A mine tunnel intelligent environment monitoring and control method

Abstract

The present application relates to the technical field of mine environment control, and discloses a kind of intelligent environment monitoring and control method in mine roadway.The method includes the real-time environmental parameter set of collection mine roadway, the set covers gas concentration data, dust concentration data and temperature and humidity data, realize the real-time capture of multi-dimensional parameter of roadway environment;Then based on the real-time environmental parameter set collected, calculate environmental safety evaluation index, to scientifically and objectively reflect the safety situation of roadway environment;Then according to environmental safety evaluation index generates dynamic control strategy, the strategy contains ventilation equipment control parameter and early warning level parameter, can be adjusted flexibly according to environmental change;Finally, the ventilation equipment control parameter is sent to mine ventilation system, and executes roadway environment control.The method can monitor environmental parameters comprehensively, accurately assess safety risks, flexibly regulate ventilation equipment, improve early warning functions, reduce energy waste, reduce manual intensity, and ensure underground operation safety and mining efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mine environment control, in particular to an intelligent environment monitoring and control method in a mine roadway. BACKGROUND

[0002] In the process of mine exploitation, the environmental conditions in the roadway are directly related to the safety of the underground workers and the smooth progress of the exploitation.

[0003] Most mines still use artificial periodic inspection to collect roadway environmental parameters. This method not only requires a large amount of labor cost, but also has a fixed inspection cycle, making it difficult to realize real-time capture of environmental parameters. When there are emergency situations such as sudden increase in gas concentration and sudden increase in dust concentration in the roadway, artificial inspection often cannot discover the situation in time, which may miss the best disposal opportunity and even cause safety accidents. Even though some mines have introduced automatic monitoring equipment, the monitoring function is relatively single, and most of them can only monitor one or two environmental parameters, and cannot comprehensively obtain multi-dimensional environmental information such as gas concentration, dust concentration, temperature and humidity in the roadway, making it difficult for workers to make overall and accurate judgments on the safety of the roadway environment.

[0004] In terms of environmental control, the existing technology mostly uses a fixed parameter control mode, that is, the ventilation equipment is controlled according to the preset fixed value, and the control strategy cannot be flexibly adjusted according to the real-time changing environmental parameters in the roadway. When the gas concentration in a certain area of the roadway is slightly over the standard, and the environmental parameters in other areas are normal, the fixed parameter control mode will still start high-intensity ventilation in the whole roadway, which not only causes a lot of energy waste, but also may cause unnecessary disturbance to the working environment in the roadway due to the excessive ventilation intensity. The existing system also has obvious defects in the early warning function. The early warning level is relatively rough, and only a single early warning signal can be sent, which cannot provide different levels of early warning prompts according to the severity of the environmental safety risk, making it difficult for workers to quickly grasp the emergency level of the risk and affecting the efficiency and accuracy of emergency disposal. The existence of these problems makes the existing mine roadway environment monitoring and control method difficult to meet the production needs of modern mine safety, high efficiency and energy saving, and a more intelligent, comprehensive and flexible monitoring and control method is needed to solve the above problems. SUMMARY

[0005] The present application relates to the technical field of mine environment control, in particular to an intelligent environment monitoring and control method in a mine roadway.

[0006] To achieve the above-mentioned purpose, the present application provides an intelligent environment monitoring and control method in a mine roadway, which comprises:

[0007] Collect a real-time environment parameter set of a mine roadway, the real-time environment parameter set comprising gas concentration data, dust concentration data and temperature and humidity data;

[0008] Calculate an environment safety evaluation index based on the real-time environment parameter set;

[0009] Generate a dynamic control strategy according to the environment safety evaluation index, the dynamic control strategy comprising ventilation equipment control parameters and early warning level parameters;

[0010] Send the ventilation equipment control parameters to a mine ventilation system to perform roadway environment control.

[0011] Preferably, the calculation of the environment safety evaluation index comprises:

[0012] Determine a weight coefficient of the gas concentration data, a weight coefficient of the dust concentration data and a weight coefficient of the temperature and humidity data;

[0013] Add a product of the gas concentration data and the weight coefficient of the gas concentration data, a product of the dust concentration data and the weight coefficient of the dust concentration data, and a product of the temperature and humidity data and the weight coefficient of the temperature and humidity data to generate an initial safety evaluation value;

[0014] Correct the initial safety evaluation value according to a topological structure feature of the roadway to obtain a final environment safety evaluation index.

[0015] Preferably, the generation of the dynamic control strategy according to the environment safety evaluation index comprises:

[0016] Establish a strategy space comprising the ventilation equipment control parameters and the early warning level parameters;

[0017] Obtain current ventilation equipment operating states and roadway personnel distribution data;

[0018] Input the environment safety evaluation index, the current ventilation equipment operating states and the roadway personnel distribution data into a fuzzy reasoning engine;

[0019] Match an optimal ventilation equipment control parameter and early warning level parameter combination in the strategy space through the fuzzy reasoning engine.

[0020] Preferably, the method further comprises:

[0021] Divide the environment safety evaluation index into grade intervals, each grade interval being associated with an independent weight adjustment rule;

[0022] When the environment safety evaluation index enters a first grade interval, a first set of weight coefficients is used to calculate a ventilation equipment control parameter change amount;

[0023] When the environmental safety evaluation index enters the second level interval, a second set of weight coefficients is used to combine and calculate the ventilation equipment regulation parameter change amount;

[0024] The ventilation equipment regulation parameter change amount is added to the current ventilation equipment regulation parameter to generate an updated ventilation equipment regulation parameter.

[0025] Preferably, the method further comprises:

[0026] A distributed decision-making model of the roadway monitoring nodes is established, and each monitoring node generates a local control strategy according to a local environmental parameter set;

[0027] The local control strategies of adjacent monitoring nodes are collected to form a strategy set;

[0028] The consistency error of the local control strategy of the current monitoring node and the local control strategies of adjacent monitoring nodes is calculated;

[0029] The local control strategy parameters are adjusted based on the consistency error to generate a cooperative control strategy.

[0030] Preferably, the generation of the cooperative control strategy comprises:

[0031] When the consistency error exceeds a preset threshold, a strategy adjustment vector is calculated;

[0032] The strategy adjustment vector is applied to the local control strategy of the current monitoring node;

[0033] The application strength of the strategy adjustment vector is corrected according to a device response delay coefficient;

[0034] The corrected cooperative control strategy is output to the regional execution device.

[0035] Preferably, the method further comprises:

[0036] A case library containing a historical environmental parameter set and a historical control strategy is constructed;

[0037] A historical case subset matching the current environmental safety evaluation index is retrieved;

[0038] High-frequency control strategy features in the historical case subset are extracted;

[0039] The high-frequency control strategy features are injected into the rule base of the fuzzy reasoning engine.

[0040] Preferably, the method further comprises:

[0041] The strategy execution effect data in each environmental regulation process is recorded;

[0042] A mapping relationship between the strategy execution effect data and the environmental safety evaluation index is established;

[0043] When the change trend of the mapping relationship exceeds the fluctuation threshold, a weight coefficient redistribution mechanism is triggered;

[0044] The weight coefficient of the gas concentration data, the weight coefficient of the dust concentration data and the weight coefficient of the temperature and humidity data are updated through the weight coefficient redistribution mechanism.

[0045] Preferably, the method further comprises:

[0046] The dynamic priority corresponding to the early warning level parameter is divided;

[0047] When the environmental safety evaluation index reaches the emergency threshold, the execution priority of the ventilation equipment control parameter is improved;

[0048] The execution priority is adjusted according to the device state health coefficient to adjust the improvement range of the execution priority;

[0049] The control strategy execution sequence is scheduled based on the updated execution priority.

[0050] Preferably, the method further comprises:

[0051] An environmental parameter propagation model between the roadway regions is established;

[0052] The parameter diffusion path is predicted according to the environmental parameter propagation model;

[0053] The parameter diffusion path is matched with real-time topological structure data;

[0054] The initial value of the ventilation equipment control parameter of the adjacent region is adjusted based on the matching result.

[0055] Compared with the prior art, the beneficial effects of the present application are:

[0056] The intelligent environment monitoring and control method in the mine roadway can realize comprehensive and real-time collection of the roadway environment parameters, breaking the limitations of traditional monitoring methods in monitoring dimensions and timeliness. By simultaneously collecting gas concentration data, dust concentration data and temperature and humidity data, a complete set of real-time environmental parameters is formed, and the staff can comprehensively understand the environmental conditions in the roadway, avoiding environmental safety judgment deviation caused by single parameter monitoring, and ensuring the comprehensiveness and accuracy of the roadway environmental safety evaluation from the monitoring source.

[0057] In the environmental safety evaluation link, the environmental safety evaluation index is calculated based on the real-time environmental parameter set in multiple dimensions. Compared with the traditional mode of relying on experience judgment or single parameter evaluation, the actual safety status of the roadway environment can be more scientifically and objectively reflected. This data-based evaluation method eliminates the interference of subjective factors, making the evaluation result more reliable, providing a reliable basis for subsequent development of reasonable control strategies, and helping workers accurately grasp the core of the safety risk of the roadway environment.

[0058] The generation of the dynamic control strategy realizes flexible and accurate regulation and control of the ventilation equipment, changing the disadvantages of the traditional fixed parameter control mode. According to the different environmental safety evaluation indexes, the dynamic control strategy including the ventilation equipment control parameters and the warning level parameters is generated, which can adapt to the real-time changes of the roadway environment. When the environmental safety evaluation index shows that the gas concentration in a certain area is slightly over standard, only the ventilation equipment parameters corresponding to the area can be fine-tuned, without the need to start high-intensity ventilation of the whole roadway, effectively reducing energy consumption and unnecessary energy waste, and avoiding the interference of excessive ventilation on the working environment, balancing the effectiveness and economy of environmental control.

[0059] The inclusion of the warning level parameter makes the warning function more perfect, and can provide different levels of warning prompts according to the severity of the environmental safety risk. Through the warning level parameter, workers can quickly judge the emergency degree of the risk, and then take corresponding emergency measures, avoiding the problem of delayed or excessive response caused by a single warning signal, significantly improving the efficiency and pertinence of emergency disposal, and providing stronger protection for the life safety of underground workers.

[0060] The ventilation equipment control parameters are sent to the mine ventilation system for regulation and control, realizing closed-loop management of monitoring, evaluation and control, reducing the manual intervention link and the probability of human operation errors. The whole process does not need workers to manually adjust the ventilation equipment parameters, not only reducing the labor intensity of workers, but also improving the response speed of environmental regulation and control, ensuring that the regulation and control measures can be started quickly when the environmental parameters are abnormal, and the roadway environment can be restored to the safety range in time, creating good environmental conditions for the continuous and stable advancement of mine exploitation, and meeting the development trend of modern mine intelligence and automation, which helps to improve the overall production management level of the mine. BRIEF DESCRIPTION OF DRAWINGS

[0061] Figure 1 A working principle diagram of the mine roadway intelligent environment monitoring and control method described in the present application;

[0062] Figure 2 A flowchart for calculating the environmental safety evaluation index;

[0063] Figure 3 Flowchart for updating ventilation equipment regulation parameters based on grade intervals;

[0064] Figure 4 Flowchart for modifying the coordinated control strategy. DETAILED DESCRIPTION

[0065] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work are within the protection scope of the present application.

[0066] Please refer to Figure 1 The present application provides a kind of intelligent environment monitoring and control method in mine roadway, the method comprises:

[0067] Intelligent regulation and control of roadway environment is realized by integrating sensor network, data processing unit and control execution mechanism. The method collects real-time environmental parameter set of mine roadway, including gas concentration data, dust concentration data and temperature and humidity data. These data are obtained in real time by multiple sensors deployed in the roadway, and transmitted to the central processing unit. Based on the real-time environmental parameter set, environmental safety evaluation index is calculated, which is used to quantify the safety state of the current environment. Dynamic control strategy is generated according to the environmental safety evaluation index, including ventilation equipment regulation parameters and warning level parameters. Ventilation equipment regulation parameters involve fan speed, damper opening and other adjustable variables, and warning level parameters are used to trigger different levels of alarm. The ventilation equipment regulation parameters are sent to the mine ventilation system, and the actuator is used to adjust the operating state of the ventilation equipment, so as to realize real-time regulation and control of the roadway environment.

[0068] Embodiment 1: refer to Figure 2 Gas concentration data, dust concentration data and temperature and humidity data are continuously collected by sensor nodes distributed throughout the roadway. These sensor nodes form a monitoring network covering key areas, and the data collected by them are transmitted to the central processing unit through wired or wireless communication. Gas concentration data usually covers oxygen, methane, carbon monoxide and other key gases, and the values are in percentage or ppm. Dust concentration data is in milligrams per cubic meter, reflecting the content of suspended particulate matter in the air. Temperature and humidity data include temperature readings in Celsius and relative humidity in percentage.

[0069] The core of the calculation of the safety evaluation index of the environment is to give different attention to the above-mentioned multi-dimensional data, that is, the weight coefficient. The determination of these weight coefficients is not fixed, but is set based on mine safety regulations, historical accident statistical analysis and the functional properties of the specific roadway. In the coal seam roadway with large gas emission, the weight coefficient of gas concentration data will be given a higher value to highlight its risk dominance. The weight coefficient of dust concentration data may be more significant in rock roadway drivage working face. The weight coefficient of temperature and humidity data is related to the labor intensity and man-machine efficiency requirements of the work area. The specific value of the weight coefficient is determined by expert evaluation and risk matrix analysis and stored in the system database. After obtaining the weight coefficient of each data, the system performs weighted calculation. Specifically, the real-time collected gas concentration data is multiplied by its corresponding weight coefficient to obtain the weighted contribution value of the gas. Similarly, the dust concentration data is multiplied by its weight coefficient to obtain the weighted contribution value of the dust, and the temperature and humidity data are also processed in a similar manner. These weighted contribution values are then added to produce an initial safety evaluation value. This value is a dimensionless scalar that reflects the absolute level of the environmental parameters and their relative importance in the overall safety evaluation.

[0070] Although the initial safety evaluation value integrates the information of multiple key parameters in the development process, it still has certain limitations, mainly in that the specific distribution of environmental parameters in the roadway space and their propagation characteristics have not been fully considered. In order to make the evaluation result more accurate and close to the actual situation, it is necessary to make detailed corrections to this initial evaluation value according to the topological structure characteristics of the roadway. The topological structure characteristics of the roadway is a multi-dimensional concept, covering the geometric shape, spatial connection relationship and ventilation network characteristics of the roadway. The parameters involved include but are not limited to the total length of the roadway, the size of each section, the overall slope of the roadway, the number of branch roadways, the connection angle between the main ventilation roadway and the local obstacle distribution in the roadway, etc. These parameters together constitute the complex appearance of the topological structure of the roadway, which has a significant impact on the distribution and propagation of environmental parameters. In order to obtain these feature data, it is necessary to use the digital model of the roadway. This model is a three-dimensional spatial database constructed by integrating geological survey data and engineering design drawings, which can accurately reflect the actual structure and spatial layout of the roadway. Through this model, various feature data required can be efficiently and accurately extracted, providing solid data support for the correction of the initial safety evaluation value.

[0071] The correction process is realized by an intermediate variable called topological influence factor, which is a coefficient greater than zero, whose calculation depends on the combined analysis of topological structure characteristics and parameter diffusion model. In a long and narrow blind lane with closed ends, harmful gases are easy to accumulate and not easy to diffuse, at this time the topological influence factor is greater than one, thus correcting the initial safety evaluation value upwards, amplifying the risk it represents. Conversely, in a wide cross-section, directly connected to the main airflow and without obvious obstacles, the environmental parameters tend to be uniform, the diffusion is good, and the topological influence factor may be less than one, correcting the initial value downwards. The calculation of the topological influence factor involves fluid mechanics simulation or empirical formula, and its output is used to multiply the initial safety evaluation value, and the final generated environmental safety evaluation index is a more accurate and more realistic space risk distribution evaluation result.

[0072] Embodiment 2: refer to Figure 3 The space is a multi-dimensional decision set, which covers all controllable ventilation equipment parameters, such as the speed gear of the main ventilation fan, the start-stop state of the auxiliary local fan, the opening angle of the regulation air window, the opening-closing position of the air door, etc. At the same time, the warning level parameter is divided into multiple discrete levels as another important dimension, such as normal state, first-level warning, second-level warning and emergency alarm, each level corresponds to different sound and light alarm modes, information broadcast content and personnel evacuation instructions. The strategy space is composed of all possible value combinations of these dimensions, forming a huge strategy library.

[0073] The generation of dynamic strategies is not done in a vacuum, but is closely dependent on the current state of the system. Therefore, two key pieces of information need to be obtained in real-time: first, the current operating state of the ventilation equipment, including the real-time speed, current, and power consumption of each main fan, as well as the current opening degree of various dampers and air windows; second, the personnel distribution data in the roadway, which can be obtained through personnel positioning systems, patrol records, or sensors installed in important areas to understand the degree of personnel concentration in different roadway areas. The calculated environmental safety evaluation indicators, collected current ventilation equipment operating states, and roadway personnel distribution data are input into a fuzzy reasoning engine. The engine has a pre-set fuzzy rule base based on expert knowledge and historical experience. These rules are usually in the form of "if-then", with the condition part involving fuzzy concepts such as the level of environmental indicators, the busy or idle state of equipment, and the dense or sparse distribution of personnel, and the conclusion part pointing to specific areas in the strategy space. A rule may state: "If the environmental safety evaluation indicator is high and the personnel distribution is dense, then the fan speed should be significantly increased and a level one warning should be triggered." After receiving these precise input values, the fuzzy reasoning engine converts them into membership degrees belonging to different fuzzy sets through fuzzification, then activates all relevant rules and performs synthetic reasoning based on the weights and membership degrees of the rules, and finally outputs an accurate optimal ventilation equipment control parameter and warning level parameter combination through defuzzification.

[0074] To further enhance the adaptability and refinement of strategy generation, the system divides the environmental safety evaluation indicators into more detailed grade intervals. Specifically, the system scientifically divides the indicator value range into four different grade intervals: safe interval, attention interval, warning interval, and danger interval. Each interval is directly associated with a different warning level, ensuring that appropriate warning signals are sent in specific situations. More importantly, each interval is associated with a separate set of weight adjustment rules. These rules are specifically designed to calculate the change in control parameters, ensuring that the system can adjust control strategies flexibly according to different interval levels when environmental safety conditions change, achieving more accurate and efficient management. Through this refined interval division and weight adjustment mechanism, the system can better cope with various complex and changing environmental safety challenges and improve overall safety management levels.

[0075] When the environmental safety assessment indicator is in the lower attention interval, the system adopts the first set of weight coefficient combination. This set of weights may focus more on energy efficiency and smooth operation of equipment, and the calculated ventilation equipment control parameter change is relatively moderate, aiming to fine-tune to improve the environmental trend. When the indicator rises into the higher warning or danger interval, the system activates the second set of completely different weight coefficient combination. This set of weights significantly increases the proportion of safety factors, tends to take more decisive and forceful control actions, and the calculated ventilation equipment control parameter change will increase significantly at this time. The calculated change, whether it is an increase or a decrease, will eventually be added to the current ventilation equipment control parameter to generate the updated control parameter instruction to be executed. This method of dynamically adjusting weights based on safety levels enables the control system to run smoothly in normal times and respond quickly in abnormal times, achieving a balance between safety and efficiency.

[0076] Embodiment 3: refer to Figure 4 Each node is an autonomous unit integrating environmental sensors, processors, and communication modules. The node continuously collects a set of local environmental parameters at its location, including gas concentration, dust concentration, and temperature and humidity. Based on these real-time data, each node independently runs a local decision algorithm to generate a local control strategy for its surrounding area. The strategy usually includes recommended ventilation equipment operation, adjusting the opening of nearby dampers or changing the speed of local fans. This process enables each node to respond quickly to local environmental changes.

[0077] Isolated local decision-making may lead to inconsistent actions of the entire roadway ventilation system, or even conflicts. A node may suggest increasing air volume to dilute local high concentration of gas, which may interfere with the air flow field designed by neighboring nodes to control dust. To solve this problem, the system establishes a communication network between nodes. Each node regularly broadcasts its generated local control strategy to neighboring nodes within its communication range, and also receives strategy information from these neighboring nodes. All received strategies and the node's own strategy form a strategy set, representing the decision intentions of the entire local area that the node can perceive. The current node needs to evaluate the coordination of its own decision and the surrounding decisions. It completes this evaluation by calculating the consistency error. The error quantifies the difference between the current node's local control strategy and the received local control strategies of neighboring nodes. A typical calculation method is based on the difference between strategy vectors.

[0078] Let the local control strategy of the current monitoring node be represented as a vector where each component represents a control parameter, such as fan speed set value. The strategy set of all neighboring nodes is , with k neighboring nodes. The consistency error can be calculated by the following relationship:

[0079]

[0080] wherein: represents the length of the module of the difference between the current node policy and the average of all neighboring node policies, the larger the value, the higher the inconsistency. represents the Euclidean distance between two policy vectors. k represents the total number of neighboring nodes. represents the policy vector of the nth neighboring node.

[0081] This error value is the key to trigger policy adjustment. When the consistency error exceeds a preset threshold, it indicates that the decision of the current node deviates from the consensus of the surrounding nodes, and adjustment is needed to converge. The system will calculate a policy adjustment vector . The direction of this vector points to the average direction of the neighboring node policy, and the size is related to the current inconsistency. Its role is to pull the current node policy to the average value direction of the neighbor policy, mathematically expressed as .

[0082] Before actually executing the adjustment, the inertia delay of the system must also be considered. There is a certain lag from the time the ventilation equipment receives the instruction to the time it is fully executed and produces an effect. This time is defined as the device response delay coefficient. If the adjustment action is too drastic, it may cause system oscillation due to device response delay. Therefore, the strength of the policy adjustment vector needs to be corrected according to the device response delay coefficient. The usual way is to introduce a gain factor (0 <1), and the actual adjustment amount is corrected to , so as to smooth the adjustment process and avoid excessive regulation. Finally, the collaborative control policy produced after consistency coordination and delay correction is output to the regional execution equipment under the jurisdiction of the node, such as the local fan controller or damper actuator, so as to realize the coordination and synchronization of regional ventilation control. This distributed collaborative mechanism effectively solves the local decision conflict and improves the stability and effectiveness of the entire roadway environment regulation system.

[0083] Embodiment 4: The implementation of this approach begins with the construction of a structured case library. Rather than simply storing raw data, each record in the case library contains a complete environmental control event. Each case consists of three parts: a set of historical environmental parameters, a historical control strategy, and an implied strategy execution effect. The set of historical environmental parameters records a snapshot of gas, dust, temperature, and humidity data from one or more monitoring nodes at the time of the event. The historical control strategy details all the control actions taken by the system at that time, including main fan speed setting, auxiliary fan start-stop status, and warning level. The strategy execution effect is not directly recorded, but can be indirectly reflected by comparing the trends of environmental parameters and equipment energy consumption before and after the strategy is executed. The case library is continuously expanded as the system runs over time, forming a rich knowledge base of experience.

[0084] When the system again faces a critical decision-making moment, that is, after the current environmental safety assessment index is calculated in detail and a specific value is obtained, it will immediately start an efficient case retrieval process. The system takes the current environmental safety assessment index as the core retrieval key and searches deeply into the vast case library to find a subset of cases that are most similar to the current environment. This retrieval process usually relies on advanced distance-based algorithms to calculate the similarity between each historical environmental safety assessment index value and the current value, and to filter out the historical cases that are most similar to the current value. These strictly filtered and selected cases collectively form a representative subset of historical cases. This subset not only contains rich historical data, but also represents the valuable decision-making experience accumulated by the system in the past when dealing with similar safety conditions, providing strong reference and support for the current decision.

[0085] The system needs to extract valuable decision-making patterns from these similar cases, and it will perform statistical analysis on all historical control strategies contained in the historical case subset to extract high-frequency control strategy features. Analysis shows that in more than a certain percentage (such as 80%) of similar cases, the system has taken the operation of increasing the main fan speed to a certain specific speed interval; or in most cases, a certain specific level of warning is triggered. These frequently occurring control actions are identified as high-frequency features, which suggest that certain strategies may be more universally effective when dealing with this type of environmental condition.

[0086] These high-frequency features distilled from historical experience are not ignored, but are injected into the rule base of the fuzzy inference engine. The way of injection can be to add new fuzzy rules, whose condition part corresponds to the environmental conditions that produce this high-frequency feature, and the conclusion part points to the high-frequency control strategy; or to adjust the weight or confidence of existing rules, so that those rules repeatedly verified by historical data as effective have greater influence in subsequent reasoning. In this way, the decision logic of the system is continuously evolving, becoming more accurate and reliable. The system establishes a parallel learning cycle to optimize the weight coefficients relied on when initially calculating the environmental safety assessment indicators. The system continuously records data of the entire process of environmental regulation, especially the effect data after the implementation of the strategy. Effect data includes the change value of environmental safety assessment indicators within a certain period of time after the implementation of the regulation action, the stabilization time of each environmental parameter, and the energy cost of the equipment to achieve this effect, etc.

[0087] The system is committed to establishing a mapping relationship between strategy execution effect data and environmental safety assessment indicators. This relationship reveals the performance of different types of control strategies in changing the state of the environment. Through long-term observation, the system can identify the trend of change in the mapping relationship. It may be observed that the regulation strategy for dust concentration is gradually weakening its effect on improving the environmental safety assessment indicators. When the strength of this change trend exceeds the preset fluctuation threshold, it indicates that the weight coefficient used to calculate the environmental safety assessment indicators (such as the weight coefficient of dust concentration data) may have failed to accurately reflect the actual risk contribution of the parameter, thereby triggering the weight coefficient redistribution mechanism.

[0088] Table 1: Historical case library records.

[0089] Case No. Environmental safety assessment index Main fan speed setting (RPM) Auxiliary fan state Early warning level Change rate of index after regulation C-20230901-0852 0.72 1450 On Secondary early warning -0.18 C-20230905-1420 0.68 1400 Off Primary early warning -0.15 C-20230910-1015 0.75 1500 On Secondary early warning -0.20 C-20230915-1530 0.71 1420 On Primary early warning -0.16 C-20230920-0910 0.69 1380 Off Primary early warning -0.14

[0090] Example 5: The implementation of this approach first divides the execution priority corresponding to the warning level parameter. Different levels of warning signals mean different degrees of environmental risk and emergency situations, so it is necessary to match differentiated resource scheduling urgency. The system maps the warning level parameter to a dynamic priority value sequence. The normal monitoring state corresponds to the lowest priority, which is used to arrange periodic equipment inspection and parameter fine-tuning. The first level of warning corresponds to a higher priority, requiring the system to respond and execute the regulation instruction within a shorter time. The second level of warning and emergency alarm correspond to a higher priority, and their instructions are given the characteristics of immediately interrupting the current low-priority task and executing first. This division ensures that system resources can be reasonably allocated according to the urgency of the risk.

[0091] The core feature of dynamic priority is its adjustability. When the environmental safety assessment index continues to deteriorate and reaches the preset emergency threshold, the system automatically promotes the execution priority of the related ventilation equipment control parameters. The speed-up instruction of a certain fan originally in medium priority, after the environmental index reaches the emergency threshold, its priority value will be amplified by a multiplier, so as to jump to a more forward position in the queue of instructions to be executed. This promotion mechanism ensures that in crisis situations, the most critical control actions can be executed in priority and quickly. The promotion amplitude of the instruction priority is not fixed, it is subject to the actual running state of the equipment. The system introduces a device state health coefficient, which is obtained by real-time monitoring and analysis of the running data of the ventilation equipment (such as vibration frequency, noise level, motor temperature rise, historical maintenance records), to quantify the current reliability and load capacity of the equipment. When the device state health coefficient is low, it indicates that the equipment may have potential faults or performance degradation. At this time, if it is greatly promoted in priority and high-intensity operation is performed, it may exacerbate equipment wear or even cause unexpected shutdown. Therefore, the system adjusts the promotion amplitude of the execution priority according to the coefficient. When the health is high, the promotion amplitude can be larger; when the health is low, a more conservative, small-amplitude priority promotion is adopted, or the upper limit of the equipment running intensity required by the instruction is automatically reduced while the priority is promoted, to balance between responding to risks and protecting equipment.

[0092] Based on the updated execution priority, the system sorts all the control strategies to be executed to form the final execution sequence. The dispatcher sends control instructions to the ventilation equipment one by one according to this sequence, ensuring that high-priority, safety-related critical operations are executed in priority, while low-priority optimization operations are appropriately delayed. The system runs a parallel predictive analysis module to respond to the spatial diffusion of environmental risks in the roadway network. This module is based on an environmental parameter propagation model between roadway areas. This model can simulate the migration and diffusion path and rate of environmental parameters such as gas and dust between different areas by integrating the physical topology of the roadway, the characteristics of the ventilation network, the aerodynamic parameters, and the historical parameter diffusion data. According to this environmental parameter propagation model, the system can predict the potential path of parameter diffusion. Simulation shows that a sudden high concentration of gas in a certain area, under the action of the main airflow, is expected to diffuse to the adjacent connected roadway downwind after a certain time. The system matches this predicted parameter diffusion path with the real-time topological structure data of the mine. The matching process aims to confirm whether the predicted diffusion path is still valid under the actual running state of the current ventilation network, and accurately locate the adjacent areas that will be affected and the degree of their impact.

[0093] Based on the matching result, the system will actively adjust the initial value of the ventilation equipment control parameters of these adjacent areas. This is a proactive intervention strategy. Instead of waiting for the pollution to spread to the site and the environment deteriorates, the system will issue instructions to the ventilation equipment in the risk-affected area in advance. The fan speed in the downstream area is increased in advance to enhance the dilution capacity, or the damper opening is adjusted in advance to change the local air flow direction, to build a "virtual barrier", so as to effectively block or mitigate the spread of risk, contain the environmental problem in a local area, and avoid it from evolving into a global event affecting the entire roadway system. This proactive prevention based on prediction combined with priority-based scheduling significantly enhances the comprehensive ability of the system to respond to complex and dynamic environments.

[0094] It should be noted that the relational terms herein such as first and second and the like are used solely to distinguish one entity or action from another, without necessarily requiring or implying any actual relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0095] Although embodiments of the present application have been shown and described, it is to be understood that various modifications, substitutions, replacements and variations can be made to these embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A method for intelligent environment monitoring and control in a mine tunnel, characterized by, The method comprises: Collecting a set of real-time environmental parameters of a mine tunnel, the set of real-time environmental parameters comprising gas concentration data, dust concentration data, and temperature and humidity data; Based on the set of real-time environmental parameters, calculating an environmental safety evaluation index; Generating a dynamic control strategy according to the environmental safety evaluation index, the dynamic control strategy comprising ventilation equipment control parameters and early warning level parameters; Sending the ventilation equipment control parameters to a mine ventilation system to execute tunnel environment control; The method further comprises: Establishing a distributed decision-making model of a tunnel monitoring node, each monitoring node generating a local control strategy according to a set of local environmental parameters; Collecting local control strategies of adjacent monitoring nodes to form a strategy set; Calculating the consistency error of the local control strategy of the current monitoring node and the local control strategies of adjacent monitoring nodes; Based on the consistency error, adjusting the local control strategy parameters to generate a cooperative control strategy; The generation of the cooperative control strategy comprises: When the consistency error exceeds a preset threshold, calculating a strategy adjustment vector; Applying the strategy adjustment vector to the local control strategy of the current monitoring node; According to the equipment response delay coefficient, correcting the action strength of the strategy adjustment vector; Outputting the corrected cooperative control strategy to the regional execution equipment.

2. The method for monitoring and controlling intelligent environment in mine roadway according to claim 1, characterized in that, The calculation of the environmental safety evaluation index comprises: Determining the weight coefficients of the gas concentration data, the weight coefficients of the dust concentration data, and the weight coefficients of the temperature and humidity data; Adding the product of the gas concentration data and the weight coefficients of the gas concentration data, the product of the dust concentration data and the weight coefficients of the dust concentration data, and the product of the temperature and humidity data and the weight coefficients of the temperature and humidity data to generate an initial safety evaluation value; According to the topological structure characteristics of the tunnel, correcting the initial safety evaluation value to obtain the final environmental safety evaluation index.

3. The method for monitoring and controlling intelligent environment in mine roadway according to claim 2, characterized in that, The generation of the dynamic control strategy according to the environmental safety evaluation index comprises: Establishing a strategy space containing ventilation equipment control parameters and early warning level parameters; Obtaining the current ventilation equipment operating state and the tunnel personnel distribution data; Inputting the environmental safety evaluation index, the current ventilation equipment operating state, and the tunnel personnel distribution data into a fuzzy reasoning engine; Through the fuzzy reasoning engine, matching the optimal ventilation equipment control parameter and early warning level parameter combination in the strategy space.

4. The method for monitoring and controlling intelligent environment in mine roadway according to claim 3, characterized in that, The method further comprises: Dividing the level intervals of the environmental safety evaluation index, each level interval being associated with an independent weight adjustment rule; When the environmental safety evaluation index enters the first level interval, a first set of weight coefficients is used to calculate the ventilation equipment control parameter change; When the environmental safety evaluation index enters the second level interval, a second set of weight coefficients is used to calculate the ventilation equipment control parameter change; Adding the ventilation equipment control parameter change to the current ventilation equipment control parameter to generate an updated ventilation equipment control parameter.

5. The method for monitoring and controlling intelligent environment in mine roadway according to claim 1, characterized in that, The method further comprises: Building a case library containing a set of historical environmental parameters and historical control strategies; Retrieving a subset of historical cases matching the current environmental safety evaluation index; Extracting high-frequency control strategy features from the subset of historical cases; Injecting the high-frequency control strategy features into the rule base of the fuzzy reasoning engine.

6. The method for monitoring and controlling intelligent environment in mine roadway according to claim 5, characterized in that, The method further comprises: Record the policy execution effect data in each environmental regulation process; Establish a mapping relationship between the policy execution effect data and the environmental safety evaluation index; When the change trend of the mapping relationship exceeds the fluctuation threshold, trigger the weight coefficient redistribution mechanism; Update the weight coefficients of the gas concentration data, the dust concentration data, and the temperature and humidity data through the weight coefficient redistribution mechanism.

7. The method for monitoring and controlling intelligent environment in mine roadway according to claim 6, characterized in that, The method further comprises: Divide the dynamic priority corresponding to the early warning level parameter; When the environmental safety evaluation index reaches the emergency threshold, improve the execution priority of the ventilation equipment regulation parameter; Adjust the improvement amplitude of the execution priority according to the equipment state health degree coefficient; Schedule the control policy execution sequence based on the updated execution priority.

8. The method for monitoring and controlling intelligent environment in mine roadway according to claim 7, characterized in that, The method further comprises: Establish an environmental parameter propagation model between the roadway regions; Predict the parameter diffusion path according to the environmental parameter propagation model; Match the parameter diffusion path with the real-time topological structure data; Adjust the initial value of the ventilation equipment regulation parameter of the adjacent region based on the matching result.

Images