executing the control scheme, monitors the valve operation status data, constructs a corresponding valve status data set, and then constructs a difference degree Cyd. If the difference degree Cyd exceeds a difference threshold, the control strategy is optimized with the trained optimization model to obtain an optimized control strategy;

[0012] The backup component switching unit predicts the operating status of the valve control system with the trained valve control model, and generates the reliability Kdv from the predicted data. If the reliability Kdv exceeds the reliability threshold, it is the backup of the key component of the valve control system, and determines whether to switch the key component based on the constructed adjustment degree Tds.

[0013] Furthermore, the area to be installed of the valve is divided into several sub-areas, and a detection point is set in each sub-area. The communication quality is detected at the detection point, and the intensity coefficient Dsx is constructed from the detection data. The low-quality area is screened out with the intensity coefficient Dsx. After an electronic map covering the area to be installed is constructed, the low-quality area is marked on the electronic map.

[0014] Furthermore, a data acquisition device and an actuator are installed on the valve; the data acquisition device collects image information in the area around the current valve or receives control instructions, identifies the two, identifies the current valve usage scenario and outputs it; configures the corresponding valve control scheme according to several pre-set usage scenarios, and constructs a control scheme library after summarizing.

[0015] Furthermore, after executing the control scheme, a number of equally spaced collection nodes are set, and the state data after the valve is opened is collected by the data collection device at the collection node, and the corresponding preset state data is obtained by the control scheme; the difference degree is constructed by the valve state data set, and if the difference degree Cyd obtained by analysis exceeds the difference threshold, an optimization instruction is issued to the outside.

[0016] Furthermore, the control strategy of the valve is obtained, with improving the precision of the valve response as the optimization goal and no increase in water consumption as the constraint condition, and an ant colony algorithm is used to build an optimization model. The control strategy is optimized with the trained optimization model to obtain the optimized control strategy.

[0017] Furthermore, the valve control model is obtained by training with sample data, and the valve control system test and its related words are used as search terms to complete the construction of the valve test knowledge graph; after feature recognition of the data of the valve and its control system, the corresponding test features are obtained.

[0018] Furthermore, a corresponding test plan is matched for the current valve control system; the test plan is used as input, and the operating state of the valve control system is predicted using the trained valve control model, and after several predictions, the obtained test parameters are summarized to construct a test data set.

[0019] Furthermore, the reliability Kdv is generated from the test data set in the following manner: the leakage rate Lv, response speed Xv and flow coefficient Sv obtained from the test are linearly normalized, and the corresponding data values ​​are mapped to the interval [0, 1] according to the following formula:

[0020]

[0021] Weight coefficient: 0≤ρ≤1, 0≤ζ≤1.

[0022] Furthermore, after the valve control coefficient enters the use state, the corresponding difference Cyd and intensity coefficient Dsx are obtained in each sub-period within the use cycle, and the adjustment degree Tds is constructed after the two are aggregated. If the obtained adjustment degree Tds exceeds the adjustment degree threshold, the key components of the valve control system are replaced with backup parts.

[0023] Furthermore, the adjustment degree Tds is generated as follows:

[0024]

[0025] Among them, k 2 , k 1 is the weight, 0≤k 1 ≤1,0≤k 2 ≤1, and k 1 +k 2 =1, Cyd i is the difference within the ith sub-period, Dsx i Intensity coefficient in the i-th sub-period, i=1, 2, ...m, m is the number of sub-periods.

[0026] (III) Beneficial effects

[0027] The present invention provides a valve intelligent management and control platform based on the Internet of Things, which has the following beneficial effects:

[0028] 1. Evaluate the communication conditions in the installation area through the constructed strength coefficient Dsx, judge the communication environment in the installation area, and verify the ability of the valve control system in the installation area to receive and issue control instructions. If the ability to receive control instructions is poor, if it can be optimized and improved in time, the valve control system will not delay the adjustment of the valve usage status, or even fail to receive the corresponding control instructions, thus ensuring the reliability of the valve control system.

[0029] 2. Quickly give the corresponding control plan according to the usage scenario, and make targeted control of the valve according to the control plan, so that after the valve enters the use state, no additional manual intervention and adjustment are required, and the opening and closing of the valve can be accurately adjusted, thereby saving water resources when controlling the valve.

[0030] 3. Evaluate the execution effect of the control scheme with the degree of difference. If the execution effect fails to meet expectations, it means that the valve control system fails to achieve the expected control effect on the valve. Optimize the existing control strategy and obtain the optimized control strategy. When the valve is controlled according to the optimized control strategy, the control of the valve is more refined, thereby improving the reliability of the valve control system.

[0031] 4. The valve test knowledge graph provides a test plan to avoid manual design of the test plan, thereby improving the test efficiency; the trained valve control model predicts and analyzes the obtained test plan, so that the manual test can be replaced by simulation test analysis to improve the test efficiency.

[0032] 5. Build the corresponding reliability based on the test data and evaluate the reliability of the current valve control system with the reliability. If the reliability is lower than expected, back up the key components of the valve control system and replace them when necessary to improve the reliability of the valve system and ensure that the valve can be accurately executed after entering the use state or receiving the corresponding control instructions.

[0033] 6. Construct the corresponding adjustment degree based on the acquired monitoring data, and judge whether the key components of the valve control system need to be switched according to the adjustment degree. If necessary, the components that need to be replaced can be quickly switched, or each component can be replaced in turn according to the criticality of each component. After the valve control system enters the use state, the reliability of the valve control system operation can be guaranteed by switching the key components. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 This is a schematic diagram of the structure of the valve intelligent management and control platform based on the Internet of Things of the present invention;

[0035] Figure 2 It is a structural schematic diagram of the valve intelligent control method based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0036] 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 only 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.

[0037] See also Figure 1 and Figure 2 The present invention provides a valve intelligent management and control platform based on the Internet of Things, comprising:

[0038] A communication quality monitoring unit monitors the communication quality in the valve installation area and constructs a corresponding communication quality data set, generates a strength coefficient Dsx from the communication quality data set, and optimizes the communication conditions in the corresponding sub-area if the strength coefficient Dsx does not exceed the communication quality threshold;

[0039] When applied, include the following:

[0040] Step 101: After the installation of several valves is completed, the area to be installed of the valves is divided into several sub-areas, and each sub-area is numbered respectively. A detection point is set in each sub-area, and the communication quality is detected at the detection point. The detection data is summarized to construct a communication quality data set;

[0041] Step 102: construct the strength coefficient Dsx from the detection data in the communication quality data set in the following manner: perform linear normalization processing on the collected data transmission rate Cs and signal strength Cd, and map the corresponding data values ​​to the interval [0, 1] according to the following formula:

[0042]

[0043] Weight coefficient: 0≤β≤1, 0≤α≤1, and α+β=1, i=1, 2, …, k, k is the number of sub-regions; Cs avg is the mean data transmission rate, is the qualified standard value of data transmission rate, Cs i is the data transmission rate of the ith sub-area; Cd avg is the mean signal strength, is the qualified standard value of signal strength, Cd i is the signal strength in the i-th sub-area;

[0044] When in use, before installing and using the valve control system, the communication quality in the valve installation area is detected and the intensity coefficient Dsx used to describe the communication quality is constructed, which can evaluate the communication quality in the installation area;

[0045] Step 103: pre-set a communication quality threshold according to the usage data of the communication unit adapted to the valve and the expectation of its communication quality; if the strength coefficient Dsx does not exceed the communication quality threshold, it means that the data communication quality in the corresponding sub-area is poor, and the ability of the communication unit corresponding to the valve to receive control instructions is poor, and optimization is required;

[0046] The corresponding sub-area is determined as a low-quality area. After constructing an electronic map covering the area to be installed, the low-quality area is marked on the electronic map, and an optimization instruction is issued to the outside. After receiving the optimization instruction, the communication conditions in the corresponding sub-area are optimized, for example, the communication unit is replaced, or a communication enhancement module is set.

[0047] When using, combine the contents in steps 101 to 103:

[0048] By evaluating the communication conditions in the installation area through the constructed strength coefficient Dsx, the communication environment in the installation area can be judged, and the ability of the valve control system in the installation area to receive and issue control commands can be verified. If the ability to receive control commands is poor, if it can be optimized and improved in time, the valve control system will not delay or lag in adjusting the valve usage status, or even fail to receive the corresponding control commands, thereby ensuring the reliability of the valve control system.

[0049] After the valve and installation system are installed, if there is a certain amount of communication signal interference or a communication blind spot in the area where the valve control system is located, the valve control system may not be able to effectively receive the given control instructions when in use, making it difficult for the valve to execute the corresponding control instructions as expected, reducing the reliability of the valve control system. Moreover, after receiving the control instructions, due to the insufficient execution of the valve control strategy by the actuator, the valve may not achieve the expected execution effect when executing the control instructions.

[0050] The scene adaptation unit identifies the current valve usage scene when the valve is used, matches the valve control scheme corresponding to the usage scene, executes the control scheme, and adjusts the operating state of the valve;

[0051] When applied, include the following:

[0052] Step 201: Install a data acquisition device on the valve, including: an image sensor, a pressure sensor, a temperature sensor, a flow sensor, etc., for monitoring the working state of the valve, and install an actuator, such as an electric or pneumatic actuator, to achieve remote or automatic control of the opening and closing of the valve; thereby, receiving data from the sensor, and after processing and analyzing the collected data, so as to adjust or control the valve;

[0053] Step 202: When the valve enters the use state, the data acquisition device collects image information in the area around the current valve or receives control instructions, identifies the two, and obtains the recognized data features; compares the recognized data features with the use scenarios in the pre-built use scenario library, identifies the current valve use scenario and outputs it;

[0054] During use, through data recognition and image recognition, after the valve enters the use state or receives the control instruction, the current usage scenario of the valve is judged and the use status of the valve is classified, thereby forming targeted management when controlling and scheduling the valve.

[0055] Step 203: Configure corresponding valve control schemes according to several pre-set usage scenarios, and build a control scheme library after summarizing. After obtaining the usage scenario of the valve, execute the corresponding control scheme to adjust the operating state of the valve, for example, automatically adjust the valve opening according to the real-time data of flow or pressure.

[0056] When using, combine the contents in steps 201 to 203:

[0057] After obtaining the current usage scenario of the valve, the corresponding control plan is quickly given according to the usage scenario, and the valve is controlled in a targeted manner according to the control plan. Therefore, after the valve enters the use state, no additional manual intervention and adjustment are required, and the opening and closing of the valve are accurately adjusted, thereby saving water resources when controlling the valve.

[0058] A control strategy optimization unit, after executing the control scheme, monitors the valve operation status data, constructs a corresponding valve status data set, constructs a difference degree Cyd from the valve status data set, and optimizes the control strategy with the trained optimization model if the difference degree Cyd exceeds the difference threshold, to obtain an optimized control strategy;

[0059] When applied, include the following:

[0060] Step 301: After executing the corresponding control scheme on the valve, a number of equally spaced collection nodes are set, and the state data after the valve is opened is collected by the data collection device on the collection node, and the corresponding preset state data is obtained by the control scheme; and a valve state data set is constructed;

[0061] Step 302: Determine the difference between the control scheme and the actual effect, and construct the difference degree from the valve state data set in the following manner: linearly normalize the acquired valve opening and closing speed Fs, and map the corresponding data value to the interval [0, 1] according to the following formula:

[0062]

[0063] Where, j = 1, 2, ..., q, q is the number of acquisition nodes, weight coefficient: 0 ≤ F 3 ≤1,0≤F 4 ≤1 and F 3 +F 4 =1; Fs j is the opening and closing speed at the jth acquisition node, Fs avg is its mean value; is the qualified standard value of the opening and closing speed at the jth acquisition node;

[0064] Based on historical data and the expected effect of the valve, a difference threshold is set in advance. If the difference Cyd obtained by analysis exceeds the difference threshold, it means that the execution effect of the scheme has not actually reached the expected level, and the control strategy of the valve needs to be optimized. At this time, an optimization instruction is issued to the outside.

[0065] Step 303: after receiving the optimization instruction, the control strategy of the corresponding valve is obtained, the refinement of the valve response is taken as the optimization target, the water consumption is not increased as the constraint condition, the ant colony algorithm is used to build the optimization model, the control strategy is optimized with the trained optimization model, and the optimized control strategy is obtained;

[0066] When using, combine the contents in steps 301 to 303:

[0067] After the corresponding control scheme is determined by the usage scenario of the valve, the valve control system executes the corresponding control scheme, monitors and compares the execution effect of the control scheme, and evaluates the execution effect of the control scheme by the degree of difference. If the execution effect fails to meet expectations, it means that the valve control system fails to achieve the desired control effect on the valve. Therefore, it is necessary to optimize the existing control strategy and obtain the optimized control strategy. When the valve is controlled according to the optimized control strategy, the control of the valve is more refined, which further improves the reliability of the valve control system.

[0068] The backup component switching unit predicts the operating status of the valve control system with the trained valve control model, and generates the reliability Kdv from the predicted data. If the reliability Kdv exceeds the reliability threshold, it is the backup of the key component of the valve control system, and determines whether to switch the key component based on the constructed adjustment degree Tds;

[0069] When applied, include the following:

[0070] Step 401: collect valve specification data and performance data, communication status data, and water pipe and water flow status data; construct an initial model using a convolutional neural network, extract part of the collected data as sample data, train and test the initial model using the sample data, and obtain a trained valve control model;

[0071] Using valve control system test and its related words as search words, after searching and aggregating the corresponding data, a knowledge graph set is established. After processing the data in the knowledge graph set and building entity relationships, the construction of the valve test knowledge graph is completed.

[0072] Step 402: After feature recognition is performed on the data of the valve and its control system, the corresponding test features are obtained, and the corresponding test scheme is matched for the current valve control system using the trained matching model according to the correspondence between the test features and the test scheme; the running state of the valve control system is predicted using the trained valve control model with the test scheme as input, and after several predictions, the obtained test parameters are summarized to construct a test data set;

[0073] When in use, after optimizing the valve control strategy, the valve control system is tested. At this time, after completing data collection, the trained valve control model and valve test knowledge graph are obtained respectively, so that with the cooperation of the two, the valve test knowledge graph gives a test plan to avoid manually designing the test plan, thereby improving the test efficiency; the trained valve control model predicts and analyzes the obtained test plan, so that the manual test can be replaced by simulation test analysis to improve the test efficiency;

[0074] Step 403: Generate the reliability Kdv from the test data set in the following manner: perform linear normalization on the leakage rate Lv, response speed Xv and flow coefficient Sv obtained from the test, and map the corresponding data values ​​to the interval [0, 1] according to the following formula:

[0075]

[0076] Weight coefficient: 0≤ρ≤1, 0≤ζ≤1. The weight coefficient can be set by the user or obtained by referring to the hierarchical analysis method;

[0077] According to the historical data of the valve control system and the expected use of the valve control system reliability, the reliability threshold is set in advance; if the reliability exceeds the reliability threshold, redundant control is implemented to set the backup of key components, such as the backup of various sensors, controllers and actuators;

[0078] During use, after the trained valve control model performs predictive analysis on the valve control system, the corresponding reliability is constructed based on the test data, and the reliability of the current valve control system is evaluated by the reliability. If the reliability is lower than expected, the key components of the valve control system are backed up and replaced when necessary, thereby improving the reliability of the valve system and ensuring that the valve can be accurately executed after entering the use state or receiving the corresponding control instructions.

[0079] Step 404: After the valve control coefficient enters the use state, a use cycle is set, and several sub-cycles of equal length are set in the use cycle, and the corresponding difference Cyd and intensity coefficient Dsx are obtained in each sub-cycle. After the two are aggregated, the adjustment degree Tds is constructed, and the generation method is as follows:

[0080]

[0081] Among them, k 2 , k 1 is the weight, 0≤k 1 ≤1,0≤k 2 ≤1, and k 1 +k 2 =1, Cyd iis the difference within the ith sub-period, Dsx i The intensity coefficient in the i-th sub-period, i = 1, 2, ... m, m is the number of sub-periods;

[0082] According to the historical data of the valve control system and the expected use of the valve control system reliability, the adjustment degree threshold is pre-set; if the obtained adjustment degree Tds exceeds the adjustment degree threshold, a switching instruction is issued; after receiving the switching instruction, the key components of the valve control system are replaced with backup parts;

[0083] When used, combine the contents in steps 401 to 404:

[0084] After the valve control system enters the use state, continue to monitor its use state, and finally construct the corresponding adjustment degree based on the acquired monitoring data. According to the degree of adjustment, judge whether the key components of the valve control system need to be switched. If necessary, the components that need to be replaced can be quickly switched, or each component can be replaced in turn according to its criticality. Thus, after the valve control system enters the use state, the reliability of the valve control system operation can be guaranteed by switching the key components.

[0085] It should be noted that the hierarchical analysis method is a combination of qualitative and quantitative analysis methods. It can decompose complex problems into multiple levels. By comparing the importance of factors at each level, it can help decision makers make decisions on complex issues and determine the final decision plan. In this process, the hierarchical analysis method can be used to determine the weight coefficients of these indicators.

[0086] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0087] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0088] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0089] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only some logical function divisions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0090] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0091] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0092] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0093] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0094] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A valve intelligent management and control platform based on the Internet of Things, characterized by: include, A communication quality monitoring unit monitors the communication quality in the valve installation area and constructs a corresponding communication quality data set, thereby generating a strength coefficient Dsx. If the strength coefficient Dsx does not exceed the communication quality threshold, the communication conditions in the corresponding sub-area are optimized; A scene adaptation unit identifies the current valve usage scene, matches a valve control scheme corresponding to the usage scene, executes the control scheme, and adjusts the operating state of the valve; The control strategy optimization unit monitors the valve operation status data after executing the control scheme, constructs a corresponding valve status data set, and then constructs a difference degree Cyd. If the difference degree Cyd exceeds the difference threshold, the control strategy is optimized with the trained optimization model to obtain an optimized control strategy. The backup component switching unit predicts the operating status of the valve control system with the trained valve control model, generates the reliability Kdv from the predicted data, and backs up the key components of the valve control system if the reliability Kdv exceeds the reliability threshold, and determines whether to switch the key components based on the constructed adjustment degree Tds; After the valve control system enters the use state, the corresponding difference Cyd and strength coefficient Dsx are obtained in each sub-period within the use cycle, and the adjustment degree Tds is constructed after the two are summarized. If the obtained adjustment degree Tds exceeds the adjustment degree threshold, the key components of the valve control system are replaced with backup parts; The adjustment degree Tds is generated as follows: Among them, k2 and k1 are weights, 0≤k1≤1, 0≤k2≤1, and k1+k2=1, Cyd i is the difference within the ith sub-period, Dsx i Intensity coefficient in the i-th sub-period, i=1, 2, ...m, m is the number of sub-periods.

2. According to the IoT-based valve intelligent management and control platform of claim 1, it is characterized by: The area to be installed of the valve is divided into several sub-areas, and detection points are set in each sub-area. The communication quality is detected at the detection points, and the intensity coefficient Dsx is constructed from the detection data. The low-quality areas are screened out with the intensity coefficient Dsx. After an electronic map covering the area to be installed is constructed, the low-quality areas are marked on the electronic map.

3. According to the IoT-based valve intelligent management and control platform of claim 1, it is characterized by: A data acquisition device and an actuator are installed on the valve; the data acquisition device collects image information in the area around the current valve or receives control instructions, identifies the two, identifies the current valve usage scenario and outputs it; configures the corresponding valve control scheme according to several pre-set usage scenarios, and constructs a control scheme library after summarizing.

4. According to the IoT-based valve intelligent management and control platform of claim 3, it is characterized by: After executing the control scheme, several equally spaced collection nodes are set. The data collection device collects the status data after the valve is opened on the collection node, and the control scheme obtains the corresponding preset status data; the difference degree is constructed from the valve status data set. If the difference degree Cyd obtained by analysis exceeds the difference threshold, an optimization instruction is issued to the outside.

5. According to the IoT-based valve intelligent management and control platform of claim 4, it is characterized by: The control strategy of the valve is obtained, with improving the precision of the valve response as the optimization goal and no increase in water consumption as the constraint condition. The ant colony algorithm is used to build an optimization model, and the control strategy is optimized with the trained optimization model to obtain the optimized control strategy.

6. According to the IoT-based valve intelligent management and control platform of claim 5, it is characterized by: The valve control model is obtained by training with sample data, and the valve control system test is used as the search term to complete the construction of the valve test knowledge graph; after feature recognition of the data of the valve and its control system, the corresponding test features are obtained.

7. The valve intelligent management and control platform based on the Internet of Things according to claim 6 is characterized by: Match the corresponding test plan for the current valve control system; use the test plan as input, use the trained valve control model to predict the operating status of the valve control system, and after several predictions, summarize the obtained test parameters to construct a test data set.

8. The valve intelligent management and control platform based on the Internet of Things according to claim 7 is characterized by: The reliability Kdv is generated from the test data set in the following way: the leakage rate Lv, response speed Xv and flow coefficient Sv obtained from the test are linearly normalized and the corresponding data values ​​are mapped to the interval [0,1] according to the following formula: Weight coefficient: 0≤ρ≤1, 0≤ζ≤1.

Images