Risk prevention and control platform for underground comprehensive pipe gallery

Abstract

The invention discloses a risk prevention and control platform for an underground comprehensive pipe gallery, and relates to the technical field of the Internet of Things, and the platform comprises a fixed-point monitoring module which is used for obtaining a multi-source monitoring data set through the Internet of Things; operating a risk assessment module to obtain a plurality of risk coefficients; the comprehensive risk calculation module obtains an overall risk coefficient; and the operation risk early warning module carries out pipe gallery operation risk early warning. The technical problems that in the prior art, accurate multi-source monitoring data of an underground comprehensive pipe gallery is difficult to obtain, an effective method for accurately evaluating the operation risk of each pipeline by using the monitoring data is lacked, and early warning cannot be carried out timely and accurately according to a risk evaluation result are solved. The technical effects of accurately obtaining the multi-source monitoring data of the underground comprehensive pipe gallery, accurately evaluating the operation risk of each pipeline, calculating the overall risk coefficient, realizing timely and accurate risk early warning and effectively guaranteeing safe and stable operation of the underground comprehensive pipe gallery are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of the Internet of Things, and particularly to the technical field of a risk prevention and control platform for an underground utility tunnel. Background Art

[0002] In the field of risk prevention and control of underground utility tunnels, the existing technologies mainly rely on manual inspections and simple monitoring devices. Manual inspections have problems such as low efficiency and untimely detection, and it is difficult to conduct real-time monitoring of various public pipelines in the tunnel. Simple monitoring devices can only obtain a small amount of data and cannot comprehensively reflect the operating conditions of the pipelines. These traditional methods expose many limitations when facing the complex environment and diverse pipelines in the tunnel. Due to the enclosed space and complex environment of the underground utility tunnel, and it contains various pipelines such as power, communication, water supply and drainage, traditional methods cannot accurately obtain the operating data of each pipeline, and it is difficult to accurately evaluate the operating risks of the tunnel and give timely warnings, which cannot meet the requirements for ensuring the safe and stable operation of the tunnel. Summary of the Invention

[0003] The present application provides a risk prevention and control platform for an underground utility tunnel, which is used to solve the technical problems in the prior art that it is difficult to obtain accurate multi-source monitoring data for underground utility tunnels, lack of effective methods to use the monitoring data to accurately evaluate the operating risks of each pipeline, and cannot give timely and accurate warnings according to the risk assessment results.

[0004] In view of the above problems, the present application provides a risk prevention and control platform for an underground utility tunnel.

[0005] The present application provides a risk prevention and control platform for an underground utility tunnel, and the platform includes:

[0006] A fixed-point monitoring module, which is used to use the Internet of Things to conduct fixed-point monitoring of various public pipelines in the underground utility tunnel and obtain a multi-source monitoring data set; an operating risk assessment module, which is used to conduct operating risk assessments respectively according to the multi-source monitoring data set to obtain a plurality of risk coefficients; a comprehensive risk calculation module, which is used to conduct comprehensive risk calculation based on the plurality of risk coefficients to obtain an overall risk coefficient; an operating risk warning module, which is used to give a warning of the operating risk of the tunnel if the overall risk coefficient is greater than a predetermined risk coefficient threshold.

[0007] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0008] The fixed-point monitoring module is used to utilize the Internet of Things to perform fixed-point monitoring on various public pipelines in the underground integrated pipe gallery, and obtain a multi-source monitoring data set; the operation risk assessment module is used to perform operation risk assessment respectively according to the multi-source monitoring data set to obtain a plurality of risk coefficients; the comprehensive risk calculation module is used to perform comprehensive risk calculation based on the plurality of risk coefficients to obtain an overall risk coefficient; the operation risk early warning module is used to perform pipe gallery operation risk early warning if the overall risk coefficient is greater than a predetermined risk coefficient threshold. It achieves the technical effects of accurately obtaining multi-source monitoring data of the underground integrated pipe gallery, accurately evaluating the operation risks of each pipeline and calculating the overall risk coefficient, realizing timely and accurate risk early warning, and effectively ensuring the safe and stable operation of the underground integrated pipe gallery. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0010] Figure 1 It is a schematic structural diagram of a risk prevention and control platform for an underground integrated pipe gallery provided by an embodiment of the present application.

[0011] Figure 2 It is a schematic structural diagram of a plug-in evaluation unit in a risk prevention and control platform for an underground integrated pipe gallery provided by an embodiment of the present application.

[0012] Description of reference numerals: fixed-point monitoring module 10, operation risk assessment module 20, comprehensive risk calculation module 30, operation risk early warning module 40. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0013] The present application provides a risk prevention and control platform for an underground integrated pipe gallery, which is used to solve the technical problems in the prior art that it is difficult to obtain accurate multi-source monitoring data for the underground integrated pipe gallery, lack of effective methods to accurately evaluate the operation risks of each pipeline using the monitoring data, and cannot perform early warning in a timely and accurate manner according to the risk assessment results.

[0014] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments in the present application belong to the scope of protection of the present application.

[0015] Embodiment, such as Figure 1As shown in the figure, the present application provides a risk prevention and control platform for an underground integrated pipe gallery, and the platform includes:

[0016] A fixed-point monitoring module 10, which is used to utilize the Internet of Things to perform fixed-point monitoring on various public pipelines in the underground integrated pipe gallery and obtain a multi-source monitoring data set.

[0017] In an embodiment of the present application, the underground integrated pipe gallery is a public tunnel built underground in a city for centrally laying more than two municipal pipelines such as electricity, communication, radio and television, water supply, drainage, heat, and gas. The multi-source monitoring data set is a data set obtained by performing fixed-point monitoring on various public pipelines in the underground integrated pipe gallery by using the Internet of Things.

[0018] Specifically, first, in the underground integrated pipe gallery, various types of sensors are reasonably deployed on various public pipelines such as electricity, communication, water supply pipelines, drainage pipelines, gas pipelines, and heating pipelines. These sensors have different monitoring functions, such as monitoring pressure, temperature, flow, displacement, etc. Then, the sensors start to work and collect the relevant data of the pipelines at their respective positions in real time. Subsequently, through the Internet of Things communication technology, the data collected by these sensors scattered throughout the pipe gallery are aggregated and encoded and packaged according to a certain protocol, such as the MQTT (a lightweight message transmission protocol based on the publish / subscribe mode) protocol, which has the characteristics of being lightweight, low-power, and suitable for transmitting data in an environment with unstable network, and is very suitable for the complex environment of the underground integrated pipe gallery. Finally, these data are transmitted to the data processing center, where they are unpacked and sorted to obtain a multi-source monitoring data set containing various types and multi-dimensional information, providing a comprehensive and accurate data basis for subsequent operations such as risk assessment of public pipelines in the pipe gallery.

[0019] An operation risk assessment module 20, which is used to perform operation risk assessment according to the multi-source monitoring data set respectively and obtain a plurality of risk coefficients.

[0020] In an embodiment of the present application, the plurality of risk coefficients are a series of numerical values obtained by performing operation risk assessment on various public pipelines in the underground integrated pipe gallery respectively.

[0021] Specifically, first, a public pipeline is randomly selected from various public pipelines and set as the first public pipeline. Then, a first risk assessment plug-in is constructed for the first public pipeline. Inputting the first monitoring data set obtained in real time by the first public pipeline into this plug-in can output the first risk assessment coefficient, which is added to the plurality of risk coefficients. The specific steps are described in detail in the pipeline selection unit, the plug-in evaluation unit, and the risk coefficient addition unit.

[0022] Through this series of steps, the information in multi-source monitoring data can be fully exploited, and the operation risks of each public pipeline can be accurately evaluated, obtaining multiple reliable risk coefficients, providing strong support for subsequent comprehensive risk calculation and early warning.

[0023] The comprehensive risk calculation module 30 is used to perform comprehensive risk calculation based on the multiple risk coefficients to obtain an overall risk coefficient.

[0024] In the embodiment of the present application, the comprehensive risk calculation is a process of respectively counting the failure frequency and scale of each public pipeline according to the monitoring records of the corridor operation within a preset time range, and calculating the multiple risk coefficients obtained through the operation risk assessment module 20. The overall risk coefficient is obtained through comprehensive risk calculation and is a value used to reflect the overall operation risk status of the underground integrated corridor.

[0025] Specifically, first, deep mining is performed according to the monitoring records of the corridor operation within a preset time range. Then, in-depth analysis is carried out based on the obtained multiple failure frequencies and multiple failure scale data to determine multiple weight ratios. Finally, according to the determined multiple weight ratios, comprehensive risk calculation is performed on the multiple risk coefficients obtained previously. Multiply the risk coefficient of each public pipeline by its corresponding weight ratio, and then add up all the products to finally obtain an overall risk coefficient that can comprehensively reflect the overall operation risk status of the underground integrated corridor. The specific steps are detailed in the monitoring record operation unit, weight determination unit, and risk calculation unit.

[0026] Through the above steps, the comprehensive risk of the corridor can be evaluated more precisely, providing a reliable basis for subsequent risk early warning and prevention and control.

[0027] The operation risk early warning module 40 is used to perform operation risk early warning of the corridor if the overall risk coefficient is greater than a predetermined risk coefficient threshold.

[0028] In the embodiment of the present application, the predetermined risk coefficient threshold is a value comprehensively determined according to various factors such as the corridor operation safety standard, historical failure data, the importance of various pipelines, and actual risk prevention and control requirements. The operation risk early warning of the corridor is a series of operations performed by the operation risk early warning module 40 when the overall risk coefficient is greater than the predetermined risk coefficient threshold.

[0029] Specifically, first, with the help of the Internet of Things technology, all-round and real-time fixed-point monitoring is performed on various public pipelines such as power, communication, and water supply pipelines in the underground integrated corridor to obtain a multi-source monitoring data set containing information such as pressure, temperature, and flow. These data are the basis for subsequent risk assessment and can comprehensively reflect the operation status of various pipelines in the corridor.

[0030] Next, perform an operation risk assessment for each type of public pipeline respectively. The process includes randomly selecting a type of public pipeline to construct a risk assessment plug-in, obtaining the monitoring index set of the pipeline, retrieving the historical operation logs to obtain sample data and analyzing the sample risk coefficient set, training a feedforward neural network and a series of other operations to obtain the risk coefficient corresponding to each public pipeline. These risk coefficients reflect the potential operation risks of each pipeline.

[0031] Then, perform comprehensive calculations based on the multiple risk coefficients obtained above. According to the operation monitoring records of the pipe gallery within a preset time range, count the failure frequency and scale of each type of public pipeline, and then determine the weight ratio corresponding to each risk coefficient. Then, combine the multiple risk coefficients with the weight ratio according to the corresponding calculation rules to finally obtain the overall risk coefficient that can reflect the overall operation risk status of the pipe gallery.

[0032] Finally, compare the calculated overall risk coefficient with a preset risk coefficient threshold. This threshold is comprehensively determined by those skilled in the art based on various factors such as the safety standards of the pipe gallery operation, historical data, and actual requirements. If the overall risk coefficient is greater than the preset risk coefficient threshold, the operation risk warning module 40 will immediately initiate the operation risk warning of the pipe gallery. The warning methods can include issuing audible and visual alarms, sending notifications to the terminal devices of the management personnel, etc., to ensure that relevant personnel can promptly know the risks existing in the pipe gallery, so as to quickly take corresponding measures to ensure the safe operation of the pipe gallery and its pipelines.

[0033] In a possible implementation manner, the fixed-point monitoring module 10 further includes:

[0034] The multiple types of public pipelines at least include power pipelines, communication pipelines, water supply pipelines, drainage pipelines, gas pipelines, and heating pipelines.

[0035] Specifically, through the fixed-point monitoring module 10, sensors are reasonably deployed on various types of pipelines by using Internet of Things technology. For power pipelines, sensors for monitoring parameters such as current and voltage will be installed; communication pipelines are equipped with devices for monitoring signal strength and transmission rate; water supply pipelines are provided with water pressure and water flow sensors; drainage pipelines focus on water level and flow; gas pipelines monitor gas concentration and pressure; heating pipelines monitor temperature and pressure, etc. These sensors continuously collect data to form a multi-source monitoring data set, enabling management personnel to understand the operation status of each pipeline in real time.

[0036] In a possible implementation manner, the operation risk assessment module 20 further includes:

[0037] A pipeline selection unit, configured to randomly select a type of public pipeline from the multiple types of public pipelines and set it as the first public pipeline.

[0038] A plug-in evaluation unit for constructing a first risk assessment plug-in based on the first common pipeline.

[0039] A risk coefficient adding unit for obtaining a first monitoring data set of the first common pipeline, inputting the first risk assessment plug-in, outputting a first risk assessment coefficient, and adding it to the multiple risk coefficients.

[0040] In the embodiment of the present application, the first risk assessment plug-in is obtained by acquiring a first monitoring index set of the first common pipeline, retrieving its historical operation logs with this index set as a constraint, obtaining multiple sample monitoring data sets and analyzing the sample risk coefficient set, and training a feedforward neural network with these data until convergence. The first monitoring data set is a real-time monitoring data set of the first common pipeline, containing various information on the operation status of the pipeline. The first risk assessment coefficient is a value representing the operation risk degree of the first common pipeline output by the plug-in after inputting the first monitoring data set of the first common pipeline.

[0041] Specifically, first, the pipeline selection unit randomly selects one of various common pipelines such as power pipelines, communication pipelines, water supply pipelines, drainage pipelines, gas pipelines, and heating pipelines as the first common pipeline. The random selection method can ensure that each pipeline has an equal chance of being preferentially evaluated, avoid biases caused by selecting in a fixed order, and comprehensively and evenly cover the risk assessment requirements of various pipelines.

[0042] Then, the plug-in evaluation unit starts to work. It first obtains the first monitoring index set of the first common pipeline. With these indexes as constraints, it retrieves the historical operation logs of the first common pipeline and obtains multiple sample monitoring data sets from them. By deeply analyzing the pipeline failure risks under different sample monitoring data, a sample risk coefficient set is obtained. Then, these sample monitoring data sets and sample risk coefficient sets are used to train a feedforward neural network until the network converges, thereby constructing the first risk assessment plug-in. The specific steps are described in detail in the index set monitoring unit, index set constraint unit, and evaluation plug-in obtaining unit.

[0043] Finally, the risk coefficient adding unit obtains the real-time first monitoring data set of the first common pipeline and inputs it into the constructed first risk assessment plug-in. The plug-in processes the input data based on the learned rules and outputs the first risk assessment coefficient. This coefficient represents the current operation risk degree of the first common pipeline, and then this coefficient is added to the multiple risk coefficient sets. By continuously repeating the above process from pipeline selection to risk coefficient addition, the risk assessment of all common pipelines in the pipe gallery can be carried out.

[0044] By obtaining multiple risk coefficients, it provides a detailed and accurate data basis for the subsequent comprehensive assessment of the overall risk of the pipe gallery.

[0045] In a possible implementation manner, as Figure 2 shown, the plug-in evaluation unit further includes:

[0046] An index set monitoring subunit, configured to obtain a first monitoring index set of the first common pipeline.

[0047] An index set constraint subunit, configured to retrieve the historical operation log of the first common pipeline with the first monitoring index set as a constraint, obtain a plurality of sample monitoring data sets, and analyze the pipeline failure risks under different sample monitoring data to obtain a sample risk coefficient set.

[0048] An evaluation plug-in obtaining subunit, configured to use the plurality of sample monitoring data sets and the sample risk coefficient set to train a feedforward neural network until convergence, and obtain the first risk evaluation plug-in.

[0049] In the embodiment of the present application, the first monitoring index set is a set of a series of key parameters reflecting the operation state of the first common pipeline. The sample risk coefficient set is a set of a series of risk coefficients obtained by analyzing the pipeline failure risks under different sample monitoring data after obtaining a plurality of sample monitoring data sets.

[0050] Specifically, first, the index set monitoring subunit plays a role. Taking the power pipeline as an example, it will obtain current, voltage, temperature, resistance, etc. as the first monitoring index set. These indexes are key parameters reflecting the operation state of the power pipeline. Different indexes show the working conditions of the pipeline from different dimensions, providing a comprehensive data basis for subsequent risk assessment. For other types of common pipelines, such as communication pipelines, the index set may include signal strength, bit error rate, etc.; for water supply pipelines, the indexes may involve water pressure, water flow velocity, etc.

[0051] Next, the index set constraint subunit starts to work. It takes the obtained first monitoring index set as a constraint condition and retrieves the historical operation log of the first common pipeline. Through in-depth mining of historical data, a plurality of sample monitoring data sets can be obtained. These sample data cover the operation information of the pipeline under different working conditions, and the pipeline failure risks under different sample monitoring data are carefully analyzed. For example, analyze the possibility and harm degree of the power pipeline failure under different conditions such as too high current and unstable voltage, so as to obtain the sample risk coefficient set. This step makes full use of the rules in historical data and provides a strong basis for risk assessment.

[0052] Finally, the evaluation plug-in's obtained subunit uses the multiple sample monitoring data sets and sample risk coefficient sets it acquired to train a feedforward neural network. The multiple sample monitoring data sets and sample risk coefficient sets are used as training data and input into the feedforward neural network. The neurons inside the network transmit signals according to a specific connection method. At the beginning of training, the weights and thresholds of the network are randomly initialized. During the training process, the feedforward neural network calculates based on the input sample monitoring data, outputs the predicted risk coefficient, and then compares the prediction result with the actual sample risk coefficient set. The difference between the two is calculated through a loss function. Based on this difference, the backpropagation algorithm is used to adjust the weights and thresholds of the network, continuously optimizing the network's fitting ability for the sample data. This process is repeated continuously until the difference between the network's output result and the actual sample risk coefficient reaches a minimum value, that is, the network converges. At this time, the training of the feedforward neural network is completed, and the first risk assessment plug-in that can be used to evaluate the operation risk of the first public pipeline is obtained.

[0053] Through this plug-in, the operation risk of the first public pipeline can be accurately evaluated according to the input real-time monitoring data, providing a precise evaluation tool for the risk prevention and control of the underground utility tunnel.

[0054] In a possible implementation manner, the obtained subunit of the evaluation plug-in further includes:

[0055] The training set obtaining micro-unit is used to use the multiple sample monitoring data sets and sample risk coefficient sets as training data, and divide them equally into K parts to obtain K training sets.

[0056] The evaluation model obtaining micro-unit is used to use the K training sets to respectively conduct supervised training on the feedforward neural network until convergence, obtaining K first risk assessment models.

[0057] The evaluation plug-in constructing micro-unit is used to construct the first risk assessment plug-in based on the K first risk assessment models according to ensemble learning.

[0058] In the embodiment of the present application, the first risk assessment model is a model obtained by respectively conducting supervised training on the feedforward neural network using the K training sets obtained by equally dividing the multiple sample monitoring data sets and sample risk coefficient sets into K parts until convergence.

[0059] Specifically, first, the training set obtaining micro-unit comes into play. It uses the multiple sample monitoring data sets and sample risk coefficient sets obtained based on the first public pipeline as training data. To ensure the reliability and generalization ability of model training, these data are equally divided into K parts, thereby obtaining K training sets. This operation can make full use of the data and avoid affecting the model performance due to problems such as uneven data distribution or overfitting.

[0060] Next, the evaluation model enables the micro-unit to use these K training sets to separately conduct supervised training on the feedforward neural network. During the training process, each training set is input into the feedforward neural network. The network calculates based on the input data and outputs the predicted risk assessment results. Then, the predicted results are compared with the actual sample risk coefficients in the training set, and the difference between the two is calculated through the backpropagation algorithm. Based on this difference, the weights and thresholds of the network are adjusted to continuously optimize the performance of the network. This iterative process is repeated until the network converges, and finally K first risk assessment models are obtained. Each model has learned the relationship between the sample monitoring data and the risk coefficient from different subsets of the training data and has its own advantages.

[0061] Finally, the evaluation plug-in constructs a micro-unit based on the method of ensemble learning to comprehensively combine these K first risk assessment models to build the first risk assessment plug-in. First, the K first risk assessment models are regarded as independent individuals. These models are separately trained on the feedforward neural network using different training sets and have each learned a partial relationship between the sample monitoring data and the risk coefficient. Then, according to specific ensemble strategies, such as performing weighted averaging on the output results of the K models, assigning weights based on the performance of each model during training, with better-performing models having higher weights; or using a voting method, where the K models conduct risk assessments on the same set of monitoring data, and the final risk assessment coefficient is determined based on the assessment results of the majority of the models. In this way, the advantages of the K models are combined, and finally, the first risk assessment plug-in that can more accurately and stably evaluate the operation risk of the first public pipeline is constructed.

[0062] By fusing the results of the K models, the constructed first risk assessment plug-in can more accurately evaluate the operation risk of the first public pipeline, overcome the limitations of traditional single models, and provide more reliable support for the risk prevention and control of the underground utility tunnel.

[0063] In a possible implementation manner, the comprehensive risk calculation module 30 further includes:

[0064] A monitoring record operation unit, configured to respectively count the failure frequency and scale of each type of public pipeline according to the utility tunnel operation monitoring records within a preset time range, and obtain a plurality of failure frequencies and a plurality of failure scales.

[0065] A weight determination unit, configured to analyze and determine a plurality of weight ratios based on the plurality of failure frequencies and the plurality of failure scales.

[0066] A risk calculation unit, configured to perform a comprehensive risk calculation on the plurality of risk coefficients according to the plurality of weight ratios to obtain an overall risk coefficient.

[0067] In the embodiments of the present application, the failure frequency is data obtained by separately counting the number of failures of each public pipeline according to the monitoring records of the operation of the utility tunnel within a preset time range. The failure scale is data on aspects such as the affected range and the magnitude of losses caused when each public pipeline fails, separately counted according to the monitoring records of the operation of the utility tunnel within a preset time range. The overall risk coefficient is a value obtained by performing a comprehensive risk calculation on multiple risk coefficients after determining the weight ratios based on the failure frequency and scale of each public pipeline counted according to the monitoring records of the operation of the utility tunnel within a preset time range.

[0068] Specifically, first, the monitoring record operation unit starts to work. It collects the monitoring records of the operation of the utility tunnel within a preset time range, which detail the operation conditions of various public pipelines such as power, communication, and water supply pipelines at different times. By deeply analyzing these records, the failure frequency and scale of each public pipeline are separately counted. For example, count the number of failures of the power pipeline in the past year, as well as the area range affected by each failure or the magnitude of losses caused; for the communication pipeline, count the frequency of signal interruptions and the number of users affected by the interruptions, etc., thus obtaining multiple failure frequencies and multiple failure scale data.

[0069] Next, the weight determination unit comes into play. It conducts a comprehensive analysis based on the multiple failure frequency and multiple failure scale data obtained by the monitoring record operation unit. Public pipelines with higher failure frequencies and larger scales should have higher weight ratios in the overall risk assessment because their impact on the safe operation of the utility tunnel is more significant. Through the analytic hierarchy process, the weight ratio corresponding to each public pipeline is determined, and it is ensured that the sum of the multiple weight ratios is 1, ensuring the rationality and scientific nature of the weight distribution.

[0070] First, construct a hierarchical structure model, with the overall risk of the utility tunnel as the target layer; the failure frequency and failure scale of various public pipelines such as power, communication, and water supply pipelines as the criterion layer; and each public pipeline itself as the alternative layer. Determine the relative importance of each element in the criterion layer and the alternative layer through pairwise comparison, and construct a judgment matrix. Use the eigenvalue method or other methods to calculate the maximum eigenvalue and eigenvector of the judgment matrix, and then obtain the relative weight of each element with respect to the upper-level element. After obtaining the weight of each public pipeline based on the failure frequency and scale, perform normalization processing on it to make the sum of the multiple weight ratios 1. This not only considers the impact of the failure frequency and scale of different public pipelines on the overall risk but also ensures the rationality and scientific nature of the weight distribution through rigorous mathematical calculations.

[0071] Finally, based on the multiple weight ratios obtained by the weight determination unit, the risk calculation unit comprehensively calculates the multiple risk coefficients obtained by the operation risk assessment module 20. Multiply the risk coefficient of each type of public pipeline by its corresponding weight ratio, and then sum all the products to finally obtain an overall risk coefficient that can comprehensively reflect the overall operation risk status of the underground utility tunnel. This coefficient comprehensively considers the risk situations of various public pipelines and can more accurately evaluate the tunnel risk compared with the prior art, providing a reliable basis for subsequent risk early warning and prevention and control.

[0072] In a possible implementation manner, the weight determination unit further includes:

[0073] The weight ratio is positively correlated with the failure frequency and failure scale, and the sum of the multiple weight ratios is 1.

[0074] Specifically, first start from the utility tunnel operation monitoring records. By collecting detailed records within a preset time range, respectively count the failure frequency and scale of various public pipelines such as power, communication, and water supply pipelines, which are the basic data for subsequent weight determination. For example, count how many times the power pipeline failed in the past year, and the scale data such as the size of the power outage area and the number of affected users caused by each failure; for the communication pipeline, count the number of signal interruptions and the communication range affected by each interruption.

[0075] Then, use these failure frequency and scale data for weight analysis. Since the weight ratio is positively correlated with the failure frequency and failure scale, the pipelines with more frequent failures and larger scales are more important in the overall risk assessment, and their corresponding weight ratios are larger. For example, if the gas pipeline has a higher failure frequency during the statistical period and the dangerous range and harm degree caused by each failure are wide, then its weight ratio in the comprehensive risk calculation will be relatively large.

[0076] To ensure the scientificity of weight allocation, the analytic hierarchy process (AHP) is adopted. Construct a hierarchical structure model, take the overall risk of the utility tunnel as the target layer, the failure frequency and failure scale of various public pipelines as the criterion layer, and each type of public pipeline as the scheme layer. Through expert scoring or data analysis, make pairwise comparisons of the elements in the criterion layer and the scheme layer to construct a judgment matrix. Then use a professional algorithm to calculate the maximum eigenvalue and eigenvector of the judgment matrix to obtain the relative weight of each public pipeline relative to the overall risk.

[0077] Finally, to ensure the normalization and additivity of the weights, the calculated multiple weight ratios are normalized. Through specific mathematical operations, the sum of the weight ratios of all public pipelines is made equal to 1. In this way, it not only meets the requirements of mathematical logic but also ensures that each weight ratio is within a reasonable range, accurately reflecting the relative importance of each type of public pipeline in the comprehensive risk calculation, providing a scientific basis for accurately calculating the overall risk coefficient based on multiple risk coefficients in the subsequent process.

[0078] In a possible implementation manner, the operation risk warning module 40 further includes:

[0079] If any one of the multiple risk coefficients is greater than a predetermined risk scalar, a pipeline risk warning signal corresponding to the public pipeline is generated, and pipeline operation risk warning is executed.

[0080] Specifically, first, the operation risks of various public pipelines in the utility tunnel are respectively evaluated based on the multi-source monitoring data set, and multiple risk coefficients are obtained. These risk coefficients are obtained based on the analysis of the real-time operation data of the pipelines and can reflect the current risk degree of the pipelines.

[0081] Next, each risk coefficient is compared with the predetermined risk scalar one by one. The predetermined risk scalar is a key index comprehensively determined based on various factors such as the safe operation standards of various types of public pipelines in the utility tunnel, historical failure data, and actual risk prevention and control requirements. It is an important basis for judging whether the pipeline is in a risk state.

[0082] When it is found that any one of the multiple risk coefficients is greater than the predetermined risk scalar, the warning signal generation unit will immediately generate a pipeline risk warning signal corresponding to the public pipeline. For example, if the risk coefficient of the power pipeline exceeds the predetermined risk scalar, a warning signal specifically for the power pipeline will be generated, and this signal contains key information such as the pipeline type and the risk degree.

[0083] Subsequently, the pipeline operation risk warning operation is executed. This may include various methods, such as issuing an audible and visual alarm in the monitoring center to attract the attention of the staff; sending notifications to the mobile phones, computers and other terminal devices of relevant management personnel to ensure that they can obtain risk information in a timely manner; and may also be linked with other systems, such as starting emergency lighting and closing the valves in relevant areas, so as to reduce the harm that may be brought by the risk and ensure the safe operation of the utility tunnel and its pipelines.

[0084] Through such a process, compared with the prior art, the risk problems of public pipelines in the underground utility tunnel can be discovered and processed more accurately and timely.

[0085] It should be noted that the above order of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. In addition, the specific embodiments of this specification have been described. Moreover, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0086] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

[0087] This specification and the drawings are only exemplary descriptions of the present application and are considered to have covered any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A risk prevention and control platform for an underground integrated pipe gallery, characterized in that, The risk prevention and control platform for the underground utility tunnel includes: A fixed-point monitoring module, which is used to utilize the Internet of Things to perform fixed-point monitoring on various public pipelines in the underground utility tunnel and obtain a multi-source monitoring data set; An operation risk assessment module, which is used to perform operation risk assessment respectively according to the multi-source monitoring data set and obtain multiple risk coefficients; A comprehensive risk calculation module, which is used to perform comprehensive risk calculation based on the multiple risk coefficients to obtain an overall risk coefficient; An operation risk warning module, which is used to perform a risk warning for the operation of the utility tunnel if the overall risk coefficient is greater than a predetermined risk coefficient threshold.

2. The risk prevention and control platform for the underground integrated pipe gallery according to claim 1, wherein The various public pipelines at least include power pipelines, communication pipelines, water supply pipelines, drainage pipelines, gas pipelines and heating pipelines.

3. The risk prevention and control platform for the underground integrated pipe gallery according to claim 2, characterized in that, The operation risk assessment module includes: A pipeline selection unit, which is used to randomly select a public pipeline from the various public pipelines and set it as the first public pipeline; A plug-in evaluation unit, which is used to construct a first risk assessment plug-in based on the first public pipeline; A risk coefficient adding unit, which is used to obtain the first monitoring data set of the first public pipeline, input it into the first risk assessment plug-in, output a first risk assessment coefficient, and add it to the multiple risk coefficients.

4. The risk prevention and control platform for the underground utility tunnel according to claim 3, wherein The plug-in evaluation unit includes: An index set monitoring subunit, which is used to obtain the first monitoring index set of the first public pipeline; An index set constraint subunit, which is used to retrieve the historical operation log of the first public pipeline with the first monitoring index set as a constraint, obtain multiple sample monitoring data sets, and analyze the pipeline failure risks under different sample monitoring data to obtain a sample risk coefficient set; An evaluation plug-in obtaining subunit, which is used to train a feedforward neural network until convergence by using the multiple sample monitoring data sets and the sample risk coefficient set to obtain the first risk assessment plug-in.

5. The risk prevention and control platform for an underground integrated pipe gallery according to claim 4, characterized in that, The evaluation plug-in obtaining subunit includes: A training set obtaining micro-unit, which is used to use the multiple sample monitoring data sets and the sample risk coefficient set as training data and equally divide them into K parts to obtain K training sets; An evaluation model obtaining micro-unit, which is used to perform supervised training on the feedforward neural network respectively by using the K training sets until convergence to obtain K first risk assessment models; An evaluation plug-in constructing micro-unit, which is used to construct the first risk assessment plug-in based on the K first risk assessment models according to ensemble learning.

6. The risk prevention and control platform for the underground utility tunnel according to claim 2, wherein, The comprehensive risk calculation module includes: A monitoring record operation unit, which is used to respectively count the failure frequency and scale of each public pipeline according to the operation monitoring records of the utility tunnel within a preset time range to obtain multiple failure frequencies and multiple failure scales; A weight determination unit, which is used to analyze and determine multiple weight ratios based on the multiple failure frequencies and multiple failure scales; A risk calculation unit, which is used to perform comprehensive risk calculation on the multiple risk coefficients according to the multiple weight ratios to obtain an overall risk coefficient.

7. The risk prevention and control platform for the underground utility tunnel according to claim 6, wherein The weight ratio is positively correlated with the failure frequency and the failure scale, and the sum of the multiple weight ratios is 1.

8. The risk prevention and control platform for the underground utility tunnel according to claim 1, wherein If any one of the multiple risk coefficients is greater than a predetermined risk scalar, a pipeline risk warning signal corresponding to the public pipeline is generated, and a pipeline operation risk warning is executed.

Images