Water conservancy and hydropower equipment remote operation and maintenance management system based on internet of things

Abstract

The present application relates to the technical field of water conservancy and hydropower equipment, and particularly relates to a water conservancy and hydropower equipment remote operation and maintenance management system based on the Internet of Things, which comprises: a front-end monitoring module for monitoring water quality of an introduced grid cleaner; a sensing module for sensing grid cleaner operation state parameters in real time under the operation state of the grid cleaner; and an evaluation module for receiving water quality monitoring results in the front-end monitoring module and grid cleaner operation state parameters in the sensing module, and evaluating the current performance state of the grid cleaner in combination with the two. The present application takes the water quality monitoring results as parameters for evaluating the operation state of the grid cleaner, and the system assists in performing operation safety evaluation on the grid cleaner in combination with the operation state parameters of the grid cleaner itself, generates a visual image representing changes in the operation state of the grid cleaner based on the evaluation results, and configures different early warning logics to issue operation safety early warning of the grid cleaner, thereby providing protection for stable operation of the grid cleaner.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of water conservancy and hydropower equipment, and particularly relates to a water conservancy and hydropower equipment remote operation and maintenance management system based on Internet of Things. BACKGROUND

[0002] In a water conservancy and hydropower project, a grid trash cleaner is very important. It is usually installed at a water inlet and can effectively intercept branches, weeds, garbage and other sundries in water flow. Through continuous cleaning, the water flow is ensured to flow smoothly into equipment such as a water turbine, preventing sundries from damaging the equipment and maintaining power generation efficiency, which plays a key role in stable operation of the project and safety of the equipment.

[0003] An application patent application with the application number 202210969479.4 discloses an intelligent monitoring and early warning method for a grid trash cleaner. The method comprises: acquiring a front pool monitoring image, a first rake monitoring image and a second rake monitoring image; identifying and extracting an area of interest from the front pool monitoring image, the first rake monitoring image and the second rake monitoring image respectively; identifying front pool garbage from the area of interest of the front pool monitoring image, rake-in garbage from the area of interest of the first rake monitoring image and rake-under garbage from the area of interest of the second rake monitoring image according to a preset garbage identification model; calculating a front pool garbage proportion according to the identified front pool garbage, and if the front pool garbage proportion is greater than a preset first garbage proportion threshold, performing front pool garbage abnormality warning; screening rake-in large garbage according to the identified rake-in garbage, and if the rake-in large garbage length is greater than a preset length threshold, performing rake-in garbage abnormality warning; screening rake-under large garbage according to the identified rake-under garbage, and if the rake-under large garbage proportion is greater than a preset second garbage proportion threshold, performing rake-under garbage abnormality warning; the method further comprises: acquiring a third rake monitoring image, identifying and extracting an area of interest from the third rake monitoring image; inputting the area of interest in the third rake monitoring image into a preset rake tilt detection model to obtain a rake horizontal tilt angle; and if the rake horizontal tilt angle is greater than a preset angle threshold, performing rake tilt abnormality warning. The application solves the problem that in the daily operation process of the grid trash cleaner, situations such as grid bars being stuck by garbage, rakes being tilted by garbage, and electric motors being overloaded and heated due to being stuck often occur, causing damage to the equipment and even failure to operate, and the failure situation affects the daily production of the water purification plant. At present, the water purification plant uses artificial regular patrol to monitor the garbage condition in the sewage lifting pump water collecting pool during the daily operation process of the equipment, and decides whether to start the grid trash cleaner. Meanwhile, the operation condition of the equipment needs to be monitored, and the equipment needs to be stopped for treatment in case of abnormal condition, but this way wastes human resources, and may cause missed detection due to inattention, affecting the operation of the grid trash cleaner.

[0004] However, for the operation monitoring of the grid cleaner, the prior art is often committed to the fault judgment of the equipment itself, which is blank in fault prediction, and the fault judgment usually only considers the operation parameters of the equipment, without considering the related parameters of the water body processed by the equipment.

[0005] Therefore, a remote operation and maintenance management system for water conservancy and hydropower equipment based on Internet of Things is proposed. SUMMARY

[0006] In view of the above shortcomings of the prior art, the present application provides a remote operation and maintenance management system for water conservancy and hydropower equipment based on Internet of Things, which solves the technical problems raised in the background art.

[0007] To achieve the above purpose, the present application is realized by the following technical solutions:

[0008] The remote operation and maintenance management system for water conservancy and hydropower equipment based on Internet of Things comprises:

[0009] The front-end monitoring module is used to monitor the water quality introduced into the grid cleaner. The sensing module is used to sense the operating state parameters of the grid cleaner in real time under the operating state of the grid cleaner. The evaluation module is used to receive the water quality monitoring results in the front-end monitoring module and the operating state parameters of the grid cleaner in the sensing module, and evaluate the current performance state of the grid cleaner in combination with the two. The early warning module is used to set a safety judgment threshold for the performance state of the grid cleaner, receive the current performance state evaluation result of the grid cleaner in the evaluation module, and compare the evaluation result with the judgment threshold. When the evaluation result is less than the judgment threshold, an early warning prompt is triggered. The message module is used to record the triggering time of the historical early warning prompt of the early warning module, and generate a grid cleaner operation message based on the recorded triggering time.

[0010] Further, the front-end monitoring module is integrated by a camera, and the front-end monitoring module collects water body images introduced into the grid cleaner, and monitors the water quality based on the water body images.

[0011] The front-end monitoring module performs water quality monitoring once based on a preset time threshold, and when collecting water body images within the preset time threshold, the flow rate of the water body introduced into the grid cleaner is used to adaptively control the water body image collection frequency, so that the faster the water flow rate, the higher the water body image collection frequency, and the slower the water flow rate, the lower the water body image collection frequency.

[0012] The front-end monitoring module and the sensing module are synchronously operated in the system.

[0013] Further, the monitoring logic of the water quality introduced into the grid cleaner in the front-end monitoring module is represented as:

[0014] ;

[0015] In the formula: C is the water body quality performance value; n is the total amount of water body images; α and β are weight coefficients; M and N are the width and height of the water body image; F i (x,y) is the pixel value of the image after the i-th water body image is subjected to gray scale processing and Gaussian filtering at the coordinate (x,y); is the average gray scale value of the water body image; S i is the area of the impurity region image segmented from the i-th water body image using an image segmentation algorithm; A is the area of the water body image;

[0016] The weight coefficients α and β are both positive numbers, and their sum is 1, and their values are defined by the system user, C is larger, indicating that the water quality is worse, and vice versa, indicating that the water quality is better.

[0017] Further, the perception module runs the grid cleaner running state parameters of perception include: running power, water level difference before and after the grid, noise level, driving torque, rake depth;

[0018] The perception module stores the grid cleaner running state parameters perceived by the perception module, and distinguishes the storage based on the preset time threshold of the front-end monitoring module running application, so that the time threshold of the grid cleaner running state parameters stored in each distinguished storage interval is equal to the preset time threshold of the front-end monitoring module running application.

[0019] Further, in the evaluation module, the evaluation stage of the current performance state of the grid cleaner is based on the grid cleaner running state parameters to evaluate the health of the grid cleaner running state;

[0020] Define the parameter deviation value, for example, running power:

[0021] ;

[0022] In the formula: ΔP is the running power deviation value; (P min ,P max ) is the normal range of running power; is the average value of the running power in the grid cleaner running state parameters perceived by the perception module;

[0023] Wherein, the parameter deviation value definition logic of the grid level difference before and after the grid, noise level, driving torque, and rake depth in the grid cleaner running state parameters is the same as the running power deviation value definition logic, and the deviation values of the grid level difference before and after the grid, noise level, driving torque, and rake depth are recorded as ΔH, ΔN, ΔT, and ΔD.

[0024] Further, the grid cleaner running health evaluation logic is:

[0025] ;

[0026] The larger S is, the better the health of the operation of the grid cleaner is, and vice versa.

[0027] The evaluation logic of the current performance state of the grid cleaner in the evaluation module is:

[0028] ;

[0029] In the formula: is the performance value of the current performance state of the grid cleaner; S is the health of the operation of the grid cleaner; and C is the performance value of the water quality.

[0030] Wherein, The larger S is, the better the health of the operation of the grid cleaner is, and vice versa.

[0031] Further, the performance state safety judgment threshold of the grid cleaner in the early warning module is customized by the system end user, and when the early warning module triggers the early warning prompt, the early warning module sends the early warning prompt information to the grid cleaner management background, and the content of the early warning prompt information is the text information preset by the system end user in the form of text.

[0032] The lower level of the early warning module is provided with a visualization unit and a prediction unit, the visualization unit is used to record the evaluation results received by the early warning module, and a line graph representing the digital change trend of the evaluation results is generated based on the evaluation results, and the prediction unit is used to traverse the line graph generated in the visualization unit, and whether the grid cleaner has hidden hazards is predicted based on the line graph.

[0033] Wherein, when the prediction unit running prediction result is yes, the early warning module is controlled to trigger the early warning prompt synchronously, the early warning prompt content triggered based on the prediction unit is different from the early warning prompt content triggered by the early warning module autonomously, and the early warning prompt content triggered based on the prediction unit is customized by the system end user.

[0034] Further, the prediction unit updates the line graph in real time based on the evaluation results received by the early warning module, and when the evaluation results applied when the early warning module autonomously triggers the early warning prompt exist in the line graph, the line graph is reset, and the line graph is regenerated based on the subsequent received evaluation results;

[0035] When the prediction unit traverses the line graph to predict whether the grid cleaner has hidden hazards, the line in the line graph corresponding to the latest three evaluation results is predicted, the line is continuously decreasing, the prediction result is yes, and vice versa, the prediction result is no.

[0036] Further, the generated grille cleaner operation message content generated by the message module further includes the grille cleaner performance state evaluation result corresponding to the early warning prompt trigger time.

[0037] The grille cleaner operation message generated by the message module is fed back to the grille cleaner management background in real time.

[0038] Further, the front-end monitoring module is interactively connected with the sensing module and the evaluation module through a wireless network, the evaluation module is interactively connected with the early warning module through a wireless network, the early warning module is interactively connected with a visualization unit and a prediction unit through a wireless network, and the early warning module is interactively connected with the message module through a wireless network.

[0039] Compared with the known prior art, the technical scheme provided by the present application has the following beneficial effects:

[0040] The present application provides a water conservancy and hydropower equipment remote operation and maintenance management system based on the Internet of Things, which introduces the water quality monitoring of the grille cleaner as a parameter for evaluating the operation state of the grille cleaner during operation, further assists the system in evaluating the operation safety of the grille cleaner in combination with the self-operation state parameters of the grille cleaner, generates a visual image representing the operation state change of the grille cleaner based on the evaluation result, and configures different early warning logics to issue an operation safety early warning of the grille cleaner, thereby providing a guarantee for the long-term stable operation of the grille cleaner. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to more clearly illustrate the technical schemes in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0042] Figure 1 It is a structural schematic diagram of the water conservancy and hydropower equipment remote operation and maintenance management system based on the Internet of Things. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical scheme and advantages of the embodiments of the present application more clear, the technical scheme in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0044] The present application will be further described below in combination with embodiments.

[0045] Embodiment:

[0046] The water conservancy and hydropower equipment remote operation and maintenance management system based on the Internet of Things of the embodiment, as shown in Figure 1 , comprises:

[0047] The front-end monitoring module is used for monitoring the water quality of the intake grid cleaner;

[0048] The front-end monitoring module is integrated by the camera, and the front-end monitoring module collects water body images of the intake grid cleaner, and monitors the water quality based on the water body images;

[0049] The front-end monitoring module performs water quality monitoring once based on a preset time threshold, and when collecting water body images within the preset time threshold, the flow rate of the water body introduced into the grid cleaner is used to adaptively control the water body image collection frequency, so that the faster the water flow rate, the higher the water body image collection frequency, and the slower the water flow rate, the lower the water body image collection frequency;

[0050] The front-end monitoring module and the sensing module are synchronously operated in the system;

[0051] The monitoring logic of the water quality of the intake grid cleaner in the front-end monitoring module is represented as:

[0052] ;

[0053] In the formula, C is the water quality performance value; n is the total amount of water body images; α and β are weight coefficients; M and N are the width and height of the water body image; F i (x,y) is the pixel value of the image at coordinates (x,y) after the i-th water body image is subjected to grayscale processing and Gaussian filtering; is the average grayscale value of the water body image; S i is the impurity area image area segmented by the i-th water body image using an image segmentation algorithm; and A is the water body image area.

[0054] The weight coefficients α and β are both positive numbers, and their sum is 1, and their values are defined by the system end user, and the larger C is, the worse the water quality is, and vice versa, the better the water quality is;

[0055] Through the above logical formula calculation, the water quality performance value is calculated to provide support for the further operation of the evaluation module in the system, and the monitoring result in this digital form is more convenient for the system end user to read and judge the specific situation of the water quality.

[0056] The sensing module is used for real-time sensing of the grid cleaner running state parameters under the grid cleaner running state;

[0057] The grid cleaner running state parameters perceived by the perception module include: running power, water level difference before and after the grid, noise level, driving torque, and rake insertion depth.

[0058] The perception module stores the perceived grid cleaner running state parameters, and distinguishes the storage based on the preset time threshold of the front-end monitoring module running application in the storage stage, so that the time threshold of the grid cleaner running state parameters stored in each distinguished storage interval is equal to the preset time threshold of the front-end monitoring module running application.

[0059] The evaluation module receives the water body quality monitoring results in the front-end monitoring module and the grid cleaner running state parameters in the perception module, and evaluates the current performance state of the grid cleaner in combination with the two.

[0060] In the evaluation stage of the current performance state of the grid cleaner in the evaluation module, the health of the grid cleaner running state is evaluated based on the grid cleaner running state parameters.

[0061] Define the parameter deviation value, taking the running power as an example:

[0062] ;

[0063] In the formula: ΔP is the running power deviation value; (P min ,P max ) is the normal range of running power; is the average value of the running power in the grid cleaner running state parameters perceived by the perception module;

[0064] Wherein, the parameter deviation value definition logic of the water level difference before and after the grid, noise level, driving torque, and rake insertion depth in the grid cleaner running state parameters is the same as the running power deviation value definition logic, and the deviation values of the water level difference before and after the grid, noise level, driving torque, and rake insertion depth are recorded as ΔH, ΔN, ΔT, and ΔD.

[0065] The grid cleaner running health evaluation logic is:

[0066] ;

[0067] The larger S is, the better the health of the grid cleaner running is, and vice versa, indicating that the health of the grid cleaner running is worse.

[0068] The evaluation logic of the current performance state of the grid cleaner in the evaluation module is:

[0069] ;

[0070] In the formula: is the current performance state value of the grid cleaner; S is the operation health of the grid cleaner; C is the water quality performance value;

[0071] wherein, The greater, the better the current performance state of the grid cleaner, and vice versa, the worse the current performance state of the grid cleaner;

[0072] Through the above logical formula, the operation health of the grid cleaner is evaluated to support the operation of the warning module of the system in this embodiment, and to ensure that the stable triggering of the warning module remotely maintains and manages the grid cleaner.

[0073] The warning module is used to set a performance state safety judgment threshold of the grid cleaner, receive the current performance state evaluation result of the grid cleaner in the evaluation module, compare the evaluation result with the judgment threshold, and trigger a warning prompt when the evaluation result is less than the judgment threshold;

[0074] The performance state safety judgment threshold of the grid cleaner in the warning module is defined by the system end user, and when the warning module triggers a warning prompt, the warning module sends a warning prompt information to the grid cleaner management background. The content of the warning prompt information is text format of the system end user preset text information;

[0075] The lower level of the warning module is provided with a visualization unit and a prediction unit. The visualization unit is used to record the evaluation result received by the operation of the warning module, and to generate a line graph representing the digital change trend of the evaluation result based on the evaluation result. The prediction unit is used to traverse the line graph generated in the visualization unit, and to predict whether there is a hidden hazard in the grid cleaner based on the line graph;

[0076] Wherein, when the prediction unit operation prediction result is yes, the warning module is controlled to trigger a warning prompt synchronously. The content of the warning prompt triggered based on the prediction unit is different from the content of the warning prompt triggered by the autonomous operation of the warning module, and the content of the warning prompt triggered based on the prediction unit is defined by the system end user;

[0077] The prediction unit updates the line graph in real time based on the evaluation result received by the warning module, and when the evaluation result applied when the warning module autonomously triggers a warning prompt exists in the line graph, the line graph is reset, and the line graph is regenerated based on the subsequent received evaluation result;

[0078] When the prediction unit traverses the line graph to predict whether there is a hidden hazard in the grid cleaner, the line in the line graph corresponding to the latest three evaluation results is predicted. If the line is continuously decreasing, the prediction result is yes, otherwise, the prediction result is no;

[0079] The message module is used to record the triggering time of the historical warning prompt of the warning module, and to generate a grid cleaner operation message based on the recorded triggering time;

[0080] The generated grille cleaner operation message content also includes the performance state evaluation result corresponding to the early warning prompt trigger time of the grille cleaner;

[0081] The grille cleaner operation message generated by the message module runs in real time feedback to the grille cleaner management background;

[0082] The front-end monitoring module is interactively connected with the sensing module and the evaluation module through a wireless network, the evaluation module is interactively connected with the early warning module through a wireless network, the early warning module is interactively connected with a visualization unit and a prediction unit through a wireless network, and the early warning module is interactively connected with the message module through a wireless network.

[0083] In the embodiment, the front-end monitoring module monitors the water quality introduced into the grille cleaner, the sensing module synchronously runs to sense the grille cleaner operation state parameters in real time under the grille cleaner operation state, the evaluation module receives the water quality monitoring results in the front-end monitoring module and the grille cleaner operation state parameters in the sensing module, evaluates the current performance state of the grille cleaner in combination with the two, the early warning module further sets a performance state safety judgment threshold of the grille cleaner, receives the current performance state evaluation result of the grille cleaner in the evaluation module, compares the evaluation result with the judgment threshold, triggers an early warning prompt when the evaluation result is less than the judgment threshold, the visualization unit synchronously records the evaluation result received by the early warning module, generates a line graph representing the digital change trend of the evaluation result based on the evaluation result, the prediction unit traverses the line graph generated in the visualization unit in real time, predicts whether the grille cleaner has hidden hazards based on the line graph, and finally records the trigger time of the early warning prompt of the early warning module through the message module. The grille cleaner operation message is generated based on the recorded trigger time, so as to realize the remote management and intelligent operation of the grille cleaner, and save the application cost of the grille cleaner in water conservancy and hydropower engineering.

[0084] In summary, in the above embodiment, the water quality introduced into the grille cleaner is monitored as a parameter for evaluating the operation state of the grille cleaner, which further assists the system to evaluate the operation safety of the grille cleaner in combination with the operation state parameters of the grille cleaner itself, generates a visualization image representing the operation state change of the grille cleaner based on the evaluation result, and configures different early warning logics to issue an operation safety early warning of the grille cleaner, thereby providing a guarantee for long-term and stable operation of the grille cleaner.

[0085] The above examples are only used to illustrate the technical solutions of the present application, and are not intended to limit the present application; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that the technical solutions recorded in the foregoing examples can be modified, or some technical features can be replaced by equivalent features; and these modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A remote operation and maintenance management system for water conservancy and hydropower equipment based on the Internet of Things, characterized in that, include: The front-end monitoring module is used to monitor the water quality introduced into the bar screen cleaning machine; The water quality monitoring logic introduced by the bar screen cleaning machine in the front-end monitoring module is expressed as follows: Where: C is the water quality performance value; n is the total amount of water image data; α and β are weighting coefficients; M and N are the width and height of the water image data; F i (x,y) represents the pixel value at coordinates (x,y) of the i-th water body image after grayscale processing and Gaussian filtering. S represents the average grayscale value of the water body image. i Let A be the area of ​​the impurity region segmented by the image segmentation algorithm in the i-th water body image; A is the area of ​​the water body image. Among them, the weighting coefficients α and β are both positive numbers, and their sum is 1. The values ​​of α and β are defined by the system user. The larger C is, the worse the water quality is, and vice versa. The sensing module is used to sense the operating status parameters of the bar screen cleaner in real time during operation. The evaluation module is used to receive water quality monitoring results from the front-end monitoring module and bar screen cleaning machine operating status parameters from the sensing module, and combine the two to evaluate the current performance status of the bar screen cleaning machine. The early warning module is used to set the safety judgment threshold for the performance status of the bar screen cleaner, receive the current performance status evaluation result of the bar screen cleaner from the evaluation module, compare the evaluation result with the judgment threshold, and trigger an early warning prompt when the evaluation result is less than the judgment threshold. The message module is used to record the trigger time of historical warning prompts from the early warning module, and to generate a bar screen cleaning machine operation message based on the recorded trigger time.

2. The IoT-based remote operation and maintenance management system for water conservancy and hydropower equipment according to claim 1, characterized in that, The front-end monitoring module is integrated with a camera. The front-end monitoring module collects water images introduced into the bar screen cleaning machine and monitors water quality based on the water images. The front-end monitoring module performs a water quality monitoring once based on a preset time threshold. When collecting water images within the preset time threshold, it adaptively adjusts the water image collection frequency based on the flow rate of the water introduced into the bar screen cleaning machine. The faster the water flow, the higher the water image collection frequency, and the slower the water flow, the lower the water image collection frequency. The front-end monitoring module and the sensing module operate synchronously in the system.

3. The IoT-based remote operation and maintenance management system for water conservancy and hydropower equipment according to claim 1, characterized in that, The sensing module senses the following operating status parameters of the bar screen cleaning machine: operating power, water level difference before and after the bar screen, noise level, driving torque, and rake insertion depth. The sensing module stores the sensing parameters of the bar screen cleaning machine's operating status. During the storage phase, it distinguishes the stored parameters based on the preset time threshold of the front-end monitoring module's operating application, ensuring that the time threshold of the bar screen cleaning machine's operating status parameters stored in each storage interval is equal to the preset time threshold of the front-end monitoring module's operating application.

4. The IoT-based remote operation and maintenance management system for water conservancy and hydropower equipment according to claim 1, characterized in that, The evaluation module includes an evaluation phase for the current performance status of the bar screen cleaner, which assesses the health of the bar screen cleaner's operating status based on its operating status parameters. Define parameter deviation values, taking operating power as an example: In the formula: ΔP is the deviation of operating power; (P min P max () represents the normal operating power range; The average operating power in the operating status parameters of the bar screen cleaner sensed by the sensing module; Among them, the deviation values ​​of the parameters of water level difference before and after the bar screen, noise level, driving torque, and rake insertion depth in the bar screen cleaning machine are defined by the same logic as the deviation values ​​of the operating power. The calculation results of the deviation values ​​of water level difference before and after the bar screen, noise level, driving torque, and rake insertion depth are recorded as ΔH, ΔN, ΔT, and ΔD.

5. The IoT-based remote operation and maintenance management system for water conservancy and hydropower equipment according to claim 4, characterized in that, The operational health assessment logic for the bar screen cleaning machine is as follows: The larger the value of S, the better the health of the bar screen cleaning machine; conversely, the smaller the value of S, the worse the health of the bar screen cleaning machine. The evaluation logic for the current performance status of the bar screen cleaner in the evaluation module is as follows: θ = S × C; In the formula: θ represents the current performance status of the bar screen cleaner; S represents the operational health of the bar screen cleaner; C represents the water quality performance value; The larger θ is, the better the current performance of the bar screen cleaner; conversely, the smaller θ is, the worse the current performance of the bar screen cleaner.

6. The IoT-based remote operation and maintenance management system for water conservancy and hydropower equipment according to claim 1, characterized in that, The safety threshold for judging the performance status of the bar screen cleaner in the early warning module is defined by the system user. When the early warning module triggers an early warning, it sends an early warning message to the bar screen cleaner management backend. The content of the early warning message is text information preset by the system user in text format. The early warning module is equipped with a visualization unit and a prediction unit. The visualization unit is used to record the evaluation results received by the early warning module and generate a line graph representing the trend of the numerical change of the evaluation results based on the evaluation results. The prediction unit is used to traverse the line graph generated in the visualization unit and predict whether there are hidden dangers in the bar screen cleaner based on the line graph. When the prediction result of the prediction unit is positive, the control and early warning module will trigger an early warning prompt simultaneously. The content of the early warning prompt triggered by the prediction unit is different from the content of the early warning prompt triggered by the early warning module running autonomously. Moreover, the content of the early warning prompt triggered by the prediction unit is customized by the system user.

7. The IoT-based remote operation and maintenance management system for water conservancy and hydropower equipment according to claim 6, characterized in that, The prediction unit updates the line graph in real time based on the evaluation results received by the early warning module. When the evaluation results applied when the early warning module autonomously triggers an early warning prompt exist in the line graph, the line graph is reset and regenerated based on the subsequently received evaluation results. When predicting whether there are hidden dangers in the bar screen cleaning machine by traversing the line graph, the prediction unit makes a prediction based on the line graph corresponding to the latest three evaluation results. If the line graph is continuously decreasing, the prediction result is yes; otherwise, the prediction result is no.

8. The IoT-based remote operation and maintenance management system for water conservancy and hydropower equipment according to claim 1, characterized in that, The bar screen cleaning machine operation message generated by the message module also includes the bar screen cleaning machine performance status evaluation result corresponding to the warning prompt trigger time; The bar screen cleaning machine operation message generated by the message module is fed back to the bar screen cleaning machine management backend in real time.

9. The IoT-based remote operation and maintenance management system for water conservancy and hydropower equipment according to claim 1, characterized in that, The front-end monitoring module interacts with the sensing module and the evaluation module via a wireless network. The evaluation module interacts with the early warning module via a wireless network. The lower level of the early warning module interacts with the visualization unit and the prediction unit via a wireless network. The early warning module interacts with the message module via a wireless network.

Images