Railway tunnel maintenance monitoring control system

Abstract

The invention relates to the field of railway tunnel maintenance and monitoring system control, in particular to a railway tunnel maintenance monitoring control system which realizes intelligent risk prediction and maintenance verification by utilizing a machine learning technology. The monitoring module sends the acquired parameter data to the storage module through the data transmission module and is used for generating tunnel log file backup and transmitting the tunnel log file backup to the control center, the control center analyzes the data to generate a monitoring report, the monitoring report is transmitted to the maintenance management module, and the maintenance management module generates a maintenance plan according to the monitoring report and sends the maintenance plan to the storage module. The user interface module visualizes and displays the system module, and the alarm module gives an alarm according to a prediction result of the control center. According to the method, the naive Bayesian algorithm is adopted for fault risk prediction and maintenance result verification, so that the fault risk of the railway tunnel can be accurately predicted, and the maintenance efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of railway tunnel maintenance and monitoring system control. The monitoring and control system utilizes machine learning technology to realize intelligent risk prediction and maintenance verification, and is specifically a railway tunnel maintenance monitoring and control system. Background Art

[0002] Railway tunnels are an important part of railway transportation, and their safe, stable and efficient operation is crucial to the smooth operation of railway transportation. However, due to the complexity of tunnel structures and the variability of operating environments, railway tunnels often face various safety hazards and failure risks. Traditional railway tunnel maintenance and monitoring methods often rely on manual inspections and regular inspections, while existing monitoring and control systems have achieved automated data collection and storage, as well as real-time analysis and processing of data, so that potential problems can be discovered more promptly. Through advanced sensing and communication technologies, the monitoring and control system can obtain various parameter information in the tunnel in real time, such as temperature, humidity, deformation, vibration, etc., providing more accurate and comprehensive data support for maintenance decisions.

[0003] However, the existing technology still has some shortcomings:

[0004] 1. Traditional railway tunnel maintenance monitoring methods often rely on manual inspections and regular testing, which is not only inefficient but also difficult to accurately predict and promptly detect potential faults.

[0005] 2. The existing railway tunnel maintenance monitoring and control system does not have the function of predicting tunnel failures. The functions are not intuitive enough and can only monitor and manage, but cannot systematically realize real-time monitoring and fault prediction of tunnel structures.

[0006] 3. The tunnel conditions in the existing technology are not intuitive enough. After the fault is discovered and handled, human judgment and identification are still required, which wastes manpower and time and may lead to untimely repairs. Summary of the invention

[0007] In order to solve the above technical problems, the present invention provides a railway tunnel maintenance monitoring and control system to solve the problems in the prior art.

[0008] A railway tunnel maintenance monitoring and control system, comprising:

[0009] Monitoring module: The monitoring module is used to monitor and collect railway tunnel status parameters;

[0010] Storage module: The storage module is used to store the data collected by the monitoring module;

[0011] Control center: The control center is used to generate a monitoring report based on the railway tunnel status parameters transmitted by the monitoring module;

[0012] Maintenance management module: The maintenance management module is used to generate a maintenance plan based on the monitoring report and record the history of tunnel maintenance, including maintenance time, maintenance content and maintenance personnel;

[0013] User interface module: The user interface module is used to provide a visualization panel;

[0014] Alarm module: The alarm module is used to issue an alarm according to the monitoring report results;

[0015] The functional interaction relationship between the modules of the railway tunnel maintenance monitoring and control system is as follows:

[0016] The monitoring module sends the acquired parameter data to the data transmission module of the storage module for generating a tunnel log file backup and transmitting it to the control center. The control center analyzes the data to generate a monitoring report, which is transmitted to the maintenance management module. The maintenance management module generates a maintenance plan based on the monitoring report. The user interface module visualizes and displays the system module. The alarm module issues an alarm based on the prediction results of the control center.

[0017] Preferably, the monitoring module includes sensors installed inside the tunnel to collect the status and parameters of the railway tunnel structure, including position, temperature, humidity, vibration, wind pressure, water pressure, concentration of various substances in the air and displacement parameters;

[0018] Preferably, the storage module includes a historical maintenance record storage unit and a monitoring log storage unit;

[0019] The historical maintenance record unit is used to store the historical maintenance records and historical fault information of the railway tunnel maintenance, the historical fault information including fault conditions, fault parameters and maintenance details;

[0020] The monitoring log storage unit is used to store data collected by the monitoring module to generate a railway tunnel monitoring log.

[0021] Preferably, the control center includes a fault prediction unit, a maintenance suggestion unit and a monitoring report unit;

[0022] The fault prediction unit is used to perform fault prediction based on railway tunnel status parameters and historical fault records;

[0023] The maintenance suggestion unit obtains a maintenance suggestion report according to the prediction result of the fault prediction unit and the historical maintenance record;

[0024] The monitoring report unit is used to generate a monitoring report according to the prediction results and maintenance suggestions, and the monitoring report content includes various parameters of the railway tunnel status, fault prediction results and maintenance suggestions.

[0025] Preferably, the fault prediction unit performs fault analysis by using a naive Bayes algorithm, and the mathematical formula is as follows:

[0026] Prior probability: P(C i ), indicating fault C i Probability of occurrence in overall failure;

[0027] Conditional probability: P(X|C i ), indicating that the tunnel status characteristic parameter X is in fault C i The probability of the following occurring;

[0028] According to the Bayesian algorithm, the formula for calculating the posterior probability is:

[0029]

[0030] Among them, P(X) is the joint probability of all tunnel state characteristic parameters, and the joint probability is obtained by multiplying the conditional probabilities of each feature;

[0031] The steps of the Naive Bayes algorithm are as follows:

[0032] Firstly, the prior probability and conditional probability are calculated according to the fault characteristic data stored in the storage module; and the posterior probability of each fault category is calculated as the prediction result according to the characteristic parameters of the railway tunnel state monitored in real time.

[0033] Preferably, the maintenance management module includes a maintenance planning unit and a maintenance verification unit;

[0034] The maintenance planning unit is used to generate a maintenance plan according to the prediction results of the control center, and the maintenance plan content includes maintenance time, maintenance location, maintenance method and maintenance personnel;

[0035] The maintenance verification unit is used to send instructions to the monitoring unit after the maintenance is completed, and the monitoring unit re-collects tunnel status parameters and sends them to the control center for analysis.

[0036] Preferably, the user interface module visualizes system content, including railway tunnel status logs, monitoring reports, maintenance plans, maintenance verification results and alarm information.

[0037] Preferably, the alarm module is used to issue an alarm when the control center predicts a failure.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] 1. The present invention monitors the internal environment of the railway tunnel in real time through the monitoring module, which can timely discover potential safety hazards and failure risks, improve the safety of the railway tunnel and reduce the inspection risks of staff.

[0040] 2. The present invention adopts the Naive Bayes algorithm to predict fault risks. By learning and analyzing historical fault data, it can more accurately predict the fault type and probability of occurrence in railway tunnels, providing more accurate data support for maintenance decisions.

[0041] 3. The present invention generates a simple and clear maintenance plan through the maintenance management module, which is visualized in the user interface module for relevant staff to review. The maintenance management module verifies the maintenance results after the maintenance plan time ends, saving manpower and material resources and improving maintenance efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is the flow chart of the present invention

[0043] Figure 2 This is a flow chart of an embodiment of the present invention DETAILED DESCRIPTION

[0044] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0045] like Figure 1-2 As shown, the present invention provides a railway tunnel maintenance monitoring and control system, comprising:

[0046] Monitoring module: The monitoring module is used to monitor and collect railway tunnel status parameters;

[0047] Storage module: The storage module is used to store the data collected by the monitoring module;

[0048] Control center: The control center is used to generate a monitoring report based on the railway tunnel status parameters transmitted by the monitoring module;

[0049] Maintenance management module: The maintenance management module is used to generate a maintenance plan based on the monitoring report and record the history of tunnel maintenance, including maintenance time, maintenance content and maintenance personnel;

[0050] User interface module: The user interface module is used to provide a visualization panel;

[0051] Alarm module: The alarm module is used to issue an alarm according to the monitoring report results;

[0052] The functional interaction relationship between the modules of the railway tunnel maintenance monitoring and control system is as follows:

[0053] The monitoring module sends the acquired parameter data to the data transmission module of the storage module for generating a tunnel log file backup and transmitting it to the control center. The control center analyzes the data to generate a monitoring report, which is transmitted to the maintenance management module. The maintenance management module generates a maintenance plan based on the monitoring report. The user interface module visualizes and displays the system module. The alarm module issues an alarm based on the prediction results of the control center.

[0054] The monitoring module includes sensors installed inside the tunnel to collect the status and parameters of the railway tunnel structure, including position, temperature, humidity, vibration, wind pressure, water pressure, concentration of various substances in the air and displacement parameters;

[0055] The storage module includes a historical maintenance record storage unit and a monitoring log storage unit;

[0056] The historical maintenance record unit is used to store the historical maintenance records and historical fault information of the railway tunnel maintenance, and the historical fault information includes fault conditions, fault parameters and maintenance details;

[0057] The monitoring log storage unit is used to store the data collected by the monitoring module to generate a railway tunnel monitoring log.

[0058] The control center includes a fault prediction unit, a maintenance suggestion unit, and a monitoring and reporting unit;

[0059] The fault prediction unit is used to predict faults based on railway tunnel status parameters and historical fault records;

[0060] The maintenance suggestion unit obtains a maintenance suggestion report according to the prediction result of the fault prediction unit and the historical maintenance record;

[0061] The monitoring report unit is used to generate a monitoring report based on the prediction results and maintenance suggestions. The monitoring report includes various parameters of the railway tunnel status, fault prediction results and maintenance suggestions.

[0062] The fault prediction unit uses the naive Bayes algorithm to predict faults. The mathematical formula is as follows:

[0063] Prior probability: P(C i ), indicating fault C i Probability of occurrence in overall failure;

[0064] Conditional probability: P(X|C i ), indicating that the tunnel status characteristic parameter X is in fault C i The probability of the following occurring;

[0065] According to the Bayesian algorithm, the formula for calculating the posterior probability is:

[0066]

[0067] Among them, P(X) is the joint probability of all tunnel state characteristic parameters, which can be obtained by multiplying the conditional probabilities of each feature;

[0068] The steps of the Naive Bayes algorithm are as follows:

[0069] First, the prior probability and conditional probability are calculated based on the fault feature data stored in the storage module; for the new feature value, the posterior probability of each fault category is calculated; and the fault with the largest posterior probability is selected as the prediction result.

[0070] The maintenance management module includes a maintenance planning unit and a maintenance verification unit;

[0071] The maintenance plan unit is used to generate a maintenance plan based on the prediction results of the control center. The maintenance plan includes maintenance time, maintenance location, maintenance method and maintenance personnel;

[0072] The maintenance verification unit is used to send instructions to the monitoring unit after the maintenance is completed, and the monitoring unit re-collects tunnel status parameters and sends them to the control center for analysis.

[0073] The user interface module visualizes the system contents, including railway tunnel status logs, monitoring reports, maintenance plans, maintenance verification results and alarm information, and the alarm module is used to issue an alarm when the control center predicts a fault.

[0074] Example 1: Figure 1-2 As shown, in this embodiment, it is assumed that we have collected some tunnel fault feature data and corresponding fault types, including the following feature parameters:

[0075] Temperature: Indicates the temperature inside the tunnel, ranging from -20℃ to 50℃.

[0076] Humidity: Indicates the humidity inside the tunnel, ranging from 0% to 100%.

[0077] Water level: Indicates the water level inside the tunnel, ranging from 0 to 200 mm.

[0078] Harmful gas concentration: indicates the concentration of harmful gases inside the tunnel, ranging from 0 to 1000ppm.

[0079] We can calculate the probability of each fault type occurring in the overall faults and the corresponding conditional probability based on historical data.

[0080] Based on the log records, we get the following probability of failure in the total failure:

[0081] P(power failure)=0.3

[0082] P(water leakage)=0.2

[0083] P(structural damage) = 0.4

[0084] P(ventilation system failure) = 0.1

[0085] P(temperature|power failure),P(humidity|power failure),P(water level|power failure),P(harmful gas concentration|power failure)

[0086] P(temperature|water leakage),P(humidity|water leakage),P(water level|water leakage),P(harmful gas concentration|water leakage)

[0087] P(temperature|structural damage),P(humidity|structural damage),P(water level|structural damage),P(harmful gas concentration|structural damage)

[0088] P(temperature|ventilation system failure),P(humidity|ventilation system failure),P(water level|ventilation system failure),P(harmful gas concentration|ventilation system failure)

[0089] Now we have the following new eigenvalues:

[0090] Temperature = 25°C, humidity = 80%, water level = 100 mm, harmful gas concentration = 200 ppm

[0091] According to the steps of the Naive Bayes algorithm, we can perform fault prediction:

[0092] Compute the posterior probability for each fault class:

[0093] For power failure, calculate the posterior probability P = P (temperature | power failure) × P (humidity | power failure) × P (water level | power failure) × P (harmful gas concentration | power failure) × P (power failure)

[0094] For water leakage, calculate the posterior probability P = P (temperature | water leakage) × P (humidity | water leakage) × P (water level | water leakage) × P (harmful gas concentration | water leakage) × P (water leakage)

[0095] For structural damage, calculate the posterior probability P = P (temperature | structural damage) × P (humidity | structural damage) × P (water level | structural damage) × P (harmful gas concentration | structural damage) × P (structural damage)

[0096] For ventilation system failure, calculate the posterior probability P = P (temperature | ventilation system failure) × P (humidity | ventilation system failure) × P (water level | ventilation system failure) × P (harmful gas concentration | ventilation system failure) × P (ventilation system failure)

[0097] Select the fault with the largest posterior probability as the prediction result:

[0098] Assume that the calculated posterior probabilities are: P(power failure) = 0.1, P(water leakage) = 0.4, P(structural damage) = 0.3, P(ventilation system failure) = 0.2

[0099] In this case, the prediction result is water leakage (with the highest probability), which means that the tunnel may have a water leakage fault and corresponding maintenance should be carried out.

[0100] Through the above steps, we can predict the fault type in railway tunnel maintenance based on the new feature values ​​so as to make preparations in advance and perform rapid maintenance.

[0101] By adopting the Naive Bayes algorithm for fault prediction and through learning and analyzing historical fault data, the fault type and probability of occurrence in railway tunnels can be accurately predicted, providing more accurate data support for maintenance decisions.

[0102] Example 2: Figure 2 As shown, in Example 1, the maintenance management module generates a specific maintenance plan based on the monitoring report of the control center. When the maintenance time in the maintenance plan ends, the maintenance management center resends instructions to the monitoring module to obtain the tunnel status parameters at the maintenance location and recalculate until the fire risk probability is reduced to zero.

[0103] Compared with the existing technology, it saves manpower and material resources and improves maintenance efficiency and accuracy.

[0104] The embodiments of the present invention are provided for the purpose of illustration and description. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present invention. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A railway tunnel maintenance monitoring and control system, characterized in that: include: Monitoring module: The monitoring module is used to monitor and collect railway tunnel status parameters; Storage module: The storage module is used to store the data collected by the monitoring module; Control center: The control center is used to generate a monitoring report based on the railway tunnel status parameters transmitted by the monitoring module; Maintenance management module: The maintenance management module is used to generate a maintenance plan based on the monitoring report and record the history of tunnel maintenance, including maintenance time, maintenance content and maintenance personnel; User interface module: The user interface module is used to provide a visualization panel; Alarm module: The alarm module is used to issue an alarm according to the monitoring report results; The functional interaction relationship between the modules of the railway tunnel maintenance monitoring and control system is as follows: The monitoring module sends the acquired parameter data to the data transmission module of the storage module for generating a tunnel log file backup and transmitting it to the control center. The control center analyzes the data to generate a monitoring report, which is transmitted to the maintenance management module. The maintenance management module generates a maintenance plan based on the monitoring report. The user interface module visualizes and displays the system module. The alarm module issues an alarm based on the prediction results of the control center.

2. A railway tunnel maintenance monitoring and control system as claimed in claim 1, characterized in that: The monitoring module includes sensors installed inside the tunnel to collect the status and parameters of the railway tunnel structure, including position, temperature, humidity, vibration, wind pressure, water pressure, concentration of various air substances and displacement parameters.

3. A railway tunnel maintenance monitoring and control system as claimed in claim 1, characterized in that: The storage module includes a historical maintenance record storage unit and a monitoring log storage unit; The historical maintenance record unit is used to store the historical maintenance records and historical fault information of the railway tunnel maintenance, the historical fault information including fault conditions, fault parameters and maintenance details; The monitoring log storage unit is used to store data collected by the monitoring module to generate a railway tunnel monitoring parameter log.

4. A railway tunnel maintenance monitoring and control system as claimed in claim 3, characterized in that: The control center includes a fault prediction unit, a maintenance suggestion unit and a monitoring report unit; The fault prediction unit is used to perform fault prediction based on railway tunnel status parameters and historical fault records; The maintenance suggestion unit obtains a maintenance suggestion report according to the prediction result of the fault prediction unit and the historical maintenance record; The monitoring report unit is used to generate a monitoring report according to the prediction results and maintenance suggestions, and the monitoring report content includes various parameters of the railway tunnel status, fault prediction results and maintenance suggestions.

5. A railway tunnel maintenance monitoring and control system as claimed in claim 4, characterized in that: The fault prediction unit performs fault prediction analysis using the Naive Bayes algorithm, and the formula is as follows: Prior probability: P(C i ), P indicates fault C i Probability of occurrence in overall failure; C represents the fault, i is the index or identifier of the fault C; Conditional probability: P(X|C i ), P represents the tunnel status characteristic parameter X in the fault C i The probability of the following occurring; According to the Bayesian algorithm, the formula for calculating the posterior probability is: Among them, P(X) is the joint probability of all tunnel state characteristic parameters, and the joint probability is obtained by multiplying the conditional probabilities of each feature; The steps of the Naive Bayes algorithm are as follows: Firstly, the prior probability and conditional probability are calculated according to the fault characteristic data stored in the storage module; and the posterior probability of each fault category is calculated as the prediction result according to the characteristic parameters of the railway tunnel state monitored in real time.

6. A railway tunnel maintenance monitoring and control system as claimed in claim 1, characterized in that: The maintenance management module includes a maintenance planning unit and a maintenance verification unit; The maintenance planning unit is used to generate a maintenance plan according to the prediction results of the control center, and the maintenance plan content includes maintenance time, maintenance location, maintenance method and maintenance personnel; The maintenance verification unit is used to send instructions to the monitoring module after the maintenance is completed, and the monitoring unit re-collects tunnel status parameters and sends them to the control center for analysis.

7. A railway tunnel maintenance monitoring and control system as claimed in claim 1, characterized in that: The user interface module visualizes the system contents, including railway tunnel status logs, monitoring reports, maintenance plans, maintenance verification results and alarm information.

8. A railway tunnel maintenance monitoring and control system as claimed in claim 1, characterized in that: The alarm module is used to send out an alarm when the control center predicts a failure.

Images