Underground construction worker safety scheduling method based on monitoring model

Abstract

The invention relates to the technical field of underground operation safety management, in particular to an underground construction operator safety scheduling method based on a monitoring model. Comprising the steps that an underground safety monitoring model is constructed, and the underground safety monitoring model is used for collecting, fusing and processing environment monitoring data, equipment operation data and personnel state data in real time; based on the data processed by the underground safety monitoring model, dynamically calculating a comprehensive safety index representing the safety condition of each current underground area; comparing the comprehensive security index with a plurality of preset thresholds, and generating a dynamic scheduling instruction according to a comparison result, qualification authentication information of the to-be-scheduled personnel and a real-time position; and sending the dynamic scheduling instruction to a mobile terminal of a target person and a central monitoring system, the underground safety monitoring model is constructed to fuse multi-source data in real time, the scheduling instruction is dynamically generated, task distribution is optimized, and the real-time performance and scheduling efficiency of underground safety management can be improved.

Description

Technical Field

[0001] This invention relates to the field of downhole operation safety management technology, specifically a method for the safe scheduling of downhole construction personnel based on a monitoring model. Background Technology

[0002] The underground working environment during oil extraction is complex, and workers often face various risks such as leaks of toxic and harmful gases, high temperature and high pressure, and sudden equipment failures. The traditional personnel safety management model mainly relies on fixed environmental sensors for threshold alarms, combined with intercom systems for manual dispatch by personnel in the central control room. However, this model has the following drawbacks.

[0003] If information perception is fragmented, environmental data, equipment status data and personnel location and physiological status data are independent of each other, forming "information silos". This makes safety management decisions lack global and systematic data support, and dispatchers find it difficult to quickly and accurately grasp the overall safety situation underground. Alternatively, response and handling may be delayed. From the emergence of risks to manual confirmation and then to the issuance of instructions, the whole process relies on manual judgment and communication, which is inefficient. This lag may lead to the inability to provide timely warnings and evacuations, thus causing more serious consequences.

[0004] With the development of IoT technology, some systems based on personnel location have emerged, but most of them are single-function and lack an intelligent decision-making model that can assess comprehensive risks in real time and dynamically and automatically generate optimal scheduling instructions accordingly. Summary of the Invention

[0005] To overcome the shortcomings of existing technologies, this invention proposes a method for safe scheduling of downhole construction workers based on a monitoring model, which solves the technical problems mentioned in the background.

[0006] The technical invention adopted by this invention to solve its technical problem is: a method for safe scheduling of downhole construction workers based on a monitoring model, comprising the following steps: S1: Construct a downhole safety monitoring model, which is used to collect and process environmental monitoring data, equipment operation data and personnel status data in real time; S2: Based on the data processed by the downhole safety monitoring model, dynamically calculate the comprehensive safety index that represents the current safety status of each area downhole; S3: Compare the comprehensive safety index with multiple preset thresholds, and generate dynamic dispatch instructions based on the comparison results, the qualification certification information of the personnel to be dispatched, and their real-time location; S4: Send the dynamic scheduling command to the target personnel's mobile terminal and the central monitoring system.

[0007] Specifically, the comprehensive safety index is calculated through a risk assessment model. The input of the risk assessment model includes at least environmental risk sub-items, equipment risk sub-items, and personnel risk sub-items. The environmental risk sub-items are calculated from toxic and harmful gas concentration, temperature, and pressure data. The equipment risk sub-items are calculated from equipment fault warning signals and key operating parameters. The personnel risk sub-items are calculated from personnel heart rate, body temperature, and real-time location data.

[0008] Specifically, the risk assessment model is as follows: S = α*F(E) + β*G(P) + γ*H(H) Wherein, S is the comprehensive security index; F(E) is the value after normalization of the environmental risk sub-item; G(P) is the value after normalization of the equipment risk sub-item; H(H) is the value after normalization of the personnel risk sub-item; α, β, γ are dynamic weighting coefficients, and satisfy α+β+γ=1. The dynamic weighting coefficients are adaptively adjusted according to the operation stage and historical risk data.

[0009] Specifically, the calculation of the personnel risk sub-item H(H) requires the introduction of personnel's cumulative working hours and movement posture data to assess personnel's fatigue status and whether accidental falls have occurred.

[0010] Specifically, the step of generating dynamic scheduling instructions includes: Set a first and a second threshold for the safety factor; When the overall safety index of a certain area is lower than the first threshold, an early warning dispatch instruction is generated to restrict non-essential personnel from entering the area. When the overall safety index of a certain area is lower than the second threshold, an emergency evacuation order is generated to plan and send the optimal escape route to the people in that area.

[0011] Specifically, this also includes the task allocation steps: In response to new job assignments, personnel who meet the qualifications and whose overall safety index at their current location is higher than the job requirements are selected from all available personnel based on the safety level and skill requirements of the task. Based on the preset optimization algorithm, the best personnel are assigned from the selected personnel to perform the task.

[0012] Specifically, the preset optimization algorithm calculates the scheduling priority score for each candidate, which is determined by the skill matching degree, experience level, and path safety coefficient from their current location to the task location, and selects the candidate with the highest score.

[0013] Specifically, the steps for constructing the downhole safety monitoring model also include: The environmental monitoring data and equipment operation data are analyzed using time series forecasting algorithms to predict the trend of the comprehensive safety index over a future period. When it is predicted that the overall safety index will fall below the preset threshold, an early warning message will be generated and incorporated into the scheduling decision.

[0014] Specifically, the personnel status data is collected through smart wearable devices configured on the personnel and transmitted to the underground safety monitoring model through the underground positioning and communication network.

[0015] The beneficial effects of this invention are as follows: 1. The present invention provides a method for safe scheduling of downhole construction workers based on a monitoring model. By constructing an downhole safety monitoring model and fusing multi-source data in real time, it dynamically generates scheduling instructions and optimizes task allocation, solving the problems of data silos and response delays in traditional methods, and improving the real-time performance and scheduling efficiency of downhole safety management.

[0016] 2. The method for safe scheduling of personnel in underground construction operations based on a monitoring model, as described in this invention, achieves collaborative analysis and risk-coupled calculation of environmental, equipment, and personnel data, and can dynamically identify complex safety hazards in underground operations. By establishing a quantitative assessment system for multi-dimensional risk sub-items, it provides comprehensive data support for safety scheduling, covering the physical environment, mechanical equipment, and personnel status, thus solving the assessment blind spot problem caused by data isolation in traditional systems. Attached Figure Description

[0017] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0018] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0019] The technical invention described below with reference to the accompanying drawings is clear and complete. Obviously, the described embodiments are only a part of the embodiments of the invention, and not all of them. The components of the invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention.

[0020] like Figure 1As shown, this invention proposes a method for safe scheduling of personnel in underground construction operations based on a monitoring model, comprising the following steps: constructing an underground safety monitoring model, collecting and integrating environmental monitoring data, equipment operation data, and personnel status data in real time; dynamically calculating a comprehensive safety index representing the current safety status of various areas underground based on the processed data; comparing the comprehensive safety index with multiple preset thresholds, and generating dynamic scheduling instructions based on the comparison results, the qualification certification information of the personnel to be scheduled, and their real-time location; and sending the dynamic scheduling instructions to the target personnel's mobile terminal and the central monitoring system. It should be noted that the personnel status data is collected through smart wearable devices worn by personnel and transmitted to the underground safety monitoring model via the underground positioning and communication network. The smart wearable device refers to a wearable device that integrates multiple types of sensors, such as a smart bracelet with a built-in heart rate monitoring module, body temperature detection unit, and inertial measurement unit. This device connects to the underground positioning and communication network via the Bluetooth Low Energy protocol to capture physiological indicators and movement trajectories in real time, solving the problem of the inability to continuously collect the status data of mobile personnel. The underground positioning and communication network refers to a wireless communication system with dual functions of positioning and data transmission. It is implemented by base station networking based on UWB ultra-wideband technology. By deploying anchor point devices in the roadway to form a signal coverage area, the stability of data transmission in complex geological environments is ensured.

[0021] The smart wearable device continuously collects personnel's heart rate, body temperature, and three-dimensional acceleration data. Through built-in algorithms, it identifies abnormal physiological states and fall actions, forming structured data packets. These data packets are transmitted to the safety monitoring model via a UWB base station network using a multi-hop relay method. During transmission, forward error correction coding technology is used to compensate for signal attenuation. The underground positioning and communication network updates personnel coordinate data in real time and keeps it synchronized with environmental monitoring data in terms of timestamps, enabling the safety monitoring model to spatially correlate personnel location with regional risk values.

[0022] In some specific implementations, smart wearable devices can integrate gas detection modules to simultaneously collect local gas concentration data of the microenvironment in which personnel are located. The UWB base station network can deploy redundant relay nodes to form signal overlap coverage in the intersection area of ​​alleyways, ensuring that data transmission can still be maintained through nearby base stations when personnel enter blind spots.

[0023] The underground safety monitoring model refers to a data acquisition system integrating multiple types of sensors, implemented using distributed IoT nodes. This involves deploying gas concentration sensors and temperature and humidity sensors on the tunnel walls, installing vibration monitoring modules on equipment, and equipping personnel with smart wristbands to collect physiological data, thus achieving synchronous acquisition of environmental, equipment, and personnel data. The comprehensive safety index refers to the quantitative assessment result of multi-dimensional risk factors, implemented using a weighted fusion algorithm. This involves normalizing the gas concentration exceedance rate, equipment failure probability, and abnormal personnel heart rate values, and generating regional safety scores through dynamic weight allocation. The dynamic scheduling command refers to the execution output of the graded response strategy, implemented using a rule engine. When the index of a certain region falls below the first threshold, regional access restrictions are triggered; when it falls below the second threshold, personnel location data is automatically retrieved to generate the optimal evacuation path.

[0024] In the specific implementation process, the underground safety monitoring model gathers raw data from each monitoring point in real time through the LoRa wireless network, uses edge computing nodes for noise filtering and data alignment, and processes the methane concentration sampling value in the environmental monitoring data through moving average processing and then performs correlation analysis with the ventilation equipment rotation speed parameters to identify the risk of gas accumulation. The heart rate data uploaded by personnel smart wristbands is compared with the baseline and combined with the positioning system to determine whether there is any abnormal lingering situation. The comprehensive safety index is updated every 30 seconds, and the exponential weighted moving average method is used to eliminate instantaneous fluctuation interference. When the central monitoring system detects that the index of the mining face has dropped to the second threshold, it automatically retrieves the location of all personnel with gas detection qualifications in the area, calculates the shortest safe evacuation path in combination with the three-dimensional model of the roadway, and pushes navigation instructions with countdown prompts to the affected personnel through a dedicated communication channel.

[0025] Therefore, this invention achieves deep integration of environmental, equipment, and personnel data, solves the problem of incomplete decision-making basis caused by information silos, and replaces manual experience judgment with a dynamic safety index quantitative assessment mechanism, improving the objectivity and timeliness of risk identification. The intelligent matching of hierarchical response strategies with personnel qualifications and location information ensures that dispatch instructions are both compliant with safety standards and operable. The two-way channel design for instruction transmission not only ensures timely response from on-site personnel but also provides traceability of the handling process for the central system.

[0026] As a specific embodiment of the present invention, the comprehensive safety index is calculated by a risk assessment model. The input of the risk assessment model includes at least environmental risk sub-items, equipment risk sub-items, and personnel risk sub-items. The environmental risk sub-items are calculated from toxic and harmful gas concentration, temperature, and pressure data. The equipment risk sub-items are calculated from equipment fault warning signals and key operating parameters. The personnel risk sub-items are calculated from personnel heart rate, body temperature, and real-time location data.

[0027] It should be noted that the environmental risk sub-item refers to the quantitative assessment of the concentration, temperature, and pressure parameters of toxic and harmful gases in the underground environment. Data is collected using gas concentration sensors, temperature sensors, and pressure sensors, and the environmental risk value is obtained through weighted calculation. The equipment risk sub-item refers to the quantitative assessment of abnormal equipment operating conditions. Vibration sensors are used to monitor mechanical faults in equipment, and current transformers are used to collect motor operating parameters. The equipment risk value is generated by combining these with fault codes from the equipment control system. The personnel risk sub-item refers to the quantitative assessment of the physiological state and location safety of workers. Smart bracelets are used to collect heart rate and body temperature data, and UWB positioning tags are used to obtain real-time location coordinates. The personnel risk value is generated by combining this with a preset safe zone electronic fence.

[0028] In practice, environmental monitoring data is collected in real time through a distributed sensor network. The concentration of toxic and harmful gases is detected using electrochemical sensors, temperature data is collected using thermocouple sensors, and pressure data is measured using piezoresistive sensors. Equipment operation data is obtained through the equipment PLC controller and vibration monitoring module. Fault warning signals include overload alarms and short-circuit trip signals. Key operating parameters include motor current and pump speed. Personnel status data is collected through wearable devices. Heart rate data is monitored using photoelectric heart rate sensors, and body temperature data is obtained using infrared temperature measurement modules. Real-time location is calculated through triangulation using underground positioning base stations. After normalization, the three types of data are input into the risk assessment model and weighted and fused using dynamic weight coefficients to generate a comprehensive safety index that reflects the overall safety situation underground.

[0029] Therefore, this invention achieves collaborative analysis and risk-coupled calculation of environmental, equipment, and personnel data, enabling dynamic identification of complex safety hazards in downhole operations. By establishing a quantitative assessment system for multi-dimensional risk sub-items, it provides comprehensive data support for safety scheduling, covering the physical environment, mechanical equipment, and personnel status, thus solving the assessment blind spot problem caused by data isolation in traditional systems. The risk assessment model is as follows: S = α*F(E) + β*G(P) + γ*H(H) Wherein, S is the comprehensive security index; F(E) is the value after normalization of the environmental risk sub-item; G(P) is the value after normalization of the equipment risk sub-item; H(H) is the value after normalization of the personnel risk sub-item; α, β, γ are dynamic weighting coefficients, and satisfy α+β+γ=1. The dynamic weighting coefficients are adaptively adjusted according to the operation stage and historical risk data.

[0030] It should be noted that dynamic weighting coefficients refer to weighting parameters that are automatically adjusted based on the characteristics of the downhole operation stage and historical risk data. This is achieved by combining weighting allocation rules based on operation stage classification with statistical analysis of the frequency of risk events. For example, in the blasting operation stage, the environmental risk weight α can be set to 0.5, the equipment risk weight β to 0.3, and the personnel risk weight γ to 0.2; in the equipment maintenance stage, β can be increased to 0.6. Normalization processing refers to converting raw data of different dimensions into risk values ​​of a unified dimension, achieved using the range method or Z-score standardization method, such as mapping gas concentration data to the 0-1 range. The operation stage refers to the type of operation currently being performed downhole, identified by obtaining the operation plan from the central dispatch system. Historical risk data refers to historical risk event records stored in the database, using a time-series database to store data such as the number of equipment failures and the frequency of abnormal personnel conditions over the past 30 days.

[0031] During underground operations, when the system identifies that it is currently in the tunnel excavation stage, it automatically calls the preset initial weight coefficients α=0.4, β=0.3, and γ=0.3 for that stage. At the same time, the risk analysis module retrieves records of equipment failures exceeding the threshold in the past 7 days for that area, triggering a weight adjustment mechanism. This increases the equipment risk weight β by 0.1 and correspondingly decreases the environmental risk weight α by 0.1. The adjusted weight coefficients α=0.3, β=0.4, and γ=0.3 will be applied to the safety index calculation for the current area. This dynamic adjustment mechanism increases the weight of abnormal changes in equipment operating status on the comprehensive safety index in areas with high equipment failure rates, thus more accurately reflecting the actual risk level. This dynamic weight adjustment mechanism enables the comprehensive safety index to accurately reflect the real-time risk distribution underground, providing a reliable basis for personnel scheduling.

[0032] As a specific implementation of the present invention, the calculation of the personnel risk sub-item H(H) requires the incorporation of personnel's cumulative working time and motion posture data to assess personnel fatigue status and the likelihood of accidental falls. Cumulative working time refers to the total duration of continuous work from the moment a person enters the work area, achieved through a time recording system configured in personnel identification cards or smart bracelets, calculated by accumulating timestamp data. This data reflects the continuous state of personnel's physical exertion, providing a quantitative basis for fatigue assessment. Motion posture data refers to the personnel's body motion characteristic parameters captured by sensors, achieved using a three-axis accelerometer or inertial measurement unit, by real-time acquisition of acceleration and angular velocity data and calculation of posture change amplitude. This data can identify sudden posture abnormalities, providing a dynamic monitoring method for fall risk assessment.

[0033] In practice, during the calculation of personnel risk sub-items, the cumulative working hours data is compared with the preset fatigue threshold. When the threshold is exceeded, a fatigue status marker is triggered. Motion posture data is analyzed by analyzing acceleration waveform characteristics to detect whether there is sudden instability or free fall motion mode, thereby determining whether an accidental fall has occurred. After these two types of data are integrated with environmental risk and equipment risk indicators, a comprehensive safety index is generated, providing a more comprehensive decision-making basis for dynamic scheduling instructions.

[0034] Therefore, this invention can identify the risk of slow reaction due to excessive fatigue in advance, capture sudden fall events in a timely manner during operation, avoid secondary accidents caused by abnormal personnel conditions, and the dynamic scheduling system can adjust the distribution of personnel according to real-time updated risk data, and implement preventive evacuation or task reassignment before danger occurs.

[0035] As a specific implementation of the present invention, the step of generating dynamic dispatch instructions specifically includes: setting a first threshold and a second threshold for safety factors; when the comprehensive safety index of a certain area is lower than the first threshold, generating an early warning dispatch instruction to restrict non-essential personnel from entering the area; when the comprehensive safety index of a certain area is lower than the second threshold, generating an emergency evacuation instruction to plan and send the optimal escape route for the personnel in the area.

[0036] Specifically, when the overall safety index of the underground area continues to decline, the system automatically compares it with preset dual thresholds. If the index falls below the first threshold, an electronic fence is immediately activated to restrict entry for non-essential personnel, and a warning signal is sent to the central monitoring system. When the index further falls below the second threshold, the system calculates the shortest evacuation route to avoid the danger point based on real-time collected data on tunnel ventilation status and equipment failure locations using a path planning algorithm, and overlays this route onto the navigation interface of the personnel positioning terminal. The entire process requires no manual intervention, achieving automated, tiered response to risk management through a threshold-triggered mechanism.

[0037] It should be noted that the first and second thresholds of the safety factor refer to two critical values ​​used to classify risk levels. These values ​​are determined jointly through statistical analysis of historical accident data and expert evaluation models. These two thresholds construct a graded response mechanism, providing clear triggering conditions for risk management. The early warning dispatch instruction refers to a control instruction that includes regional access restrictions. This is implemented through the electronic fence function of the underground broadcasting system and personnel positioning terminals. In the initial stage of a risk, this instruction prevents unauthorized personnel from entering the danger zone, thus avoiding the spread of risk. The emergency evacuation instruction is a mandatory command that triggers the evacuation process. This is implemented by combining audible and visual alarm devices and mobile terminal push notifications. This instruction quickly initiates the emergency process when the risk escalates, shortening the response time. The optimal escape route refers to a safe evacuation route that comprehensively considers real-time environmental parameters and tunnel topology. It is generated using algorithms such as Dijkstra's algorithm combined with a dynamic obstacle detection module. This route adjusts its planning based on real-time changes underground to ensure the safety of the evacuation process.

[0038] As a specific embodiment of the present invention, the present invention also proposes a task allocation step: In response to a new work task, based on the required safety level and skill requirements of the task, personnel who meet the qualifications and whose current location's comprehensive safety index is higher than the task requirements are selected from all available personnel; according to a preset optimization algorithm, the optimal personnel are assigned to perform the task from the selected personnel; for example, when the downhole operation system receives a new drilling task, it first parses the task's safety level requirement as Level 2 and the skill requirement as hydraulic drilling rig operation certification. The system traverses the list of currently idle personnel, selecting a set of personnel who simultaneously hold the certification and whose area's comprehensive safety index is higher than the Level 2 threshold. Subsequently, the scheduling priority score is calculated for each candidate. For example, operator A's score is determined by factors such as a perfect skill matching score, ten years of experience bonus, and meeting the minimum safety index requirement along the path from the current area to the drilling point. Finally, operator A with the highest score is selected, and task instructions and navigation routes are sent to them via a mobile terminal.

[0039] It should be explained that the safety level refers to the minimum safety access standard of the task execution area, which is realized through a task type and area risk association mapping table to ensure that personnel qualifications match the task risk level. Skill requirements refer to the technical certification or operating authority required to complete a specific operation, which is matched using qualification tags in the personnel database to exclude unauthorized personnel from participating in high-risk operations. The comprehensive safety index is a real-time dynamically calculated area safety assessment value, output by a multi-source data fusion model, to reflect whether the safety status of the personnel's location meets the task execution conditions. The preset optimization algorithm is a multi-objective decision model, which is implemented by using a weighted scoring mechanism combined with a path safety assessment function to select the personnel with the best comprehensive efficiency under the premise of meeting safety constraints. Therefore, this invention achieves accurate matching of personnel safety qualifications, real-time location risk, and task requirements during underground task scheduling, avoiding the risk of low-safety-level personnel accidentally entering high-risk areas or insufficiently skilled personnel performing complex operations. At the same time, by using the path safety coefficient in the optimization calculation, it ensures that personnel do not cross areas with safety hazards during their movement to the task location, thus strengthening the safety of the scheduling process from a spatial dimension.

[0040] As a specific implementation of the present invention, the preset optimization algorithm calculates the scheduling priority score for each candidate. This score is jointly determined by the skill matching degree, experience level, and path safety coefficient from their current location to the task location. The candidate with the highest score is selected. The skill matching degree refers to the degree of conformity between the candidate's job qualifications and the task requirements. This is achieved using a skill tag comparison algorithm, which decomposes the task requirements into several skill items and calculates the matching degree with the certification information in the personnel file to ensure that the task executor has the necessary professional ability. The experience level refers to the quantitative value of the candidate's historical job performance, which is achieved using a scoring model based on the number of jobs, accident rate, and task complexity. The path safety coefficient refers to the dynamic evaluation value of the comprehensive safety index of each area on the movement route from the current location to the task location. This is achieved by superimposing real-time safety index data into a path planning algorithm to avoid high-risk areas that may be encountered during personnel movement.

[0041] Specifically, when the system receives a new task, it first extracts the required safety level and skill tag set based on the task attributes. Then, it iterates through all online personnel, filtering out candidates whose qualifications meet the certification requirements and whose area's safety index meets the standards. For each candidate, it calculates their skill matching score, experience level score, and the weighted average of the safety index of each segment along their movement path. The scores from these three dimensions are then combined according to a preset ratio to generate a comprehensive priority score, for example, 50% for skill matching, 30% for experience level, and 20% for path safety coefficient. Finally, the candidate with the highest total score is selected as the task executor, and the safety assessment result of that person's movement path is synchronized to the scheduling instructions. Therefore, this invention effectively solves the problems of low task allocation efficiency, mismatch between personnel capabilities and task requirements, and uncontrollable movement path risks in traditional scheduling models. Through a dynamic priority scoring mechanism, the optimal personnel can be quickly matched in complex underground environments while ensuring the safety of personnel movement, significantly improving the intelligence level and emergency response efficiency of underground operation scheduling.

[0042] As a specific embodiment of the present invention, the step of constructing the downhole safety monitoring model further includes: using a time series prediction algorithm to analyze environmental monitoring data and equipment operation data to predict the trend of the comprehensive safety index in the future; when it is predicted that the comprehensive safety index will be lower than a preset threshold, early warning information is generated in advance and incorporated into the scheduling decision.

[0043] Time series forecasting algorithms refer to techniques for building predictive models based on historical data sequences. These can be implemented using ARIMA or LSTM neural network algorithms. By analyzing the temporal correlation between environmental monitoring data and equipment operation data, they capture the periodic and trend characteristics of data changes. Preset thresholds refer to the critical conditions that trigger early warnings. These thresholds are dynamically adjusted through the safety risk assessment model. For example, different thresholds can be set according to the type of work area or the stage of work to determine whether the predicted results reach a risk level requiring proactive intervention.

[0044] The system inputs parameters such as gas concentration and temperature from environmental monitoring data and parameters such as vibration frequency and current value from equipment operation data into a time series prediction model. The model extracts time-series features through a sliding window mechanism. For example, a data window of the past 30 minutes is used to predict the trend of the comprehensive safety index for the next 5 minutes. When the prediction curve shows that the index will fall below a preset threshold within a set time span, the system automatically triggers the early warning generation module. This early warning information is transmitted to the dynamic scheduling instruction generation module, so that the scheduling decision is not only based on the current safety status, but also incorporates the results of future risk prediction. For example, when a methane concentration in a certain area is detected to be showing an exponential upward trend, even if the current comprehensive safety index is still within a safe range, the system can still prohibit non-essential personnel from entering the area in advance.

[0045] Therefore, this invention solves the problem of delayed early warning in downhole safety monitoring and enables early prediction of risk trends. When environmental or equipment parameters are detected to show a continuous deterioration trend, the system can generate dispatch instructions before the actual risk occurs, such as evacuating personnel with low safety levels or allocating emergency resources in advance. This proactive early warning mechanism transforms dispatch decisions from passive response to active defense, effectively avoiding safety accidents caused by response delays.

[0046] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for safe scheduling of personnel in downhole construction operations based on a monitoring model, characterized in that: Includes the following steps: S1: Construct a downhole safety monitoring model, which is used to collect and process environmental monitoring data, equipment operation data and personnel status data in real time; S2: Based on the data processed by the downhole safety monitoring model, dynamically calculate the comprehensive safety index that represents the current safety status of each area downhole; S3: Compare the comprehensive safety index with multiple preset thresholds, and generate dynamic dispatch instructions based on the comparison results, the qualification certification information of the personnel to be dispatched, and their real-time location; S4: Send the dynamic scheduling command to the target personnel's mobile terminal and the central monitoring system.

2. The method for safe scheduling of downhole construction workers based on a monitoring model according to claim 1, characterized in that: The comprehensive safety index is calculated through a risk assessment model. The input of the risk assessment model includes at least environmental risk sub-items, equipment risk sub-items, and personnel risk sub-items. The environmental risk sub-items are calculated from toxic and harmful gas concentration, temperature, and pressure data. The equipment risk sub-items are calculated from equipment fault warning signals and key operating parameters. The personnel risk sub-items are calculated from personnel heart rate, body temperature, and real-time location data.

3. The method for safe scheduling of downhole construction workers based on a monitoring model according to claim 2, characterized in that: The risk assessment model is as follows: S = α*F(E) + β*G(P) + γ*H(H) Wherein, S is the comprehensive security index; F(E) is the value after normalization of the environmental risk sub-item; G(P) is the value after normalization of the equipment risk sub-item; H(H) is the value after normalization of the personnel risk sub-item; Wherein, α, β, γ are dynamic weighting coefficients, and satisfy α+β+γ=1. The dynamic weighting coefficients are adaptively adjusted according to the operation stage and historical risk data.

4. The method for safe scheduling of downhole construction workers based on a monitoring model according to claim 3, characterized in that: The calculation of the personnel risk sub-item H(H) requires the introduction of personnel's cumulative working hours and movement posture data to assess personnel's fatigue status and whether accidental falls have occurred.

5. The method for safe scheduling of downhole construction workers based on a monitoring model according to claim 1, characterized in that: The steps for generating dynamic scheduling instructions specifically include: Set a first and a second threshold for the safety factor; When the overall safety index of a certain area is lower than the first threshold, an early warning dispatch instruction is generated to restrict non-essential personnel from entering the area. When the overall safety index of a certain area is lower than the second threshold, an emergency evacuation order is generated to plan and send the optimal escape route to the people in that area.

6. The method for safe scheduling of downhole construction workers based on a monitoring model according to claim 1, characterized in that: It also includes the task assignment step: In response to new job assignments, personnel who meet the qualifications and whose overall safety index at their current location is higher than the job requirements are selected from all available personnel based on the safety level and skill requirements of the task. Based on the preset optimization algorithm, the best personnel are assigned from the selected personnel to perform the task.

7. The method for safe scheduling of downhole construction workers based on a monitoring model according to claim 6, characterized in that: The preset optimization algorithm calculates the scheduling priority score for each candidate, which is determined by the skill matching degree, experience level, and path safety coefficient from their current location to the task location, and selects the candidate with the highest score.

8. The method for safe scheduling of downhole construction workers based on a monitoring model according to claim 1, characterized in that: The steps for constructing the downhole safety monitoring model also include: The environmental monitoring data and equipment operation data are analyzed using time series forecasting algorithms to predict the trend of the comprehensive safety index over a future period. When it is predicted that the overall safety index will fall below the preset threshold, an early warning message will be generated and incorporated into the scheduling decision.

9. The method for safe scheduling of downhole construction workers based on a monitoring model according to claim 1, characterized in that: The personnel status data is collected through smart wearable devices configured on the personnel and transmitted to the underground safety monitoring model through the underground positioning and communication network.

Images