A heterogeneous fusion mine pressure monitoring system of a fiber grating pressure sensor and a MEMS acceleration sensor

Abstract

The present application relates to a kind of optical fiber grating pressure sensor and the heterogeneous fusion mine pressure monitoring system of MEMS acceleration sensor, belong to mine safety monitoring technical field.The present application is aimed at solving the problem that the pressure measurement is not accurate in the vibration environment and the pressure and vibration monitoring data are isolated, which makes it difficult to accurately assess the risk.The system physically fuses the two sensors and connects to the host computer using a heterogeneous method that combines optical cable cascading and LoRa wireless communication.The host computer synchronously acquires pressure and vibration signals and calculates risk probability based on a Bayesian risk decision model.The system significantly improves the accuracy of pressure monitoring in a vibrating environment, enabling scientific and accurate risk assessment and real-time warning of mine support structure status.

Description

Technical Field

[0001] This invention belongs to the field of mine safety monitoring technology and relates to a heterogeneous fusion mine pressure monitoring system of fiber optic grating pressure sensor and MEMS acceleration sensor. Background Technology

[0002] In the field of mine safety monitoring technology, real-time monitoring of rock strata stress, roof pressure, and support deformation in coal mines is crucial for ensuring production safety. Currently, fiber optic pressure sensors are widely used to monitor changes in support column pressure and surrounding rock stress.

[0003] However, existing fiber Bragg grating pressure sensors have significant limitations in practical applications. Firstly, existing monitoring equipment fails to adequately consider the vibration of the object being measured. When the object is under strong vibration, the pressure measurements from the fiber Bragg grating pressure sensor often deviate significantly from the actual values, resulting in an inaccurate reflection of the object's true pressure parameters. Secondly, relying solely on pressure data makes it difficult to accurately determine the risk factor of the object in complex and dynamic downhole environments.

[0004] With the development of sensing technology, Micro-Electro-Mechanical Systems (MEMS) accelerometers, due to their high sampling rate and high-precision vibration monitoring capabilities, offer a potential solution to the aforementioned problems. However, in existing mine pressure monitoring systems, pressure monitoring and vibration monitoring typically operate independently, lacking effective hardware integration and data fusion mechanisms. How to deeply integrate fiber optic grating sensing technology with MEMS accelerometer sensing technology, and combine this with scientific decision-making models to achieve accurate determination of normal, warning, and hazardous states, is a pressing technical challenge in the field of mine safety monitoring. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide a heterogeneous fusion mine pressure monitoring system of fiber optic grating pressure sensor and MEMS accelerometer.

[0006] To achieve the above objectives, the present invention provides the following technical solution: A heterogeneous fusion mine pressure monitoring system combining a fiber optic pressure sensor and a MEMS accelerometer includes a pressure vibration signal acquisition host and multiple pressure vibration signal detection sensors communicatively connected to the pressure vibration signal acquisition host. Each of the pressure vibration signal detection sensors is physically fused together from a fiber optic pressure sensor and a MEMS accelerometer. The fiber optic pressure sensor is connected to the pressure vibration signal acquisition host via a serial cascade of optical cables. The MEMS accelerometer integrates a low-power self-organizing network wireless communication (Long Range Radio, LoRa) module and is connected to the pressure vibration signal acquisition host via LoRa wireless communication; The pressure vibration signal acquisition host synchronously acquires the wavelength drift data of the fiber optic pressure sensor and the triaxial vibration signal of the MEMS accelerometer in real time, and constructs a risk decision model based on Bayes' theorem to calculate the risk probability of the monitored object in order to determine the state of the monitored object.

[0007] Furthermore, the state of the monitored object includes a normal state. Warning status and dangerous situation .

[0008] Furthermore, the specific steps for the pressure vibration signal acquisition host to calculate the risk probability include: Step 1: Collect sensor data and obtain abnormal observation data of the fiber Bragg grating pressure sensor. and the abnormal observation data of the MEMS accelerometer. ; Step 2: Calculate the joint probability and preset the monitored object in different states based on historical data. The observed data and joint probability ,in ; Step 3: Calculate the posterior probability and use Bayes' theorem to calculate the state of the monitored object under given sensor observation data. posterior probability ; Step 4: State determination. Determine the state of the monitored object based on the magnitude of the posterior probability.

[0009] Furthermore, the calculation expression for Bayes' formula in step 3 is as follows:

[0010] in, The system is in a state The prior probability, For sensor data and The joint marginal probability.

[0011] Furthermore, the specific determination logic of step 4 is as follows: if If the value is at its maximum, the monitored object is determined to be in an early warning state; if... If the value is at its maximum, the monitored object is determined to be in a dangerous state.

[0012] Furthermore, step 4 also includes a normalization process and a threshold alarm step: setting a risk threshold of 90%, and when the normalized posterior probability of the dangerous state... At that time, the pressure vibration signal acquisition host will issue an alarm message.

[0013] Furthermore, the wavelength drift data resolution of the fiber Bragg grating pressure sensor is less than or equal to 0.01 nm.

[0014] Furthermore, the sampling rate of the MEMS accelerometer is greater than or equal to 1 kHz.

[0015] Furthermore, the LoRa wireless communication module adopts a self-organizing star topology, and the pressure vibration signal acquisition host acts as the central node responsible for network initialization, channel allocation, and address management.

[0016] A heterogeneous fusion decision-making method based on the system includes the following steps: S1: The pressure change wavelength signal of the monitored object is acquired by the fiber optic pressure sensor, and the pressure value is demodulated by the pressure vibration signal acquisition host. S2: Acquire real-time acceleration data of the monitored object through the MEMS accelerometer; S3: The pressure vibration signal acquisition host combines the pressure value increase trend and acceleration data, and calculates the posterior probability in real time through the risk decision model when the monitored object is in a vibration state or a relatively static state. S4: Based on the calculation result of the posterior probability and the preset threshold, output the risk level of the monitored object and execute the corresponding alarm action.

[0017] The beneficial effects of this invention are as follows: 1. Significantly improve the accuracy and reliability of monitoring data. This invention effectively overcomes the shortcomings of single pressure sensors, which exhibit significant measurement deviations under strong vibration environments, by heterogeneously fusing a fiber optic pressure sensor with a microelectromechanical system (MEMS) accelerometer. By simultaneously acquiring wavelength drift data and triaxial vibration signals, the system fully considers the impact of vibration on pressure monitoring, thereby more accurately reflecting the true parameters of stress in mine support columns and surrounding rock.

[0018] 2. Achieve scientific and accurate risk assessment and decision-making. This invention introduces a risk decision-making model based on Bayes' theorem, using anomaly pressure data and anomaly vibration data as joint observation variables. By calculating the posterior probabilities of normal, warning, and hazardous states, the system can provide a quantitative assessment of the risk status of the monitored object from a probabilistic statistical perspective. Compared to traditional single-threshold alarms, this model can more scientifically determine the risk coefficient of the monitored object, providing a reliable decision-making basis for coal mine safety systems.

[0019] 3. Possesses a complete hardware integration and communication architecture. This system achieves physical integration of pressure and vibration signal detection sensors and the data acquisition host in terms of hardware, simplifying the deployment of downhole monitoring equipment. Simultaneously, the system employs a heterogeneous communication architecture combining fiber optic serial cascading and low-power self-organizing network wireless communication LoRa technology. The LoRa module utilizes a self-organizing network star topology to achieve efficient transmission of acceleration data, ensuring the flexibility and stability of the monitoring network.

[0020] 4. Construct a closed-loop monitoring mechanism for the entire scenario. This invention not only encompasses a risk assessment mechanism when the monitored object is in a vibration state, but also incorporates decision-making logic based on increasing pressure values ​​and relatively static states, thus forming a complete closed-loop monitoring and decision-making system. This comprehensive monitoring capability enables real-time prediction and fault diagnosis of rock strata stress, roof pressure, and support deformation in coal mines, significantly improving the level of intelligence in mine safety monitoring.

[0021] Other advantages, objectives, and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination, or may be learned from practice of the invention. The objectives and other advantages of the invention can be realized and obtained through the following description. Attached Figure Description

[0022] To make the objectives, technical solutions, and advantages of the present invention clearer, the preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings, wherein: Figure 1 This is a schematic diagram of the communication architecture of a heterogeneous converged system; Figure 2 This is a schematic diagram of a decision-making model for a heterogeneous fusion system. Detailed Implementation

[0023] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0024] The accompanying drawings are for illustrative purposes only and are schematic diagrams, not actual pictures. They should not be construed as limiting the invention. To better illustrate the embodiments of the invention, some parts in the drawings may be omitted, enlarged, or reduced, and do not represent the actual product dimensions. It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0025] In the accompanying drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components. In the description of the present invention, it should be understood that if terms such as "upper," "lower," "left," "right," "front," and "rear" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, the terms used to describe positional relationships in the drawings are only for illustrative purposes and should not be construed as limiting the present invention. For those skilled in the art, the specific meaning of the above terms can be understood according to the specific circumstances.

[0026] Example 1 1. System Architecture and Hardware Connection like Figure 1 As shown, the mine pressure monitoring system in this embodiment includes a pressure vibration signal acquisition host and multiple pressure vibration signal detection sensors. Each pressure vibration signal detection sensor integrates a fiber Bragg grating pressure sensor and a MEMS accelerometer together through physical fusion.

[0027] At the physical link level, the fiber Bragg grating pressure sensor is connected to the host via a serial cascade of optical cables, and pressure data is demodulated using the unique wavelength signals reflected by different gratings. Simultaneously, the MEMS accelerometer integrates a LoRa wireless communication module. This module employs a self-organizing star topology, with the host data acquisition unit acting as the central node responsible for channel allocation and management, and the accelerometer acting as a child node uploading triaxial vibration signals in real time.

[0028] 2. Core Technical Parameters To ensure monitoring accuracy, the wavelength drift data resolution of the fiber Bragg grating pressure sensor is set to less than or equal to 0.01 nm. The sampling rate of the MEMS accelerometer is set to greater than or equal to 1 kHz to ensure complete capture of minute vibrations when the support is under pressure.

[0029] 3. Work Process Data acquisition phase: The acquisition host synchronously receives wavelength drift signals from the optical cable and acceleration data from the LoRa wireless link.

[0030] Feature extraction stage: The host adjusts the pressure value of the support column by the wavelength change, and at the same time extracts the vibration frequency and amplitude in the acceleration signal.

[0031] Risk assessment phase: The system inputs the extracted pressure anomaly observation data B and vibration anomaly observation data C into the Bayesian risk model.

[0032] Decision output stage: Calculate the posterior probability that the monitored object is in a normal state, a warning state, or a dangerous state.

[0033] Example 2 1. Decision Model Construction like Figure 2 As shown, this embodiment constructs a closed-loop decision-making mechanism that can handle different risk assessment needs of the tested object in a vibration state and a relatively static state.

[0034] 2. Specific Calculation Process When the surrounding rock undergoes deformation or sudden stress change, the specific calculation steps are as follows: Step 1: Data Collection. Stress-related anomaly data is acquired using a fiber Bragg grating pressure sensor. B Abnormal data related to vibration frequency are obtained through MEMS accelerometers. C .

[0035] Step 2: Determine the prior and joint probabilities. Assume the system is in a normal state. H 1. Warning Status H 2. Dangerous situation H Prior probability of 3 P ( H i Based on big data analysis, different preset states are used. B and C joint probability P ( B ∩ C | H i For example, the joint probability under dangerous conditions. P ( B ∩ C| H 3) = 0.8.

[0036] Step 3: Calculate the posterior probability. The posterior probability is calculated using Bayes' theorem. P ( H i | B ∩ C In the simulation calculations of this embodiment, the results are as follows: P ( H 1| B ∩ C ) = 0.043, P ( H 2| B ∩ C =0.05, P ( H 3| B ∩ C =0.9.

[0037] Step 4: Normalization and Threshold Alarm. The calculation results are normalized. The system sets the risk threshold to 90%, based on the calculated probability of the hazardous state. P ( H 3| B ∩ C If the value reaches 91%, exceeding the preset threshold, the data acquisition host will immediately issue an alarm message, indicating that the surrounding rock is in a dangerous state.

[0038] 3. Dynamic adjustment mechanism Based on the increasing trend of the pressure value of the measured object and the magnitude of the acceleration data, the system automatically switches between dynamic vibration model and relatively static model to ensure that accurate risk decision-making basis can be provided under various working conditions.

[0039] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A heterogeneous fusion mine pressure monitoring system combining a fiber optic grating pressure sensor and a MEMS accelerometer, characterized in that: It includes a pressure and vibration signal acquisition host and multiple pressure and vibration signal detection sensors that are communicatively connected to the pressure and vibration signal acquisition host; Each of the pressure vibration signal detection sensors is physically fused together from a fiber optic pressure sensor and a MEMS accelerometer. The fiber optic pressure sensor is connected to the pressure vibration signal acquisition host via a serial cascade of optical cables. The MEMS accelerometer integrates a low-power self-organizing network wireless communication LoRa module and is connected to the pressure vibration signal acquisition host via LoRa wireless communication. The pressure vibration signal acquisition host synchronously acquires the wavelength drift data of the fiber optic pressure sensor and the triaxial vibration signal of the MEMS accelerometer in real time, and constructs a risk decision model based on Bayes' theorem to calculate the risk probability of the monitored object in order to determine the state of the monitored object.

2. The heterogeneous fusion mine pressure monitoring system of fiber optic grating pressure sensor and MEMS accelerometer according to claim 1, characterized in that: The status of the monitored object includes a normal status. Warning status and dangerous situation .

3. The heterogeneous fusion mine pressure monitoring system of fiber optic grating pressure sensor and MEMS accelerometer according to claim 2, characterized in that: The specific steps for the pressure vibration signal acquisition host to calculate the risk probability include: Step 1: Collect sensor data and obtain abnormal observation data of the fiber Bragg grating pressure sensor. and the abnormal observation data of the MEMS accelerometer. ; Step 2: Calculate the joint probability and preset the monitored object in different states based on historical data. Observed data and joint probability ,in ; Step 3: Calculate the posterior probability and use Bayes' theorem to calculate the state of the monitored object under given sensor observation data. posterior probability ; Step 4: State determination. Determine the state of the monitored object based on the magnitude of the posterior probability.

4. The heterogeneous fusion mine pressure monitoring system of fiber optic grating pressure sensor and MEMS accelerometer according to claim 3, characterized in that: The Bayes formula calculation expression in step 3 is as follows: in, The system is in a state The prior probability, For sensor data and The joint marginal probability.

5. The heterogeneous fusion mine pressure monitoring system of fiber optic grating pressure sensor and MEMS accelerometer according to claim 3, characterized in that: The specific determination logic for step 4 is as follows: If If the value is at its maximum, the monitored object is determined to be in an early warning state; if... If the value is at its maximum, the monitored object is determined to be in a dangerous state.

6. The heterogeneous fusion mine pressure monitoring system of fiber optic grating pressure sensor and MEMS accelerometer according to claim 5, characterized in that: Step 4 also includes normalization and threshold alarm steps: setting the risk threshold to 90%, and when the normalized posterior probability of the dangerous state... At that time, the pressure vibration signal acquisition host will issue an alarm message.

7. The heterogeneous fusion mine pressure monitoring system of fiber optic grating pressure sensor and MEMS accelerometer according to claim 1, characterized in that: The wavelength drift data resolution of the fiber Bragg grating pressure sensor is less than or equal to 0.01 nm.

8. The heterogeneous fusion mine pressure monitoring system of fiber optic grating pressure sensor and MEMS accelerometer according to claim 1, characterized in that: The sampling rate of the MEMS accelerometer is greater than or equal to 1 kHz.

9. The heterogeneous fusion mine pressure monitoring system of fiber optic grating pressure sensor and MEMS accelerometer according to claim 1, characterized in that: The LoRa wireless communication module adopts a self-organizing star topology, and the pressure vibration signal acquisition host acts as the central node, responsible for network initialization, channel allocation, and address management.

10. A heterogeneous fusion decision-making method based on any one of the systems described in claims 1 to 9, characterized in that: Includes the following steps: S1: The pressure change wavelength signal of the monitored object is acquired by the fiber optic pressure sensor, and the pressure value is demodulated by the pressure vibration signal acquisition host. S2: Acquire real-time acceleration data of the monitored object through the MEMS accelerometer; S3: The pressure vibration signal acquisition host combines the pressure value increase trend and acceleration data, and calculates the posterior probability in real time through the risk decision model when the monitored object is in a vibration state or a relatively static state. S4: Based on the calculation result of the posterior probability and the preset threshold, output the risk level of the monitored object and execute the corresponding alarm action.

Images