Mining optical cable state monitoring system

Abstract

The invention provides a mining optical cable state monitoring system. The mining optical cable state monitoring system comprises a self-organizing sensing module, an optical cable health assessment module, a fault identification module, an automatic repair module and a block chain storage module. The problems of blind areas, information lag and low repairing efficiency in a traditional optical cable monitoring and repairing system can be solved, and full-coverage, efficient, real-time and automatic optical cable monitoring and repairing are achieved. The innovations not only improve the safety and stability of the mine optical cable, but also significantly reduce the manual maintenance cost and the system fault repair time, and provide a brand new and intelligent management scheme for mine communication infrastructures.

Description

Technical Field

[0001] The invention belongs to the underground field, and in particular relates to a mining optical cable status monitoring system. Background Art

[0002] As a vital communication and data transmission facility in mines, mining optical cables are responsible for providing real-time information flow and communication connections for various equipment and operations in mines. Especially in underground mines, optical cables are not only used as a transmission medium for real-time monitoring and data acquisition, but also play an important role in remote monitoring, environmental monitoring and dispatching command. However, the particularity of the mine environment has led to many potential risks and problems for mining optical cables. Factors such as temperature, humidity, airflow changes, geological activities, and chemical corrosion in mines often cause optical cables to be exposed to extremely complex and unstable conditions, which pose a serious threat to the operating life, stability, and safety of optical cables. Traditional optical cable status monitoring and fault detection methods mostly rely on manual inspections, regular maintenance, or local sensor detection. These methods have problems with monitoring blind spots and time lags.

[0003] Traditional mine optical cable monitoring technology usually monitors the operating status of optical cables by installing single-point sensors. However, these sensors can only cover a limited range in the vast and complex environment of mines, and cannot achieve real-time monitoring of the entire optical cable. The failure or failure of a single sensor will cause information loss and monitoring blind spots in the system. In addition, traditional manual inspection methods often face a series of problems such as low efficiency, long response time, and personnel safety in the dangerous environment of mines, and cannot detect minor damage in real time, resulting in many potential optical cable faults not being discovered in the early stages. On the other hand, even if monitoring is performed through traditional sensors, existing fault diagnosis technologies often have major limitations. For example, the early state of optical cable damage is difficult to detect in time, and in many cases, the location of the fault cannot be accurately located, resulting in maintenance work having to rely on cumbersome positioning processes, increasing mine maintenance costs and downtime.

[0004] In order to overcome these technical defects, researchers have explored the possibility of combining a variety of new technologies into the field of mine optical cable monitoring in recent years, such as distributed sensor networks, wireless sensor nodes, and Internet of Things technologies. Although these technologies have improved the real-time and breadth of monitoring to a certain extent, they still have problems with poor connectivity between systems, information processing lags, and data authenticity and security. For example, although remote monitoring achieved through the Internet of Things has made breakthroughs in data transmission, due to the complex communication environment in mines, especially in deep wells or complex rock formations, signal coverage is incomplete or network instability still often occurs. In addition, most of the current mine monitoring systems focus on information collection and transmission, and have not fundamentally solved the problem of repairing damaged mine optical cables, and the autonomous repair capability of existing technologies is almost zero, which also leads to the fact that once the optical cable of mine equipment is damaged, it usually takes a long time for manual intervention or scheduling, which affects the production efficiency of the mine.

[0005] Although these existing technologies have promoted the progress of mine monitoring systems to a certain extent, they have not completely solved the core problem of health monitoring and self-repair of mine optical cables, that is, how to achieve full coverage, high efficiency, and low latency real-time health monitoring of optical cables, and automatically repair them when damage occurs. Therefore, there is an urgent need for a new type of mine optical cable status monitoring and repair system, which should not only be able to monitor the health status of mine optical cables in real time and accurately, and provide comprehensive fault diagnosis, but also have automatic repair functions to reduce the need for manual intervention, improve the efficiency and accuracy of optical cable repair, and ensure the long-term stable operation of optical cables. Summary of the invention

[0006] The purpose of the present invention is to provide a mining optical cable status monitoring system, which fundamentally solves the problems of blind spots, information lag and failure to be repaired in time in mining optical cable status monitoring.

[0007] In order to solve the above technical problems, an embodiment of the present invention provides a mining optical cable status monitoring system, the system comprising: a self-organizing perception module, an optical cable health assessment module, a fault identification module, an automatic repair module and a blockchain storage module;

[0008] The self-organizing sensing module is used to obtain sensor node data of the optical cable in the mine, and a regional gridded self-organizing sensing network constructed based on the sensor nodes, and pre-process the sensor node data, and fuse the pre-processed data based on a preset neural network model to obtain an optical cable health assessment value; wherein the sensor node data includes temperature, humidity, vibration and strain data;

[0009] The optical cable health assessment module is used to calculate and adjust the upload frequency of its node according to the health assessment value, and to perform adaptive bandwidth allocation according to the upload frequency of its node and the total upload frequency of all nodes to obtain the bandwidth allocation of the node. At the same time, by performing a difference analysis between the current health assessment value of the node and its historical health assessment value, the faulty node is identified while avoiding false alarms. Once a node is marked as abnormal, the upload frequency of the node is automatically increased based on the abnormal identification result, and the bandwidth is reallocated;

[0010] The fault identification module is used to perform difference analysis and change rate analysis between the current health assessment value of the node and its historical health assessment value, determine the fault location, obtain a regional fault probability map, and determine the priority of the repair task based on the regional fault probability map;

[0011] The automatic repair module is used to enable the micro-robot to automatically repair the faulty node according to the regional fault probability map and the priority of the repair task, generate repair status data, and generate feedback data in combination with the micro-robot's own sensors;

[0012] The blockchain storage module is used to input the repair status data and feedback data into the blockchain as a smart contract, and automatically manage the repair tasks and reward mechanism through the smart contract.

[0013] As a preferred embodiment, the regional grid-based self-organizing sensing network forms a distributed topology through a dynamic self-organizing protocol, wherein each node in the network transmits data through a low-power communication protocol, combined with an adaptive communication frequency control mechanism, and can automatically adjust the transmission frequency under different environmental conditions. At the same time, each node is responsible for collecting environmental data of its area, and exchanges data with adjacent nodes through a self-organizing mechanism to adjust the network topology in real time.

[0014] As a preferred embodiment, the preprocessing includes: removing random noise in the data by using a sliding average filter or a Gaussian filter method; identifying and removing abnormal values ​​in the sensor data by a threshold method or a standard deviation method; applying a Kalman filter to smooth the time series data; performing local data fusion on the data at each node to obtain preprocessed data;

[0015] The preset neural network model structure is:

[0016] Input layer: pre-processed data from each sensor;

[0017] Hidden layer: Use nonlinear activation functions to process the complex relationships between different sensor data and learn the contribution weight of each data to health assessment;

[0018] Output layer: Outputs the health assessment value of the optical cable, which is used to indicate the health status of the optical cable;

[0019] And through L2 regularization, the growth of the weight of the neural network model is limited, thereby improving the generalization ability of the neural network model.

[0020] As a preferred embodiment, the calculation and adjustment of the upload frequency of the node according to the health assessment value, and the adaptive bandwidth allocation according to the upload frequency of the node and the total upload frequency of all nodes to obtain the bandwidth allocation of the node include:

[0021] According to the health assessment value of the optical cable, the upload frequency is calculated using the Sigmoid function;

[0022] According to the upload frequency, combined with the total upload frequency of all nodes in the current network, the bandwidth allocation corresponding to the current node is obtained;

[0023] The identifying of the faulty node comprises:

[0024] Based on the difference analysis results of the node's current health assessment value and its historical health assessment value, combined with the change rate, through trend analysis, the rate of change of the node's health assessment value is calculated. If the rate of change of the node's health assessment value is greater than a preset threshold, the node is considered to have an abnormality and enters a warning state.

[0025] As a preferred embodiment, the avoiding false alarms comprises:

[0026] In the difference analysis, a regularized anomaly detection method is introduced. , combined with the normal healthy fluctuation range of each node to control the abnormal fluctuation of the node; wherein the regular term , expressed as:

[0027]

[0028] in, For Node The standard deviation of health assessment fluctuations indicates the normal fluctuation range of the node; The rate at which the node health assessment value changes; is the total number of nodes.

[0029] As a preferred embodiment, the fault identification module executes the steps including:

[0030] Obtain the difference analysis result and the change rate, build a fault location model, and obtain the position weight of the node; wherein the position weight of the node in the fault location model is related to the abnormality degree of the node and its position;

[0031] Integrate the location weights of all nodes to obtain the regional failure probability map , represents the probability of failure in each area of ​​the mine; the regional failure probability map The calculation is obtained by superposition of node weights:

[0032]

[0033] in, is an indicator function, indicating that the node Coordinates In the current area Inside; is the number of all sensor nodes in the mine.

[0034] As a preferred embodiment, after the fault area is determined, the repair task is automatically triggered, and the priority of the repair task is automatically determined according to the location of the fault area. , and its calculation formula is:

[0035]

[0036] in, is the scheduling sensitivity coefficient, which controls the relationship between the regional failure probability and the task location in task scheduling; Indicates the distance between the execution location of the repair task and the fault area;

[0037] If you fix the priority of the task If the set task trigger threshold is exceeded, the repair task will be automatically scheduled and relevant personnel will be notified.

[0038] As a preferred embodiment, the micro-robot is enabled to automatically repair the faulty node according to the regional fault probability map and the priority of the repair task, and the repair status data generated includes:

[0039] Taking the failure probability of the regional failure probability map and the minimization of the distance from the current position of the micro-robot to the failure node as the optimization goal, the corresponding optimization objective function is established;

[0040] Collect the sensor data of the micro robot, and determine the exact location of the damage and the severity of the damaged area by fusing the sensor data of the robot; the severity of the damaged area is based on the regional failure probability map and confirmed by the indicator function;

[0041] When the micro robot completes the repair task, it detects the repair effect through the built-in sensor and feeds back the repaired health status to the mine management system; the repaired health status is determined based on the health status before repair and the rate of change of the severity of the damaged area.

[0042] As a preferred embodiment, each block of the blockchain includes: stored task data, a hash value pointing to the previous block, and a timestamp of task execution;

[0043] Every time a repair task is completed, a new block will be added to the blockchain, containing the complete data of the task;

[0044] Among them, the smart contract will define the rules in the following ways:

[0045] When the severity of a new damage area exceeds a preset threshold, a smart contract is automatically generated and activated to create a new repair task;

[0046] The execution of the repair task is triggered by the robot. After the task is completed, a new repaired health status will be generated and the result will be submitted to the smart contract, triggering a repair completion event;

[0047] The smart contract automatically verifies the execution of the repair task. If the new repaired health status meets expectations within a certain threshold, the contract is executed successfully and the repair is recorded as complete;

[0048] Among them, in the smart contract, the task status will be updated as the repair task progresses. The status includes: task not started, task started but not completed, and task completed.

[0049] As a preferred embodiment, once the smart contract completes the verification of the repair task and confirms that the task is successfully executed, the relevant data will be recorded in the blockchain. The smart contract also includes a reward mechanism, which automatically distributes rewards according to the execution quality of each repair task; wherein, the repair task The reward is determined by the quality of the repair and the completion of the task, and is calculated as follows:

[0050]

[0051] in, and is the adjustment coefficient, controlling the effects of health status and task status on rewards; is the health status of the node after repair, indicating the effect of the repair; It is the task status, reflecting the task completion status.

[0052] The beneficial technical effects of the present invention are at least as follows:

[0053] The present invention introduces the concept of regional grid layout and self-organizing sensing network for the first time, dividing the optical cable monitoring area of ​​the mine into multiple independent and adaptive grids. Each grid is equipped with multiple sensor nodes. While monitoring the mine environment, these nodes can also dynamically adjust the data acquisition strategy and working frequency according to local conditions, ensuring that the system can achieve real-time and comprehensive monitoring even when the mine environment is complex and the optical cable coverage is wide. The introduction of the self-organizing sensing network enables each sensor node to work independently and collaborate with surrounding nodes, enhancing the robustness of data acquisition and transmission, and solving the problem of unstable information transmission and lack of full coverage in traditional sensor systems.

[0054] Another innovation of the present invention is the introduction of a micro-robot repair mechanism. Through the autonomous positioning and repair functions of the micro-robot, once the monitoring system detects an abnormality in the optical cable, the robot can respond in real time and automatically go to the fault area to perform on-site repairs. The micro-robot can effectively repair different types of optical cable damage through built-in self-healing materials or repair tools, greatly improving the efficiency and accuracy of optical cable damage repair, and avoiding the time delays and cost waste caused by manual maintenance in traditional systems.

[0055] In terms of data storage and management, the present invention uses blockchain technology to encrypt and store all sensor data, monitoring reports and repair records to ensure the immutability and integrity of the data. At the same time, the automatic scheduling and execution of repair tasks are realized through smart contracts. A series of operations from fault detection to automatic triggering of repair tasks and fee settlement can be automated, reducing the need for manual intervention and improving the transparency, efficiency and security of the system. The application of blockchain further ensures the traceability of the entire process of mine optical cable status monitoring and repair, greatly improving the reliability and management efficiency of the system.

[0056] Through the above technical innovations, the present invention can solve the blind spot problems, information lag problems and low repair efficiency problems in the traditional optical cable monitoring and repair system, and realize full coverage, high efficiency, real-time and automatic optical cable monitoring and repair. These innovations not only improve the safety and stability of mine optical cables, but also significantly reduce the manual maintenance costs and system fault repair time, providing a new and intelligent management solution for mine communication infrastructure. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The present invention is further described using the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.

[0058] Figure 1 This is a framework diagram of a mining optical cable status monitoring system of the present invention. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0061] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0062] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0063] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0064] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0065] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0066] like Figure 1 As shown, an embodiment of the present invention provides a mining optical cable status monitoring system, the system comprising: a self-organizing perception module 100, an optical cable health assessment module 200, a fault identification module 300, an automatic repair module 400 and a blockchain storage module 500.

[0067] Among them, the self-organizing sensing module 100 is used to obtain sensor node data of optical cables in the mine, and a regional gridded self-organizing sensing network constructed based on the sensor nodes, and pre-process the sensor node data, and fuse the pre-processed data based on a preset neural network model to obtain an optical cable health assessment value; wherein the sensor node data includes temperature, humidity, vibration and strain data.

[0068] As a preferred embodiment, the regional grid-based self-organizing sensing network forms a distributed topology through a dynamic self-organizing protocol, wherein each node in the network transmits data through a low-power communication protocol, combined with an adaptive communication frequency control mechanism, and can automatically adjust the transmission frequency under different environmental conditions. At the same time, each node is responsible for collecting environmental data of its area, and exchanges data with adjacent nodes through a self-organizing mechanism to adjust the network topology in real time.

[0069] As a preferred embodiment, the preprocessing includes: removing random noise in the data by using a sliding average filter or a Gaussian filter method; identifying and removing abnormal values ​​in the sensor data by a threshold method or a standard deviation method; applying a Kalman filter to smooth the time series data; performing local data fusion on the data at each node to obtain preprocessed data;

[0070] The preset neural network model structure is:

[0071] Input layer: pre-processed data from each sensor;

[0072] Hidden layer: Use nonlinear activation functions to process the complex relationships between different sensor data and learn the contribution weight of each data to health assessment;

[0073] Output layer: Outputs the health assessment value of the optical cable, which is used to indicate the health status of the optical cable;

[0074] And through L2 regularization, the growth of the weight of the neural network model is limited, thereby improving the generalization ability of the neural network model.

[0075] Specifically, in this scheme, the present invention will focus on the health monitoring of mining optical cables, combine it with the design of regional gridded self-organizing sensing network, and further use neural network models to fuse data and provide fault warnings.

[0076] First, a comprehensive, flexible, and efficient sensor network is needed in the mine to ensure that the entire length of the optical cable and its surrounding environment can be monitored. To this end, a regional grid self-organizing sensing network is designed and deployed to meet the monitoring needs in the complex environment of the mine. This network consists of multiple types of sensor nodes, including temperature sensors, humidity sensors, strain sensors, vibration sensors, etc.

[0077] Network structure: The network forms a distributed topology through a dynamic self-organizing protocol, which can adjust the network structure in real time according to changes in the mine environment, avoiding single point failure problems that may occur in traditional mine sensor networks. Specifically, each node in the network transmits data through a low-power communication protocol (such as LoRa), combined with an adaptive communication frequency control mechanism, which can automatically adjust the transmission frequency under different environmental conditions, reduce the burden on communication bandwidth, and ensure the stability of data transmission.

[0078] Network training and maintenance: The initial layout of sensor nodes should take into account the spatial structure of the mine and key monitoring points. Each node is responsible for collecting environmental data in its area and exchanging data with adjacent nodes through a self-organizing mechanism to adjust the network topology in real time.

[0079] In a mine environment, sensor nodes may be affected by physical obstacles (such as walls, cables, rock formations, etc.). The dynamic self-organizing protocol can optimize the connectivity of the network to prevent network interruptions due to communication failures between nodes.

[0080] Preferably, each sensor node first performs data preprocessing after collecting the data. Since the sensor may be affected by noise, interference and other factors, the data needs to be de-noised, outlier removed, smoothed and other steps before transmission. The purpose of the preprocessing operation is to ensure the accuracy of subsequent analysis.

[0081] Specific data preprocessing methods:

[0082] Denoising: Use sliding average filtering or Gaussian filtering to remove random noise in the data and improve the quality of the data.

[0083] Outlier removal: Identify and remove outliers in sensor data using thresholding or standard deviation methods.

[0084] Smoothing: Apply Kalman filter to smooth time series data to further improve data usability.

[0085] Each node performs local data fusion on the data, that is, simplifies the data integration within the node based on the data of other nearby nodes. This local fusion not only improves the stability of the data, but also reduces the dependence on the central processing system and alleviates the pressure on the network bandwidth. Data preprocessing formula:

[0086]

[0087] in, Representation Node The collected raw data (temperature, humidity, strain, vibration). The data is after preprocessing. It is a data preprocessing function, including filtering and denoising steps to ensure data cleanliness and accuracy.

[0088] Preferably, the processed data is periodically uploaded to the central data processing system of the mine network through an adaptive upload frequency mechanism. The upload cycle of each node is dynamically adjusted according to the type, frequency and real-time status of the data collected. By reducing unnecessary uploads, energy consumption is reduced and the efficiency of data transmission is effectively improved.

[0089] Preferably, in the health monitoring of mining optical cables, the data collected by the sensors have different physical meanings and dimensions, and direct weighted average cannot provide effective fusion results. In order to better fuse these data, the present invention proposes an adaptive data fusion model based on a neural network. The core of the model is to perform multi-level processing of data from different sensors through a neural network, and convert the raw data output by all sensors into a standardized health assessment value. The network input layer accepts pre-processed data from various types of sensors. Through training, the neural network can automatically learn the contribution weight of each type of data to the final health assessment.

[0090] The network structure of the neural network:

[0091] Input layer: preprocessed data from each sensor, such as temperature, humidity, strain, etc.

[0092] Hidden layer: Use nonlinear activation functions to process the complex relationships between different sensor data.

[0093] Output layer: Outputs a health assessment value, which is used to indicate the health status of the optical cable.

[0094] The calculation formula for the comprehensive health assessment value is:

[0095]

[0096] in, , , , Represent the preprocessed temperature, humidity, vibration and strain data respectively. , , , is the weight coefficient of each input data in the neural network. is the output function of the neural network model.

[0097] In order to avoid the overfitting problem of the neural network during training, this paper introduces L2 regularization to limit the growth of model weights and improve the generalization ability of the model:

[0098]

[0099] in, is the number of training samples, is the true health assessment value, is the predicted health assessment value of the neural network. The first weights, is the regularization coefficient.

[0100] Among them, the optical cable health assessment module 200 is used to calculate and adjust the upload frequency of its node according to the health assessment value, and perform adaptive bandwidth allocation according to the upload frequency of its node and the total upload frequency of all nodes to obtain the bandwidth allocation of the node. At the same time, by performing a difference analysis between the current health assessment value of the node and its historical health assessment value, the faulty node is identified while avoiding false alarms. Once a node is marked as abnormal, the upload frequency of the node is automatically increased based on the abnormal identification result, and the bandwidth is reallocated.

[0101] As a preferred embodiment, the calculation and adjustment of the upload frequency of the node according to the health assessment value, and the adaptive bandwidth allocation according to the upload frequency of the node and the total upload frequency of all nodes to obtain the bandwidth allocation of the node include:

[0102] According to the health assessment value of the optical cable, the upload frequency is calculated using the Sigmoid function;

[0103] According to the upload frequency, combined with the total upload frequency of all nodes in the current network, the bandwidth allocation corresponding to the current node is obtained;

[0104] The identifying of the faulty node comprises:

[0105] Based on the difference analysis results of the node's current health assessment value and its historical health assessment value, combined with the change rate, through trend analysis, the rate of change of the node's health assessment value is calculated. If the rate of change of the node's health assessment value is greater than a preset threshold, the node is considered to have an abnormality and enters a warning state.

[0106] Specifically, in the mine monitoring system, real-time data transmission and anomaly detection are key parts to ensure the stable operation of the system. By building an intelligent sensor network and performing effective anomaly detection during data transmission, the present invention can achieve comprehensive monitoring of the mine environment, identify faults or dangers in advance and issue early warnings. This module directly inherits the results of data preprocessing and local analysis in the first part (node ​​health assessment data). The goal of the present invention is to design an innovative data transmission mechanism and ensure the efficiency and real-time performance of the system through an intelligent anomaly detection algorithm.

[0107] In order to solve the communication bandwidth limitation and node energy consumption problems in mines, the present invention adopts a dynamic, adaptive data transmission mechanism based on health evaluation value. This mechanism determines when and how to transmit data based on the health status of each node, thereby balancing the efficiency and energy consumption of data transmission. The specific design is as follows:

[0108] Preferably, the present invention is based on the health evaluation value of the node To adjust the upload frequency , in order to reduce energy consumption and improve the stability of data transmission. This adjustment follows the following relationship:

[0109]

[0110] in, Is a node health assessment value. is the threshold of health assessment, when When this threshold is exceeded, the upload frequency increases significantly. It is a coefficient that adjusts the transmission frequency sensitivity and controls the impact of the health assessment value on the frequency. is a constant coefficient, regulating the maximum value of the frequency. This formula uses a Sigmoid function to ensure that when the node health assessment value is low (i.e., healthy), its upload frequency remains low, reducing unnecessary energy consumption; when the node health assessment value approaches or exceeds the threshold, the upload frequency increases to ensure real-time transmission of key health data.

[0111] Preferably, in order to ensure that data transmission does not cause congestion in the mine network, the present invention adopts an adaptive bandwidth allocation strategy. Bandwidth Allocation Is with the node Upload frequency Proportional and dynamically adjusted according to the current network load of the mine:

[0112]

[0113] in, Representation Node bandwidth allocation. is a constant coefficient that adjusts the overall allocation of bandwidth. Indicates the total upload frequency of all nodes in the network. This bandwidth allocation scheme ensures that when the node upload frequency increases, the bandwidth will be automatically allocated according to the overall load of the network, thereby avoiding local network overload.

[0114] Preferably, in this step, the present invention designs an intelligent anomaly detection algorithm for data transmission. The algorithm is based on the health assessment value and historical data of each node, identifies anomalies by comparing current data with historical trends, and issues fault warnings in a timely manner. The specific algorithm design is as follows:

[0115] First, the present invention calculates the node Current health assessment Historic health assessment The difference between , this step helps to capture the rapid changes of nodes in a short time:

[0116]

[0117] Based on the difference The present invention further adopts a trend analysis method to determine whether the change of the node health assessment value is within the normal fluctuation range. The specific method is to calculate the rate of change of the node health assessment value :

[0118]

[0119] in, The difference between current and historical health assessment values. is the time interval. If The change exceeds the preset threshold , the node is considered to have an abnormality and enters the warning state.

[0120] Preferably, in order to avoid false positives and overfitting, the present invention designs an innovative regularized anomaly detection method, which introduces a regularization term to control the abnormal fluctuation of nodes based on the health assessment difference analysis and the normal health fluctuation range of each node. It is expressed as:

[0121]

[0122] in, For Node The health assessment fluctuation standard deviation indicates the normal fluctuation range of the node. is the total number of nodes. This regularization term reduces false positives due to normal fluctuations and improves the accuracy of anomaly detection by standardizing the health changes of each node.

[0123] Preferably, after anomaly detection, if the node's health assessment value Exceeding the threshold or its rate of change If it exceeds the expected range, the system will start the data upload mechanism and send a fault warning signal through the central system of the mine network. The specific implementation steps are as follows:

[0124] Once a node is marked as abnormal, the system will automatically increase the upload frequency of the node based on the abnormal detection results. , and reallocate bandwidth according to the network bandwidth scheduling algorithm to ensure that data is uploaded to the central processing system in real time.

[0125] Preferably, through the mine management system, the system will send early warning information to relevant staff and provide real-time node health status and fault type. Staff can take necessary repair or replacement actions based on this information.

[0126] In this module, the present invention designs an innovative adaptive data transmission and anomaly detection framework that can efficiently manage data flows in mine sensor networks. By dynamically adjusting the upload frequency and real-time anomaly detection, the entire system can ensure the stability and real-time performance of the system while maintaining low energy consumption and high efficiency. This solution greatly improves the fault response speed of the mine health monitoring system and reduces the risk of false alarms through accurate health assessment, difference analysis, and regularized anomaly detection. It is an indispensable core part of the mine sensor network.

[0127] Among them, the fault identification module 300 is used to determine the fault location based on the difference analysis results between the current health assessment value of the node and its historical health assessment value, as well as the change rate, obtain a regional fault probability map, and determine the priority of the repair task based on the regional fault probability map.

[0128] Specifically, in the mine optical cable health monitoring system, the automatic triggering of fault location and repair tasks is the key to ensuring the reliability of mine facilities. The present invention designs an intelligent fault location and task scheduling system, which can quickly locate the optical cable fault location based on the abnormal detection and data analysis results (such as health assessment values ​​and abnormal detection outputs) in the previous module, and automatically trigger the corresponding repair tasks. This solution not only achieves accurate fault location, but also ensures the continuity and safety of mine operations. The input of this module is abnormal data (such as the health assessment value of the node). , Health Change Rate , and fault alarms), based on this information, the present invention can locate the potential fault area and trigger the repair task. The following are the detailed steps of fault location and automatic triggering of repair tasks:

[0129] Differences based on health assessment With the rate of change The present invention first analyzes the distribution of health assessment values ​​in each area of ​​the mine to identify the area where failure is most likely to occur. The present invention defines each sensor node The difference in health assessment is:

[0130]

[0131] in, Representation Node Current health assessment value. Representation Node Historical health assessment values.

[0132] Rate of change is defined as:

[0133]

[0134] in, Assess differences for health. is the measurement time interval.

[0135] In order to transform these data into a fault location model, the present invention introduces a position weighted model to transform the fault location problem into a weighted average problem of each node in the area. The position weight is , which is related to the node The degree of abnormality ( and ) and their locations (such as node coordinates and )related:

[0136]

[0137] in, and It is the maximum value of the health assessment difference and change rate among all nodes, which is used to normalize the data. Is a node Euclidean distance from the center of the mine fault area. is the attenuation coefficient, which controls the effect of distance on node weight. is a weighting factor used to adjust the proportion of the impact of health differences and change rates when calculating location weights.

[0138] Through the above weighted calculation, the present invention obtains a weight value for each node ,The larger the node weight is, the more likely that the node is in the fault area.

[0139] Preferably, a weighted position model is used to weight all nodes Integration to obtain a regional failure probability map , represents the probability of a failure occurring in each area of ​​the mine. The calculation is obtained by superposition of node weights:

[0140]

[0141] in, is an indicator function, indicating that the node Coordinates In the current area Inside. is the number of all sensor nodes in the mine.

[0142] Through this weighted probability mapping, the present invention can derive the fault probability values ​​of each area of ​​the mine, thereby accurately identifying the fault area. The repair tasks of the mine can be prioritized according to the values ​​of the regional fault probability map. For example, if the fault probability of a certain area exceeds a set threshold , it is considered that a fault has occurred in this area.

[0143] Preferably, once the system determines the fault area, the next step is to automatically trigger the repair task. Through the task scheduling algorithm, the system can automatically determine the most suitable repair team, repair tools and repair time according to the location of the fault area.

[0144] First, the present invention defines the priority of the repair task , and its calculation formula is:

[0145]

[0146] in, is the scheduling sensitivity coefficient, which controls the relationship between the regional failure probability and the task location in task scheduling. Indicates the distance between the execution location of the repair task and the fault area. Exceeding the set task trigger threshold , the system automatically schedules the repair task and notifies the relevant personnel. During the task scheduling process, the system will also comprehensively consider the task load and resource allocation of different areas in the mine to ensure the efficient execution of the repair task.

[0147] Preferably, once the repair task is executed and completed, the system will provide feedback on the repair effect and update the mine health monitoring model based on the actual repaired data. For example, if the health assessment value of the relevant sensor node is Once the health status of the mine is restored to the normal range, the health assessment model can be updated to reflect the changes in the mine health status, ensuring that subsequent fault location and repair tasks are more accurate. Health assessment value The present invention uses the weighted average method to update the node status and to adjust the next fault detection strategy based on the changes.

[0148] The automatic repair module 400 is used to enable the micro-robot to automatically repair the faulty node according to the regional fault probability map and the priority of the repair task, generate repair status data, and generate feedback data in combination with the micro-robot's own sensors.

[0149] As a preferred embodiment, the micro-robot is enabled to automatically repair the faulty node according to the regional fault probability map and the priority of the repair task, and the repair status data generated includes:

[0150] Taking the failure probability of the regional failure probability map and the minimization of the distance from the current position of the micro-robot to the failure node as the optimization goal, the corresponding optimization objective function is established;

[0151] Collect the sensor data of the micro robot, and determine the exact location of the damage and the severity of the damaged area by fusing the sensor data of the robot; the severity of the damaged area is based on the regional failure probability map and confirmed by the indicator function;

[0152] When the micro robot completes the repair task, it detects the repair effect through the built-in sensor and feeds back the repaired health status to the mine management system; the repaired health status is determined based on the health status before repair and the rate of change of the severity of the damaged area.

[0153] Specifically, in the mine optical cable health monitoring system, micro-robots undertake key repair tasks. According to the fault area and the repair task scheduling results, this module aims to use autonomous micro-robots to automatically repair optical cable damage. Through precise positioning and efficient repair tools, the micro-robot can quickly repair the damaged area to ensure the stability of the optical cable and the safety of the mine environment.

[0154] Preferably, the following are the detailed steps for the micro robot to repair the optical cable damage:

[0155] Path planning and repair target confirmation:

[0156] According to the generated fault area probability map ,The micro robot first plans a path to reach the location where the optical cable is damaged. Different fault areas correspond to different repair priorities , the robot prioritizes repairing areas with high damage levels.

[0157] When planning the path, the robot will The paths are weighted and selected. When selecting a path, the robot should avoid obstacles outside the fault area while considering energy consumption and repair efficiency. To this end, the present invention defines an objective function that combines the fault probability and path length for optimization:

[0158]

[0159] in, For Node probability of failure. From the robot's current position to the node distance.

[0160] The robot selects the optimal path by optimizing the objective function, avoids unnecessary detours, and reaches the damaged area efficiently.

[0161] Preferably, the microrobot carries multiple sensors to monitor the degree of damage to the optical cable in real time. These sensors will detect multiple indicators of the optical cable, such as strain, temperature, vibration, etc., and determine the exact location of the damage by fusing the sensor data. Through the fused sensor data, the robot can form a detailed report on the damage.

[0162] Assume that the severity of the damaged area is , the present invention assesses the severity of the injury in the following manner:

[0163]

[0164] in, is the indicator function, if the node If the damage level exceeds the threshold, , otherwise 0. When the robot detects a severely damaged area, it will select a repair tool (such as heating welding, repair coating, etc.) for targeted repair. The specific repair tool selection is adjusted according to the degree of damage and the type of optical cable.

[0165] Preferably, once the robot reaches the target location for repair, it will automatically perform the repair task. During the repair process, the robot uses special tools to connect broken optical cables, repair surface coatings, and other operations. After the repair is completed, the robot detects the repair effect through built-in sensors and reports the repair results to the mine management system through a health status feedback mechanism.

[0166] Assume that after the repair task is completed, the node The health status of The health status after repair is calculated by the following formula:

[0167]

[0168] in, It is the health status before repair, indicating the original status of the optical cable at the node. The health assessment value reflects the effectiveness of the repair, and the data will serve as the basis for the next round of maintenance and monitoring decisions.

[0169] Preferably, the robot optimizes subsequent repair tasks through real-time feedback of repair results. For example, if the repair task fails to fully restore the health of the optical cable, the system will automatically readjust the repair strategy or dispatch other robots for subsequent repairs.

[0170] The system also monitors the robot’s path planning and repair task execution efficiency during the mission. Based on the task execution results, the system will adjust the robot’s route, task priority, and the use of repair tools to ensure the most efficient repair process.

[0171] Through the above steps, the micro-robot can efficiently perform the task of repairing optical cable damage and continuously optimize the repair strategy based on feedback data, thereby realizing the automated and intelligent maintenance of the optical cable system.

[0172] The blockchain storage module 500 is used to input the repair status data and feedback data into the blockchain as a smart contract, and automatically manage the repair tasks and reward mechanism through the smart contract.

[0173] As a preferred embodiment, each block of the blockchain includes: stored task data, a hash value pointing to the previous block, and a timestamp of task execution;

[0174] Every time a repair task is completed, a new block will be added to the blockchain, containing the complete data of the task;

[0175] Among them, the smart contract will define the rules in the following ways:

[0176] When the severity of a new damage area exceeds a preset threshold, a smart contract is automatically generated and activated to create a new repair task;

[0177] The execution of the repair task is triggered by the robot. After the task is completed, a new repaired health status will be generated and the result will be submitted to the smart contract, triggering a repair completion event;

[0178] The smart contract automatically verifies the execution of the repair task. If the new repaired health status meets expectations within a certain threshold, the contract is executed successfully and the repair is recorded as complete;

[0179] Among them, in the smart contract, the task status will be updated as the repair task progresses. The status includes: task not started, task started but not completed, and task completed.

[0180] Specifically, the core purpose of this module is to ensure the transparency, security and immutability of data storage, sharing and task execution in the process of mine optical cable health monitoring and repair through blockchain technology. Smart contracts are used to automate the mine monitoring and repair process to ensure that all repair tasks are executed according to predetermined rules and that relevant data cannot be tampered with.

[0181] The following is a specific solution for implementing blockchain data storage and smart contract management:

[0182] Every change in the health status of the optical cable, fault detection, repair task execution and other data need to be stored in the blockchain. These data are generated in real time when sensors and robots in the mine perform tasks and uploaded to the blockchain to ensure its transparency and immutability. The data of each node, including fault detection, repair status and robot execution records, need to be recorded in the blockchain as input for smart contracts.

[0183] Assume that the data of each repair task is , including health status before and after repair and , execution robot ID, repair tool type and other information. This information will be stored in each block.

[0184] Each block in the blockchain network It consists of the following contents:

[0185] : stored task data ( ).

[0186] : Points to the hash value of the previous block.

[0187] : Timestamp of task execution.

[0188] Whenever a repair task is completed, a new block will be added to the blockchain, containing the complete data of the task, ensuring data security and consistency.

[0189] Preferably, the smart contract realizes transparent management and execution of tasks by automating the logic of the repair task. Each repair task needs to be defined as an item of the smart contract, and the triggering, execution, completion and payment of the task are all controlled by the smart contract.

[0190] Preferably, in order to automatically manage the repair task, the smart contract will define rules in the following way:

[0191] Task triggering rules: When new damage detection data When a certain threshold is exceeded, the system automatically generates and activates a smart contract to create a new repair task.

[0192] Task execution rules: The execution of the repair task is triggered by the robot, and the health status of the optical cable will be updated after the task is completed. , and submit the results to the smart contract to trigger the repair completion event.

[0193] Task verification rules: Smart contracts automatically verify the execution of repair tasks. If it meets expectations within a certain threshold, the contract execution is successful and the record repair is completed.

[0194] In smart contracts, task status Will be updated as the repair task progresses, status includes:

[0195] 0: The task is not started.

[0196] 1: The task was started but not completed.

[0197] 2: Mission accomplished.

[0198] The smart contract dynamically adjusts the task status and reward mechanism according to the progress of the executed task to ensure the reliable execution of the repair task.

[0199] Preferably, once the smart contract completes the verification of the repair task and confirms that the task is successfully executed, the system will record the relevant data in the blockchain to ensure that all repair records cannot be tampered with. In order to further motivate the enthusiasm of robots and maintenance personnel, the smart contract also includes a reward mechanism. According to the execution quality of each repair task, the system will automatically distribute rewards. It is linked to the quality of repair and task completion, and the calculation formula is as follows:

[0200]

[0201] in, and is the adjustment coefficient, which controls the impact of health status and task status on the reward. It is the health status of the node after repair, indicating the effect of the repair. It is the task status, reflecting the task completion status.

[0202] This reward mechanism ensures the transparent execution of tasks and records the issuance of each reward through the blockchain.

[0203] By combining blockchain technology with smart contracts, the cable health monitoring and repair process in the mine not only achieves secure data storage and transparent sharing, but also manages task execution efficiently, ensuring the reliability and automation of the entire process. All data and operations are recorded in the blockchain, ensuring immutability and efficient task execution.

[0204] Unless otherwise specifically stated, the relative steps, numerical expressions and values ​​of the components and steps set forth in these embodiments do not limit the scope of the present application.

[0205] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application can essentially or in other words, the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the system described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0206] In the description of the present application, it should be noted that the terms "upper", "lower", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, or the orientations or positional relationships in which the inventive product is usually placed when in use. These are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0207] In the description of this application, it should also be noted that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0208] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A mining optical cable status monitoring system, characterized in that: The system includes: a self-organizing perception module, an optical cable health assessment module, a fault identification module, an automatic repair module and a blockchain storage module; The self-organizing sensing module is used to obtain sensor node data of the optical cable in the mine, and a regional gridded self-organizing sensing network constructed based on the sensor nodes, and pre-process the sensor node data, and fuse the pre-processed data based on a preset neural network model to obtain an optical cable health assessment value; wherein the sensor node data includes temperature, humidity, vibration and strain data; The optical cable health assessment module is used to calculate and adjust the upload frequency of its node according to the health assessment value, and to perform adaptive bandwidth allocation according to the upload frequency of its node and the total upload frequency of all nodes to obtain the bandwidth allocation of the node. At the same time, by performing a difference analysis between the current health assessment value of the node and its historical health assessment value, the faulty node is identified while avoiding false alarms. Once a node is marked as abnormal, the upload frequency of the node is automatically increased based on the abnormal identification result, and the bandwidth is reallocated; The fault identification module is used to perform difference analysis and change rate analysis between the current health assessment value of the node and its historical health assessment value, determine the fault location, obtain a regional fault probability map, and determine the priority of the repair task based on the regional fault probability map; The automatic repair module is used to enable the micro-robot to automatically repair the faulty node according to the regional fault probability map and the priority of the repair task, generate repair status data, and generate feedback data in combination with the micro-robot's own sensors; The blockchain storage module is used to input the repair status data and feedback data into the blockchain as a smart contract, and automatically manage the repair tasks and reward mechanism through the smart contract.

2. A mining optical cable status monitoring system according to claim 1, characterized in that: The regional grid-based self-organizing sensing network forms a distributed topology through a dynamic self-organizing protocol, wherein each node in the network transmits data through a low-power communication protocol, and combined with an adaptive communication frequency control mechanism, can automatically adjust the transmission frequency under different environmental conditions. At the same time, each node is responsible for collecting environmental data of its area, and exchanges data with adjacent nodes through a self-organizing mechanism to adjust the network topology in real time.

3. A mining optical cable status monitoring system according to claim 1, characterized in that: The preprocessing includes: removing random noise in the data by using a sliding average filter or a Gaussian filter method; identifying and removing abnormal values ​​in the sensor data by a threshold method or a standard deviation method; applying a Kalman filter to smooth the time series data; performing local data fusion on the data at each node to obtain preprocessed data; The preset neural network model structure is: Input layer: pre-processed data from each sensor; Hidden layer: Use nonlinear activation functions to process the complex relationships between different sensor data and learn the contribution weight of each data to health assessment; Output layer: Outputs the health assessment value of the optical cable, which is used to indicate the health status of the optical cable; And through L2 regularization, the growth of the weight of the neural network model is limited, thereby improving the generalization ability of the neural network model.

4. A mining optical cable status monitoring system according to claim 1, characterized in that: The step of calculating and adjusting the upload frequency of the node according to the health evaluation value, and performing adaptive bandwidth allocation according to the upload frequency of the node and the total upload frequency of all nodes to obtain the bandwidth allocation of the node includes: According to the health assessment value of the optical cable, the upload frequency is calculated using the Sigmoid function; According to the upload frequency, combined with the total upload frequency of all nodes in the current network, the bandwidth allocation corresponding to the current node is obtained; The identifying of the faulty node comprises: Based on the difference analysis results of the node's current health assessment value and its historical health assessment value, combined with the change rate, through trend analysis, the rate of change of the node's health assessment value is calculated. If the rate of change of the node's health assessment value is greater than a preset threshold, the node is considered to have an abnormality and enters a warning state.

5. A mining optical cable status monitoring system according to claim 4, characterized in that: Avoiding false positives includes: In the difference analysis, a regularized anomaly detection method is introduced. , combined with the normal healthy fluctuation range of each node to control the abnormal fluctuation of the node; wherein the regular term , expressed as: in, For Node The standard deviation of health assessment fluctuations indicates the normal fluctuation range of the node; The rate at which the node health assessment value changes; is the total number of nodes.

6. A mining optical cable status monitoring system according to claim 4, characterized in that: The fault identification module executes the steps including: Obtain the difference analysis result and the change rate, build a fault location model, and obtain the position weight of the node; wherein the position weight of the node in the fault location model is related to the abnormality degree of the node and its position; Integrate the location weights of all nodes to obtain the regional failure probability map , represents the probability of failure in each area of ​​the mine; the regional failure probability map The calculation is obtained by superposition of node weights: in, is an indicator function, indicating that the node Coordinates In the current area Inside; is the number of all sensor nodes in the mine.

7. A mining optical cable status monitoring system according to claim 6, characterized in that: When the fault area is determined, the repair task is automatically triggered, and the priority of the repair task is automatically determined based on the location of the fault area. , and its calculation formula is: in, is the scheduling sensitivity coefficient, which controls the relationship between the regional failure probability and the task location in task scheduling; Indicates the distance between the execution location of the repair task and the fault area; If you fix the priority of the task If the set task trigger threshold is exceeded, the repair task will be automatically scheduled and relevant personnel will be notified.

8. A mining optical cable status monitoring system according to claim 6, characterized in that: The micro-robot is enabled to automatically repair the faulty node according to the regional fault probability map and the priority of the repair task, and the repair status data generated includes: Taking the failure probability of the regional failure probability map and the minimization of the distance from the current position of the micro-robot to the failure node as the optimization goal, the corresponding optimization objective function is established; Collect the sensor data of the micro robot, and determine the exact location of the damage and the severity of the damaged area by fusing the sensor data of the robot; the severity of the damaged area is based on the regional failure probability map and confirmed by the indicator function; When the micro robot completes the repair task, it detects the repair effect through the built-in sensor and feeds back the repaired health status to the mine management system; the repaired health status is determined based on the health status before repair and the rate of change of the severity of the damaged area.

9. A mining optical cable status monitoring system according to claim 8, characterized in that: Each block of the blockchain includes: stored task data, a hash value pointing to the previous block, and a timestamp of task execution; Every time a repair task is completed, a new block will be added to the blockchain, containing the complete data of the task; Among them, the smart contract will define the rules in the following ways: When the severity of a new damage area exceeds a preset threshold, a smart contract is automatically generated and activated to create a new repair task; The execution of the repair task is triggered by the robot. After the task is completed, a new repaired health status will be generated and the result will be submitted to the smart contract, triggering a repair completion event; The smart contract automatically verifies the execution of the repair task; if the new repaired health status meets expectations within a certain threshold, the contract is executed successfully and the repair is recorded as complete; Among them, in the smart contract, the task status will be updated as the repair task progresses. The status includes: task not started, task started but not completed, and task completed.

10. A mining optical cable status monitoring system according to claim 9, characterized in that: Once the smart contract completes the verification of the repair task and confirms that the task is successfully executed, the relevant data will be recorded in the blockchain. The smart contract also includes a reward mechanism, which automatically distributes rewards based on the execution quality of each repair task; The reward is determined by the quality of the repair and the completion of the task, and is calculated as follows: in, and is the adjustment coefficient, controlling the effects of health status and task status on rewards; is the health status of the node after repair, indicating the effect of the repair; It is the task status, reflecting the task completion status.

Images