A tailings conveying multi-node cooperative scheduling method and system based on a risk constraint model

Abstract

This invention relates to the field of tailings transportation technology, specifically to a multi-node collaborative scheduling method and system for tailings transportation based on a risk constraint model. The method includes the following steps: data acquisition, risk prediction, risk constraint generation, joint optimization, dynamic collaborative control, intelligent emergency response, and closed-loop feedback update. The beneficial effects are: by integrating multi-source heterogeneous data acquisition and transmission technology, deep learning algorithms, fuzzy logic and expert systems, multi-objective joint optimization models, and intelligent early warning and emergency response mechanisms, comprehensive monitoring, scientific evaluation, optimized scheduling, and intelligent management of the tailings transportation system are achieved. This system can not only collect and process comprehensive and accurate operational data in real time, providing a scientific basis for scheduling decisions, but also ensure the safe operation of the tailings dam through high-precision risk prediction and dynamic risk constraint generation.

Description

Technical Field

[0001] This invention relates to the field of tailings transportation technology, specifically to a multi-node collaborative scheduling method and system for tailings transportation based on a risk constraint model. Background Technology

[0002] In mining operations, tailings transportation and disposal are crucial links, directly impacting mine safety and environmental protection. Traditional tailings transportation systems often employ single-node control or simple multi-node linkage methods, making them ill-suited for complex and variable operating conditions, such as sudden natural disasters like torrential rains and earthquakes, as well as performance degradation caused by equipment aging and wear. Furthermore, traditional scheduling methods often lack scientific risk assessment and constraint mechanisms, easily leading to tailings dams operating beyond their limits and increasing the risk of safety accidents such as dam failures. With the expansion of mining scale and the increase in tailings volume, traditional scheduling methods are no longer sufficient to meet the modern mining production requirements for safety, efficiency, and environmental protection.

[0003] Specifically, existing tailings conveying systems have the following shortcomings: Incomplete data collection: Traditional systems often rely on a single type of data collection equipment, making it difficult to obtain comprehensive and accurate operational data, resulting in a lack of scientific basis for scheduling decisions.

[0004] Inaccurate risk assessment: The lack of scientific risk assessment models and constraint mechanisms makes it difficult to accurately predict and assess the safety status of tailings ponds, increasing the risk of safety accidents.

[0005] Non-optimal scheduling strategy: Traditional scheduling methods often rely on experience-based scheduling or simple linkage, which makes it difficult to achieve globally optimal scheduling, resulting in high energy consumption and low efficiency.

[0006] Untimely emergency response: The lack of intelligent early warning and emergency response mechanisms makes it difficult to take effective measures quickly in case of emergencies to ensure the safety and stability of mine production.

[0007] Weak continuous optimization capability: Traditional systems lack closed-loop feedback and continuous optimization mechanisms, making it difficult to continuously optimize scheduling strategies and model parameters based on actual operating data, resulting in poor system adaptability. Summary of the Invention

[0008] The purpose of this invention is to provide a multi-node collaborative scheduling method and system for tailings transportation based on a risk constraint model, so as to solve the problems mentioned in the background art.

[0009] To achieve the above objectives, the present invention provides the following technical solution: a multi-node collaborative scheduling method for tailings transportation based on a risk constraint model, comprising the following steps: Data acquisition steps: Real-time acquisition of operating data of distribution pump stations through sensor network, including outlet pressure, flow rate, speed and power; acquisition of tailings dam safety monitoring data, including reservoir water level, rainfall, flood discharge flow, seepage pressure / infiltration line height and dam displacement; acquisition of filling station operating data, including feed density, slurry supply flow, terminal pressure and filling demand, and transmission to the central control system.

[0010] Preferably, it also includes a risk prediction step: By using machine learning algorithms and combining historical and real-time data, the risk status of tailings dams can be predicted with high accuracy within the prediction period. The predicted values ​​or trends of key indicators such as reservoir water level, seepage line / pressure, and dam displacement are obtained. Furthermore, by taking into account rainfall forecasts, flood discharge capacity, and current inflow, the future risk margin can be dynamically assessed.

[0011] Preferably, it further includes a risk constraint generation step: Based on the risk prediction results, a risk constraint set containing multi-dimensional safety indicators is automatically generated, including but not limited to the reservoir water level not exceeding the safety threshold, the phreatic line height not exceeding the control value, and the dam displacement trend being within the safe range. At the same time, the operating pressure and flow limits of the pumping station and the stability requirements of the filling and grouting are considered to form a comprehensive scheduling feasible domain.

[0012] Preferably, it also includes a joint optimization step: Within the feasible domain defined by the risk constraint set, a multi-objective joint scheduling optimization model is constructed. The tailings allocation ratio, the target flow / speed of the pump station, and the opening degree of the allocation valve are used as decision variables. The objective function comprehensively considers minimizing the energy consumption of the pump station, minimizing the stability fluctuation of the filling and slurry supply, minimizing the risk constraint penalty function, and the penalty for the rate of change of the control quantity. The optimal control quantity sequence is solved by model predictive control or intelligent optimization algorithm.

[0013] Preferably, it also includes a dynamic collaborative control step: Based on the optimal control sequence, the pump station speed is adjusted in real time by the frequency converter to control the flow rate, and the opening of the distribution valve is precisely controlled by the electric actuator. At the same time, the slurry flow rate and density setting instructions are sent to the filling station to realize dynamic coordinated control between the distribution pump station, tailings dam and filling station, ensuring that the actual operating parameters closely track the optimization results.

[0014] Preferably, it also includes intelligent emergency response steps: The integrated intelligent monitoring and early warning system automatically triggers a set of graded emergency response strategies when the tailings dam risk indicators exceed or are close to exceeding limits, or when the pipeline pressure is abnormal. These strategies include, but are not limited to, dynamically adjusting the tailings allocation ratio to reduce the amount entering the dam, prioritizing the filling slurry supply, limiting the maximum output flow of the pumping station, activating the tailings dam emergency drainage facilities, switching to backup pipelines, or executing emergency shutdown procedures, and generating a detailed emergency handling report.

[0015] Preferably, it also includes a closed-loop feedback update step: Collect actual operating data after execution, and use data-driven methods to correct risk prediction models, energy consumption models, pipeline resistance characteristic parameters and risk constraint margins online, so as to realize closed-loop optimization and continuous improvement of scheduling strategies and improve the system's adaptability and robustness to complex operating conditions.

[0016] A multi-node collaborative scheduling system for tailings transportation based on a risk constraint model includes: Data acquisition and transmission subsystem: Deploy a high-precision sensor network to realize real-time acquisition and wireless transmission of operating data from distribution pump stations, tailings dams and filling stations; Central control subsystem: integrates a high-performance computing platform and intelligent algorithm library, and is responsible for data processing, risk prediction, constraint generation, joint optimization calculation and control command generation; The actuator subsystem includes frequency converters, electric valve actuators, and an automated control system for the filling station, ensuring accurate execution of optimized commands from the central control subsystem. Intelligent Emergency Response Subsystem: Integrates risk warning, strategy decision-making, and execution functions to ensure rapid response in emergency situations; Closed-loop feedback and optimization subsystem: Continuously optimize model parameters using execution data to form a closed-loop control system.

[0017] Preferably, the central control subsystem is further configured as follows: It adopts a modular design, supports flexible configuration and expansion of multi-objective joint optimization algorithms, and can adjust the weights of objective functions, constraints and optimization strategies according to the actual working conditions and needs of different mines, so as to realize the rapid generation and deployment of personalized scheduling schemes.

[0018] Preferably, the intelligent emergency response subsystem is further configured as follows: It possesses self-learning and adaptive capabilities, and can continuously optimize the emergency response strategy set based on historical emergency event data and processing results, thereby improving the efficiency and effectiveness of emergency handling. At the same time, it supports manual intervention and remote control to ensure the safe and stable operation of the system under extreme conditions.

[0019] Compared with the prior art, the beneficial effects of the present invention are: This invention proposes a multi-node collaborative scheduling method and system for tailings transportation based on a risk constraint model. By integrating multi-source heterogeneous data acquisition and transmission technology, deep learning algorithms, fuzzy logic and expert systems, a multi-objective joint optimization model, and intelligent early warning and emergency response mechanisms, it achieves comprehensive monitoring, scientific evaluation, optimized scheduling, and intelligent management of the tailings transportation system. This system not only collects and processes comprehensive and accurate operational data in real time, providing a scientific basis for scheduling decisions, but also ensures the safe operation of tailings ponds through high-precision risk prediction and dynamic risk constraint generation. Simultaneously, the system employs a multi-objective joint optimization model to achieve global optimality of the scheduling strategy, reducing energy consumption and improving efficiency. Furthermore, the integration of intelligent early warning and emergency response mechanisms enables the system to respond quickly and take effective measures in emergency situations, ensuring the safety and stability of mine production. Finally, the introduction of closed-loop feedback and continuous optimization mechanisms allows the system to continuously optimize scheduling strategies and model parameters based on actual operational data, improving the system's adaptability and robustness. In summary, the multi-node collaborative scheduling method and system for tailings transportation proposed in this invention significantly improves the safety, efficiency, and environmental friendliness of mine production, and has broad application prospects and promotional value. Attached Figure Description

[0020] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the present invention clear and complete, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only some, not all, embodiments of the present invention, and are merely illustrative of the embodiments of the present invention. They are not intended to limit 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.

[0022] Example 1: Tailings transportation scheduling optimization based on multi-source data fusion.

[0023] A certain mining company has a large tailings dam, and its tailings transportation system involves multiple pumping stations and filling stations. Traditional scheduling methods are insufficient to handle the complex and ever-changing operating conditions. This embodiment aims to achieve multi-node collaborative scheduling optimization of tailings transportation through multi-source data fusion technology.

[0024] Data Acquisition: Pump Station A: Outlet pressure 1.2MPa, flow rate 500m³ / h 3 / h, speed 1450rpm, electric power 300kW.

[0025] Tailings dam: water level 15.2m, rainfall 5mm / h, discharge flow 200m³.3 / h, seepage pressure / infiltration line height 8.5m, dam displacement 3mm.

[0026] Filling station: feed density 1.8t / m³, slurry supply flow rate 400m³ 3 / h, terminal pressure 0.8MPa, filling requirement 450m³ 3 / h.

[0027] Risk prediction: Using an LSTM neural network model, combined with historical and real-time data, it is predicted that the tailings dam water level will rise to 15.8m, the phreatic line height will rise to 9.0m, and the dam displacement will increase to 4mm in the next 24 hours.

[0028] Risk constraint generation: Based on the prediction results, a set of risk constraints is generated: reservoir water level not exceeding 16.0m, phreatic line height not exceeding 9.5m, dam displacement not exceeding 5mm, and pump station flow rate not less than 450m³ / h. 3 / h, the stability fluctuation of grout supply does not exceed ±5%.

[0029] Joint Optimization and Scheduling: A multi-objective optimization model is constructed and solved using a hybrid algorithm combining MPC and PSO to obtain the optimal control sequence: the flow rate of pump station A is adjusted to 480 m³ / s. 3 / h, adjust the rotation speed to 1400rpm, adjust the distribution valve opening to 80%, and adjust the grout supply flow rate of the filling station to 420m³ / h. 3 / h.

[0030] After the scheduling, the tailings dam water level stabilized at 15.7m, the phreatic line height was 8.8m, the dam displacement was 3.5mm, the pump station energy consumption decreased by 5%, and the stability of filling and grouting increased by 10%.

[0031] Example 2: Application of intelligent early warning and emergency response in tailings transportation.

[0032] A mining company's tailings dam is located in a rainy season-prone area, and traditional dispatching methods are insufficient to address the risks posed by sudden torrential rains. This embodiment aims to improve the safety of the tailings transport system through an intelligent early warning and emergency response system.

[0033] Data collection and risk prediction: Same as Example 1, but the real-time rainfall is increased to 20 mm / h. It is predicted that the tailings dam water level will rise to 16.2 m in the next 6 hours, approaching the safety threshold.

[0034] Intelligent early warning: The system automatically triggers a yellow warning to alert dispatchers to pay attention to changes in the tailings dam water level.

[0035] Emergency Response: Based on the early warning information, dispatchers activated the emergency response strategy: dynamically adjusting the tailings allocation ratio to reduce the amount entering the storage facility by 20%; prioritizing the supply of slurry for backfilling to ensure the needs of the backfilling station; and limiting the maximum output flow of pump station A to 500 m³ / h. 3 / h; Activate the emergency flood discharge facilities of the tailings dam, increasing the flood discharge flow to 300m³. 3 / h.

[0036] After the emergency response, the tailings dam water level stabilized at 16.0m, which was within the limit. The filling and slurry supply were not affected, and the pumping station operated stably.

[0037] Example 3: Application of closed-loop feedback and continuous optimization in tailings transportation scheduling.

[0038] A mining company's tailings conveying system has been in operation for a long time, and some equipment has aged, leading to a decrease in scheduling efficiency. This embodiment aims to improve the adaptability and robustness of the scheduling system through a closed-loop feedback and continuous optimization mechanism.

[0039] Initial scheduling: Same as in Example 1, perform initial scheduling optimization.

[0040] Data Acquisition and Feedback: After the scheduling is executed, actual operating data is collected: Pump station A's actual flow rate is 475 m³ / h. 3 / h, rotation speed 1395rpm, actual grout supply flow rate of filling station 415m³ / h, grouting speed 1395rpm, actual grout supply flow rate of filling station 415m³ / h. 3 / h.

[0041] Model Correction and Optimization: Using actual operating data, the risk prediction model, energy consumption model, and pipeline resistance characteristic parameters are corrected online. A new multi-objective optimization model is reconstructed, and a new optimal control sequence is obtained: the flow rate of pump station A is adjusted to 470 m³ / h. 3 / h, adjust the rotation speed to 1390rpm, adjust the opening of the distribution valve to 78%, and adjust the grout supply flow rate of the filling station to 410m³ / h.

[0042] Through closed-loop feedback and continuous optimization, the dispatching system is more adapted to actual working conditions, the energy consumption of the pumping station is further reduced by 3%, and the stability of filling and grouting is improved by 5%.

[0043] Example 4: Application of multi-level emergency response mechanism in tailings transportation.

[0044] A mining company's tailings dam is located in a seismically active zone, requiring a multi-level emergency response mechanism to cope with earthquakes of different magnitudes. This embodiment aims to improve the seismic safety of the tailings conveying system through a multi-level emergency response mechanism.

[0045] Earthquake Warning: The earthquake monitoring system has issued a yellow warning, indicating that a magnitude 4-5 earthquake is expected to occur within the next 24 hours.

[0046] Level 1 Emergency Response: Dispatch personnel activate Level 1 emergency response strategies: dynamically adjust the tailings allocation ratio to reduce the amount entering the dam by 15%; check the tightness of equipment at pumping stations and filling stations; increase the frequency of tailings dam inspections to once per hour.

[0047] Earthquake Occurrence: A magnitude 4.5 earthquake actually occurred, and the earthquake monitoring system was upgraded to a red alert.

[0048] Level II Emergency Response: Dispatchers immediately activated the Level II emergency response strategy: Stop transporting tailings to the tailings dam and divert all shipments to the backfilling station; limit the maximum output flow of the pumping station to 400 m³ / h. 3 / h; Activate the emergency flood discharge facilities of the tailings dam and discharge floodwater at all costs; Check the dam displacement and seepage pressure, and report every half hour.

[0049] During the earthquake, no safety accidents such as dam failure occurred at the tailings dam, and the pumping station and filling station operated stably, quickly resuming production after the earthquake.

[0050] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A multi-node collaborative scheduling method for tailings transportation based on a risk constraint model, characterized in that: Includes the following steps: Data acquisition steps: Real-time acquisition of operating data of distribution pump stations through sensor network, including outlet pressure, flow rate, speed and power; acquisition of tailings dam safety monitoring data, including reservoir water level, rainfall, flood discharge flow, seepage pressure / infiltration line height and dam displacement; acquisition of filling station operating data, including feed density, slurry supply flow, terminal pressure and filling demand, and transmission to the central control system.

2. The tailings transportation multi-node collaborative scheduling method based on a risk constraint model according to claim 1, characterized in that: It also includes the risk prediction step: By using machine learning algorithms and combining historical and real-time data, the risk status of tailings dams can be predicted with high accuracy within the prediction period. The predicted values ​​or trends of key indicators such as reservoir water level, seepage line / pressure, and dam displacement are obtained. Furthermore, by taking into account rainfall forecasts, flood discharge capacity, and current inflow, the future risk margin can be dynamically assessed.

3. The tailings transportation multi-node collaborative scheduling method based on a risk constraint model according to claim 2, characterized in that: This further includes the risk constraint generation step: Based on the risk prediction results, a risk constraint set containing multi-dimensional safety indicators is automatically generated, including but not limited to the reservoir water level not exceeding the safety threshold, the phreatic line height not exceeding the control value, and the dam displacement trend being within the safe range. At the same time, the operating pressure and flow limits of the pumping station and the stability requirements of the filling and grouting are considered to form a comprehensive scheduling feasible domain.

4. The tailings transportation multi-node collaborative scheduling method based on a risk constraint model according to claim 3, characterized in that: It also includes joint optimization steps: Within the feasible domain defined by the risk constraint set, a multi-objective joint scheduling optimization model is constructed. The tailings allocation ratio, the target flow / speed of the pump station, and the opening degree of the allocation valve are used as decision variables. The objective function comprehensively considers minimizing the energy consumption of the pump station, minimizing the stability fluctuation of the filling and slurry supply, minimizing the risk constraint penalty function, and the penalty for the rate of change of the control quantity. The optimal control quantity sequence is solved by model predictive control or intelligent optimization algorithm.

5. The tailings transportation multi-node collaborative scheduling method based on a risk constraint model according to claim 4, characterized in that: It also includes dynamic collaborative control steps: Based on the optimal control sequence, the pump station speed is adjusted in real time by the frequency converter to control the flow rate, and the opening of the distribution valve is precisely controlled by the electric actuator. At the same time, the slurry flow rate and density setting instructions are sent to the filling station to realize dynamic coordinated control between the distribution pump station, tailings dam and filling station, ensuring that the actual operating parameters closely track the optimization results.

6. The multi-node collaborative scheduling method for tailings transportation based on a risk constraint model according to claim 5, characterized in that: It also includes intelligent emergency response steps: The integrated intelligent monitoring and early warning system automatically triggers a set of graded emergency response strategies when the tailings dam risk indicators exceed or are close to exceeding limits, or when the pipeline pressure is abnormal. These strategies include, but are not limited to, dynamically adjusting the tailings allocation ratio to reduce the amount entering the dam, prioritizing the filling slurry supply, limiting the maximum output flow of the pumping station, activating the tailings dam emergency drainage facilities, switching to backup pipelines, or executing emergency shutdown procedures, and generating a detailed emergency handling report.

7. A multi-node collaborative scheduling method for tailings transportation based on a risk constraint model according to claim 6, characterized in that: It also includes a closed-loop feedback update step: Collect actual operating data after execution, and use data-driven methods to correct risk prediction models, energy consumption models, pipeline resistance characteristic parameters and risk constraint margins online, so as to realize closed-loop optimization and continuous improvement of scheduling strategies and improve the system's adaptability and robustness to complex operating conditions.

8. A multi-node collaborative scheduling system for tailings transportation based on a risk constraint model, applied to the multi-node collaborative scheduling method for tailings transportation based on a risk constraint model as described in claim 7, characterized in that: include: Data acquisition and transmission subsystem: Deploy a high-precision sensor network to realize real-time acquisition and wireless transmission of operating data from distribution pump stations, tailings dams and filling stations; Central control subsystem: integrates a high-performance computing platform and intelligent algorithm library, and is responsible for data processing, risk prediction, constraint generation, joint optimization calculation and control command generation; The actuator subsystem includes frequency converters, electric valve actuators, and an automated control system for the filling station, ensuring accurate execution of optimized commands from the central control subsystem. Intelligent Emergency Response Subsystem: Integrates risk warning, strategy decision-making, and execution functions to ensure rapid response in emergency situations; Closed-loop feedback and optimization subsystem: Continuously optimize model parameters using execution data to form a closed-loop control system.

9. A multi-node collaborative scheduling of tailings transportation based on a risk constraint model according to claim 8, characterized in that: The central control subsystem is further configured as follows: It adopts a modular design, supports flexible configuration and expansion of multi-objective joint optimization algorithms, and can adjust the weights of objective functions, constraints and optimization strategies according to the actual working conditions and needs of different mines, so as to realize the rapid generation and deployment of personalized scheduling schemes.

10. A multi-node collaborative scheduling method and system for tailings transportation based on a risk constraint model according to claim 9, characterized in that: The intelligent emergency response subsystem is further configured as follows: It possesses self-learning and adaptive capabilities, and can continuously optimize the emergency response strategy set based on historical emergency event data and processing results, thereby improving the efficiency and effectiveness of emergency handling. At the same time, it supports manual intervention and remote control to ensure the safe and stable operation of the system under extreme conditions.

Images