Multi-parameter dynamic calibration method and system for measurement while drilling under mining mine

Abstract

The invention discloses a multi-parameter dynamic calibration method and system for measurement while drilling under a mining mine, and relates to the technical field of parameter dynamic calibration, and the method comprises the steps: dynamically selecting at least one main monitoring parameter from a measurement while drilling parameter set based on an underground multi-parameter data flow obtained in real time; continuously collecting a time sequence measurement value of the main monitoring parameter, and calculating a comprehensive confidence influence value of each tail end parameter node; generating a to-be-calibrated parameter sequence sorted according to the calibration priority, and matching the calibration operation type of each parameter; according to the to-be-calibrated parameter sequence and the calibration operation type, calibrating to-be-calibrated parameters; and when an environment sudden change is monitored, triggering a re-decision process of the main monitoring parameter. The method has the advantages that the main monitoring parameters are dynamically selected for environment error sensing, resource waste and misjudgment risks caused by all-parameter scanning are eliminated, and the timeliness and reliability of calibration of the key working conditions of drilling are ensured by mainly breaking through error source rapid positioning under environment sudden change.

Description

Technical Field

[0001] The present invention relates to the technical field of parameter dynamic calibration, and specifically to a multi-parameter dynamic calibration method and system for measurement while drilling in underground coal mines. Background Art

[0002] In the complex underground environment of measurement while drilling, multi-parameter real-time calibration faces severe challenges. Existing technologies generally adopt a global parameter synchronous monitoring and analysis strategy, resulting in huge consumption of computing resources and being difficult to meet the real-time requirements of drilling conditions. Traditional methods must continuously process all sensor data, which not only increases the computing power burden of the system but also causes misjudgment delay due to the coupling effect of environmental interference. Especially when the underground working conditions change suddenly, the response speed of full-parameter scanning calibration is much lower than the geological change rate, resulting in a lag in calibration decisions and triggering chain errors.

[0003] In recent years, some studies have tried to construct an environmental classification model to optimize calibration, but still rely on a large number of parallel computing resources to establish a multi-parameter correlation matrix. Such solutions have low efficiency in identifying error sources caused by sudden environmental changes, cannot quickly locate the core influencing parameters, and lead to inaccurate calibration operations targeting the core error sources. The mapping relationship between the environment and errors is difficult to decouple in real time, forcing the system to continuously maintain a high-load operation state, which not only restricts the deployment feasibility of underground embedded devices but also raises the overall power consumption threshold of the measurement-while-drilling system. Summary of the Invention

[0004] To solve the above technical problems, a multi-parameter dynamic calibration method for measurement while drilling in underground coal mines is provided. This technical solution solves the problem that the response speed of full-parameter scanning calibration is much lower than the geological change rate, resulting in a lag in calibration decisions and triggering chain errors.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows: A multi-parameter dynamic calibration method for measurement while drilling in underground coal mines, including: Based on the real-time acquired underground multi-parameter data stream, identify the current underground environment type, and dynamically select at least one main monitoring parameter from the measurement-while-drilling parameter set according to the preset mapping relationship between the environment type and the main monitoring parameter; Continuously collect the time-series measurement values of the main monitoring parameter, input them into a pre-constructed error propagation network model. The error propagation network model characterizes the error transfer path through the directed dependence topology and weight coefficients between parameter nodes. According to the abnormal change characteristics of the main monitoring parameter, activate the corresponding error source nodes, and calculate the confidence influence value of the activated error source nodes on the associated parameter nodes. Summarize the confidence influence values of all activated error source nodes on the associated parameter nodes, and calculate the comprehensive confidence influence value of each end parameter node; Record the parameter nodes with the comprehensive confidence influence value exceeding the dynamic threshold as the parameters to be calibrated. Based on the topological positions of all the parameters to be calibrated in the error propagation network model, generate a sequence of parameters to be calibrated sorted by calibration priority, and match the calibration operation types of each parameter; According to the sequence of parameters to be calibrated and the calibration operation types, call at least one of the hardware-level calibration method, transmission-level calibration method or model-level calibration method to perform calibration on the parameters to be calibrated; When an environmental mutation is detected, trigger the re-decision process of the main monitoring parameters.

[0006] Preferably, the identifying the current downhole environment type based on the real-time acquired downhole multi-parameter data stream, and dynamically selecting at least one main monitoring parameter from the set of measurement-while-drilling parameters according to the preset mapping relationship between the environment type and the main monitoring parameters specifically includes: Construct an environmental feature vector based on the downhole multi-parameter data stream, where the environmental feature vector includes the statistical features of the combination of geological, mechanical and fluid parameters; Output an environment type identifier through an environment classification model, where the environment classification model is a random forest classifier trained with historical drilling data; Based on the output environment type identifier, query the preset decision matrix according to the label, and select the parameter with the highest sensitivity weight as the main monitoring parameter.

[0007] Preferably, the error propagation network model includes a three-layer structure. Among them, the first-layer nodes of the three-layer structure are the selected main monitoring parameters, the middle-layer nodes of the three-layer structure are the error sources, and the end-layer nodes of the three-layer structure are the other parameters except the main monitoring parameters.

[0008] Preferably, the activating the corresponding error source nodes according to the abnormal change characteristics of the main monitoring parameters, calculating the confidence influence values of the activated error source nodes on the associated parameter nodes, summarizing the confidence influence values of all the activated error source nodes on the associated parameter nodes, and calculating the comprehensive confidence influence value of each end parameter node specifically includes: Based on the parameter data of the main monitoring parameters collected in real time, extract the real-time data characteristics of the main monitoring parameters; Perform similarity matching based on the real-time data characteristics of the main detection parameters and the typical data characteristics of the main detection parameters caused by each error source. If the similarity is greater than the threshold, activate the corresponding error source nodes in the error propagation network model, otherwise, do not activate the error source nodes; Record the end node parameters connected by the activated error source nodes as the associated parameter nodes, and calculate the confidence influence of the activated error source nodes on all their associated parameter nodes; Determine the comprehensive confidence influence value of each end node parameter based on the confidence influence of all activated error source nodes connected to the end node parameter.

[0009] Preferably, the generating a sequence of parameters to be calibrated sorted by calibration priority based on the topological positions of all parameters to be calibrated in the error propagation network model, and matching the calibration operation types of each parameter specifically includes: If the parameter to be calibrated is only affected by a single activated error source node, then divide the parameter to be calibrated into the optional calibration domain; If the parameter to be calibrated is affected by at least two activated error source nodes and the sorting of the comprehensive confidence influence value is higher than the global median, then divide it into the high-priority calibration domain; If the parameter to be calibrated is affected by at least two activated error source nodes, but the sorting of the comprehensive confidence influence value is lower than the global median, then divide it into the forced calibration domain.

[0010] Preferably, the invoking at least one of the hardware-level calibration method, the transmission-level calibration method, or the model-level calibration method according to the sequence of parameters to be calibrated and the calibration operation type, and performing calibration on the parameters to be calibrated specifically includes: For the parameter to be calibrated divided into the optional calibration domain, adopt the transmission-level calibration method, including signal noise reduction filtering and / or sampling rate adaptive improvement; For the parameter to be calibrated divided into the high-priority calibration domain, adopt the hardware-level calibration method, including sensor reference voltage reset and / or multi-channel synchronous sampling verification; For the parameter to be calibrated divided into the forced calibration domain, adopt the model-level calibration method, including residual compensation based on physical equations and / or deep learning prediction deviation correction.

[0011] Preferably, the triggering the re-decision process of the main monitoring parameter when detecting an environmental mutation specifically includes: Based on the underground environment type, determine its corresponding standard environment vector; Calculate the cosine similarity between the environment feature vector constructed based on the multi-parameter data stream underground and the standard environment vector; If the decline rate of the cosine similarity in three consecutive sampling windows exceeds the threshold, it is determined that an environmental mutation has occurred.

[0012] Furthermore, a multi-parameter dynamic calibration system for measurement while drilling in underground mines is proposed, including an environment perception and decision module, an error propagation analysis module, and a calibration control and execution module: The environment perception and decision module includes a multi-channel data acquisition interface, an environment classification processor, and a main parameter decision maker: The multi-channel data acquisition interface accesses the multi-parameter data stream of the underground measurement while drilling sensor in real time; The environmental classification processor runs a random forest classification algorithm, extracts environmental feature vectors based on multi-parameter data streams, and outputs environmental type labels; The main parameter decision maker queries a pre-stored decision matrix according to the environmental type label and outputs a main monitoring parameter selection instruction; The error propagation analysis module includes a three-layer topology network processor and a confidence calculation unit: The three-layer topology network processor internally solidifies the directed dependence topology and weight coefficients between parameter nodes, and receives the parameter data of the main monitoring parameters in real time; The confidence calculation unit activates the error source node according to the abnormal characteristics of the main monitoring parameter, and calculates its comprehensive confidence influence value on the end node; The calibration control and execution module includes a dynamic sequence generator, a multi-mode calibration controller, and a feedback detection unit: The dynamic sequence generator generates a partitioned parameter sequence to be calibrated based on the comprehensive confidence influence value and the topological position; The multi-mode calibration controller calls the hardware-level calibration method, the transmission-level calibration method, or the model-level calibration method for parameter calibration according to the partition type; The feedback detection unit monitors the similarity between the environmental feature vector and the standard environmental vector, and determines whether to trigger a main parameter decision restart signal based on the similarity within the continuous sampling window.

[0013] Optionally, the physical architecture of the three-layer topology network processor is a three-layer pipeline structure implemented by an FPGA chip, specifically including; The first-layer processing unit: receives the time-series data of the main monitoring parameter, and performs wavelet packet decomposition to extract high-frequency features; The middle-layer processing unit: performs similarity matching based on the high-frequency features and the stored error source feature library, and activates the error source nodes with a similarity exceeding the threshold; The end-layer processing unit: calculates the comprehensive confidence influence value of the activated error source nodes on the associated end parameters, and outputs it to the dynamic sequence generator.

[0014] Optionally, the multi-mode calibration controller includes three independent hardware channels; The hardware calibration channel: connects the reference voltage adjustment circuit and the multiplexer of the sensor, and performs reference voltage reset or synchronous sampling; The transmission optimization channel: embeds a programmable noise reduction filter and a bandwidth switching circuit to achieve signal noise reduction and sampling rate improvement; The model compensation channel: deploys a physical equation residual compensator and a neural network predictor, and outputs a parameter deviation correction amount.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention significantly reduces the computing power consumption caused by traditional multi-parameter global analysis by dynamically selecting the main monitoring parameter as the core node for environmental error perception. The change characteristics of the main monitoring parameter drive a fast error tracing mechanism, avoiding the real-time calculation requirements of complex correlation models, enabling the downhole embedded system to achieve fast calibration response with lower power consumption. At the same time, based on the targeted calibration strategy identified by the main parameter characteristics, only the associated parameter sub-measurement systems affected by error propagation are precisely corrected, eliminating both the resource waste and misjudgment risks caused by full-parameter scanning and quickly locating the error sources under environmental mutations through key breakthroughs, ensuring the timeliness and reliability of calibration for key drilling conditions. Description of the Drawings

[0016] Figure 1 Flow chart of the multi-parameter dynamic calibration method for measurement-while-drilling in a coal mine shaft for Embodiment 1; Figure 2 Flow chart of the method for dynamically selecting at least one main monitoring parameter from the measurement-while-drilling parameter set for Embodiment 1; Figure 3 Flow chart of the method for summarizing and calculating the comprehensive confidence influence value of each end parameter node for Embodiment 2; Figure 4 Flow chart of the method for triggering the re-decision process of the main monitoring parameter when environmental mutations are detected for Embodiment 3. Detailed Embodiments

[0017] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments in the following description are only examples, and those skilled in the art can think of other obvious variations.

[0018] Embodiment 1 Referring to Figure 1 As shown, the multi-parameter dynamic calibration method for measurement-while-drilling in a coal mine shaft includes: Based on the real-time acquired downhole multi-parameter data stream, identify the current downhole environment type, and dynamically select at least one main monitoring parameter from the measurement-while-drilling parameter set according to the preset mapping relationship between the environment type and the main monitoring parameter; By targeting and focusing on key parameters to replace full-parameter parallel monitoring, the computing power resources of the downhole embedded system are concentrated on the analysis of core sensitive parameters, breaking through the computing power bottleneck of traditional global scanning.

[0019] Continuously collect the time-series measurement values of the main monitoring parameters and input them into a pre-constructed error propagation network model. The error propagation network model characterizes the error transfer path through the directed dependence topology and weight coefficients between parameter nodes. According to the abnormal change characteristics of the main monitoring parameters, activate the corresponding error source nodes, and calculate the confidence influence value of the activated error source nodes on the associated parameter nodes. Aggregate the confidence influence values of all activated error source nodes on the associated parameter nodes, and calculate the comprehensive confidence influence value of each terminal parameter node. Among them, the error propagation network model includes a three-layer structure. Among them, the first-layer nodes are the selected main monitoring parameters, the middle nodes are the error sources, and the terminal nodes are other parameters except the main monitoring parameters; Based on single-parameter rapid error source location, avoid the complex matrix operations of traditional multi-parameter coupling analysis, improve the error tracing speed, and at the same time quantify and calibrate the urgency through the comprehensive confidence influence value to ensure the timeliness of key parameter correction; Record the parameter nodes with the comprehensive confidence influence value exceeding the dynamic threshold as the parameters to be calibrated. Based on the topological positions of all parameters to be calibrated in the error propagation network model, generate a sequence of parameters to be calibrated sorted by calibration priority, and match the calibration operation types of each parameter; Based on the principle of network centrality priority, dynamically allocate calibration resources, perform source-level calibration on high-error-risk parameters, and delay the processing of low-error-risk parameters as needed to achieve the global optimal balance of computing power and calibration accuracy.

[0020] According to the sequence of parameters to be calibrated and the calibration operation types, call at least one of the hardware-level calibration method, transmission-level calibration method, or model-level calibration method to perform calibration on the parameters to be calibrated; Through the decoupled design of the calibration method and the error type, the hardware-level calibration directly targets sensor drift, the model-level compensation suppresses the accumulation of system errors, and the transmission-level optimization blocks signal interference, forming a multi-dimensional defense chain to reduce the comprehensive calibration error rate in a complex environment.

[0021] When an environmental mutation is detected, trigger the re-decision process of the main monitoring parameters.

[0022] Establish an environment-parameter dynamic binding mechanism. When the lithology mutates or the drilling tool is abnormal, immediately switch the main monitoring parameters to avoid error mis-tracing caused by environmental mismatch and ensure the real-time reliability of the full drilling process calibration strategy.

[0023] Refer to Figure 2 As shown, in this embodiment: Based on the real-time acquired downhole multi-parameter data stream, identify the current downhole environment type, and according to the preset mapping relationship between the environment type and the main monitoring parameters, dynamically select at least one main monitoring parameter from the set of measurement-while-drilling parameters, which specifically includes: Constructing environmental feature vectors based on downhole multi-parameter data streams. The environmental feature vectors include statistical characteristics of geological, mechanical, and fluid parameter combinations. Outputting the environmental type identifier through the environmental classification model, which is a random forest classifier trained with historical drilling data; Based on the output environment type identification, the preset decision matrix is queried according to the label, and the parameter with the highest sensitivity weight is selected as the main monitoring parameter.

[0024] The preset decision matrix is pre-set based on the typical error sources under different environmental types and the sensitivity of various parameters to the typical error sources. By setting the parameters that are highly sensitive to the typical error sources under the environmental type as the main monitoring parameters, the error source information in the downhole environment can be obtained by analyzing the parameter change characteristics of the main detection parameters, and then targeted parameter calibration can be carried out in combination with the error source information.

[0025] By integrating multi-dimensional environmental features with a collaborative mechanism based on a preset decision matrix, an intelligent correlation mapping between environmental types and error sources is achieved, providing an accurate basis for the dynamic selection of primary monitoring parameters: a highly discriminative environmental signature is formed based on the composite statistical characteristics of geological, mechanical, and fluid parameters, enabling the random forest classifier to accurately identify complex downhole working conditions; at the same time, the preset decision matrix anchors the characteristics of typical error sources and parameter sensitivity weights in different environments, ensuring that the selected primary monitoring parameters have the optimal characterization capability for the current core error source. This design allows the system to reversely infer the dominant downhole error source by simply analyzing the changing characteristics of a single primary parameter, significantly reducing the computational complexity of the error tracing process and significantly saving computing power resources on the embedded platform. It also directly triggers targeted parameter calibration based on error source information, effectively eliminating redundant operations caused by traditional global analysis.

[0026] Example 2 Reference Figure 3 As shown, based on the first embodiment, this embodiment further points out that the corresponding error source node is activated according to the abnormal change characteristics of the main monitoring parameters, and the confidence influence value of the activated error source node on the associated parameter node is calculated, the confidence influence values of all activated error source nodes on the associated parameter nodes are summarized, and the comprehensive confidence influence value of each terminal parameter node is calculated. Specifically, the following steps are included: Based on the parameter data of the main monitoring parameters collected in real time, extract the real-time data features of the main monitoring parameters; Based on the similarity matching between the real-time data features of the main detection parameters and the typical data features of the main detection parameters caused by each error source, if the similarity is greater than the threshold, the corresponding error source node is activated in the error propagation network model; otherwise, the error source node is not activated; Denote the end-node parameters connected to the activated error source node as associated parameter nodes, and calculate the confidence influence of the activated error source node on all its associated parameter nodes; Determine the comprehensive confidence influence value of each end-node parameter based on the confidence influence of all activated error source nodes connected to the end-node parameter.

[0027] Specifically, the calculation method for the confidence influence of the activated error source node on all its associated parameter nodes is as follows: where, is the comprehensive confidence influence of the i-th activated error source node on its j-th associated parameter node, is the similarity between the typical data characteristics of the main detection parameter caused by the i-th activated error source node and the real-time data characteristics of the main detection parameter, is the correlation coefficient of the i-th activated error source node with its j-th associated parameter node. In some embodiments, the correlation coefficient is represented by the associated parameter error rate caused by the error; Specifically, the calculation formula for the comprehensive confidence influence value of each end-node parameter is: where, is the comprehensive confidence influence value of the j-th end-node parameter, is the set composed of all activated error source nodes connected to the j-th end-node parameter, is the element therein, [[ID=***]]is the confidence influence of e on the j-th associated parameter node.

[0028] Specifically, illustrate the calculation process of the comprehensive confidence influence value in this embodiment by way of example; If similarity matching is performed based on the real-time data characteristics of the main detection parameter and the typical data characteristics of the main detection parameter caused by each error source, and it is obtained that the activated error source nodes are A and B, and the similarity of A is 0.85 and the similarity of B is 0.75, the error rate of parameter t caused by error source A is 0.3, and the error rate of parameter t caused by error source B is 0.5, then it can be obtained that error source A will cause parameter t to have an unbelievability of 0.85×0.3 = 0.255, and error source B will cause parameter t to have an unbelievability of 0.75×0.5 = 0.375. Without considering the coupling relationship between error source A and error source B, then under the combined action of error source A and error source B, the comprehensive confidence influence value of parameter t is 1 - (1 - 0.255)×(1 - 0.375) = 0.53. That is, under the dual action of the activated error source A and error source B, the credibility of parameter t is 1 - 0.53 = 0.47.

[0029] In this embodiment, a dynamic matching mechanism between the characteristics of the main monitoring parameters and the influence of error sources is established. By comparing similarities, the associated error nodes are accurately activated, and based on the probability synthesis model, the comprehensive influence of multi-source errors on the terminal parameters is objectively quantified. This design realizes the intelligent deconstruction of the error propagation chain in a complex underground environment, transforming the traditional multi-parameter coupling analysis relying on manual experience into a data-driven mathematical calculation process. With the probability synthesis mechanism of the confidence influence value, the system can deeply restore the non-linear effects of the superposition and interaction of multiple errors, significantly improving the accuracy of parameter credibility evaluation and providing a scientific basis for targeted calibration strategies. At the same time, only the error sources with high similarity associations are activated for calculation, effectively avoiding the waste of computing power caused by traversing all network nodes, and concentrating the limited computing resources on the real-time tracking of key propagation paths, strengthening the decision-making timeliness and resource utilization efficiency of the embedded platform from the source.

[0030] Specifically, in this embodiment, based on the topological positions of all parameters to be calibrated in the error propagation network model, a sequence of parameters to be calibrated is generated in the order of calibration priorities, and the specific calibration operation types for each parameter are matched, including: If the terminal parameter node is only affected by a single activated error source node, then this terminal parameter node is classified into the optional calibration domain; If the terminal parameter node is affected by at least two activated error source nodes and the comprehensive confidence influence value ranking is higher than the global median, it is classified into the high-priority calibration domain; If the terminal parameter node is affected by at least two activated error source nodes, but the comprehensive confidence influence value ranking is lower than the global median, it is classified into the forced calibration domain.

[0031] Specifically, this embodiment also proposes that for the parameters in the optional calibration domain, a transmission-level calibration method is adopted, including signal noise reduction filtering and / or adaptive improvement of the sampling rate; For the parameters in the high-priority calibration domain, a hardware-level calibration method is adopted, including resetting the sensor reference voltage and / or multi-channel synchronous sampling verification; For the parameters in the forced calibration domain, a model-level calibration method is adopted, including residual compensation based on physical equations and / or correction of deep learning prediction deviations.

[0032] In this embodiment, a three-layer calibration domain dynamic partitioning mechanism based on confidence influence and topological coupling strength is constructed, and the calibration urgency of the end parameter nodes is intelligently determined through the complexity of the error sources and the comprehensive confidence level. The parameters affected by a single error source are classified into the optional calibration domain, enabling the system to delay the processing of non-urgent interferences; the parameters with multi-source coupling and prominent confidence risks are assigned to the high-priority calibration domain to ensure that critical parameters are corrected in a timely manner; while the parameters affected by multi-sources but with a gentle confidence decay are allocated to the forced calibration domain to prevent the spread of potential errors. Cooperating with the hierarchical calibration strategies at the transmission level, hardware level, and model level to accurately match the characteristics of each partition significantly improves the intelligent level of system resource allocation. This design not only avoids the problem of wasted resources caused by traditional uniform calibration but also realizes the optimal allocation of limited downhole computing power through the gradient mapping of the error propagation depth and calibration intensity, making it possible to perform targeted maintenance with millisecond-level response and building a dynamic protection barrier for drilling safety under complex working conditions.

[0033] Embodiment 3 Referring to Figure 4 As shown, based on Embodiment 1, this embodiment further points out that when an environmental mutation is detected, the specific process of triggering the re-decision process of the main monitoring parameters includes: Based on the downhole environment type, determine its corresponding standard environmental vector; Calculate the cosine similarity between the environmental feature vector constructed based on the downhole multi-parameter data stream and the standard environmental vector; If the similarity decline rate in three consecutive sampling windows exceeds the threshold, it is determined that an environmental mutation has occurred.

[0034] This embodiment constructs a dynamic tracking and trend analysis mechanism for environmental feature vectors, and intelligently perceives the qualitative change of downhole working conditions through the attenuation trend of the similarity between the environmental feature vector and the standard vector within consecutive periods. This design breaks through the threshold-triggering limitation of traditional environmental mutations. At key working condition turning points such as lithology conversion and drill tool anomalies, the environmental reconstruction nodes are determined based on the feature variation rate, realizing near-zero delay reconfiguration of the main monitoring parameters. The immediate refresh of the environmental mapping relationship effectively blocks the distortion of error tracing caused by parameter-environment mismatch, establishing an environment-adaptive elastic decision chain for the downhole measurement-while-drilling system, ensuring that the calibration strategy always remains precisely synchronized with the actual working conditions during the dynamic drilling process, and essentially improving the safety redundancy and measurement reliability of drilling in complex formations.

[0035] Embodiment 4 Based on the same inventive concept as Embodiments 1 to 3, this embodiment proposes a multi-parameter dynamic calibration system for mine downhole measurement-while-drilling, including an environmental perception and decision module, an error propagation analysis module, and a calibration control and execution module: The environmental perception and decision module includes a multi-channel data acquisition interface, an environmental classification processor, and a main parameter decision maker: The multi-channel data acquisition interface accesses the multi-parameter data streams of downhole sensors while drilling in real time; The environmental classification processor runs the random forest classification algorithm, extracts environmental feature vectors based on the multi-parameter data streams, and outputs environmental type labels; The main parameter decision maker queries the pre-stored decision matrix according to the environmental type label and outputs the main monitoring parameter selection instruction; The error propagation analysis module includes a three-layer topology network processor and a confidence calculation unit: The three-layer topology network processor internally solidifies the directed dependence topology and weight coefficients between parameter nodes, and receives the parameter data of the main monitoring parameters in real time; The confidence calculation unit activates the error source nodes according to the real-time data characteristics of the main monitoring parameters, and calculates the comprehensive confidence influence value of the activated error source nodes on the end nodes; The calibration control and execution module includes a dynamic sequence generator, a multi-mode calibration controller, and a feedback detection unit: The dynamic sequence generator generates a partitioned parameter sequence to be calibrated based on the comprehensive confidence influence value and the topological position; The multi-mode calibration controller calls the hardware-level calibration method, the transmission-level calibration method, or the model-level calibration method according to the partition type to perform parameter calibration; The feedback detection unit monitors the similarity between the environmental feature vector and the standard environmental vector, and determines whether to trigger the main parameter decision restart signal based on the similarity within the continuous sampling window.

[0036] Optionally, the physical architecture of the three-layer topology network processor is a three-layer pipeline structure implemented by an FPGA chip; The first-layer processing unit: receives the timing data of the main monitoring parameters, and performs wavelet packet decomposition to extract high-frequency features; The middle-layer processing unit: performs similarity matching based on the high-frequency features and the stored error source feature library, and activates the error source nodes whose similarity exceeds the threshold; The end-layer processing unit: calculates the comprehensive confidence influence value of the activated error source nodes on the associated end parameters, and outputs it to the dynamic sequence generator.

[0037] Optionally, the multi-mode calibration controller includes three independent hardware channels; The hardware calibration channel: connects the reference voltage regulation circuit and the multiplexer of the sensor, and performs reference voltage reset or synchronous sampling; The transmission optimization channel: embeds a programmable noise reduction filter and a bandwidth switching circuit to achieve signal noise reduction and sampling rate improvement; The model compensation channel: deploys a physical equation residual compensator and a neural network predictor to output the parameter deviation correction amount.

[0038] In summary, the advantages of the present invention are as follows: By dynamically selecting the main monitoring parameter as the core node for environmental error perception, the computing power consumption caused by traditional multi-parameter global analysis is significantly reduced. The change characteristics of the main monitoring parameter drive a fast error tracing mechanism, avoiding the real-time calculation requirements of complex correlation models, enabling the downhole embedded system to achieve millisecond-level calibration response with lower power consumption. At the same time, based on the targeted calibration strategy identified by the main parameter characteristics, precise correction is only performed on the associated parameter subsystem affected by error propagation, eliminating both the resource waste and misjudgment risk caused by full-parameter scanning, and quickly locating the error source under environmental mutations through key breakthroughs, ensuring the timeliness and reliability of calibration for critical drilling conditions.

[0039] The above shows and describes 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 by the above embodiments. What is described in the above embodiments and the specification is only the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection required by the present invention is defined by the appended claims and their equivalents.

Claims

1. A multi-parameter dynamic calibration method for measurement while drilling in coal mines, characterized in that, Including: Based on the real-time obtained downhole multi-parameter data stream, identify the current downhole environment type, and according to the preset mapping relationship between the environment type and the main monitoring parameters, dynamically select at least one main monitoring parameter from the set of measurement parameters while drilling; Continuously collect the time-series measurement values of the main monitoring parameters and input them into a pre-constructed error propagation network model. The error propagation network model characterizes the error transmission path through the directed dependence topology and weight coefficients between parameter nodes. Activate the corresponding error source nodes according to the abnormal change characteristics of the main monitoring parameters, and calculate the confidence influence value of the activated error source nodes on the associated parameter nodes. Summarize the confidence influence values of all activated error source nodes on the associated parameter nodes, and calculate the comprehensive confidence influence value of each terminal parameter node; Mark the parameter nodes with the comprehensive confidence influence value exceeding the dynamic threshold as the parameters to be calibrated. Based on the topological positions of all the parameters to be calibrated in the error propagation network model, generate a sequence of parameters to be calibrated sorted by calibration priority, and match the calibration operation types of each parameter; According to the sequence of parameters to be calibrated and the calibration operation types, call at least one of the hardware-level calibration method, transmission-level calibration method or model-level calibration method to perform calibration on the parameters to be calibrated; When an environmental mutation is detected, trigger the re-decision process of the main monitoring parameters.

2. The multi-parameter dynamic calibration method for measurement while drilling in coal mine underground according to claim 1, wherein, The step of based on the real-time obtained downhole multi-parameter data stream, identifying the current downhole environment type, and according to the preset mapping relationship between the environment type and the main monitoring parameters, dynamically selecting at least one main monitoring parameter from the set of measurement parameters while drilling specifically includes: Construct an environmental feature vector based on the downhole multi-parameter data stream, and the environmental feature vector includes the statistical features of the combination of geological, mechanical and fluid parameters; Output the environmental type identifier through an environmental classification model, and the environmental classification model is a random forest classifier trained with historical drilling data; Based on the output environmental type identifier, query the preset decision matrix according to the label, and select the parameter with the highest sensitivity weight as the main monitoring parameter.

3. The multi-parameter dynamic calibration method for measurement while drilling in coal mine underground according to claim 2, wherein The error propagation network model includes a three-layer structure. Among them, the first-layer nodes of the three-layer structure are the selected main monitoring parameters, the middle nodes of the three-layer structure are the error sources, and the terminal nodes of the three-layer structure are the other parameters except the main monitoring parameters.

4. The multi-parameter dynamic calibration method for measurement while drilling in coal mine underground according to claim 3, characterized in that, The step of activating the corresponding error source nodes according to the abnormal change characteristics of the main monitoring parameters, calculating the confidence influence value of the activated error source nodes on the associated parameter nodes, summarizing the confidence influence values of all activated error source nodes on the associated parameter nodes, and calculating the comprehensive confidence influence value of each terminal parameter node specifically includes: Based on the parameter data of the main monitoring parameters collected in real time, extract the real-time data characteristics of the main monitoring parameters; Perform similarity matching between the real-time data characteristics of the main detection parameters and the typical data characteristics of the main detection parameters caused by each error source. If the similarity is greater than the threshold, activate the corresponding error source nodes in the error propagation network model, otherwise, do not activate the error source nodes; Record the terminal node parameters connected to the activated error source nodes as the associated parameter nodes, and calculate the confidence influence of the activated error source nodes on all their associated parameter nodes; Determine the comprehensive confidence influence value of each end - node parameter based on the confidence influence of all activated error - source nodes connected to the end - node parameter.

5. The multi-parameter dynamic calibration method for measurement while drilling in coal mine underground according to claim 4, characterized in that, The generating a sequence of parameters to be calibrated sorted by calibration priority based on the topological positions of all parameters to be calibrated in the error - propagation network model, and matching the calibration operation types of each parameter specifically includes: If the parameter to be calibrated is only affected by a single activated error - source node, then classify the parameter to be calibrated into the optional calibration domain; If the parameter to be calibrated is affected by at least two activated error - source nodes and the comprehensive confidence influence value is ranked higher than the global median, then classify the parameter to be calibrated into the high - priority calibration domain; If the parameter to be calibrated is affected by at least two activated error - source nodes, but the comprehensive confidence influence value is ranked lower than the global median, then classify the parameter to be calibrated into the forced calibration domain.

6. The multi-parameter dynamic calibration method for measurement while drilling in coal mine underground according to claim 5, wherein The performing calibration on the parameter to be calibrated by invoking at least one of the hardware - level calibration method, transmission - level calibration method, or model - level calibration method according to the sequence of parameters to be calibrated and the calibration operation type specifically includes: For the parameter to be calibrated classified into the optional calibration domain, adopt the transmission - level calibration method, including signal noise reduction filtering and / or adaptive improvement of the sampling rate; For the parameter to be calibrated classified into the high - priority calibration domain, adopt the hardware - level calibration method, including resetting the sensor reference voltage and / or verifying multi - channel synchronous sampling; For the parameter to be calibrated classified into the forced calibration domain, adopt the model - level calibration method, including residual compensation based on physical equations and / or correction of deep - learning prediction deviation.

7. The multi-parameter dynamic calibration method for measurement while drilling in coal mine underground according to claim 6, characterized in that, The triggering the re - decision process of the main monitoring parameter when detecting an environmental mutation specifically includes: Determine the corresponding standard environmental vector based on the underground environmental type; Calculate the cosine similarity between the environmental feature vector constructed based on the underground multi - parameter data stream and the standard environmental vector; If the decline rate of the cosine similarity in three consecutive sampling windows exceeds the threshold, it is determined that an environmental mutation has occurred.

8. A multi-parameter dynamic calibration system for measurement while drilling in coal mines, characterized in that, A multi - parameter dynamic calibration method for realizing the measurement - while - drilling in coal mines as described in any one of claims 1 - 7, including an environmental perception and decision - making module, an error - propagation analysis module, and a calibration control and execution module, wherein: The environmental perception and decision - making module includes a multi - channel data acquisition interface, an environmental classification processor, and a main - parameter decision - maker: The multi - channel data acquisition interface real - time accesses the multi - parameter data stream of the downhole measurement - while - drilling sensors; The environmental classification processor runs a random - forest classification algorithm, extracts the environmental feature vector based on the multi - parameter data stream, and outputs the environmental type label; The main - parameter decision - maker queries the pre - stored decision matrix according to the environmental type label and outputs the main monitoring parameter selection instruction; The error - propagation analysis module includes a three - layer topological network processor and a confidence - calculation unit: The three - layer topological network processor internally solidifies the directed dependence topology and weight coefficients between parameter nodes and real - time receives the parameter data of the main monitoring parameter; The confidence - calculation unit activates the error - source nodes according to the real - time data characteristics of the main monitoring parameter and calculates the comprehensive confidence influence value of the activated error - source nodes on the end - nodes; The calibration control and execution module includes a dynamic sequence generator, a multi - mode calibration controller, and a feedback detection unit: The dynamic sequence generator generates a partitioned parameter sequence to be calibrated based on the comprehensive confidence influence value and the topological position; The multi-mode calibration controller calls the hardware-level calibration method, the transmission-level calibration method, or the model-level calibration method according to the partition type of the parameter sequence to be calibrated for parameter calibration; The feedback detection unit monitors the similarity between the environmental feature vector and the standard environmental vector, and determines whether to trigger the main parameter decision restart signal based on the similarity within the continuous sampling window.

9. The multi-parameter dynamic calibration system for measurement while drilling in coal mine underground according to claim 8, characterized in that, The physical architecture of the three-layer topology network processor is a three-layer pipeline structure implemented by an FPGA chip, specifically including: The first-layer processing unit: receives the timing data of the main monitoring parameters and performs wavelet packet decomposition to extract high-frequency features; The middle-layer processing unit: performs similarity matching based on the high-frequency features and the stored error source feature library, and activates the error source nodes whose similarity exceeds the threshold; The end-layer processing unit: calculates the comprehensive confidence influence value of the activated error source nodes on the associated end parameters and outputs it to the dynamic sequence generator.

10. The multi-parameter dynamic calibration system for measurement while drilling in a coal mine shaft according to claim 8, wherein, The multi-mode calibration controller includes three independent hardware channels, specifically: The hardware calibration channel: The hardware calibration channel is connected to the reference voltage adjustment circuit and the multiplexer of the sensor, and performs reference voltage reset or multi-channel synchronous sampling verification; The transmission optimization channel: The transmission optimization channel is embedded with a programmable noise reduction filter and a bandwidth switching circuit to achieve signal noise reduction filtering and adaptive increase of the sampling rate; The model compensation channel: The model compensation channel deploys a physical equation residual compensator and a neural network predictor to output the deviation correction amount of the parameter to be calibrated.

Images