Water pump house three-dimensional dynamic monitoring system based on ICONCIS configuration
By designing a three-dimensional dynamic monitoring system for water pump rooms based on ICONCIS configuration, combining reinforcement learning and fault prediction methods of autoencoder and long-term memory network, the problem of lack of independent decision-making and fault prediction of existing systems is solved, and efficient decision-making is achieved and intuitive information display.
Patent Information
- Application Number
- CN202411563373.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-05
- Publication Date
- 2025-02-11
AI Technical Summary
The existing pump room monitoring system lacks independent decision-making capabilities, fault prediction functions and intuitive information display, which leads to the system being unable to warning in advance when facing potential faults, affecting the normal operation of mine drainage.
A three-dimensional dynamic monitoring system for water pump room configuration based on ICONCIS is designed, including a cloud data center, a three-dimensional dynamic monitoring platform, an intelligent decision-making module, a fault prediction module and a data acquisition module, using reinforcement learning and autoencoder combined with a long and short-term memory network The fault prediction method realizes independent decision-making and fault prediction.
The system's independent decision-making function is realized, and the best decision-making is able to obtain the best decision-making according to custom goals. It has the advantages of high decision-making efficiency, strong adaptability and good scalability. It also intuitively displays the operating status of the water pump room through a three-dimensional dynamic monitoring platform, improving management The efficiency of personnel obtaining critical information.
Smart Images
Figure CN119415887A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of monitoring systems, and in particular to a three-dimensional dynamic monitoring system for a water pump room based on ICONCIS configuration. Background Art
[0002] The mine water pump room monitoring system is a system that monitors, controls and manages the mine drainage process in real time. It is mainly composed of sensors, controllers, actuators and monitoring software. The sensor is used to collect parameters such as water level, flow, pressure, temperature, etc., and transmit these data to the controller. The controller controls the actuators such as drainage pumps and valves according to the preset control strategy and the collected data to realize the automatic operation of mine drainage. The existing pump room monitoring system has the following defects when in use: First, the existing monitoring system lacks autonomous decision-making ability and can only operate according to the preset procedures and parameters, and cannot be adjusted and optimized autonomously according to the actual situation; second, the existing monitoring system lacks fault prediction function, which makes the system unable to warn in advance when facing potential faults, increases the risk of sudden equipment failure, and affects the normal operation of mine drainage; third, the information display of the existing monitoring system is not intuitive enough, making it difficult for managers to quickly understand the actual situation of mine drainage, which requires managers to spend more time and energy to analyze and understand when obtaining key information. Summary of the invention
[0003] The object of the present invention is to provide a three-dimensional dynamic monitoring system for a pump room based on ICONCIS configuration to solve the problems raised in the above background technology.
[0004] To achieve the above-mentioned objectives, the present invention provides the following technical solutions: a three-dimensional dynamic monitoring system for a pump room based on ICONCIS configuration, comprising a cloud data center, a three-dimensional dynamic monitoring platform, an intelligent decision-making module, a fault prediction module and a data acquisition module, wherein the cloud data center establishes data connections with the three-dimensional dynamic monitoring platform, the intelligent decision-making module, the fault prediction module and the data acquisition module respectively.
[0005] Preferably, the cloud data center includes a cloud storage unit and a cloud computing unit, the cloud storage unit is used to provide cloud storage services, and the cloud computing unit is used to provide cloud computing services.
[0006] Preferably, the three-dimensional dynamic monitoring platform includes a three-dimensional modeling unit, a data processing unit, a dynamic display unit, an interactive unit, an alarm prompt unit and a data query unit. The three-dimensional dynamic monitoring platform is implemented using ICONCIS configuration. The three-dimensional modeling unit is used to construct a three-dimensional model of the pump room scene. The data processing unit is used to process and analyze the received data and convert it into a form displayed on the three-dimensional model. The dynamic display unit is used to display the processed data in real time on the three-dimensional model. The interactive unit is used to provide interactive services. The alarm prompt unit is used to issue alarm prompts. The data query unit is used to query historical monitoring data.
[0007] Preferably, the intelligent decision-making module includes a target definition unit, a strategy generation unit, and a strategy simulation unit. The intelligent decision-making module is implemented using reinforcement learning. The target definition unit is used to define the target of the generated strategy, the strategy generation unit is used to generate the strategy according to the defined target, and the strategy simulation unit is used to simulate the execution effect of the strategy on the three-dimensional model.
[0008] Preferably, the fault prediction module includes a data preprocessing unit, an autoencoder unit and a long short-term memory network unit. The data preprocessing unit is used to clean, denoise and normalize the data, the autoencoder unit is used for anomaly detection, and the long short-term memory network unit is used to analyze abnormal data and output the fault probability and type.
[0009] Preferably, the autoencoder unit includes an encoder body, a decoder and an anomaly detector, the encoder body is used to compress the input data into a low-dimensional latent representation, the decoder is used to reconstruct the original data from the latent representation, and the anomaly detector is used to calculate the error between the input data and the reconstructed data, and if the error exceeds a threshold, it is determined to be abnormal data.
[0010] Preferably, the anomaly detector uses mean square error as the loss function, and the formula is as follows:
[0011] in, is the sample size, is the original input, is the output of the reconstruction.
[0012] Preferably, the long short-term memory network unit includes an input layer, an LSTM layer and an output layer, the input layer is used to input abnormal data, the LSTM layer is used to predict the future state of the device based on the input data, and the output layer is used to output the prediction result.
[0013] Preferably, the data acquisition module includes a liquid level sensor, a pressure sensor, a negative pressure sensor, a flow sensor, a temperature sensor, a vibration sensor and a start / stop sensor.
[0014] Preferably, the liquid level sensor is used to monitor the water level in the water tank, the pressure sensor is used to monitor the discharge pressure of the water pump, the negative pressure sensor is used to monitor the water suction negative pressure of the water pump, the flow sensor is used to monitor the total discharge volume of the pump room, the temperature sensor is used to monitor the temperature of the water pump, the vibration sensor is used to monitor the vibration of the water pump, and the start-stop sensor is used to monitor the operating status of the water pump.
[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention utilizes an intelligent decision-making module based on reinforcement learning to realize autonomous decision-making functions, can obtain optimal decisions according to customized goals, and has the advantages of high decision-making efficiency, strong adaptability, and good scalability. It utilizes a fault prediction module based on an autoencoder and a long short-term memory network to realize a fault prediction function, has strong learning ability and good real-time performance, can process large-scale data, and utilizes a three-dimensional dynamic monitoring platform based on ICONCIS configuration to intuitively display the operating status of the pump room, allowing managers to quickly understand the actual situation of mine drainage. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 It is the overall structural diagram of the present invention; Figure 2 It is a structural block diagram of the three-dimensional dynamic monitoring platform of the present invention; Figure 3 It is a structural block diagram of the intelligent decision-making module of the present invention; Figure 4 This is a structural block diagram of a fault prediction module of the present invention; Figure 5 It is a structural block diagram of the data acquisition module of the present invention; Figure 6 This is a flowchart of the operation of the fault prediction module of the present invention; Figure 7 It is a schematic diagram of the structure of the three-dimensional dynamic monitoring platform of the present invention.
[0017] In the figure: 1. Cloud data center; 11. Cloud storage unit; 12. Cloud computing unit; 2. Three-dimensional dynamic monitoring platform; 21. Three-dimensional modeling unit; 22. Data processing unit; 23. Dynamic display unit; 24. Interaction unit; 25. Alarm prompt unit; 26. Data query unit; 3. Intelligent decision-making module; 31. Target definition unit; 32. Strategy generation unit; 33. Strategy simulation unit; 4. Fault prediction module; 41. Data preprocessing unit; 42. Autoencoder unit; 421. Encoder body; 422. Decoder; 423. Anomaly detector; 43. Long short-term memory network unit; 431. Input layer; 432. LSTM layer; 433. Output layer; 5. Data acquisition module; 51. Liquid level sensor; 52. Pressure sensor; 53. Negative pressure sensor; 54. Flow sensor; 55. Temperature sensor; 56. Vibration sensor; 57. Start-stop sensor. DETAILED DESCRIPTION
[0018] 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.
[0019] Please refer to the attached Figure 1 -Attached Figure 7, an embodiment provided by the present invention: a three-dimensional dynamic monitoring system for a pump room based on ICONCIS configuration, comprising a cloud data center 1, a three-dimensional dynamic monitoring platform 2, an intelligent decision-making module 3, a fault prediction module 4 and a data acquisition module 5, wherein the cloud data center 1 establishes data connections with the three-dimensional dynamic monitoring platform 2, the intelligent decision-making module 3, the fault prediction module 4 and the data acquisition module 5 respectively; the cloud data center 1 comprises a cloud storage unit 11 and a cloud computing unit 12, wherein the cloud storage unit 11 is used to provide cloud storage services, and the cloud computing unit 12 is used to provide cloud computing services; the three-dimensional dynamic monitoring platform 2 comprises a three-dimensional modeling unit 21, a data processing unit 22, a dynamic display unit 23, an interaction unit 24, an alarm prompt unit 25 and a data query unit 26, wherein the three-dimensional dynamic monitoring platform 2 is implemented by ICONCIS configuration, the three-dimensional modeling unit 21 is used to construct a three-dimensional model of a pump room scene, the data processing unit 22 is used to process and analyze the received data and convert it into a form displayed on the three-dimensional model, the dynamic display unit 23 is used to display the processed data on the three-dimensional model in real time, the interaction unit 24 is used to provide interactive services, the alarm prompt unit 25 is used to issue an alarm prompt, and the data query unit 26 is used to query the data. The query unit 26 is used to query historical monitoring data; the intelligent decision-making module 3 includes a target definition unit 31, a strategy generation unit 32, and a strategy simulation unit 33. The intelligent decision-making module 3 is implemented by reinforcement learning. The target definition unit 31 is used to define the target of the generated strategy, the strategy generation unit 32 is used to generate the strategy according to the defined target, and the strategy simulation unit 33 is used to simulate the execution effect of the strategy on the three-dimensional model; the fault prediction module 4 includes a data preprocessing unit 41, an autoencoder unit 42 and a long short-term memory network unit 43. The data preprocessing unit 41 is used to clean, denoise and Normalization processing, the autoencoder unit 42 is used for anomaly detection, and the long short-term memory network unit 43 is used to analyze abnormal data and output the fault probability and type; the autoencoder unit 42 includes an encoder body 421, a decoder 422 and an anomaly detector 423, the encoder body 421 is used to compress the input data into a low-dimensional potential representation, the decoder 422 is used to reconstruct the original data from the potential representation, and the anomaly detector 423 is used to calculate the error between the input data and the reconstructed data. If the error exceeds the threshold, it is determined to be abnormal data; the anomaly detector 423 uses the mean square error as the loss function, and the formula is as follows:
[0020] in, is the sample size, is the original input, is the reconstructed output; the long short-term memory network unit 43 includes an input layer 431, an LSTM layer 432 and an output layer 433, the input layer 431 is used to input abnormal data, the LSTM layer 432 is used to predict the future state of the equipment according to the input data, and the output layer 433 is used to output the prediction result; the data acquisition module 5 includes a liquid level sensor 51, a pressure sensor 52, a negative pressure sensor 53, a flow sensor 54, a temperature sensor 55, a vibration sensor 56 and a start-stop sensor 57; the liquid level sensor 51 is used to monitor the water level of the water tank, the pressure sensor 52 is used to monitor the drainage pressure of the water pump, the negative pressure sensor 53 is used to monitor the water suction negative pressure of the water pump, the flow sensor 54 is used to monitor the total drainage of the pump room, the temperature sensor 55 is used to monitor the temperature of the water pump, the vibration sensor 56 is used to monitor the vibration of the water pump, and the start-stop sensor 57 is used to monitor the operating status of the water pump.
[0021] Working principle: When using the present invention, a three-dimensional model of a mine water pump room is constructed using a three-dimensional dynamic monitoring platform 2, which can realize three-dimensional dynamic monitoring of the water pump room. Visual switching, video, and operation parameter query functions can be performed at any time to intuitively display the operation status of the water pump room. The data acquisition module 5 collects the equipment operation data of the mine water pump room, and the fault prediction module 4 analyzes and processes the equipment operation data to predict faults. The intelligent decision-making module 3 generates decisions such as fault handling solutions and drainage solutions. Specifically, the three-dimensional modeling unit 21 is used to construct a three-dimensional model of the water pump room scene, and the data processing unit 22 is used to process and analyze the received data and convert it into a three-dimensional model. The processed data is displayed on the three-dimensional model in real time by using the dynamic display unit 23, the interactive service is provided by using the interactive unit 24, the alarm prompt unit 25 is used to issue an alarm prompt, and the data query unit 26 is used to query the historical monitoring data; the liquid level sensor 51 is set in the water suction well to monitor the water level of the water tank, the pressure sensor 52 is set in the water pump discharge pipe to monitor the water pump discharge pressure, the negative pressure sensor 53 is set on the negative pressure side of the water pump to monitor the negative pressure of the water pump suction, the flow sensor 54 is set on the total water outlet pipeline to monitor the total discharge volume of the pump room, and the temperature sensor 55 is set on the front and rear axes of the water pump to monitor Measure the temperature of the water pump, set the vibration sensor 56 at the horizontal and vertical positions of the water pump and the motor to monitor the vibration of the water pump, and set the start-stop sensor 57 on the power line of the water pump motor to monitor the running status of the water pump; use the data preprocessing unit 41 to clean, denoise and normalize the collected data, use the encoder body 421 of the autoencoder unit 42 to compress the input data into a low-dimensional potential representation, use the decoder 422 to reconstruct the original data from the potential representation, use the anomaly detector 423 to calculate the error between the input data and the reconstructed data, and if the error exceeds the threshold, it is determined to be abnormal data, and the abnormal data is input into the long short-term memory network unit The input layer 431 of 43, the LSTM layer 432 predicts the future state of the equipment according to the input data, and outputs the prediction result through the output layer 433; the target definition unit 31 is used to define the target of the generated strategy, such as drainage solutions with the highest drainage efficiency or the lowest energy consumption, or fault handling solutions with the lowest maintenance cost and the least time consumption, and then the strategy generation unit 32 is used to generate the strategy according to the defined target, and the strategy simulation unit 33 simulates the execution effect of the strategy on the three-dimensional model; the cloud storage unit 11 of the cloud data center 1 provides cloud storage services for the system, and the cloud computing unit 12 provides cloud computing services for the system, LSTM is a long short-term memory network.
[0022] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.
Claims
1. A three-dimensional dynamic monitoring system for a pump room based on ICONCIS configuration, comprising a cloud data center (1), a three-dimensional dynamic monitoring platform (2), an intelligent decision-making module (3), a fault prediction module (4) and a data acquisition module (5), characterized in that: The cloud data center (1) establishes data connections with the three-dimensional dynamic monitoring platform (2), the intelligent decision-making module (3), the fault prediction module (4) and the data acquisition module (5) respectively.
2. The three-dimensional dynamic monitoring system for a pump room based on ICONCIS configuration according to claim 1, characterized in that: The cloud data center (1) comprises a cloud storage unit (11) and a cloud computing unit (12); the cloud storage unit (11) is used to provide cloud storage services, and the cloud computing unit (12) is used to provide cloud computing services.
3. The three-dimensional dynamic monitoring system for a pump room based on ICONCIS configuration according to claim 1 is characterized in that: The three-dimensional dynamic monitoring platform (2) comprises a three-dimensional modeling unit (21), a data processing unit (22), a dynamic display unit (23), an interaction unit (24), an alarm prompt unit (25) and a data query unit (26). The three-dimensional dynamic monitoring platform (2) is implemented using ICONCIS configuration. The three-dimensional modeling unit (21) is used to construct a three-dimensional model of a pump room scene. The data processing unit (22) is used to process and analyze received data and convert it into a form displayed on the three-dimensional model. The dynamic display unit (23) is used to display the processed data in real time on the three-dimensional model. The interaction unit (24) is used to provide interactive services. The alarm prompt unit (25) is used to issue an alarm prompt. The data query unit (26) is used to query historical monitoring data.
4. The three-dimensional dynamic monitoring system for a pump room based on ICONCIS configuration according to claim 1 is characterized in that: The intelligent decision-making module (3) comprises a target definition unit (31), a strategy generation unit (32), and a strategy simulation unit (33). The intelligent decision-making module (3) is implemented by reinforcement learning. The target definition unit (31) is used to define a target for generating a strategy. The strategy generation unit (32) is used to generate a strategy according to the defined target. The strategy simulation unit (33) is used to simulate the execution effect of the strategy on the three-dimensional model.
5. The three-dimensional dynamic monitoring system for a pump room based on ICONCIS configuration according to claim 1 is characterized in that: The fault prediction module (4) comprises a data preprocessing unit (41), an autoencoder unit (42) and a long short-term memory network unit (43); the data preprocessing unit (41) is used to clean, denoise and normalize data; the autoencoder unit (42) is used for anomaly detection; and the long short-term memory network unit (43) is used to analyze abnormal data and output a fault probability and type.
6. The three-dimensional dynamic monitoring system for a pump room based on ICONCIS configuration according to claim 5 is characterized in that: The autoencoder unit (42) comprises an encoder body (421), a decoder (422) and an anomaly detector (423), wherein the encoder body (421) is used to compress input data into a low-dimensional potential representation, the decoder (422) is used to reconstruct the original data from the potential representation, and the anomaly detector (423) is used to calculate the error between the input data and the reconstructed data, and if the error exceeds a threshold, it is determined to be abnormal data.
7. The three-dimensional dynamic monitoring system for a pump room based on ICONCIS configuration according to claim 6 is characterized in that: The anomaly detector (423) uses mean square error as the loss function, and the formula is as follows: in, is the sample size, is the original input, is the output of the reconstruction.
8. The three-dimensional dynamic monitoring system for a pump room based on ICONCIS configuration according to claim 5 is characterized in that: The long short-term memory network unit (43) comprises an input layer (431), an LSTM layer (432) and an output layer (433), wherein the input layer (431) is used to input abnormal data, the LSTM layer (432) is used to predict the future state of the device based on the input data, and the output layer (433) is used to output the prediction result.
9. The three-dimensional dynamic monitoring system for a pump room based on ICONCIS configuration according to claim 1 is characterized in that: The data acquisition module (5) comprises a liquid level sensor (51), a pressure sensor (52), a negative pressure sensor (53), a flow sensor (54), a temperature sensor (55), a vibration sensor (56), and a start / stop sensor (57).
10. The three-dimensional dynamic monitoring system for a pump room based on ICONCIS configuration according to claim 9 is characterized in that: The liquid level sensor (51) is used to monitor the water level of the water tank, the pressure sensor (52) is used to monitor the water pump discharge pressure, the negative pressure sensor (53) is used to monitor the water pump suction negative pressure, the flow sensor (54) is used to monitor the total discharge volume of the pump room, the temperature sensor (55) is used to monitor the temperature of the water pump, the vibration sensor (56) is used to monitor the vibration of the water pump, and the start / stop sensor (57) is used to monitor the running state of the water pump.