Monitoring and early warning processing system and method for underground construction site

Abstract

The invention relates to the technical field of underground roadway monitoring, in particular to a monitoring and early warning processing system and method for an underground construction site. The server comprises a data acquisition module, an identification module, a calculation module, a prediction module and an early warning module; wherein the prediction module is used for calling the first monitoring and early warning models corresponding to the abnormal sensors and the normal sensors after completing the calculation of the sensor data of all the abnormal sensors, and sending the sensor data corresponding to the abnormal sensors to the normal sensors; the sensor data corresponding to the normal sensor are used as input data to be input into the corresponding first monitoring early warning prediction model, and a first prediction result corresponding to the underground roadway at the current moment is output; and the early warning module is used for judging whether the underground roadway at the current moment is dangerous or not according to the first prediction result corresponding to the underground roadway at the current moment, and if yes, first early warning information is sent to the management end.

Description

Technical Field

[0001] The present invention relates to the technical field of underground tunnel monitoring, and in particular to a monitoring and early warning processing system and method for an underground construction site. Background Art

[0002] The underground construction site environment is extremely complex and changeable, facing a variety of potential safety risks, including but not limited to gas explosion, roof collapse, fire, harmful gas leakage, etc. These risks not only threaten the lives of construction workers, but may also lead to interruptions in production activities and cause huge economic losses. Therefore, real-time monitoring and early warning systems are particularly important in protecting the lives of construction workers and ensuring the smooth progress of production activities.

[0003] Traditional underground monitoring and early warning systems mainly rely on direct collection of sensor data and simple data analysis methods. However, this system has the following significant limitations:

[0004] Each sensor works independently, lacking comprehensive analysis of multiple sensor data. When a sensor node encounters performance degradation, signal distortion, or complete failure, the key parameters that the node is responsible for monitoring will not be effectively collected and transmitted, which will affect the data integrity and accuracy of the entire monitoring network. At the same time, the failure of a single sensor will not only lead to local information loss, but may also trigger a chain reaction, interfere with the working status evaluation of other normally operating units, and even cause a significant decrease in the reliability of the entire underground monitoring.

[0005] Based on this, there is an urgent need for a monitoring, early warning and processing system and method for underground construction sites, which can solve the problem in the prior art that due to the failure of some sensors, local information is lost, thereby greatly reducing the reliability of the entire underground site monitoring, and greatly improve the reliability of the corresponding underground site monitoring when some sensors fail. Summary of the invention

[0006] One of the purposes of the present invention is to provide a monitoring and early warning processing system and method for underground construction sites, which can solve the problem in the prior art that the reliability of the entire underground site monitoring is greatly reduced due to the loss of local information due to the failure of some sensors, and greatly improve the reliability of the corresponding underground site monitoring when some sensors fail.

[0007] In order to achieve the above-mentioned purpose, a monitoring and early warning processing system for underground construction sites is provided, including a service end and a management end;

[0008] The server includes:

[0009] The data acquisition module is used to collect sensor data of each sensor arranged at each sensor point of a monitoring group in the underground tunnel based on the pre-established sensor point setting plan at the current moment;

[0010] The identification module is used to determine whether the sensor data corresponding to the sensors at each sensor point at the current moment is abnormal according to the collected sensor data and the number of sensor points in the corresponding sensor point setting plan. If so, the corresponding sensor is determined to be an abnormal sensor, and if not, the corresponding sensor is a normal sensor; until the determination of all sensors is completed, the corresponding abnormal sensor set and normal sensor set are formed;

[0011] A calculation module is used to select the data association degree sets corresponding to each abnormal sensor in the abnormal sensor set according to the sensor data of the normal sensor corresponding to the normal sensor set at the current moment and based on the preset data association degree selection strategy, and calculate the sensor data corresponding to the corresponding abnormal sensor based on each data association degree in the data association degree set corresponding to each abnormal sensor and the sensor data of the normal sensor corresponding to the data association degree;

[0012] A prediction module, which is used to retrieve the first monitoring and early warning models corresponding to the abnormal sensors and the normal sensors after completing the calculation of the sensor data of all abnormal sensors, and input the sensor data corresponding to the abnormal sensors and the sensor data corresponding to the normal sensors as input data into the corresponding first monitoring and early warning prediction model, and output the first prediction result corresponding to the underground tunnel at the current moment;

[0013] The early warning module is used to determine whether there is danger in the underground tunnel at the current moment according to the first prediction result corresponding to the underground tunnel at the current moment, and if so, send a first early warning message to the management end.

[0014] Technical principle and effect of this scheme: In this scheme, firstly, the sensor data of the sensors at each sensor point corresponding to a monitoring group in the underground tunnel at the current moment is collected, and then according to the collected sensor data and the number of sensor points in the corresponding sensor point setting scheme, it is judged in turn whether the sensor data of the corresponding sensors at each sensor point at the current moment is abnormal. Through this step, the abnormal sensors and normal sensors are distinguished, and normal and abnormal sensor readings are automatically detected and distinguished. This process is crucial for early detection of possible safety hazards, because abnormal data may be a precursor to certain potential problems.

[0015] Then, according to the sensor data of the normal sensors corresponding to the normal sensor set at the current moment, based on the preset data correlation selection strategy, the data correlation sets corresponding to each abnormal sensor in the abnormal sensor set are selected respectively, and based on each data correlation in the data correlation set corresponding to each abnormal sensor and the sensor data of the normal sensors corresponding to the data correlation, the sensor data corresponding to the corresponding abnormal sensor is calculated. By acquiring the data correlation set corresponding to each abnormal sensor, the sensor data of the abnormal sensor is accurately calculated and supplemented, thereby improving the accuracy of anomaly detection.

[0016] Then, after completing the calculation of the sensor data of all abnormal sensors, the first monitoring and early warning model corresponding to the abnormal sensors and normal sensors is called up, and the sensor data corresponding to the abnormal sensors and the sensor data corresponding to the normal sensors are input as input data into the corresponding first monitoring and early warning prediction model, and the first prediction result corresponding to the underground tunnel at the current moment is output; based on the first prediction result corresponding to the underground tunnel at the current moment, it is determined whether there is danger in the underground tunnel at the current moment, and if so, a first early warning information is sent to the management end.

[0017] Compared with the prior art, when a sensor node encounters performance degradation, signal distortion or complete failure, the key parameters that the node is responsible for monitoring will not be effectively collected and transmitted, thereby affecting the data integrity and accuracy of the entire monitoring network. At the same time, the failure of a single sensor will not only lead to local information loss, but may also trigger a chain reaction, interfere with the working status evaluation of other normally operating units, and even cause a significant decrease in the reliability of the entire downhole monitoring. When some sensors are abnormal, this solution uses the coordination between the identification module and the calculation module to accurately and reliably supplement and improve the sensor data corresponding to the abnormal sensor, and then inputs the sensor data of the abnormal sensor and the sensor data of the normal sensor as input data into the corresponding model, thereby greatly improving the reliability of downhole field monitoring and ensuring the reliability and accuracy of downhole field monitoring when some sensors are abnormal. That is, it solves the problem in the prior art that the reliability of the entire downhole field monitoring is greatly reduced due to the failure of some sensors, and greatly improves the reliability of downhole field monitoring corresponding to the failure of some sensors.

[0018] Furthermore, the preset data relevance selection strategy includes the following steps:

[0019] S100, calculating the sensor quantity ratio between the normal sensor set and the abnormal sensor set according to the normal sensor set and the abnormal sensor set at the current moment;

[0020] S200, if the sensor quantity ratio is greater than or equal to the preset quantity ratio, then based on the grouping situation corresponding to the previous moment, the normal sensors in the normal sensor set are grouped to form sensor groups; the grouping situation includes the number of groups and the sensors corresponding to each group;

[0021] S300, if the sensor quantity ratio is less than the preset quantity ratio, randomly selecting and combining each normal sensor in the normal sensor set according to each normal sensor in the normal sensor set and the number of groups corresponding to the previous moment, to form a sensor group with the same number of groups as that corresponding to the previous moment;

[0022] S400, according to each sensor in each formed sensor group, retrieve the data correlation degree corresponding to each abnormal sensor in the abnormal sensor set and all normal sensors in each sensor group;

[0023] S500, obtaining the basic data of the underground tunnel where the corresponding monitoring group is located and the installation position data of the monitoring group in the underground tunnel, and dynamically adjusting the retrieved data correlation based on the basic data of the tunnel and the installation position data;

[0024] S500, calculating sensor data corresponding to each abnormal sensor in the abnormal sensor set according to the data association degree corresponding to each abnormal sensor in the abnormal sensor set and all normal sensors in each sensor group after dynamic adjustment, and sensor data corresponding to all normal sensors in the sensor group.

[0025] Beneficial effects: In this solution, firstly, by calculating the sensor quantity ratio between the normal sensor set and the abnormal sensor set, the proportion of abnormal sensors in the corresponding monitoring group can be known.

[0026] When the sensor number ratio is greater than or equal to the preset number ratio, each normal sensor in the normal sensor set is grouped based on the grouping situation corresponding to the previous moment to form each sensor group; the grouping situation includes the number of groups and the sensors corresponding to each group, and fully considers that when the sensor number ratio meets the preset number ratio, it means that the proportion of damaged sensors is relatively small. Then, when the grouping at the previous moment is used, the corresponding subsequent calculation results are also reliable and accurate. Grouping based on the grouping situation at the previous moment can maintain the continuity and stability of sensor grouping. This continuity helps to reduce unnecessary interference caused by frequent grouping adjustments, making the system smoother and more efficient when processing data. Using the existing grouping information avoids the large amount of computing resources required to regroup from scratch. This not only saves time and computing costs, but also improves the response speed of the system, especially in large-scale sensor networks, this advantage is particularly obvious. Inheriting historical grouping information can ensure that the data of sensors in the same group at different time points are consistent, which is convenient for time series analysis and trend prediction. This is very beneficial for long-term monitoring and fault diagnosis.

[0027] If the sensor number ratio is less than the preset number ratio, each normal sensor in the normal sensor set is randomly selected and combined according to each normal sensor in the normal sensor set and the number of groups corresponding to the previous moment to form a sensor group with the same number of groups corresponding to the previous moment; while ensuring that the number of groups is the same as the previous moment, each sensor in the sensor group is matched on demand to increase the diversity of the sensor group, thereby improving the anti-interference ability of the system. Different grouping combinations help to discover more potential abnormal patterns and improve the comprehensiveness of abnormal detection. Prevent the system from over-relying on a specific grouping method, thereby avoiding overfitting problems. This allows the system to maintain good performance when facing new or unseen data. Maintaining the same number of groups as the previous moment can ensure that the system maintains consistent monitoring density and coverage in different time periods. This helps to maintain the overall balance of the system and avoid monitoring blind spots or redundancy caused by changes in the number of groups. The same number of groups ensures the comparability of data in different time periods, which facilitates cross-time data comparison and analysis. This is very helpful for long-term trend analysis and historical data backtracking.

[0028] Then, for each abnormal sensor, the data correlation between it and all normal sensors in each sensor group is retrieved. For example, for abnormal sensor A, the normal sensors in the sensor group are a, b, and c. When the corresponding data correlation is retrieved, the correlation between abnormal sensor A and normal sensors a, b, and c will be retrieved. By quantifying the relationship between normal and abnormal sensors, a basis for subsequent analysis is provided.

[0029] Then, combined with the basic data of the underground tunnel (such as geological structure, ventilation conditions, etc.) and the specific installation location of the sensor, the correlation of the retrieved data is dynamically adjusted, which greatly improves the authenticity and reliability of the adjusted data correlation and is more in line with the actual situation.

[0030] Furthermore, the prediction module is also used to retrieve the second monitoring and early warning prediction model corresponding to the normal sensor, and input the sensor data corresponding to the normal sensor as input data into the second monitoring and early warning prediction model, and output the second prediction result corresponding to the underground tunnel at the current moment;

[0031] The server also includes an analysis module for calculating the corrected latest prediction result based on the first prediction result and the second prediction result corresponding to the underground tunnel at the current moment outputted and based on the weight values ​​corresponding to each prediction structure;

[0032] The early warning module is also used to determine whether there is danger in the underground tunnel at the current moment based on the latest corrected prediction result, and if so, send a second early warning message to the management end.

[0033] Beneficial effects: In this solution, by combining the first prediction result and the second prediction result, the abnormal data is corrected using normal data, which effectively reduces the probability of false positives and false negatives and significantly improves the accuracy of the prediction. This multi-model fusion method can more comprehensively reflect the actual environmental conditions of the underground tunnel.

[0034] As an independent verification method, the second prediction result can effectively detect anomalies in the first prediction result, enhancing the robustness and reliability of the system. This dual verification mechanism ensures the stability and credibility of the prediction results. Moreover, through correction calculation, the system can effectively reduce false positives and false negatives caused by single model errors, improving the overall reliability of the system.

[0035] Furthermore, the basic tunnel data includes tunnel geological data and tunnel data, and the tunnel data includes tunnel structure data, tunnel support data and tunnel size data.

[0036] Furthermore, the server also includes:

[0037] The report making module is used to generate a corresponding early warning maintenance report and feed it back to the management end according to the corresponding first prediction result when the judgment result is that there is danger in the underground tunnel at the current moment. The early warning maintenance report includes the current early warning level and the corresponding maintenance solution.

[0038] Beneficial effects: When the system determines that there is danger in the underground tunnel at the current moment, the report making module can immediately generate an early warning maintenance report and quickly feedback it to the management end. This immediate response mechanism greatly shortens the time from discovering risks to taking measures, improves the efficiency of emergency response, and the early warning maintenance report not only includes the current warning level, but also provides detailed maintenance solutions, so that managers can quickly understand the specific situation and take corresponding measures.

[0039] The present invention also provides a monitoring and early warning processing method for an underground construction site, using the above-mentioned monitoring and early warning processing system for an underground construction site, comprising the following steps:

[0040] S1. At the current moment, the sensor data of each sensor arranged at each sensor point of a monitoring group in the underground tunnel based on the pre-established sensor point setting plan are collected;

[0041] S2. According to the collected sensor data and the number of sensor points in the corresponding sensor point setting scheme, it is judged in turn whether the sensor data of the corresponding sensor at each sensor point at the current moment is abnormal. If so, the corresponding sensor is judged to be an abnormal sensor, and if not, the corresponding sensor is a normal sensor; until the judgment of all sensors is completed, the corresponding abnormal sensor set and normal sensor set are formed;

[0042] S3, according to the sensor data of the normal sensor corresponding to the normal sensor set at the current moment, based on the preset data association selection strategy, respectively select the data association sets corresponding to each abnormal sensor in the abnormal sensor set, and calculate the sensor data corresponding to the corresponding abnormal sensor based on each data association in the data association set corresponding to each abnormal sensor and the sensor data of the normal sensor corresponding to the data association;

[0043] S4. After completing the calculation of the sensor data of all abnormal sensors, the first monitoring and early warning models corresponding to the abnormal sensors and the normal sensors are retrieved, and the sensor data corresponding to the abnormal sensors and the sensor data corresponding to the normal sensors are input as input data into the corresponding first monitoring and early warning prediction model, and the first prediction result corresponding to the underground tunnel at the current moment is output;

[0044] S5. According to the first prediction result corresponding to the underground tunnel at the current moment, it is determined whether the underground tunnel at the current moment is dangerous. If so, a first warning message is sent to the management end. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1This is a logic block diagram of a monitoring and early warning processing system for an underground construction site in Embodiment 1 of the present invention;

[0046] Figure 2 This is a flow chart of a monitoring and early warning processing method for an underground construction site in Embodiment 1 of the present invention. DETAILED DESCRIPTION

[0047] The following is further described in detail through specific implementation methods:

[0048] Embodiment 1

[0049] A monitoring and early warning processing system and method for underground construction sites is basically as follows Figure 1 As shown, it includes the server side and the management side;

[0050] The server includes:

[0051] The data acquisition module is used to collect the sensor data of each sensor arranged at each sensor point of a monitoring group in the pre-established sensor point setting plan in the underground tunnel at the current moment; in this embodiment, the sensor types include temperature sensors, humidity sensors, gas concentration sensors, anchor stress gauges, surface strain gauges, axial force gauges, vibrating wire data acquisition instruments, crack meters, steel bar meters, earth pressure boxes and multi-point displacement meters. Different sensors correspond to different positions and installation methods. For example, when installing the multi-point displacement meter, the debugged multi-point displacement meter is placed in the drilled hole (the hole diameter is φ90-110 drill bit), and the drilling depth is 4 meters. After the drilling is completed, the hole is rinsed with pressurized water before the instrument is installed. The grouting casing mouth is anchored with cement mortar or epoxy anchoring agent. The outer side of the casing is flush with the hole mouth. During installation, the sensor must be tied and reinforced to prevent the sensor from falling and causing safety accidents. The installation position is set around the primary support surrounding rock. The installation method of the earth pressure box is to place the earth pressure box close to the primary support surrounding rock and the surface of the secondary support structure, and fix it with a special fixture. During the installation, it is necessary to pay attention to whether there is a gap between the pressure surface of the earth pressure gauge and the soil, and try to eliminate the accumulation of water caused by soil decomposition between the instrument and the soil. Installation location: primary support surrounding rock, surface of the primary structure, surface of the secondary structure.

[0052] In this embodiment, the settings of various sensors in the underground tunnels are arranged according to a pre-established sensor point setting plan. The sensor data of the sensors deployed at each sensor point of a specific monitoring group in the underground tunnels are accurately collected to provide basic data support and guarantee for subsequent monitoring and early warning work.

[0053] The identification module is used to determine whether the sensor data corresponding to the sensors at each sensor point at the current moment is abnormal according to the collected sensor data and the number of sensor points in the corresponding sensor point setting plan. If so, the corresponding sensor is determined to be an abnormal sensor, and if not, the corresponding sensor is a normal sensor; until the determination of all sensors is completed, the corresponding abnormal sensor set and normal sensor set are formed;

[0054] A calculation module is used to select the data association degree sets corresponding to each abnormal sensor in the abnormal sensor set according to the sensor data of the normal sensor corresponding to the normal sensor set at the current moment and based on the preset data association degree selection strategy, and calculate the sensor data corresponding to the corresponding abnormal sensor based on each data association degree in the data association degree set corresponding to each abnormal sensor and the sensor data of the normal sensor corresponding to the data association degree;

[0055] The preset data relevance selection strategy includes the following steps:

[0056] S100, calculating the sensor quantity ratio between the normal sensor set and the abnormal sensor set according to the normal sensor set and the abnormal sensor set at the current moment;

[0057] S200, if the sensor quantity ratio is greater than or equal to the preset quantity ratio, then based on the grouping situation corresponding to the previous moment, the normal sensors in the normal sensor set are grouped to form sensor groups; the grouping situation includes the number of groups and the sensors corresponding to each group;

[0058] S300, if the sensor quantity ratio is less than the preset quantity ratio, randomly selecting and combining each normal sensor in the normal sensor set according to each normal sensor in the normal sensor set and the number of groups corresponding to the previous moment, to form a sensor group with the same number of groups as that corresponding to the previous moment;

[0059] S400, according to each sensor in each formed sensor group, retrieve the data correlation degree corresponding to each abnormal sensor in the abnormal sensor set and all normal sensors in each sensor group;

[0060] S500. Obtain the basic data of the underground tunnel where the corresponding monitoring group is located and the installation position data of the monitoring group in the underground tunnel, and dynamically adjust the relevance of the retrieved data based on the basic data of the tunnel and the installation position data; in this embodiment, the basic data of the tunnel includes tunnel geological data and tunnel data, and the tunnel data includes tunnel structure data, tunnel support data and tunnel size data.

[0061] S500, calculating sensor data corresponding to each abnormal sensor in the abnormal sensor set according to the data association degree corresponding to each abnormal sensor in the abnormal sensor set and all normal sensors in each sensor group after dynamic adjustment, and sensor data corresponding to all normal sensors in the sensor group.

[0062] For example, a monitoring group includes 13 different sensors, among which there are 10 normal sensors and 2 abnormal sensors in the underground tunnel at the current moment. Each sensor has corresponding sensor data, so the corresponding number of sensors is The corresponding preset quantity ratio is 4.

[0063] Since the sensor data ratio B=5 is less than the preset number ratio 4, it is necessary to group based on the grouping situation at the last moment. Assume that there are 3 groups at the last moment, one group includes sensors a, b, c, another includes sensors d, e, f, and the last group includes sensors h, i, j, k. Then the grouping is also done this time.

[0064] Assuming there are 6 normal sensors and 6 abnormal sensors, the corresponding number of sensors is Since the number of sensors at this time is less than 1 and less than the preset number of sensors 4, random grouping is required, and the corresponding number of groups during grouping is the same as the number of groups at the previous moment. Assuming that the number of groups at the previous moment is also 3, then at this time, 6 normal sensors can be randomly selected and placed in three groups. For example, sensor group 1 finally includes sensor 1 and sensor 2, sensor group 2 includes sensor 3, and sensor group 3 includes sensor 4, sensor 5 and sensor 6.

[0065] After the grouping is completed, the data correlation will be retrieved. During the retrieval, the abnormal sensor A will retrieve the data correlation corresponding to the abnormal sensor A and sensor group 1, sensor group 2 and sensor group 3. The data correlation corresponding to each group is the common data correlation between all sensors in the group and the abnormal sensor A.

[0066] A prediction module, which is used to retrieve the first monitoring and early warning models corresponding to the abnormal sensors and the normal sensors after completing the calculation of the sensor data of all abnormal sensors, and input the sensor data corresponding to the abnormal sensors and the sensor data corresponding to the normal sensors as input data into the corresponding first monitoring and early warning prediction model, and output the first prediction result corresponding to the underground tunnel at the current moment;

[0067] The prediction module is also used to call the second monitoring and early warning prediction model corresponding to the normal sensor, and input the sensor data corresponding to the normal sensor as input data into the second monitoring and early warning prediction model, and output the second prediction result corresponding to the underground tunnel at the current moment; in this embodiment, the first prediction result is the prediction result formed by inputting the sensor data of the abnormal sensor and the sensor data of the normal sensor as input data into the corresponding model, and the second prediction result is the prediction result formed by inputting only the sensor data of the normal sensor as input data into the corresponding model, and a new prediction result is formed by analyzing and fusion of the two prediction results, which greatly improves the authenticity and reliability of the prediction result. The first monitoring and early warning prediction model and the second monitoring and early warning prediction model involved in this embodiment both use BP neural network technology to construct the corresponding model. And there are multiple second monitoring and early warning prediction models, and the sensors corresponding to different second monitoring and early warning prediction models are different.

[0068] For example, when there are five sensors in total, the model will be constructed by combining multiple sensors according to the sensor data corresponding to the five sensors, so as to form a second monitoring and early warning prediction model formed by the combination of multiple sensors. For example, the sensor group formed by the four sensors aa, ba, ca, and da corresponds to the second monitoring and early warning model AA. Specifically, a three-layer BP neural network model is first constructed, including an input layer, a hidden layer, and an output layer. In this embodiment, the sensor data corresponding to sensors aa, ba, ca, and da are used as inputs of the input layer, so the input layer has four nodes, and the output is the corresponding second prediction result, so there is a total of one node. For the hidden layer, this embodiment uses the following formula to determine the number of hidden layer nodes: Wherein, Y is the number of nodes in the hidden layer, n is the number of nodes in the input layer, m is the number of nodes in the output layer, and a is a number between 1 and 10. In this embodiment, it is 4, so there are 6 hidden layer nodes in total. BP neural network usually uses Sigmoid differentiable function and linear function as the excitation function of the network. This paper selects the S-type tangent function tansig as the excitation function of the hidden layer neurons. The prediction model selects the S-type logarithmic function tansig as the excitation function of the output layer neurons.

[0069] The server also includes an analysis module for calculating the corrected latest prediction result based on the first prediction result and the second prediction result corresponding to the underground tunnel at the current moment outputted and based on the weight values ​​corresponding to each prediction structure;

[0070] The early warning module is also used to determine whether there is danger in the underground tunnel at the current moment based on the latest corrected prediction result, and if so, send a second early warning message to the management end.

[0071] The early warning module is used to determine whether the underground tunnel at the current moment is dangerous according to the first prediction result corresponding to the underground tunnel at the current moment, and if so, send the first early warning information to the management end. In this embodiment, according to the first prediction result corresponding to the underground tunnel at the current moment, it is deeply judged whether the underground tunnel at that moment is in a dangerous state. If the judgment result is that there is danger, the first early warning information is immediately and accurately pushed to the management end to achieve timely notification and efficient control of risks.

[0072] The server also includes:

[0073] The report making module is used to generate a corresponding early warning maintenance report and feed it back to the management end according to the corresponding first prediction result when the judgment result is that there is danger in the underground tunnel at the current moment. The early warning maintenance report includes the current early warning level and the corresponding maintenance solution.

[0074] like Figure 2 As shown, this embodiment also discloses a monitoring and early warning processing method for an underground construction site, using the above-mentioned monitoring and early warning processing system for an underground construction site, including the following steps:

[0075] S1. At the current moment, the sensor data of each sensor arranged at each sensor point of a monitoring group in the underground tunnel based on the pre-established sensor point setting plan are collected;

[0076] S2. According to the collected sensor data and the number of sensor points in the corresponding sensor point setting scheme, it is judged in turn whether the sensor data of the corresponding sensor at each sensor point at the current moment is abnormal. If so, the corresponding sensor is judged to be an abnormal sensor, and if not, the corresponding sensor is a normal sensor; until the judgment of all sensors is completed, the corresponding abnormal sensor set and normal sensor set are formed;

[0077] S3, according to the sensor data of the normal sensor corresponding to the normal sensor set at the current moment, based on the preset data association selection strategy, respectively select the data association sets corresponding to each abnormal sensor in the abnormal sensor set, and calculate the sensor data corresponding to the corresponding abnormal sensor based on each data association in the data association set corresponding to each abnormal sensor and the sensor data of the normal sensor corresponding to the data association;

[0078] S4. After completing the calculation of the sensor data of all abnormal sensors, the first monitoring and early warning models corresponding to the abnormal sensors and the normal sensors are retrieved, and the sensor data corresponding to the abnormal sensors and the sensor data corresponding to the normal sensors are input as input data into the corresponding first monitoring and early warning prediction model, and the first prediction result corresponding to the underground tunnel at the current moment is output;

[0079] S5. According to the first prediction result corresponding to the underground tunnel at the current moment, it is determined whether the underground tunnel at the current moment is dangerous. If so, a first warning message is sent to the management end.

[0080] The above is only an embodiment of the present invention. The common sense such as the known specific structure and characteristics in the scheme is described too much here. The ordinary technicians in the relevant field know all the common technical knowledge in the technical field of the invention before the application date or priority date, can know all the existing technologies in the field, and have the ability to apply the conventional experimental means before that date. The ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the protection scope of the present invention, which will not affect the effect of the implementation of the present invention and the practicality of the patent. The protection scope required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. A monitoring and early warning processing system for underground construction sites, characterized by: Including server and management side; The server includes: The data acquisition module is used to collect sensor data of each sensor arranged at each sensor point of a monitoring group in the underground tunnel based on the pre-established sensor point setting plan at the current moment; The identification module is used to determine whether the sensor data corresponding to the sensors at each sensor point at the current moment is abnormal according to the collected sensor data and the number of sensor points in the corresponding sensor point setting plan. If so, the corresponding sensor is determined to be an abnormal sensor, and if not, the corresponding sensor is a normal sensor; until the determination of all sensors is completed, the corresponding abnormal sensor set and normal sensor set are formed; A calculation module is used to select the data association degree sets corresponding to each abnormal sensor in the abnormal sensor set according to the sensor data of the normal sensor corresponding to the normal sensor set at the current moment and based on the preset data association degree selection strategy, and calculate the sensor data corresponding to the corresponding abnormal sensor based on each data association degree in the data association degree set corresponding to each abnormal sensor and the sensor data of the normal sensor corresponding to the data association degree; A prediction module, which is used to retrieve the first monitoring and early warning models corresponding to the abnormal sensors and the normal sensors after completing the calculation of the sensor data of all abnormal sensors, and input the sensor data corresponding to the abnormal sensors and the sensor data corresponding to the normal sensors as input data into the corresponding first monitoring and early warning prediction model, and output the first prediction result corresponding to the underground tunnel at the current moment; The early warning module is used to determine whether the underground tunnel at the current moment is dangerous according to the first prediction result corresponding to the underground tunnel at the current moment, and if so, send a first early warning message to the management end.

2. The monitoring and early warning processing system for underground construction sites according to claim 1 is characterized in that: The preset data relevance selection strategy includes the following steps: S100, calculating the sensor quantity ratio between the normal sensor set and the abnormal sensor set according to the normal sensor set and the abnormal sensor set at the current moment; S200, if the sensor quantity ratio is greater than or equal to the preset quantity ratio, then based on the grouping situation corresponding to the previous moment, the normal sensors in the normal sensor set are grouped to form sensor groups; the grouping situation includes the number of groups and the sensors corresponding to each group; S300, if the sensor quantity ratio is less than the preset quantity ratio, randomly selecting and combining each normal sensor in the normal sensor set according to each normal sensor in the normal sensor set and the number of groups corresponding to the previous moment, to form a sensor group having the same number as that corresponding to the previous moment; S400, according to each sensor in each formed sensor group, retrieve the data correlation degree corresponding to each abnormal sensor in the abnormal sensor set and all normal sensors in each sensor group; S500, obtaining the basic data of the underground tunnel where the corresponding monitoring group is located and the installation position data of the monitoring group in the underground tunnel, and dynamically adjusting the retrieved data correlation based on the basic data of the tunnel and the installation position data; S500, calculating sensor data corresponding to each abnormal sensor in the abnormal sensor set according to the data association degree corresponding to each abnormal sensor in the abnormal sensor set and all normal sensors in each sensor group after dynamic adjustment, and sensor data corresponding to all normal sensors in the sensor group.

3. The monitoring and early warning processing system for underground construction sites according to claim 2 is characterized in that: The prediction module is also used to call the second monitoring and early warning prediction model corresponding to the normal sensor, and input the sensor data corresponding to the normal sensor as input data into the second monitoring and early warning prediction model, and output the second prediction result corresponding to the underground tunnel at the current moment; The server also includes an analysis module for calculating the corrected latest prediction result based on the first prediction result and the second prediction result corresponding to the underground tunnel at the current moment outputted and based on the weight values ​​corresponding to each prediction structure; The early warning module is also used to determine whether there is danger in the underground tunnel at the current moment based on the latest corrected prediction result, and if so, send a second early warning message to the management end.

4. The monitoring and early warning processing system for underground construction sites according to claim 3 is characterized in that: The basic tunnel data includes tunnel geological data and tunnel data, and the tunnel data includes tunnel structure data, tunnel support data and tunnel size data.

5. The monitoring and early warning processing system for underground construction sites according to claim 4 is characterized in that: The server also includes: The report making module is used to generate a corresponding early warning maintenance report and feed it back to the management end according to the corresponding first prediction result when the judgment result is that there is danger in the underground tunnel at the current moment. The early warning maintenance report includes the current early warning level and the corresponding maintenance solution.

6. A monitoring and early warning processing method for an underground construction site, using the monitoring and early warning processing system for an underground construction site according to any one of claims 1 to 5, characterized in that: The following steps are involved: S1. At the current moment, the sensor data of each sensor arranged at each sensor point of a monitoring group in the underground tunnel based on the pre-established sensor point setting plan are collected; S2, according to the collected sensor data and the number of sensor points in the corresponding sensor point setting scheme, determine in sequence whether the sensor data corresponding to the sensor at each sensor point at the current moment is abnormal, if so, determine that the corresponding sensor is an abnormal sensor, if not, the corresponding sensor is a normal sensor; Until all sensors are judged, their corresponding abnormal sensor sets and normal sensor sets are formed; S3, according to the sensor data of the normal sensor corresponding to the normal sensor set at the current moment, based on the preset data association selection strategy, respectively select the data association sets corresponding to each abnormal sensor in the abnormal sensor set, and calculate the sensor data corresponding to the corresponding abnormal sensor based on each data association in the data association set corresponding to each abnormal sensor and the sensor data of the normal sensor corresponding to the data association; S4. After completing the calculation of the sensor data of all abnormal sensors, the first monitoring and early warning models corresponding to the abnormal sensors and the normal sensors are retrieved, and the sensor data corresponding to the abnormal sensors and the sensor data corresponding to the normal sensors are input as input data into the corresponding first monitoring and early warning prediction model, and the first prediction result corresponding to the underground tunnel at the current moment is output; S5. According to the first prediction result corresponding to the underground tunnel at the current moment, it is determined whether the underground tunnel at the current moment is dangerous. If so, a first warning message is sent to the management end.

Images