A method and device for online monitoring of the working performance of chemical anchor bolts and planted rebar

Abstract

The present invention relates to the field of building monitoring technology, and in particular to an online monitoring method and device for the working performance of chemical anchors and rebars. A chemical glue working condition prediction model is constructed based on various acoustic dynamic characteristic data corresponding to chemical glue in a preset time period before each preset working condition event occurs in the working process of chemical anchors and rebars; real-time acoustic characteristic data fed back by chemical glue in chemical anchors and rebars are continuously collected by a monitoring device at several preset time nodes; the real-time acoustic characteristic dynamic data set is imported into the chemical glue working condition prediction model for prediction; if the probability value of a preset working condition event occurring in the chemical glue is greater than a preset probability threshold, an early warning message is generated. The present invention can accurately predict the occurrence time of a chemical glue working condition event and recommend the optimal maintenance time period, thereby improving the accuracy and maintenance efficiency of working performance monitoring of chemical anchors and rebars, and significantly improving the safety and reliability of the system.

Description

Technical Field

[0001] The present invention relates to the technical field of building monitoring, in particular to an online monitoring method and device for the working performance of a chemical anchor bolt and a planted reinforcement. Background Art

[0002] With the continuous expansion of construction projects and the increasing complexity of their structures, chemical anchors and rebar have become widely used as important connection methods in projects such as bridges, tunnels, and high-rise buildings. However, the performance of chemical anchors and rebar is affected by multiple factors, among which aging of the chemical adhesive is one of the main causes of their reduced bearing capacity and failure. The "Technical Standard for Testing the Pullout and Shear Resistance of Post-Concrete Anchors" (DBJ / T15-35-2023) clearly stipulates that the working condition of chemical anchors and rebar should be regularly inspected, with the first inspection to be carried out no later than 10 years, reflecting the concern for the long-term performance stability of chemical anchors and rebar. However, traditional testing methods mainly rely on manual periodic inspections or destructive testing, which is not only time-consuming and labor-intensive, but also difficult to monitor the performance of the chemical adhesive in real time, unable to provide timely warnings of potential risks, posing certain safety risks. Therefore, there is an urgent need to develop a method and device for online monitoring of the working performance of chemical anchors and rebar, enabling real-time monitoring of the aging of the chemical adhesive and providing timely warnings of potential failure risks to ensure structural safety. Summary of the Invention

[0003] The present invention overcomes the deficiencies of the prior art and provides a method and device for online monitoring of the working performance of chemical anchor bolts and planted reinforcement.

[0004] In order to achieve the above-mentioned purpose, the technical solution adopted by the present invention is:

[0005] The first aspect of the present invention discloses an online monitoring method for the working performance of chemical anchor bolts and planted rebar, comprising the following steps:

[0006] Acquiring a shared monitoring logbook of chemical anchors and planted rebars through a big data network, and obtaining, based on the shared monitoring logbook, various acoustic dynamic characteristic data corresponding to the chemical glue within a preset time period before each preset working condition event occurs during the operation of the chemical anchors and planted rebars;

[0007] A chemical glue working condition prediction model is constructed based on various acoustic dynamic characteristic data corresponding to the chemical glue in a preset time period before each preset working condition event occurs during the working process of the chemical anchor bolts and planted rebars;

[0008] The monitoring device continuously collects real-time acoustic characteristic data fed back by chemical anchor bolts and chemical glue in planted rebar at several preset time nodes, and classifies and processes the collected real-time acoustic characteristic data to obtain several real-time acoustic characteristic dynamic data sets;

[0009] The real-time acoustic feature dynamic data set is imported into the chemical glue working condition prediction model for prediction to obtain the probability value of the chemical glue occurrence of a preset working condition event; if the probability value of the chemical glue occurrence of a preset working condition event is greater than a preset probability threshold, an early warning message is generated and sent to a preset terminal.

[0010] Preferably, in a preferred embodiment of the present invention, a shared monitoring logbook of chemical anchors and planted rebars is obtained through a big data network, and various acoustic dynamic characteristic data corresponding to the chemical glue in a preset time period before each preset working condition event occurs during the operation of the chemical anchors and planted rebars are obtained based on the shared monitoring logbook, specifically:

[0011] Obtaining a shared monitoring logbook of chemical anchors and planted rebars through a big data network, and obtaining various working condition events of the chemical anchors and planted rebars during operation based on the shared monitoring logbook;

[0012] Clustering is performed on various working condition events of chemical anchor bolts and rebar planting during operation, generating clustering results, and extracting preset working condition events from the clustering results;

[0013] Acquiring, according to the shared monitoring logbook, various acoustic dynamic characteristic data corresponding to the chemical glue within a preset time period before each preset working condition event occurs during the operation of the chemical anchor bolts and the planted rebar;

[0014] Among them, the preset working condition events include the initial working condition, mid-term working condition and final working condition of chemical glue aging and chemical glue crack working condition; the acoustic dynamic characteristic data includes the spectrum, frequency, amplitude, peak value, spectrum entropy and frequency band energy of the sound wave.

[0015] Preferably, in a preferred embodiment of the present invention, a chemical glue working condition prediction model is constructed based on various acoustic dynamic characteristic data corresponding to the chemical glue in a preset time period before each preset working condition event occurs during the working process of the chemical anchor bolt and the planted rebar, specifically:

[0016] Arrange various acoustic dynamic characteristic data corresponding to the chemical glue in a preset time period before the occurrence of a preset working condition event in chronological order to obtain several time series data sets;

[0017] A conditional random field is introduced, each preset working condition event is defined as a random node of the conditional random field, and each time series data set is used as a conditional node of the conditional random field;

[0018] Connect each conditional node with each random node, and obtain the path length and connection direction between each conditional node and each random node;

[0019] Based on the grey correlation analysis method and combined with the path length and connection direction between each conditional node and each random node, the correlation strength between each conditional node and each random node is analyzed;

[0020] Determine the conditional association probability between the acoustic feature data in each time series data set and each preset working condition event based on the association strength between each conditional node and each random node;

[0021] Constructing a conditional association probability table based on the conditional association probability between the acoustic feature data in each time series data set and each preset working condition event;

[0022] The conditional association probability table is imported into the conditional random field for back propagation training; through training, the training parameters of the conditional random field are obtained; after the training parameters converge to preset values, the training parameters that converge to the preset values ​​are used as the final learning parameters of the conditional random field, and a chemical glue working condition prediction model is output.

[0023] Preferably, in a preferred embodiment of the present invention, the monitoring device continuously collects real-time acoustic feature data fed back by the chemical anchor bolts and the chemical glue in the rebar at several preset time nodes, and classifies and processes the collected real-time acoustic feature data to obtain several real-time acoustic feature dynamic data sets, specifically:

[0024] Continuously collecting real-time acoustic characteristic data fed back by chemical anchor bolts and chemical glue in rebar at several preset time points, and storing the collected real-time acoustic characteristic data in a database until the collection is completed;

[0025] Constructing a decision tree, obtaining the number of data items of the real-time acoustic feature data to be classified, determining a number of branch points according to the number of data items of the real-time acoustic feature data to be classified, and dividing a number of branch trunks in the decision tree according to the branch points;

[0026] Acquire data feature information of real-time acoustic feature data of each required classification, and assign corresponding feature attributes to each branch trunk according to the data feature information of real-time acoustic feature data of each required classification;

[0027] Acquiring real-time acoustic feature data in the database, and calculating the degree of membership between each real-time acoustic feature data in the database and the characteristic attribute assigned to each branch trunk;

[0028] Allocate each real-time acoustic feature data to the branch with the highest membership, and repeat this step until all real-time acoustic feature data in the database are allocated;

[0029] After the allocation is completed, the Euclidean distance between the real-time acoustic feature data on each branch trunk and the corresponding branch point is calculated respectively; the Euclidean distance between the real-time acoustic feature data on each branch trunk and the corresponding branch point is compared with the preset distance threshold;

[0030] If the Euclidean distance between a certain real-time acoustic feature data on a branch trunk and the corresponding branch point is greater than a preset distance threshold, the real-time acoustic feature data is marked as noise data and the noise data is removed from the corresponding branch trunk; repeat this step until the denoising process of the real-time acoustic feature data on all branch trunks is completed;

[0031] Each branch trunk is pruned to obtain several real-time acoustic feature data sets, and each real-time acoustic feature data on each real-time acoustic feature data set is sorted according to the acquisition timestamp to obtain several real-time acoustic feature dynamic data sets.

[0032] Preferably, in a preferred embodiment of the present invention, the real-time acoustic feature dynamic data set is imported into the chemical glue working condition prediction model for prediction to obtain a probability value of a preset working condition event of the chemical glue; if the probability value of the preset working condition event of the chemical glue is greater than a preset probability threshold, an early warning message is generated, specifically:

[0033] Importing the real-time acoustic feature dynamic data set into the chemical glue working condition prediction model to perform prediction and obtain prediction results;

[0034] Obtaining a probability value of a preset working condition event occurring in the chemical glue of the chemical anchor bolt and the planted rebar after a preset time based on the prediction result;

[0035] Compare the probability value of the chemical anchor bolt and the rebar undergoing a preset working condition event after the preset time with the preset probability threshold;

[0036] If the probability value of the chemical anchor bolt and the rebar causing the preset working condition event is greater than the preset probability threshold after the preset time, an early warning message is generated;

[0037] If the probability value of the chemical anchor bolt and the rebar causing the preset working condition event is not greater than the preset probability threshold after the preset time, no warning information will be generated.

[0038] The following steps are also included:

[0039] If the probability value of the chemical glue in the chemical anchor bolt and the planted rebar experiencing a preset working condition event after the preset time is greater than a preset probability threshold, then the time node of the chemical glue in the chemical anchor bolt and the planted rebar experiencing the preset working condition event is obtained according to the prediction result;

[0040] Determine several maintenance time periods based on the time nodes of preset working condition events of chemical glue, and obtain the predicted meteorological data information of chemical anchor bolts and rebar planting areas in each maintenance time period based on meteorological software;

[0041] Calculate the attention score between the predicted meteorological data information and the preset meteorological data for each maintenance time period based on the local sensitive attention mechanism; and sort the attention scores between the predicted meteorological data information and the preset meteorological data for each maintenance time period to obtain a sorting result;

[0042] A maximum attention score is obtained according to the ranking result, and a maintenance time period corresponding to the maximum attention score is obtained, and the maintenance time period corresponding to the maximum attention score is sent to a preset terminal as a recommended maintenance time period.

[0043] The second aspect of the present invention discloses an online monitoring device for the working performance of chemical anchors and planted rebars, which is applied to any of the above-mentioned online monitoring methods for the working performance of chemical anchors and planted rebars, comprising:

[0044] The main body of the monitoring device is buried in the concrete along with the chemical anchor bolts and rebar during the initial construction. An external wire is provided through the concrete to connect with external instruments.

[0045] Acoustic sensor module, used to collect acoustic signals around chemical anchors and rebars;

[0046] The signal acquisition and processing module amplifies, filters, digitizes, and processes the signals collected by the acoustic sensor, and converts them into data that can be analyzed;

[0047] The data analysis and processing module analyzes the collected acoustic feature data, extracts characteristic parameters related to chemical adhesive aging and cracks, and performs data modeling and early warning judgment;

[0048] The data storage and transmission module stores monitoring data and warning information and transmits them to the monitoring center or other equipment.

[0049] The present invention solves the technical defects existing in the background technology, and the present invention has the following beneficial effects: a chemical glue working condition prediction model is constructed based on the various acoustic dynamic characteristic data corresponding to the chemical glue in a preset time period before each preset working condition event occurs in the chemical anchor bolts and planted steel bars during operation; the real-time acoustic characteristic data fed back by the chemical glue in the chemical anchor bolts and planted steel bars are continuously collected at several preset time nodes by a monitoring device, and the collected real-time acoustic characteristic data are classified and processed to obtain several real-time acoustic characteristic dynamic data sets; the real-time acoustic characteristic dynamic data sets are imported into the chemical glue working condition prediction model for prediction to obtain the probability value of the chemical glue having a preset working condition event; if the probability value of the chemical glue having a preset working condition event is greater than the preset probability threshold, an early warning message is generated, and the early warning message is sent to a preset terminal. The present invention can accurately predict the occurrence time of the chemical glue working condition event and recommend the optimal maintenance time period, thereby improving the accuracy and maintenance efficiency of the working performance monitoring of the chemical anchor bolts and planted steel bars, and significantly improving the safety and reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, without paying any creative work, they can also obtain drawings of other embodiments based on these drawings.

[0051] Figure 1 This is a flow chart of the first method of the online monitoring method;

[0052] Figure 2 This is a flow chart of the second method of the online monitoring method;

[0053] Figure 3 This is a schematic diagram of the structure of the online monitoring device. DETAILED DESCRIPTION

[0054] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0055] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0056] The first aspect of the present invention discloses an online monitoring method for the working performance of chemical anchor bolts and rebar planting. Figure 1 As shown, the following steps are included:

[0057] S102: obtaining a shared monitoring logbook of chemical anchors and planted rebars through a big data network, and obtaining, based on the shared monitoring logbook, various acoustic dynamic characteristic data corresponding to the chemical glue within a preset time period before each preset working condition event occurs during the operation of the chemical anchors and planted rebars;

[0058] S104: constructing a chemical glue working condition prediction model based on various acoustic dynamic characteristic data corresponding to the chemical glue in a preset time period before each preset working condition event occurs during the working process of the chemical anchor bolt and the planted rebar;

[0059] S106: continuously collecting real-time acoustic feature data fed back by the chemical anchor bolts and the chemical glue in the rebar at a plurality of preset time points through the monitoring device, and classifying and processing the collected real-time acoustic feature data to obtain a plurality of real-time acoustic feature dynamic data sets;

[0060] S108: Import the real-time acoustic feature dynamic data set into the chemical glue working condition prediction model for prediction, and obtain the probability value of the chemical glue occurrence of a preset working condition event; if the probability value of the chemical glue occurrence of a preset working condition event is greater than a preset probability threshold, generate an early warning message, and send the early warning message to a preset terminal.

[0061] It should be noted that, first of all, historical monitoring records of chemical anchors and rebar are collected through the big data network. These records contain the behavior data of chemical glue under different working conditions. Based on historical data, the acoustic characteristic data of a period of time before a specific working condition event (such as the early, middle and late stages of chemical glue aging, or chemical glue cracks, etc.) is determined, such as the spectrum, frequency, amplitude, peak value, spectrum entropy and band energy of the sound wave. A mathematical model (i.e., a chemical glue working condition prediction model) is constructed using the above-mentioned acoustic dynamic characteristic data. This model can be used to predict the future working status of the chemical glue. The real-time acoustic characteristic data of the chemical glue is continuously collected using a monitoring device and classified into multiple dynamic data sets. The real-time acoustic characteristic data set is input into the chemical glue working condition prediction model to calculate the probability of the chemical glue experiencing a preset working condition event (such as aging or cracking). If the probability exceeds the preset threshold, the system will automatically generate an early warning message. By predicting the occurrence of potential problems in advance, measures can be taken to avoid safety accidents or structural damage caused by the failure of chemical adhesives, thereby achieving preventive maintenance; timely warnings can reduce safety hazards caused by the aging or cracking of chemical adhesives, ensuring the safety of buildings or infrastructure; by accurately monitoring the working status of chemical adhesives, maintenance plans and resources can be arranged more reasonably, avoiding unnecessary inspections or excessive maintenance. The prediction results based on a large amount of historical data and real-time data analysis can provide a scientific basis for engineering design, construction and subsequent maintenance, and promote the optimization of the decision-making process. In summary, this online monitoring method not only improves the reliability of the chemical anchor and rebar planting system, but also enhances the safety and durability of the entire structure, while also contributing to the effective utilization and management of resources.

[0062] Preferably, in a preferred embodiment of the present invention, a shared monitoring log of chemical anchor bolts and planted steel bars is obtained through a big data network, and various acoustic dynamic characteristic data corresponding to the chemical glue in a preset time period before each preset working condition event occurs in the working process of the chemical anchor bolts and planted steel bars are obtained according to the shared monitoring log, such as Figure 2 As shown, specifically:

[0063] S202: Obtaining a shared monitoring logbook of chemical anchors and planted rebars through a big data network, and obtaining various working condition events of the chemical anchors and planted rebars during operation according to the shared monitoring logbook;

[0064] S204: performing clustering processing on various working condition events of the chemical anchor bolts and the rebar planting process, generating clustering results, and extracting preset working condition events from the clustering results;

[0065] Among them, various working condition events can be clustered by using algorithms such as hierarchical clustering algorithm and fuzzy clustering algorithm;

[0066] S206: Acquiring various acoustic dynamic characteristic data corresponding to the chemical glue within a preset time period before each preset working condition event occurs during the operation of the chemical anchor bolt and the planted rebar according to the shared monitoring log;

[0067] Among them, the preset working condition events include the initial working condition, mid-term working condition and final working condition of chemical glue aging and chemical glue crack working condition; the acoustic dynamic characteristic data includes the spectrum, frequency, amplitude, peak value, spectrum entropy and frequency band energy of the sound wave.

[0068] It should be noted that historical monitoring records of chemical anchors and rebar are collected through the big data network. These records can come from different engineering projects or equipment and contain data under various working conditions. According to the shared monitoring logbook, various working condition events that occur during the operation of chemical anchors and rebar are identified and recorded. These working condition events are clustered to generate clustering results. Clustering can be performed using methods such as hierarchical clustering algorithms or fuzzy clustering algorithms, which can group according to the similarity of working condition events. Preset working condition events are extracted from the clustering results, such as the early, middle, and final working conditions of chemical glue aging and chemical glue cracking conditions. Acoustic dynamic characteristic data of chemical anchors and rebars within a preset time period before the preset working condition events occur during operation is obtained. Through the big data network and clustering algorithm, efficient monitoring and analysis of the working status of chemical anchors and rebars are achieved, the reliability and safety of the system are improved, and the robustness of the monitoring system is effectively improved.

[0069] Preferably, in a preferred embodiment of the present invention, a chemical glue working condition prediction model is constructed based on various acoustic dynamic characteristic data corresponding to the chemical glue in a preset time period before each preset working condition event occurs during the working process of the chemical anchor bolt and the planted rebar, specifically:

[0070] Arrange various acoustic dynamic characteristic data corresponding to the chemical glue in a preset time period before the occurrence of a preset working condition event in chronological order to obtain several time series data sets;

[0071] A conditional random field is introduced, each preset working condition event is defined as a random node of the conditional random field, and each time series data set is used as a conditional node of the conditional random field;

[0072] Connect each conditional node with each random node, and obtain the path length and connection direction between each conditional node and each random node;

[0073] Based on the grey correlation analysis method and combined with the path length and connection direction between each conditional node and each random node, the correlation strength between each conditional node and each random node is analyzed;

[0074] Determine the conditional association probability between the acoustic feature data in each time series data set and each preset working condition event based on the association strength between each conditional node and each random node;

[0075] Constructing a conditional association probability table based on the conditional association probability between the acoustic feature data in each time series data set and each preset working condition event;

[0076] The conditional association probability table is imported into the conditional random field for back propagation training; through training, the training parameters of the conditional random field are obtained; after the training parameters converge to preset values, the training parameters that converge to the preset values ​​are used as the final learning parameters of the conditional random field, and a chemical glue working condition prediction model is output.

[0077] It should be noted that the acoustic dynamic characteristic data of chemical glue in a preset time period before the preset working condition event are arranged in chronological order to form several time series data sets. The conditional random field (CRF) model is introduced, and the preset working condition events (such as the early, middle and final stages of chemical glue aging and crack working conditions) are defined as random nodes. Each time series data set is defined as a conditional node, that is, the acoustic dynamic characteristic data is used as a conditional node. Each conditional node (time series data set) is connected to each random node (preset working condition event). The path length and connection direction between each conditional node and the random node are obtained. The grey correlation analysis method is used to analyze the correlation strength between each conditional node and the random node in combination with the path length and connection direction. The conditional correlation probability between the acoustic characteristic data in each time series data set and the preset working condition event is determined based on the correlation strength. A conditional correlation probability table is constructed to record the correlation probability between each conditional node and the random node. The conditional correlation probability table is imported into the conditional random field model for backpropagation training. Through training, the training parameters of the conditional random field are obtained. The training parameters are gradually adjusted until they converge to the preset values. The converged training parameters serve as the final learning parameters of the conditional random field (CRF), which outputs a chemical adhesive operating condition prediction model. In summary, the CRF model and grey correlation analysis method achieve high-precision predictions of chemical adhesive operating conditions, improving system reliability and safety. Furthermore, the constructed chemical adhesive operating condition prediction model can monitor chemical adhesive status changes in real time and issue early warnings when anomalies occur.

[0078] Preferably, in a preferred embodiment of the present invention, the monitoring device continuously collects real-time acoustic feature data fed back by the chemical anchor bolts and the chemical glue in the rebar at several preset time nodes, and classifies and processes the collected real-time acoustic feature data to obtain several real-time acoustic feature dynamic data sets, specifically:

[0079] Continuously collecting real-time acoustic characteristic data fed back by chemical anchor bolts and chemical glue in rebar at several preset time points, and storing the collected real-time acoustic characteristic data in a database until the collection is completed;

[0080] Constructing a decision tree, obtaining the number of data items of the real-time acoustic feature data to be classified, determining a number of branch points according to the number of data items of the real-time acoustic feature data to be classified, and dividing a number of branch trunks in the decision tree according to the branch points;

[0081] Acquire data feature information of real-time acoustic feature data of each required classification, and assign corresponding feature attributes to each branch trunk according to the data feature information of real-time acoustic feature data of each required classification;

[0082] Acquiring real-time acoustic feature data in the database, and calculating the degree of membership between each real-time acoustic feature data in the database and the characteristic attribute assigned to each branch trunk;

[0083] Allocate each real-time acoustic feature data to the branch with the highest membership, and repeat this step until all real-time acoustic feature data in the database are allocated;

[0084] After the allocation is completed, the Euclidean distance between the real-time acoustic feature data on each branch trunk and the corresponding branch point is calculated respectively; the Euclidean distance between the real-time acoustic feature data on each branch trunk and the corresponding branch point is compared with the preset distance threshold;

[0085] If the Euclidean distance between a certain real-time acoustic feature data on a branch trunk and the corresponding branch point is greater than a preset distance threshold, the real-time acoustic feature data is marked as noise data and the noise data is removed from the corresponding branch trunk; repeat this step until the denoising process of the real-time acoustic feature data on all branch trunks is completed;

[0086] Each branch trunk is pruned to obtain several real-time acoustic feature data sets, and each real-time acoustic feature data on each real-time acoustic feature data set is sorted according to the acquisition timestamp to obtain several real-time acoustic feature dynamic data sets.

[0087] It should be noted that at several preset time nodes, a monitoring device is used to continuously collect real-time acoustic feature data of chemical anchors and chemical glue in rebar. The collected real-time acoustic feature data is stored in the database until the collection is completed. Construct a decision tree model to determine the required number of classification data items. Determine several branch points based on the required number of classification data items, and cut out several branch trunks in the decision tree. Obtain data feature information of each required classification of real-time acoustic feature data. Assign corresponding feature attributes to each branch trunk based on the data feature information. Obtain real-time acoustic feature data from the database, and calculate the degree of membership between each real-time acoustic feature data and the feature attributes assigned to each branch trunk. Assign each real-time acoustic feature data to the branch trunk with the highest degree of membership. Repeat this step until all data are assigned.

[0088] Then, the Euclidean distance between the real-time acoustic feature data and the corresponding branch point on each branch trunk is calculated respectively. The Euclidean distance between the real-time acoustic feature data and the corresponding branch point on each branch trunk is compared with the preset distance threshold. If the Euclidean distance between a certain real-time acoustic feature data and the corresponding branch point on a branch trunk is greater than the preset distance threshold, the data is marked as noise data and removed from the corresponding branch trunk. Repeat this step until the denoising process is completed on all branch trunks. By calculating the degree of membership and the Euclidean distance, noise data can be effectively identified and eliminated, thereby improving data quality; denoising makes subsequent analysis more reliable and reduces the possibility of misjudgment.

[0089] Each branch trunk is trimmed to generate several real-time acoustic feature datasets. The real-time acoustic feature data in each real-time acoustic feature dataset is sorted according to the acquisition timestamp to generate several real-time acoustic feature dynamic datasets. This trimming and sorting process generates real-time acoustic feature dynamic datasets, facilitating subsequent time series analysis and trend prediction. These dynamic datasets can be used in real-time monitoring and early warning systems, improving their response speed and accuracy. High-quality real-time acoustic feature datasets provide a reliable basis for chemical glue condition assessment.

[0090] In summary, this method realizes efficient monitoring and analysis of the status of chemical glue in chemical anchor bolts and rebar through real-time data acquisition, decision tree classification, denoising processing, and dynamic data set generation, thereby improving the reliability and safety of the system.

[0091] Preferably, in a preferred embodiment of the present invention, the real-time acoustic feature dynamic data set is imported into the chemical glue working condition prediction model for prediction to obtain a probability value of a preset working condition event of the chemical glue; if the probability value of the preset working condition event of the chemical glue is greater than a preset probability threshold, an early warning message is generated, specifically:

[0092] Importing the real-time acoustic feature dynamic data set into the chemical glue working condition prediction model to perform prediction and obtain prediction results;

[0093] Obtaining a probability value of a preset working condition event occurring in the chemical glue of the chemical anchor bolt and the planted rebar after a preset time based on the prediction result;

[0094] Compare the probability value of the chemical anchor bolt and the rebar undergoing a preset working condition event after the preset time with the preset probability threshold;

[0095] If the probability value of the chemical anchor bolt and the rebar causing the preset working condition event is greater than the preset probability threshold after the preset time, an early warning message is generated;

[0096] If the probability value of the chemical anchor bolt and the rebar causing the preset working condition event is not greater than the preset probability threshold after the preset time, no warning information will be generated.

[0097] It should be noted that the real-time acoustic signature dynamic dataset is imported into the chemical adhesive operating condition prediction model for prediction. The prediction process is based on historical data and current real-time data. The model calculates the probability of the chemical adhesive undergoing a preset operating condition event within a certain period of time. Based on the prediction results, the probability of the chemical anchor and rebar undergoing the preset operating condition event after a preset time is obtained. This probability value is compared with a preset probability threshold. The preset probability threshold is a pre-set threshold used to determine whether to generate an early warning message. If the probability value of the chemical anchor and rebar undergoing the preset operating condition event after a preset time is greater than the preset probability threshold, an early warning message is generated. If the probability value is not greater than the preset probability threshold, no early warning message is generated. The prediction model can predict future conditions based on current data and provide timely early warning information. This early warning information can notify relevant personnel to take preventive maintenance measures in advance to avoid safety accidents or structural damage caused by chemical adhesive failure. Preventive maintenance can extend the service life of chemical anchors and rebar, improve the safety of buildings or infrastructure, and reduce the possibility of accidents.

[0098] The following steps are also included:

[0099] If the probability value of the chemical glue in the chemical anchor bolt and the planted rebar experiencing a preset working condition event after the preset time is greater than a preset probability threshold, then the time node of the chemical glue in the chemical anchor bolt and the planted rebar experiencing the preset working condition event is obtained according to the prediction result;

[0100] Determine several maintenance time periods based on the time nodes of preset working condition events of chemical glue, and obtain the predicted meteorological data information of chemical anchor bolts and rebar planting areas in each maintenance time period based on meteorological software;

[0101] Calculate the attention score between the predicted meteorological data information and the preset meteorological data for each maintenance time period based on the local sensitive attention mechanism; and sort the attention scores between the predicted meteorological data information and the preset meteorological data for each maintenance time period to obtain a sorting result;

[0102] A maximum attention score is obtained according to the ranking result, and a maintenance time period corresponding to the maximum attention score is obtained, and the maintenance time period corresponding to the maximum attention score is sent to a preset terminal as a recommended maintenance time period.

[0103] It should be noted that if the probability of a preset operating condition event occurring in the chemical anchors and planted rebar after a preset time is greater than a preset probability threshold, the specific time point at which the preset operating condition event will occur is determined based on the prediction results. Based on the time point at which the preset operating condition event occurs, several maintenance time periods are determined. Using meteorological software, forecasted meteorological data for the area where the chemical anchors and planted rebar are located during each maintenance time period is obtained. This meteorological data includes factors such as temperature, humidity, wind speed, and rainfall, which can impact the feasibility and safety of maintenance work. A local sensitive attention mechanism is used to calculate the attention score between the forecasted meteorological data and the preset meteorological data for each maintenance time period. The local sensitive attention mechanism can identify which meteorological conditions are most favorable or unfavorable for maintenance work. The attention scores between the forecasted meteorological data and the preset meteorological data for each maintenance time period are sorted to obtain a sorted result. Based on the sorted result, the maximum attention score is obtained, and the maintenance time period corresponding to the maximum attention score is found. The maintenance time period corresponding to the maximum attention score is used as the recommended maintenance time period. The recommended maintenance time period is sent to a pre-set terminal for reference and action by relevant personnel. By predicting the time nodes when preset working conditions of chemical adhesives occur, maintenance work can be planned in advance to avoid safety accidents or structural damage caused by chemical adhesive failure; comprehensive consideration of meteorological data information can ensure that maintenance work is carried out under the most suitable meteorological conditions, thereby improving the feasibility and success rate of maintenance work.

[0104] In addition, the monitoring method may further comprise the following steps:

[0105] Acquire a real-time dynamic data set of acoustic characteristics fed back by the chemical glue in the chemical anchor bolts and the rebar, and construct a real-time state model diagram of the chemical glue based on the real-time dynamic data set of acoustic characteristics;

[0106] Performing feature extraction processing on the real-time state model graph to obtain defect feature information of the real-time state model graph, and obtaining a volume value of the defect in the real-time state model graph based on the defect feature information; wherein the defect feature information includes length, width, depth, and position information of the crack region and length, width, depth, and position information of the aging region;

[0107] Ratio processing is performed on the volume value of the defect in the real-time state model diagram and the total volume value of the real-time state model diagram to obtain the defect ratio of the chemical glue; the defect ratio is compared with a first preset threshold and a second preset threshold; wherein the first preset threshold is greater than the second preset threshold;

[0108] If the defect ratio is greater than a first preset threshold, a warning message is generated and sent to a preset terminal; if the defect ratio is not greater than a second preset threshold, no warning message is generated;

[0109] If the defect ratio is less than a first preset threshold and greater than a second preset threshold, then continuing to obtain a second real-time state model map of the chemical glue after a preset time period; and performing registration processing on the real-time state model map and the second real-time state model map based on an iterative closest point algorithm;

[0110] After the registration is completed, the overlapping position area and the non-overlapping position area of ​​the defect at the same position of the real-time state model image and the second real-time state model image are obtained, and the expansion speed of the defect in the chemical adhesive is calculated based on the overlapping position area and the non-overlapping position area of ​​the defect at the same position;

[0111] If the expansion speed of the defect in the chemical glue is greater than the preset expansion speed, an early warning message is generated and sent to a preset terminal; if the expansion speed of the defect in the chemical glue is not greater than the preset expansion speed, no early warning message is generated.

[0112] It should be noted that a dynamic dataset is formed by collecting acoustic characteristics (such as sound frequency and intensity) generated by the chemical adhesive during actual use. This data reflects the changes in the physical properties of the chemical adhesive under different conditions. Based on this collected acoustic characteristic data, the system can construct a three-dimensional model of the current state of the chemical adhesive. This model not only shows the overall structure of the chemical adhesive but also contains information about possible defects within it. By performing feature extraction on the real-time state model, the system can identify defects in the chemical adhesive, such as cracks and aging areas, and calculate their specific parameters (such as length, width, depth, and location). Based on the extracted defect characteristics, the system further calculates the volume of each defect, which is crucial for assessing defect severity. The defect ratio is calculated by comparing the total volume of all defects in the chemical adhesive to the total volume of the chemical adhesive. This metric is used to quantify the overall health of the chemical adhesive. When the defect ratio exceeds a first preset threshold, the system generates an alert and notifies relevant personnel. If the defect ratio is below a second preset threshold, the chemical adhesive is considered safe and no alert is required. If the defect rate falls between the first and second preset thresholds, the system reassesses the adhesive's status after a certain period of time, checking for new defects or the expansion of existing defects. While the defect rate remains between the two thresholds, the system recollects data at regular intervals and constructs a new state model. By comparing the changes in defects at the same location in the new and old models, the system calculates the defect growth rate. If the defect growth rate is too rapid, the early warning mechanism is triggered again. Real-time monitoring of adhesive state changes allows for early action to prevent safety incidents caused by adhesive failure. Based on defect growth rate monitoring, maintenance or replacement can be more accurately determined, improving work efficiency and reducing unnecessary downtime. The detailed defect information and growth rate data provided by the system provide valuable data support for subsequent improvements to material performance and optimized construction processes. In summary, advanced acoustic feature data acquisition and analysis technology enables comprehensive monitoring of the adhesive state in chemical anchors and rebar, effectively enhancing the safety and reliability of engineering structures.

[0113] The second aspect of the present invention discloses an online monitoring device for the working performance of chemical anchor bolts and planted steel bars, which is applied to any of the above-mentioned online monitoring methods for the working performance of chemical anchor bolts and planted steel bars, such as Figure 3 Shown, including:

[0114] The monitoring device body 8001 is embedded in the concrete along with the chemical anchor bolts and rebar during the initial construction. An external wire is provided through the concrete to connect to external instruments.

[0115] Acoustic sensor module 8002, used to collect acoustic signals around chemical anchors and rebars;

[0116] The signal acquisition and processing module 8003 amplifies, filters, digitizes, and processes the signals collected by the acoustic sensor and converts them into data that can be analyzed;

[0117] The data analysis and processing module 8004 analyzes the collected acoustic characteristic data, extracts characteristic parameters related to chemical adhesive aging and cracks, and performs data modeling and early warning judgment;

[0118] The data storage and transmission module 8005 stores monitoring data and warning information, and transmits them to the monitoring center or other equipment.

[0119] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0120] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0121] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0122] Those skilled in the art will appreciate that all or part of the steps of the above-mentioned method embodiments may be implemented by hardware associated with program instructions, and the aforementioned program may be stored in a computer-readable storage medium. When the program is executed, the program executes the steps of the above-mentioned method embodiments. The aforementioned storage medium includes various media that can store program codes, such as mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0123] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0124] The above are only specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be covered by the scope of protection of the present invention.

Claims

1. A method for online monitoring of the working performance of chemical anchors and rebars, characterized in that: The following steps are involved: Acquiring a shared monitoring logbook of chemical anchors and planted rebars through a big data network, and obtaining, based on the shared monitoring logbook, various acoustic dynamic characteristic data corresponding to the chemical glue within a preset time period before each preset working condition event occurs during the operation of the chemical anchors and planted rebars; A chemical glue working condition prediction model is constructed based on various acoustic dynamic characteristic data corresponding to the chemical glue in a preset time period before each preset working condition event occurs during the working process of the chemical anchor bolts and planted rebars; The monitoring device continuously collects real-time acoustic characteristic data fed back by chemical anchor bolts and chemical glue in planted rebar at several preset time nodes, and classifies and processes the collected real-time acoustic characteristic data to obtain several real-time acoustic characteristic dynamic data sets; Importing the real-time acoustic feature dynamic data set into the chemical glue working condition prediction model to perform prediction, and obtaining the probability value of the chemical glue occurrence of a preset working condition event; If the probability value of the preset working condition event of the chemical glue is greater than the preset probability threshold, an early warning message is generated and sent to a preset terminal; Among them, a chemical glue working condition prediction model is constructed based on the various acoustic dynamic characteristic data corresponding to the chemical glue in the preset time period before each preset working condition event occurs during the working process of the chemical anchor bolts and planted rebars. Specifically: Arrange various acoustic dynamic characteristic data corresponding to the chemical glue in a preset time period before the occurrence of a preset working condition event in chronological order to obtain several time series data sets; A conditional random field is introduced, each preset working condition event is defined as a random node of the conditional random field, and each time series data set is used as a conditional node of the conditional random field; Connect each conditional node with each random node, and obtain the path length and connection direction between each conditional node and each random node; Based on the grey correlation analysis method and combined with the path length and connection direction between each conditional node and each random node, the correlation strength between each conditional node and each random node is analyzed; Determine the conditional association probability between the acoustic feature data in each time series data set and each preset working condition event based on the association strength between each conditional node and each random node; Constructing a conditional association probability table based on the conditional association probability between the acoustic feature data in each time series data set and each preset working condition event; The conditional association probability table is imported into the conditional random field for back propagation training; through training, the training parameters of the conditional random field are obtained; after the training parameters converge to preset values, the training parameters that converge to the preset values ​​are used as the final learning parameters of the conditional random field, and a chemical glue working condition prediction model is output.

2. The method for online monitoring of the working performance of chemical anchors and rebars according to claim 1, characterized in that: The shared monitoring logbook of chemical anchor bolts and planted rebars is obtained through the big data network. Based on the shared monitoring logbook, various acoustic dynamic characteristic data corresponding to the chemical glue in a preset time period before each preset working condition event occurs during the operation of the chemical anchor bolts and planted rebars are obtained, specifically: Obtaining a shared monitoring logbook of chemical anchors and planted rebars through a big data network, and obtaining various working condition events of the chemical anchors and planted rebars during operation based on the shared monitoring logbook; Clustering is performed on various working condition events of chemical anchor bolts and rebar planting during operation, generating clustering results, and extracting preset working condition events from the clustering results; Acquiring, according to the shared monitoring logbook, various acoustic dynamic characteristic data corresponding to the chemical glue within a preset time period before each preset working condition event occurs during the operation of the chemical anchor bolts and the planted rebar; Among them, the preset working condition events include the initial working condition, mid-term working condition and final working condition of chemical glue aging and chemical glue crack working condition; the acoustic dynamic characteristic data includes the spectrum, frequency, amplitude, peak value, spectrum entropy and frequency band energy of the sound wave.

3. The method for online monitoring of the working performance of chemical anchors and rebars according to claim 1 is characterized in that: The monitoring device continuously collects real-time acoustic feature data fed back by chemical anchor bolts and chemical glue in rebar at several preset time nodes, and classifies and processes the collected real-time acoustic feature data to obtain several real-time acoustic feature dynamic data sets, specifically: Continuously collect real-time acoustic characteristic data fed back by chemical anchor bolts and chemical glue in rebar at several preset time points, and store the collected real-time acoustic characteristic data in a database; Until the collection is completed; Constructing a decision tree, obtaining the number of data items of the real-time acoustic feature data to be classified, determining a number of branch points according to the number of data items of the real-time acoustic feature data to be classified, and dividing a number of branch trunks in the decision tree according to the branch points; Acquire data feature information of real-time acoustic feature data of each required classification, and assign corresponding feature attributes to each branch trunk according to the data feature information of real-time acoustic feature data of each required classification; Acquiring real-time acoustic feature data in the database, and calculating the degree of membership between each real-time acoustic feature data in the database and the characteristic attribute assigned to each branch trunk; Allocate each real-time acoustic feature data to the branch with the highest membership, and repeat this step until all real-time acoustic feature data in the database are allocated; After the allocation is completed, the Euclidean distance between the real-time acoustic feature data on each branch trunk and the corresponding branch point is calculated respectively; the Euclidean distance between the real-time acoustic feature data on each branch trunk and the corresponding branch point is compared with the preset distance threshold; If the Euclidean distance between a certain real-time acoustic feature data on a branch trunk and the corresponding branch point is greater than a preset distance threshold, the real-time acoustic feature data is marked as noise data and the noise data is removed from the corresponding branch trunk; Repeat this step until the denoising process of the real-time acoustic feature data on all branches and trunks is completed; Each branch trunk is pruned to obtain several real-time acoustic feature data sets, and each real-time acoustic feature data on each real-time acoustic feature data set is sorted according to the acquisition timestamp to obtain several real-time acoustic feature dynamic data sets.

4. The method for online monitoring of the working performance of chemical anchors and rebars according to claim 1, characterized in that: The real-time acoustic feature dynamic data set is imported into the chemical glue working condition prediction model for prediction, and a probability value of a preset working condition event of the chemical glue is obtained; if the probability value of the preset working condition event of the chemical glue is greater than a preset probability threshold, an early warning message is generated, specifically: Importing the real-time acoustic feature dynamic data set into the chemical glue working condition prediction model to perform prediction and obtain prediction results; Obtaining a probability value of a preset working condition event occurring in the chemical glue of the chemical anchor bolt and the planted rebar after a preset time based on the prediction result; Compare the probability value of the chemical anchor bolt and the rebar undergoing a preset working condition event after the preset time with the preset probability threshold; If the probability value of the chemical anchor bolt and the rebar causing the preset working condition event is greater than the preset probability threshold after the preset time, an early warning message is generated; If the probability value of the chemical anchor bolt and the rebar causing the preset working condition event is not greater than the preset probability threshold after the preset time, no warning information will be generated.

5. The method for online monitoring of the working performance of chemical anchors and rebars according to claim 4 is characterized in that: The following steps are also included: If the probability value of the chemical glue in the chemical anchor bolt and the planted rebar experiencing a preset working condition event after the preset time is greater than a preset probability threshold, then the time node of the chemical glue in the chemical anchor bolt and the planted rebar experiencing the preset working condition event is obtained according to the prediction result; Determine several maintenance time periods based on the time nodes of preset working condition events of chemical glue, and obtain the predicted meteorological data information of chemical anchor bolts and rebar planting areas in each maintenance time period based on meteorological software; Calculate the attention score between the predicted meteorological data information and the preset meteorological data for each maintenance time period based on the local sensitive attention mechanism; and sort the attention scores between the predicted meteorological data information and the preset meteorological data for each maintenance time period to obtain a sorting result; A maximum attention score is obtained according to the ranking result, and a maintenance time period corresponding to the maximum attention score is obtained, and the maintenance time period corresponding to the maximum attention score is sent to a preset terminal as a recommended maintenance time period.

6. An online monitoring device for the working performance of chemical anchors and planted rebars, applied to the online monitoring method for the working performance of chemical anchors and planted rebars according to any one of claims 1 to 5, characterized in that: include: The main body of the monitoring device is buried in the concrete along with the chemical anchor bolts and rebar during the initial construction. An external wire is provided through the concrete to connect with external instruments. Acoustic sensor module, used to collect acoustic signals around chemical anchors and rebars; The signal acquisition and processing module amplifies, filters, and digitizes the signals collected by the acoustic sensor and converts them into data that can be analyzed; The data analysis and processing module analyzes the collected acoustic feature data, extracts characteristic parameters related to chemical adhesive aging and cracks, and performs data modeling and early warning judgment; The data storage and transmission module stores monitoring data and warning information and transmits them to the monitoring center.

Images