An unattended mine drainage monitoring system capable of real-time alarms
By introducing energy-saving and emission-reduction modules, fault prediction modules, and big data analysis modules into the mine drainage monitoring system, and by using genetic algorithms and deep learning models to optimize equipment operation, the energy-saving, emission-reduction, and fault prediction problems of the existing system have been solved, and the dynamic control and decision support of the system have been realized.
Patent Information
- Application Number
- CN202411900616.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-23
- Publication Date
- 2026-11-17
AI Technical Summary
Existing mine drainage monitoring systems cannot achieve energy conservation and emission reduction, cannot detect potential faults, and do not fully utilize operational data for decision support.
The system employs an energy-saving and emission-reduction module that optimizes equipment operating parameters based on a genetic algorithm, a fault prediction module that predicts potential faults based on a deep learning model, a big data analysis module for data mining and trend analysis, and a data acquisition module for real-time monitoring of the mine drainage system.
It enables dynamic energy-saving control of the mine drainage system, extends equipment service life, and provides decision support through real-time alarms.
Smart Images

Figure CN123109781A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of monitoring system technology, specifically to an unattended mine drainage monitoring system capable of real-time alarm. Background Technology
[0002] A mine drainage monitoring system is a system for real-time monitoring, control, and management of the mine drainage process. It achieves automated operation of mine drainage by controlling actuators such as drainage pumps and valves. Existing mine drainage monitoring systems have the following drawbacks: First, they only control equipment operation according to preset parameters, which is not conducive to energy conservation and emission reduction. Second, they cannot detect potential faults, increasing the risk of sudden equipment failures and easily leading to the escalation of faults, thus reducing equipment lifespan. Third, existing systems generate a large amount of data during operation, but this data is not fully utilized, thus failing to provide effective decision support for system control and maintenance. Summary of the Invention
[0003] The purpose of this invention is to provide an unattended mine drainage monitoring system capable of real-time alarms, in order to solve the problems mentioned in the background art.
[0004] To achieve the above objectives, the present invention provides the following technical solution: an unattended mine drainage monitoring system capable of real-time alarm, comprising an energy-saving and emission-reduction module, a fault prediction module, a big data analysis module, a data acquisition module, a cloud data center, and an alarm notification module, wherein the cloud data center establishes data connections with the energy-saving and emission-reduction module, the fault prediction module, the big data analysis module, the data acquisition module, and the alarm notification module, respectively.
[0005] Preferably, the energy-saving and emission-reduction module includes an encoding unit, a fitness evaluation unit, a genetic operation unit, and a control and output unit. The energy-saving and emission-reduction module is implemented using a genetic algorithm. The encoding unit is used to convert the equipment operating parameters into gene encoding form. The fitness evaluation unit is used to evaluate the combination of operating parameters according to the fitness function and calculate the fitness value. The genetic operation unit is used to perform selection, crossover, and mutation operations. The control and output unit is used to control the algorithm iteration process and output the optimal combination of operating parameters when the stopping condition is met.
[0006] Preferably, the fitness function is:
[0007]
[0008] in, For power consumption, For traffic, and These are the weighting coefficients. It is the density of water. It is gravitational acceleration. It is Yangcheng. It refers to the efficiency of the water pump.
[0009] Preferably, the fault prediction module includes a data preprocessing unit, a deep learning model unit, a fault information feedback unit, and a model evaluation and adjustment unit. The data preprocessing unit is used to preprocess the data, the deep learning model unit is used to analyze the data and output the fault type and probability, the fault information feedback unit is used to provide feedback on the actual fault information, and the model evaluation and adjustment unit is used to evaluate and adjust the model based on the feedback data.
[0010] Preferably, the data preprocessing unit includes a data cleaning subunit and a normalization processing subunit. The data cleaning subunit is used to remove outliers and noise interference, and the normalization processing subunit is used to normalize data of different dimensions.
[0011] Preferably, the deep learning model unit includes an input layer, a hidden layer, an output layer, and a fault classification layer. The input layer is used to input preprocessed time series data and equipment operating status information. The hidden layer consists of multiple LSTM units and CNN layers, used to extract features from the data. The output layer is used to output the predicted equipment status and fault probability. The fault classification layer is used to output the fault type based on the predicted equipment status.
[0012] Preferably, the big data analysis module includes a data analysis unit and a decision support unit. The data analysis unit is used for data mining, and the decision support unit is used to generate a maintenance plan based on the analysis results.
[0013] Preferably, the data analysis unit includes a trend analysis subunit, a correlation analysis subunit, and a lifespan prediction subunit. The trend analysis subunit is used to analyze the changing trend of equipment operating parameters over time, the correlation analysis subunit is used to analyze the correlation between different parameters, and the lifespan prediction subunit is used to predict the remaining lifespan of the equipment.
[0014] Preferably, the trend analysis subunit is implemented using the moving average method, the correlation analysis subunit using the Pearson correlation coefficient method, and the life prediction subunit using the Weibull distribution method. The probability density function of the Weibull distribution is:
[0015] in, For time, For shape parameters, This is the scale parameter.
[0016] 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. The liquid level sensor is used to monitor the water level in the water tank, the pressure sensor is used to monitor the drainage pressure of the water pump, the negative pressure sensor is used to monitor the suction negative pressure of the water pump, the flow sensor is used to monitor the total drainage volume of the pump house, 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.
[0017] Compared with the prior art, the beneficial effects of the present invention are as follows: The energy-saving and emission-reduction module of the present invention is based on a genetic algorithm, with the goal of minimizing power consumption and the constraint of meeting drainage requirements, to search for the optimal combination of operating parameters, thereby realizing the dynamic control of the drainage system and achieving the purpose of energy saving and emission reduction; the fault prediction module is based on a deep learning model to realize fault prediction, effectively extending the service life of the unit; the big data analysis module makes full use of the data generated by the operation of the drainage system, and provides decision support for the control and maintenance of the drainage system through trend analysis, correlation analysis and life prediction. Attached Figure Description
[0018] Figure 1 This is a block diagram of the overall structure of the present invention; Figure 2 This is a structural block diagram of the energy-saving and emission-reduction module of the present invention; Figure 3 This is a structural block diagram of the fault prediction module of the present invention; Figure 4 This is a block diagram of the big data analysis module of the present invention; Figure 5 This is a structural block diagram of the data acquisition module of the present invention; Figure 6 This is a flowchart of the energy-saving and emission-reduction module operation of the present invention; Figure 7 This is a flowchart of the fault prediction module operation of the present invention.
[0019] In the diagram: 1. Energy saving and emission reduction module; 11. Encoding unit; 12. Fitness evaluation unit; 13. Genetic operation unit; 14. Control and output unit; 2. Fault prediction module; 21. Data preprocessing unit; 211. Data cleaning sub-unit; 212. Normalization processing sub-unit; 22. Deep learning model unit; 221. Input layer; 222. Hidden layer; 223. Output layer; 224. Fault classification layer; 23. Fault information feedback unit; 24. Model evaluation and adjustment unit; 3. Big data analysis module; 31. Data analysis unit; 311. Trend analysis sub-unit; 312. Correlation analysis sub-unit; 313. Lifetime prediction sub-unit; 32. Decision support unit; 4. Data acquisition module; 41. Liquid level sensor; 42. Pressure sensor; 43. Negative pressure sensor; 44. Flow sensor; 45. Temperature sensor; 46. Vibration sensor; 47. Start / stop sensor; 5. Cloud data center; 6. Alarm prompt module. Detailed Implementation
[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0021] Please see the appendix Figure 1 -Appendix Figure 7 This invention provides an embodiment of an unattended mine drainage monitoring system capable of real-time alarms, comprising an energy-saving and emission-reduction module 1, a fault prediction module 2, a big data analysis module 3, a data acquisition module 4, a cloud data center 5, and an alarm notification module 6. The cloud data center 5 establishes data connections with the energy-saving and emission-reduction module 1, the fault prediction module 2, the big data analysis module 3, the data acquisition module 4, and the alarm notification module 6, respectively. The energy-saving and emission-reduction module 1 includes an encoding unit 11, a fitness evaluation unit 12, a genetic operation unit 13, and a control and output unit 14. The energy-saving and emission-reduction module 1 is implemented using a genetic algorithm. The encoding unit 11 is used to convert equipment operating parameters into gene encoding form. The fitness evaluation unit 12 is used to evaluate the combination of operating parameters according to the fitness function and calculate the fitness value. The genetic operation unit 13 is used to perform selection, crossover, and mutation operations. The control and output unit 14 is used to control the algorithm iteration process and output the optimal combination of operating parameters when the stopping condition is met. The fitness function is:
[0022]
[0023] in, For power consumption, For traffic, and These are the weighting coefficients. It is the density of water. It is gravitational acceleration. It is Yangcheng. This refers to pump efficiency. The fault prediction module 2 includes a data preprocessing unit 21, a deep learning model unit 22, a fault information feedback unit 23, and a model evaluation and adjustment unit 24. The data preprocessing unit 21 preprocesses the data; the deep learning model unit 22 analyzes the data and outputs the fault type and probability; the fault information feedback unit 23 provides feedback on actual fault information; and the model evaluation and adjustment unit 24 evaluates and adjusts the model based on the feedback data. The data preprocessing unit 21 includes a data cleaning subunit 211 and a normalization subunit 212. The data cleaning subunit 211 removes outliers and noise interference, and the normalization subunit 212 normalizes data of different dimensions. The deep learning model unit 22 includes an input layer 221, a hidden layer 222, an output layer 223, and a fault classification layer 224. The input layer 221 inputs preprocessed time-series data and equipment operating status information; the hidden layer 222 consists of multiple LSTM units. The system consists of a meta-layer and a CNN layer for extracting data features. The output layer 223 outputs the predicted equipment status and failure probability, and the failure classification layer 224 outputs the failure type based on the predicted equipment status. The big data analysis module 3 includes a data analysis unit 31 and a decision support unit 32. The data analysis unit 31 is used for data mining, and the decision support unit 32 generates a maintenance plan based on the analysis results. The data analysis unit 31 includes a trend analysis subunit 311, a correlation analysis subunit 312, and a lifespan prediction subunit 313. The trend analysis subunit 311 analyzes the changing trends of equipment operating parameters over time, the correlation analysis subunit 312 analyzes the correlation relationships between different parameters, and the lifespan prediction subunit 313 predicts the remaining lifespan of the equipment. The trend analysis subunit 311 uses the moving average method, the correlation analysis subunit 312 uses the Pearson correlation coefficient method, and the lifespan prediction subunit 313 uses the Weibull distribution method. The probability density function of the Weibull distribution is:
[0024] in, For time, For shape parameters, The data acquisition module 4 includes a level sensor 41, a pressure sensor 42, a negative pressure sensor 43, a flow sensor 44, a temperature sensor 45, a vibration sensor 46, and an on / off sensor 47. The level sensor 41 is used to monitor the water level in the water tank, the pressure sensor 42 is used to monitor the water pump drainage pressure, the negative pressure sensor 43 is used to monitor the water pump suction negative pressure, the flow sensor 44 is used to monitor the total drainage volume of the pump house, the temperature sensor 45 is used to monitor the water pump temperature, the vibration sensor 46 is used to monitor the water pump vibration, and the on / off sensor 47 is used to monitor the water pump operating status.
[0025] Working Principle: When using this invention, the data acquisition module 4 collects the operating data of the mine drainage system. The liquid level sensor 41 monitors the water level in the water tank, the pressure sensor 42 monitors the water pump drainage pressure, the negative pressure sensor 43 monitors the water pump suction negative pressure, the flow sensor 44 monitors the total drainage volume of the pump room, the temperature sensor 45 monitors the water pump temperature, the vibration sensor 46 monitors the water pump vibration, and the start / stop sensor 47 monitors the water pump operating status. The data is then transmitted to the cloud data center 5. The energy-saving and emission-reduction module 1 acquires the operating data of the mine drainage system. With the goal of minimizing power consumption and the constraint of meeting drainage requirements, the energy-saving and emission-reduction module 1 searches for the optimal combination of operating parameters. The encoding unit 11 converts the equipment operating parameters into a genetic code format. The fitness evaluation unit 12 evaluates the combination of operating parameters according to the fitness function and calculates the fitness value. The genetic operation unit 13 performs selection, crossover, and mutation operations. The selection operation selects excellent individuals from the current population to serve as the parents of the next generation. The crossover operation exchanges genes between the selected parent individuals to generate new individuals. The mutation operation randomly changes the genes of individuals with a certain probability to increase the diversity of the population. The control and output unit 14 controls the algorithm iteration process and outputs the optimal combination of operating parameters to the actuator when the stopping condition is met. The actuator automatically adjusts the equipment operating parameters. The energy saving and emission reduction module 1 can output the optimal equipment energy saving operation scheme corresponding to different drainage needs through the above process. The fault prediction module 2 obtains... The data preprocessing unit 21 collects operational data from the mine drainage system. The data cleaning subunit 211 removes outliers and noise interference, and the normalization subunit 212 normalizes data of different dimensions. The preprocessed time-series data and equipment operating status information are then input into the input layer 221 of the deep learning model unit 22. The input layer 221 inputs the data into the hidden layer 222. The hidden layer 222 extracts features from the data using multiple LSTM units and CNN layers. LSTM units are Long Short-Term Memory networks used to capture long-term dependencies in time-series data. For example, by analyzing the changes in parameters such as pump pressure and flow rate over time, LSTM units can identify trends and anomalies under normal operating conditions. In the case of sudden changes under normal circumstances, the CNN layer is a convolutional neural network used to extract local features from the data. For example, a specific frequency pattern in vibration data may be related to the fault state of the equipment, and the CNN layer can automatically identify these key patterns. The output layer 223 makes predictions based on the features extracted by the hidden layer 222 and outputs the predicted equipment state and fault probability. The fault classification layer 224 uses a fully connected neural network to output the fault type based on the predicted equipment state. When a fault occurs, the actual fault information can be fed back through the fault information feedback unit 23. The model evaluation and adjustment unit 24 evaluates the performance of the model based on the feedback data. If the prediction accuracy of the model decreases or a new fault mode appears, the model is adjusted in time.The big data analysis module 3 acquires operational data from the mine drainage system. After preprocessing the data, the trend analysis subunit 311 analyzes the changing trends of equipment operating parameters over time, such as the long-term changing trends of parameters like pump pressure and flow rate, to determine the equipment's health status. The correlation analysis subunit 312 analyzes the relationships between different parameters, such as identifying potential correlations between temperature and failure frequency, providing data support for the control of heat dissipation equipment. The lifespan prediction subunit 313 predicts the remaining lifespan of the equipment, providing data support for maintenance and repair work. The decision support unit 32 formulates control, maintenance, and repair plans based on the analysis results. For example, if the analysis finds that the failure frequency increases significantly when the pump motor temperature exceeds a certain threshold, then the monitoring of the motor temperature is strengthened, and the heat dissipation equipment is controlled to cool it down in a timely manner. If the failure probability of the pump is high at a certain point in its operation, it indicates that the pump may be nearing the end of its lifespan and needs to be replaced or repaired. The analysis and prediction results from the failure prediction module 2 and the big data analysis module 3 are both provided in real-time through the alarm prompt module 6 to achieve unattended operation.
[0026] It will be apparent to those skilled in the art that the present 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 its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.
Claims
1. An unattended mine drainage monitoring system capable of real-time alarm, comprising an energy-saving and emission-reduction module (1), a fault prediction module (2), a big data analysis module (3), a data acquisition module (4), a cloud data center (5), and an alarm notification module (6), characterized in that: The cloud data center (5) establishes data connections with the energy conservation and emission reduction module (1), the fault prediction module (2), the big data analysis module (3), the data acquisition module (4), and the alarm prompting module (6), respectively.
2. The unattended mine drainage monitoring system capable of real-time alarm as described in claim 1, characterized in that: The energy-saving and emission-reduction module (1) includes an encoding unit (11), a fitness evaluation unit (12), a genetic operation unit (13), and a control and output unit (14). The energy-saving and emission-reduction module (1) is implemented using a genetic algorithm. The encoding unit (11) is used to convert the equipment operating parameters into gene encoding form. The fitness evaluation unit (12) is used to evaluate the combination of operating parameters according to the fitness function and calculate the fitness value. The genetic operation unit (13) is used to perform selection, crossover, and mutation operations. The control and output unit (14) is used to control the algorithm iteration process and output the optimal combination of operating parameters when the stopping condition is met.
3. The unattended mine drainage monitoring system capable of real-time alarm as described in claim 2, characterized in that: The fitness function is: in, For power consumption, For traffic, and These are the weighting coefficients. It is the density of water. It is gravitational acceleration. It is Yangcheng. It refers to the efficiency of the water pump.
4. The unattended mine drainage monitoring system capable of real-time alarm as described in claim 1, characterized in that: The fault prediction module (2) includes a data preprocessing unit (21), a deep learning model unit (22), a fault information feedback unit (23), and a model evaluation and adjustment unit (24). The data preprocessing unit (21) is used to preprocess the data, the deep learning model unit (22) is used to analyze the data and output the fault type and probability, the fault information feedback unit (23) is used to provide feedback on the actual fault information, and the model evaluation and adjustment unit (24) is used to evaluate and adjust the model based on the feedback data.
5. The unattended mine drainage monitoring system capable of real-time alarm as described in claim 4, characterized in that: The data preprocessing unit (21) includes a data cleaning subunit (211) and a normalization processing subunit (212). The data cleaning subunit (211) is used to remove outliers and noise interference, and the normalization processing subunit (212) is used to normalize data of different dimensions.
6. The unattended mine drainage monitoring system capable of real-time alarm as described in claim 4, characterized in that: The deep learning model unit (22) includes an input layer (221), a hidden layer (222), an output layer (223), and a fault classification layer (224). The input layer (221) is used to input preprocessed time series data and equipment operating status information. The hidden layer (222) consists of multiple LSTM units and CNN layers and is used to extract features from the data. The output layer (223) is used to output the predicted equipment status and fault probability. The fault classification layer (224) is used to output the fault type based on the predicted equipment status.
7. The unattended mine drainage monitoring system capable of real-time alarm as described in claim 1, characterized in that: The big data analysis module (3) includes a data analysis unit (31) and a decision support unit (32). The data analysis unit (31) is used for data mining, and the decision support unit (32) is used to generate a maintenance plan based on the analysis results.
8. The unattended mine drainage monitoring system capable of real-time alarm as described in claim 7, characterized in that: The data analysis unit (31) includes a trend analysis subunit (311), a correlation analysis subunit (312), and a life prediction subunit (313). The trend analysis subunit (311) is used to analyze the changing trend of equipment operating parameters over time. The correlation analysis subunit (312) is used to analyze the correlation between different parameters. The life prediction subunit (313) is used to predict the remaining life of the equipment.
9. A real-time alarm-enabled unattended mine drainage monitoring system according to claim 8, characterized in that: The trend analysis subunit (311) is implemented using the moving average method, the correlation analysis subunit (312) is implemented using the Pearson correlation coefficient method, and the life prediction subunit (313) is implemented using the Weibull distribution method. The probability density function of the Weibull distribution is: in, For time, For shape parameters, This is the scale parameter.
10. The unattended mine drainage monitoring system capable of real-time alarm as described in claim 1, characterized in that: The data acquisition module (4) includes a liquid level sensor (41), a pressure sensor (42), a negative pressure sensor (43), a flow sensor (44), a temperature sensor (45), a vibration sensor (46), and a start / stop sensor (47). The liquid level sensor (41) is used to monitor the water level in the water tank, the pressure sensor (42) is used to monitor the drainage pressure of the water pump, the negative pressure sensor (43) is used to monitor the suction negative pressure of the water pump, the flow sensor (44) is used to monitor the total drainage of the pump house, the temperature sensor (45) is used to monitor the temperature of the water pump, the vibration sensor (46) is used to monitor the vibration of the water pump, and the start / stop sensor (47) is used to monitor the operating status of the water pump.
