A tunnel automation monitoring system and method based on Internet of Things

Abstract

The present invention discloses an Internet of Things-based tunnel automation monitoring system and method, which belongs to the technical field of safety monitoring. The present invention collects dangerous accidents that occurred in tunnels in history, extracts the characteristics of each dangerous accident, and classifies the dangerous accidents in the tunnel; searches for dangerous data reflecting each dangerous accident, and calculates the danger threshold of each dangerous accident according to the dangerous data in history; judges the safety hazard of each dangerous accident in real time according to the danger threshold and issues an early warning; after judging the real-time safety hazard in the tunnel and obtaining early warning information, when there are early warning information of different categories, the correlation analysis of different types of safety hazards corresponding to different early warning information is performed to judge whether there is a mutual influence relationship; when it is judged that the safety hazards corresponding to different early warning information have a mutual influence relationship, the safety hazards of each early warning information are comprehensively analyzed, and a corresponding safety hazard treatment plan is formulated.

Description

Technical Field

[0001] The present invention relates to the technical field of safety monitoring, and in particular to an Internet of Things-based tunnel automation monitoring system and method. Background Art

[0002] As people pay more and more attention to traffic safety and working environment safety, the demand for tunnel safety monitoring is also gradually increasing. The construction and operation of traffic tunnels, water conservancy tunnels, subway tunnels, etc. require reliable safety monitoring technology to ensure the safety of passers-by and staff. With the continuous development of science and technology, the progress of sensor technology, data transmission technology, data processing technology and other aspects has provided more possibilities for tunnel safety monitoring technology. The miniaturization, intelligence and multifunctionality of sensors make it possible to monitor various parameters in the tunnel in real time, such as temperature, humidity, gas concentration, vibration, etc. Some tunnel accidents and disasters in history have also played a certain role in promoting the development of tunnel safety monitoring technology. It makes people aware of the fragility and hidden dangers of tunnel structure; therefore, real-time monitoring and investigation of safety hazards in tunnels is the key to ensure safety; however, there are many dangerous accidents in tunnels, and different dangerous accidents may have mutual influence relationships, which makes the handling of dangerous accidents more complicated; and it takes a long time for manual handling of dangerous accidents in tunnels, so in order to quickly solve dangerous accidents, it is necessary to set up intelligent automatic handling devices; and when intelligent devices have mutual influence on different dangerous accidents, it is crucial to formulate reasonable handling measures. Summary of the invention

[0003] The purpose of the present invention is to provide a tunnel automation monitoring system and method based on the Internet of Things to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0005] A tunnel automation monitoring method based on the Internet of Things, the method comprising the following steps:

[0006] S100, collecting dangerous accidents that have occurred in tunnels in the past, analyzing each dangerous accident, extracting the characteristics of each dangerous accident, and classifying the dangerous accidents in the tunnel;

[0007] Furthermore, the specific steps for classifying dangerous accidents in tunnels are as follows:

[0008] S101, collect dangerous accidents in the history of tunnels, extract the environmental data in the tunnel before and after the dangerous accidents in the history, and assume that the environmental data in the tunnel before the dangerous accidents in the history are {S 1 , S 2 , S 3 ...Sn},S 1 , S 2 , S 3 ...S n It is represented by the 1st, 2nd, 3rd...nth environmental data in the tunnel before the dangerous accident occurs. The environmental data in the tunnel after the dangerous accident occurs in history is {S' 1 , S' 2 , S' 3 ...S' n}, S' 1 , S' 2 , S' 3 ...S' n Indicates the 1st, 2nd, 3rd...nth environmental data in the tunnel after a dangerous accident occurred in history, where n is a positive integer;

[0009] S102. After collecting the environmental data before and after the dangerous accident in history, calculate the change of each environmental data before and after the dangerous accident, and extract the maximum value. The formula is:

[0010] S_c=Max{S'-S}

[0011] In the formula, S_c represents the maximum difference between the environmental data before and after the dangerous data occurred in history, Max represents the maximum value among the differences of n kinds of environmental data, S represents the environmental data before the dangerous accident occurred in history, and S' represents the environmental data after the dangerous accident occurred in history;

[0012] S103, calculating the environmental data differences of all dangerous accidents that occurred in history and extracting the maximum value, taking the environmental data type corresponding to the maximum value of each environmental data difference as the characteristic data of the dangerous accident, and classifying the dangerous accidents with the same characteristic data into the same dangerous accident type according to the characteristic data of each dangerous accident in history. The types of dangerous accidents in the tunnel after classification are {T 1 , T 2 , T 3 ...T m}, T 1 , T 2 , T 3 ...T m Represents the 1st, 2nd, 3rd... dangerous accidents existing in the tunnel, and m is a positive integer.

[0013] S200, analyzing each dangerous accident in the tunnel in history, searching for dangerous data reflecting each dangerous accident, and calculating a dangerous threshold value of each dangerous accident according to the dangerous data in history;

[0014] Furthermore, the specific steps of calculating the danger threshold of each dangerous accident according to the danger data of dangerous accidents in history are as follows:

[0015] S201, collect h records of each dangerous accident in history, extract the environmental data when each dangerous accident occurred in history, and set the type of the extracted environmental data as {H 1 , H 2 , H 3 ...H j}, H 1 , H 2 , H 3 ...H j It represents the 1st, 2nd, 3rd, ... jth environmental data collected when each dangerous accident occurs, where j is a positive integer;

[0016] S202, draw a histogram using the values ​​of j kinds of environmental data before and after each dangerous accident in history, compare the environmental data histograms before and after the dangerous accident in history, extract the environmental data types with different environmental data values, compare the j record histograms of the same dangerous accident and extract the environmental data types with different values, and obtain j sets of environmental data types; compare the j types of environmental data, select the environmental data types that exist in the j sets of environmental data types as the dangerous data of each dangerous accident, and construct the dangerous data set of each dangerous accident as {H_w 1 、H_w 2 、H_w 3 ...H_w k}, H_w 1 、H_w 2 、H_w 3 ...H_w k It is represented by the 1st, 2nd, 3rd, ... kth hazard data of each selected dangerous accident, where k is a positive integer;

[0017] S203, collecting the danger data value W_z of each dangerous accident in history, and calculating the danger threshold of each dangerous accident based on the historical danger data, the formula is:

[0018]

[0019] W_c=W_z i -W

[0020]

[0021] In the formula, Th represents the danger threshold of each dangerous accident, h represents the number of each dangerous accident in the collected history, W represents the average value of all types of dangerous data for each dangerous accident; k represents the number of types of dangerous data for each dangerous accident, W_c represents the compensation value of dangerous data in each dangerous accident, W_z represents the dangerous data value of each dangerous accident, and i ranges from 1 to k;

[0022] S204, calculate the danger thresholds of m types of dangerous accidents in history, and obtain the danger threshold of each dangerous accident as {Th 1 ,Th 2 ,Th 3 ...Th m}, Th 1 ,Th 2 ,Th 3 ...Th m It is expressed as the calculated danger thresholds of the 1st, 2nd, 3rd...mth dangerous accidents.

[0023] Since the numerical ranges of the danger data in different dangerous accidents are different, some danger data values ​​are in the single digit, while some danger data values ​​are in the hundreds digit, etc., when calculating the average, the large danger data value will have a larger weight, which cannot truly reflect the change of the danger data. Therefore, the compensation value of each danger data is calculated based on the average value. After collecting the real-time danger data, the compensation value is used to perform weight processing on each danger data to ensure the effectiveness of the judgment;

[0024] S300, collecting the danger data of each dangerous accident in the tunnel in real time, judging the safety hazard of each dangerous accident in real time according to the danger threshold and issuing an early warning;

[0025] Furthermore, the specific steps of judging the potential safety hazard of each dangerous accident in real time and issuing an early warning according to the danger threshold are as follows:

[0026] S301, collect the danger data value {W_s 1 、W_s 2 、W_s 3 ...W_s k}, W_s 1 、W_s 2 、W_s 3 ...W_s k The real-time collected hazard data of the 1st, 2nd, 3rd, ... kth dangerous accidents are represented. The real-time collected hazard data are weighted using the compensation value of each hazard data calculated in S203. The formula is:

[0027] W_d=W_s-W_c

[0028] In the formula, \(W_d\) represents the real-time dangerous data value after weight processing, \(W_c\) represents the compensation value of each type of dangerous data, and \(W_s\) represents the value of each type of dangerous data collected in real time;

[0029] S302. Use the dangerous data after weight processing to calculate the average value of each real-time dangerous accident and determine whether there are potential safety hazards for each type of dangerous accident. The formula is:

[0030]

[0031] In the formula, \(W_a\) represents the average value of the real-time dangerous data after weight processing, \(W_d\) represents the real-time dangerous data value after weight processing, and \(k\) is the number of types of dangerous data collected in real time;

[0032] When the dangerous data that has changed the most after a dangerous accident occurs in history is increasing, when \(W_a\geq Th\), it is determined that there are potential safety hazards for the corresponding dangerous accident, and a safety hazard warning signal is issued; when \(W_a < Th\), it is determined that there are no potential safety hazards for the corresponding dangerous accident;

[0033] When the dangerous data that has changed the most after a dangerous accident occurs in history is decreasing, when \(W_a>Th\), it is determined that there are no potential safety hazards for the corresponding dangerous accident, and a safety hazard warning signal is issued; when \(W_a\leq Th\), it is determined that there are potential safety hazards for the corresponding dangerous accident.

[0034] S400. When the real-time safety hazards in the tunnel are determined and warning information is obtained, when there are different types of warning information, perform a correlation analysis on the different types of potential safety hazards corresponding to the different warning information to determine whether there is an interaction relationship;

[0035] Furthermore, the specific steps for determining whether there is an interaction relationship are as follows:

[0036] S401. When it is determined that there are potential safety hazards in the tunnel, extract the types of potential safety hazards that have potential safety hazards and issue warnings as \(\{T_y\) 1 、\(T_y\) 2 、\(T_y\) 3 ...\(T_y\) g \}, \(T_y\) 1 、\(T_y\) 2 、\(T_y\) 3 ...\(T_y\) g represents the 1st, 2nd, 3rd... gth types of potential safety hazards obtained through judgment, where \(g\) is a positive integer; the types of potential safety hazards are the same as the types of dangerous accidents, and extract the dangerous data sets of the g types of potential safety hazards that issue warnings;

[0037] S402, judging the g types of dangerous data sets extracted, screening out dangerous data sets with the same type of dangerous data in at least two sets, assuming that a total of A dangerous data sets are screened out, using the bar chart drawn in S202, extracting the dangerous data values ​​of the same type of dangerous data before and after the corresponding dangerous accident occurred in history, and calculating the difference, the formula is:

[0038] W_b=Wr-Wr'

[0039] In the formula, W_b represents the difference between the dangerous data before and after the warning dangerous accident history, Wr represents the dangerous data value after the warning dangerous accident history, and Wr' represents the dangerous data value before the warning dangerous accident history;

[0040] S403, calculating the difference of the hazard data before and after the corresponding hazard accident occurred in the history of the same type of hazard data, and comparing the calculated difference of the hazard data set with the same type of hazard data, when the signs of W_b are opposite, it is judged that the safety hazards corresponding to the hazard data set have a mutual influence relationship, and when the signs of W_b are the same, it is judged that the safety hazards corresponding to the hazard data set do not have a mutual influence relationship;

[0041] S404, after judging all types of safety hazards for which warnings are issued, the types of safety hazards that have mutual impact are integrated into an accident impact set {T_x 1 、T_x 2 、T_x 3 ...T_x v}, T_x 1 、T_x 2 、T_x 3 ...T_x v It indicates that there are 1st, 2nd, 3rd...vth safety hazards that affect each other, where v is a positive integer; different accident impact sets are constructed according to different types of the same hazardous data.

[0042] There are various dangerous accidents in tunnels, and different dangerous accidents may affect each other. When multiple dangerous accidents occur at the same time, handling one dangerous accident will make another dangerous accident more serious. For example, fire and gas disasters require reducing oxygen supply to extinguish fires, while gas disasters require ventilation to increase air flow. There is a mutual influence between the two. Therefore, a comprehensive analysis of such dangerous accidents occurring at the same time and handling each dangerous accident according to the degree of different dangerous accidents can minimize the losses.

[0043] S500: When it is determined that the safety hazards corresponding to different early warning information have a mutual impact relationship, a comprehensive analysis is performed on the safety hazards of each early warning information, and a corresponding safety hazard handling plan is formulated.

[0044] Furthermore, the specific steps for formulating corresponding safety hazard handling plans are as follows:

[0045] S501, when the safety hazards warned do not have a mutual influence relationship, select measures taken when each dangerous accident occurs in history, so that the danger data corresponding to the safety hazards tend to approach the danger threshold, and finally stop processing after crossing the danger threshold, so that the tunnel can be used normally;

[0046] S502: When the potential safety hazards warned have a mutual impact relationship, the absolute value of the difference between the average value of the real-time danger data of the potential safety hazards having a mutual impact relationship and the danger threshold is calculated, and the formula is:

[0047] cc=|W_a-Th|

[0048] In the formula, cc is the absolute value of the difference between the average value of real-time danger data and the danger threshold, W_a represents the average value of real-time danger data, and Th represents the danger threshold; each safety hazard in the accident impact set is calculated to obtain v cc values, and the v cc values ​​are sorted from large to small, and the corresponding safety hazards are processed according to the sorting of the cc values.

[0049] An Internet of Things-based tunnel automation monitoring system, the tunnel automation monitoring system includes a data collection module, a threshold calculation module, an early warning judgment module, an impact relationship judgment module and a plan formulation module;

[0050] The data collection module is used to collect environmental data when dangerous accidents occurred in tunnels in the past and classify the dangerous accidents;

[0051] The threshold calculation module is used to analyze the environmental data when dangerous accidents occurred in history, extract the danger data of each dangerous accident, and calculate the danger threshold of each dangerous accident using the danger data in history;

[0052] The early warning judgment module is used to collect the danger data in the tunnel in real time, and after weighting each kind of danger data, calculate the average value of the real-time danger data, and after comparing it with the danger threshold, judge whether there is a safety hazard in the real-time tunnel and issue an early warning;

[0053] The influence relationship judgment module is used to find the difference in the history of the same hazard data after judging that there is a safety hazard in the tunnel and issuing an early warning, and to judge whether each safety hazard has a mutual influence relationship;

[0054] The solution formulation module is used to formulate different safety hazard handling solutions according to whether each safety hazard obtained by judgment has a mutual influence relationship.

[0055] The data collection module includes a historical data collection unit and a dangerous accident classification unit;

[0056] The historical data collection unit is used to collect environmental data of dangerous accidents that occurred in the tunnel in the past;

[0057] The dangerous accident classification unit is used to extract the characteristics of each dangerous accident based on the environmental data when the dangerous accident occurred in history, and classify the dangerous accident according to the characteristics;

[0058] The threshold value calculation module includes a danger data search unit, a threshold value calculation unit and a compensation value calculation unit;

[0059] The danger data search unit is used to analyze the environmental data of dangerous accidents that occurred in the tunnel in the past, draw a bar graph, and search for the danger data of each dangerous accident;

[0060] The threshold value calculation unit is used to calculate the danger threshold value of each dangerous accident according to the searched danger data;

[0061] The compensation value calculation unit is used to calculate the compensation value of each risk data weight according to the average value of the risk data in history when calculating the risk threshold.

[0062] The impact relationship judgment module includes a safety hazard screening unit and a dangerous data difference judgment unit;

[0063] The potential safety hazard screening unit is used to compare the danger data in the potential safety hazard warnings and screen the potential safety hazard with the same danger data;

[0064] The risk data difference judgment unit is used to calculate the difference of the same risk data in the screened safety hazards, judge the sign of the difference, and judge whether the safety hazards have a mutual influence relationship based on the similarities and differences of the difference signs.

[0065] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0066] 1. The present invention classifies dangerous accidents in tunnels according to their characteristics, and can adopt different treatment plans for different dangerous accidents, so as to more quickly handle the dangerous accidents and reduce losses.

[0067] 2. When calculating the danger threshold based on historical danger data, the present invention obtains the compensation value of each danger data by calculating the average value. When collecting danger data in real time for safety hazard judgment, each danger data is weighted according to the compensation value, thereby reducing the influence of the proportion of data size between danger data, reflecting the safety situation in the real-time tunnel to a greater extent, and reducing the possibility of misjudgment.

[0068] 3. The present invention determines whether there is a mutual influence relationship between each safety hazard existing in the tunnel. When there is a mutual influence relationship, the safety hazards are sorted by using the difference between real-time hazard data and the hazard threshold. The existing safety hazards are processed according to the sorting, so as to solve the safety hazards existing in the tunnel to the greatest extent and reduce the possibility of dangerous accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0070] Figure 1 It is a module schematic diagram of a tunnel automation monitoring system based on the Internet of Things of the present invention;

[0071] Figure 2 It is a schematic diagram of the steps of an automatic tunnel monitoring method based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0072] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0073] See also Figure 1-Figure 2 , the present invention provides a technical solution:

[0074] A tunnel automation monitoring method based on the Internet of Things, the method comprising the following steps:

[0075] S100, collecting dangerous accidents that have occurred in tunnels in the past, analyzing each dangerous accident, extracting the characteristics of each dangerous accident, and classifying the dangerous accidents in the tunnel;

[0076] The specific steps for classifying dangerous accidents in tunnels are:

[0077] S101, collect dangerous accidents in the history of tunnels, extract the environmental data in the tunnel before and after the dangerous accidents in the history, and assume that the environmental data in the tunnel before the dangerous accidents in the history are {S 1 , S 2 , S 3 ...S n},S 1 , S 2 , S 3 ...S nIt is represented by the 1st, 2nd, 3rd...nth environmental data in the tunnel before the dangerous accident occurs. The environmental data in the tunnel after the dangerous accident occurs in history is {S' 1 , S' 2 , S' 3 ...S' n}, S' 1 , S' 2 , S' 3 ...S' n Indicates the 1st, 2nd, 3rd...nth environmental data in the tunnel after a dangerous accident occurred in history, where n is a positive integer;

[0078] S102. After collecting the environmental data before and after the dangerous accident in history, calculate the change of each environmental data before and after the dangerous accident, and extract the maximum value. The formula is:

[0079] S_c=Max{|S'-S|}

[0080] In the formula, S_c represents the maximum difference between the environmental data before and after the dangerous data occurred in history, Max represents the maximum value among the differences of n kinds of environmental data, S represents the environmental data before the dangerous accident occurred in history, and S' represents the environmental data after the dangerous accident occurred in history;

[0081] S103, calculating the environmental data differences of all dangerous accidents that occurred in history and extracting the maximum value, taking the environmental data type corresponding to the maximum value of each environmental data difference as the characteristic data of the dangerous accident, and classifying the dangerous accidents with the same characteristic data into the same dangerous accident type according to the characteristic data of each dangerous accident in history. The types of dangerous accidents in the tunnel after classification are {T 1 , T 2 , T 3 ...T m}, T 1 , T 2 , T 3 ...T m Represents the 1st, 2nd, 3rd... dangerous accidents existing in the tunnel, and m is a positive integer.

[0082] S200, analyzing each dangerous accident in the tunnel in history, searching for dangerous data reflecting each dangerous accident, and calculating a dangerous threshold value of each dangerous accident according to the dangerous data in history;

[0083] The specific steps for calculating the danger threshold of each dangerous accident based on the danger data of dangerous accidents in history are as follows:

[0084] S201, collect h records of each dangerous accident in history, extract the environmental data when each dangerous accident occurred in history, and set the type of the extracted environmental data as {H 1 , H 2 , H 3 ...H j},

[0085] H 1 , H 2 , H 3 ...H j It represents the 1st, 2nd, 3rd, ... jth environmental data collected when each dangerous accident occurs, where j is a positive integer;

[0086] S202, draw a histogram using the values ​​of j kinds of environmental data before and after each dangerous accident in history, compare the environmental data histograms before and after the dangerous accident in history, extract the environmental data types with different environmental data values, compare the j record histograms of the same dangerous accident and extract the environmental data types with different values, and obtain j sets of environmental data types; compare the j types of environmental data, select the environmental data types that exist in the j sets of environmental data types as the dangerous data of each dangerous accident, and construct the dangerous data set of each dangerous accident as {H_w 1 、H_w 2 、H_w 3 ...H_w k}, H_w 1 、H_w 2 、H_w 3 ...H_w k It is represented by the 1st, 2nd, 3rd, ... kth hazard data of each selected dangerous accident, where k is a positive integer;

[0087] S203, collecting the danger data value W_z of each dangerous accident in history, and calculating the danger threshold of each dangerous accident based on the historical danger data, the formula is:

[0088]

[0089] W_c=W_z i -W

[0090]

[0091] In the formula, Th represents the danger threshold of each dangerous accident, h represents the number of each dangerous accident in the collected history, W represents the average value of all types of dangerous data for each dangerous accident; k represents the number of types of dangerous data for each dangerous accident, W_c represents the compensation value of dangerous data in each dangerous accident, W_z represents the dangerous data value of each dangerous accident, and i ranges from 1 to k;

[0092] S204, calculate the danger thresholds of m types of dangerous accidents in history, and obtain the danger threshold of each dangerous accident as {Th 1 ,Th 2 ,Th 3 ...Th m}, Th 1 ,Th 2 ,Th 3 ...Th m It is expressed as the calculated danger thresholds of the 1st, 2nd, 3rd...mth dangerous accidents.

[0093] Since the numerical ranges of the danger data in different dangerous accidents are different, some danger data values ​​are in the single digit, while some danger data values ​​are in the hundreds digit, etc., when calculating the average, the large danger data value will have a larger weight, which cannot truly reflect the change of the danger data. Therefore, the compensation value of each danger data is calculated based on the average value. After collecting the real-time danger data, the compensation value is used to perform weight processing on each danger data to ensure the effectiveness of the judgment;

[0094] S300, collecting the danger data of each dangerous accident in the tunnel in real time, judging the safety hazard of each dangerous accident in real time according to the danger threshold and issuing an early warning;

[0095] The specific steps for judging the potential safety hazards of each dangerous accident in real time and issuing early warnings according to the danger threshold are as follows:

[0096] S301, collect the danger data value {W_s 1 、W_s 2 、W_s 3 ...W_s k}, W_s 1 、W_s 2 、W_s 3 ...W_s k The real-time collected hazard data of the 1st, 2nd, 3rd, ... kth dangerous accidents are represented. The real-time collected hazard data are weighted using the compensation value of each hazard data calculated in S203. The formula is:

[0097] W_d=W_s-W_c

[0098] In the formula, \(W_d\) represents the real-time dangerous data value after weight processing, \(W_c\) represents the compensation value of each type of dangerous data, and \(W_s\) represents the value of each type of dangerous data collected in real time;

[0099] S302. Using the dangerous data after weight processing, calculate the average value of each type of real-time dangerous accident and determine whether there are potential safety hazards for each type of dangerous accident. The formula is:

[0100]

[0101] In the formula, \(W_a\) represents the average value of the real-time dangerous data after weight processing, \(W_d\) represents the real-time dangerous data value after weight processing, and \(k\) is the number of types of dangerous data collected in real time;

[0102] When the dangerous data with the largest change after a dangerous accident occurs in history is increasing, when \(W_a\geq Th\), it is determined that there are potential safety hazards for the corresponding dangerous accident, and a safety hazard warning signal is issued; when \(W_a < Th\), it is determined that there are no potential safety hazards for the corresponding dangerous accident;

[0103] When the dangerous data with the largest change after a dangerous accident occurs in history is decreasing, when \(W_a>Th\), it is determined that there are no potential safety hazards for the corresponding dangerous accident, and a safety hazard warning signal is issued; when \(W_a\leq Th\), it is determined that there are potential safety hazards for the corresponding dangerous accident.

[0104] S400. When the real-time safety hazards in the tunnel are determined and warning information is obtained, when there are different types of warning information, perform a correlation analysis on the different types of potential safety hazards corresponding to the different warning information to determine whether there is an interaction relationship;

[0105] The specific steps for determining whether there is an interaction relationship are:

[0106] S401. After it is determined that there are potential safety hazards in the tunnel, extract the types of potential safety hazards that have potential safety hazards and issue warnings as \(\{T_y\) 1 、\(T_y\) 2 、\(T_y\) 3 ... \(T_y\) g \}, \(T_y\) 1 、\(T_y\) 2 、\(T_y\) 3 ... \(T_y\) g represents the 1st, 2nd, 3rd... gth types of potential safety hazards obtained through judgment, where \(g\) is a positive integer; the types of potential safety hazards are the same as the types of dangerous accidents, and extract the dangerous data sets of the g types of potential safety hazards that issue warnings;

[0107] S402, judging the g types of dangerous data sets extracted, screening out dangerous data sets with the same type of dangerous data in at least two sets, assuming that a total of A dangerous data sets are screened out, using the bar chart drawn in S202, extracting the dangerous data values ​​of the same type of dangerous data before and after the corresponding dangerous accident occurred in history, and calculating the difference, the formula is:

[0108] W_b=Wr-Wr'

[0109] In the formula, W_b represents the difference between the dangerous data before and after the warning dangerous accident history, Wr represents the dangerous data value after the warning dangerous accident history, and Wr' represents the dangerous data value before the warning dangerous accident history;

[0110] S403, calculating the difference of the hazard data before and after the corresponding hazard accident occurred in the history of the same type of hazard data, and comparing the calculated difference of the hazard data set with the same type of hazard data, when the signs of W_b are opposite, it is judged that the safety hazards corresponding to the hazard data set have a mutual influence relationship, and when the signs of W_b are the same, it is judged that the safety hazards corresponding to the hazard data set do not have a mutual influence relationship;

[0111] S404, after judging all types of safety hazards for which warnings are issued, the types of safety hazards that have mutual impact are integrated into an accident impact set {T_x 1 、T_x 2 、T_x 3 ...T_x v}, T_x 1 、T_x 2 、T_x 3 ...T_x v It indicates that there are 1st, 2nd, 3rd...vth safety hazards that affect each other, where v is a positive integer; different accident impact sets are constructed according to different types of the same hazardous data.

[0112] There are various dangerous accidents in tunnels, and different dangerous accidents may affect each other. When multiple dangerous accidents occur at the same time, handling one dangerous accident will make another dangerous accident more serious. For example, fire and gas disasters require reducing oxygen supply to extinguish fires, while gas disasters require ventilation to increase air flow. There is a mutual influence between the two. Therefore, a comprehensive analysis of such dangerous accidents occurring at the same time and handling each dangerous accident according to the degree of different dangerous accidents can minimize the losses.

[0113] S500: When it is determined that the safety hazards corresponding to different early warning information have a mutual impact relationship, a comprehensive analysis is performed on the safety hazards of each early warning information, and a corresponding safety hazard handling plan is formulated.

[0114] The specific steps for formulating corresponding safety hazard treatment plans are as follows:

[0115] S501, when the safety hazards warned do not have a mutual influence relationship, select measures taken when each dangerous accident occurs in history, so that the danger data corresponding to the safety hazards tend to approach the danger threshold, and finally stop processing after crossing the danger threshold, so that the tunnel can be used normally;

[0116] S502: When the potential safety hazards warned have a mutual impact relationship, the absolute value of the difference between the average value of the real-time danger data of the potential safety hazards having a mutual impact relationship and the danger threshold is calculated, and the formula is:

[0117] cc=W_a-Th

[0118] In the formula, cc is the absolute value of the difference between the average value of real-time danger data and the danger threshold, W_a represents the average value of real-time danger data, and Th represents the danger threshold; each safety hazard in the accident impact set is calculated to obtain v cc values, and the v cc values ​​are sorted from large to small, and the corresponding safety hazards are processed according to the sorting of the cc values.

[0119] An Internet of Things-based tunnel automation monitoring system, the tunnel automation monitoring system includes a data collection module, a threshold calculation module, an early warning judgment module, an impact relationship judgment module and a plan formulation module;

[0120] The data collection module is used to collect environmental data when dangerous accidents occurred in tunnels in the past and classify the dangerous accidents;

[0121] The threshold calculation module is used to analyze the environmental data when dangerous accidents occurred in history, extract the danger data of each dangerous accident, and calculate the danger threshold of each dangerous accident using the danger data in history;

[0122] The early warning judgment module is used to collect the danger data in the tunnel in real time, and after weighting each kind of danger data, calculate the average value of the real-time danger data, and after comparing it with the danger threshold, judge whether there is a safety hazard in the real-time tunnel and issue an early warning;

[0123] The influence relationship judgment module is used to find the difference in the history of the same hazard data after judging that there is a safety hazard in the tunnel and issuing an early warning, and to judge whether each safety hazard has a mutual influence relationship;

[0124] The solution formulation module is used to formulate different safety hazard handling solutions according to whether each safety hazard obtained by judgment has a mutual influence relationship.

[0125] The data collection module includes a historical data collection unit and a dangerous accident classification unit;

[0126] The historical data collection unit is used to collect environmental data of dangerous accidents that occurred in the tunnel in the past;

[0127] The dangerous accident classification unit is used to extract the characteristics of each dangerous accident based on the environmental data when the dangerous accident occurred in history, and classify the dangerous accident according to the characteristics;

[0128] The threshold value calculation module includes a danger data search unit, a threshold value calculation unit and a compensation value calculation unit;

[0129] The danger data search unit is used to analyze the environmental data of dangerous accidents that occurred in the tunnel in the past, draw a bar graph, and search for the danger data of each dangerous accident;

[0130] The threshold value calculation unit is used to calculate the danger threshold value of each dangerous accident according to the searched danger data;

[0131] The compensation value calculation unit is used to calculate the compensation value of each risk data weight according to the average value of the risk data in history when calculating the risk threshold.

[0132] The impact relationship judgment module includes a safety hazard screening unit and a dangerous data difference judgment unit;

[0133] The potential safety hazard screening unit is used to compare the danger data in the potential safety hazard warnings and screen the potential safety hazard with the same danger data;

[0134] The risk data difference judgment unit is used to calculate the difference of the same risk data in the screened safety hazards, judge the sign of the difference, and judge whether the safety hazards have a mutual influence relationship based on the similarities and differences of the difference signs.

[0135] Example 1

[0136] The dangerous accidents that have occurred in the history of a tunnel are collected, and the environmental data of each dangerous accident that has occurred is extracted. After calculation, the dangerous accidents are classified into three types: fire, gas disaster and structural abnormality.

[0137] By drawing a bar chart to search for the dangerous data of three dangerous accidents, we can find that the dangerous data of fire is (temperature, air flow rate, humidity), the dangerous data of gas disaster is (air flow rate, harmful gas density), and the dangerous data of structural abnormality is (humidity, tunnel structure density);

[0138] Collect the danger data of each dangerous accident in history and calculate the danger threshold of the corresponding dangerous accident. The formula is:

[0139]

[0140] By calculating the historical danger data, the danger thresholds of the three types of dangerous accidents are 30, 1, and 1050 respectively;

[0141] Calculate the compensation value of each dangerous data according to the formula, W_c=W_z i -W obtains the compensation values ​​for fire: temperature -10, air velocity -30, humidity 20; gas disaster: air velocity -0.95, harmful gas density 0.95; structural anomaly: humidity -982, tunnel structure density 982;

[0142] The dangerous data in the tunnel are collected in real time, and the average value is calculated after weight processing. The real-time collected temperature is 25 degrees, the air flow rate is 0.12m / s, the humidity is 70%, the harmful gas density is 3%, and the tunnel structure density is 2000kg / m 3 , to determine whether there is a fire safety hazard. After weight processing, the temperature is 35, the air flow rate is 30.12, and the humidity is 50%. The calculated average value is 38.37. It is determined that there is a fire safety hazard in the real-time tunnel. Then, the gas disaster and structural abnormality are judged, and it is found that there is a gas disaster safety hazard, but there is no structural abnormality safety hazard;

[0143] After determining the hidden dangers in the real-time tunnel, the hidden dangers with the same dangerous data are extracted. The same dangerous data in fire and gas disasters is air velocity. The difference of air velocity before and after the fire and gas disasters in the calculation history is 3.2 and -0.03 respectively. After determining that the signs of the difference of the same dangerous data are not the same, it is determined that there is a mutual influence relationship between fire and gas disasters.

[0144] According to the historical treatment methods for fire and gas disasters, water extinguishing and increased ventilation were used respectively. The mutual influence relationship between the two dangerous accidents is as follows: the air flow rate will decrease after the fire is extinguished, while increased ventilation will accelerate the spread of fire. The calculated differences between the real-time danger data and the danger threshold are 8.37 and 0.56 respectively; it is judged that the handling priority of fire is higher, and fire dangerous accidents are handled first.

[0145] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0146] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A tunnel automation monitoring method based on the Internet of Things, characterized in that: The method comprises the following steps: S100, collecting dangerous accidents that have occurred in tunnels in the past, analyzing each dangerous accident, extracting the characteristics of each dangerous accident, and classifying the dangerous accidents in the tunnel; S200, analyzing each dangerous accident in the tunnel in history, searching for dangerous data reflecting each dangerous accident, and calculating a dangerous threshold value of each dangerous accident according to the dangerous data in history; S300, collecting the danger data of each dangerous accident in the tunnel in real time, judging the safety hazard of each dangerous accident in real time according to the danger threshold and issuing an early warning; S400, after determining the real-time safety hazard in the tunnel and obtaining the warning information, when there are different types of warning information, performing correlation analysis on different types of safety hazards corresponding to different warning information to determine whether they affect each other; The specific steps to determine whether there is a mutual influence relationship are: S401, when it is determined that there are safety hazards in the tunnel, extract the types of safety hazards that have safety hazards and issue warnings {T_y1, T_y2, T_y3...T_y g }, T_y1, T_y2, T_y3...T_y g It is represented by the 1st, 2nd, 3rd, ... gth safety hazards that are determined to exist, where g is a positive integer; the types of safety hazards are the same as the types of dangerous accidents, and the dangerous data set of g safety hazards for which warnings are issued is extracted; S402: The extracted g types of dangerous data sets are judged, and dangerous data sets with the same type of dangerous data in at least two sets are screened out. Assuming that a total of A dangerous data sets are screened out, the bar chart drawn in S202 is used to extract the dangerous data values ​​of the same type of dangerous data before and after the corresponding dangerous accident occurs in history, and the difference is calculated. The formula is: W_b=Wr-Wr' In the formula, W_b represents the difference between the dangerous data before and after the warning dangerous accident history, Wr represents the dangerous data value after the warning dangerous accident history, and Wr' represents the dangerous data value before the warning dangerous accident history; S403, calculating the difference of the hazard data before and after the corresponding hazard accident occurred in the history of the same type of hazard data, and comparing the calculated difference of the hazard data set with the same type of hazard data, when the signs of W_b are opposite, it is judged that the safety hazards corresponding to the hazard data set have a mutual influence relationship, and when the signs of W_b are the same, it is judged that the safety hazards corresponding to the hazard data set do not have a mutual influence relationship; S404, after judging all types of safety hazards for which warnings are issued, the types of safety hazards that have mutual impact are integrated into an accident impact set {T_x1, T_x2, T_x3...T_x v }, T_x1, T_x2, T_x3...T_x v Indicates that there are 1st, 2nd, 3rd...vth safety hazards that affect each other, where v is a positive integer; different accident impact sets are constructed according to different types of the same hazardous data; S500: When it is determined that the safety hazards corresponding to different early warning information have a mutual impact relationship, a comprehensive analysis is performed on the safety hazards of each early warning information, and a corresponding safety hazard handling plan is formulated.

2. The method for automatic tunnel monitoring based on the Internet of Things according to claim 1, characterized in that: The specific steps of classifying dangerous accidents in the tunnel in S100 are: S101, collect dangerous accidents in the history of tunnels, extract the environmental data in the tunnel before and after the dangerous accidents in the history, and assume that the environmental data in the tunnel before the dangerous accidents in the history are {S1, S2, S3...S n }, S1, S2, S3...S n It is represented by the 1st, 2nd, 3rd...nth environmental data in the tunnel before the dangerous accident occurs. The environmental data in the tunnel after the dangerous accident occurs in history are {S'1, S'2, S'3...S' n }, S'1, S'2, S'3...S' n Indicates the 1st, 2nd, 3rd...nth environmental data in the tunnel after a dangerous accident occurred in history, where n is a positive integer; S102. After collecting the environmental data before and after the dangerous accident in history, calculate the change of each environmental data before and after the dangerous accident, and extract the maximum value. The formula is: S_c=Max{S'-S} In the formula, S_c represents the maximum difference between the environmental data before and after the dangerous data occurred in history, Max represents the maximum value among the differences of n kinds of environmental data, S represents the environmental data before the dangerous accident occurred in history, and S' represents the environmental data after the dangerous accident occurred in history; S103, calculating the environmental data differences of all dangerous accidents that occurred in history and extracting the maximum value, taking the environmental data type corresponding to the maximum value of each environmental data difference as the characteristic data of the dangerous accident, and classifying the dangerous accidents with the same characteristic data into the same dangerous accident type according to the characteristic data of each dangerous accident in history, and the types of dangerous accidents in the tunnel after classification are {T1, T2, T3...T m }, T1, T2, T3...T m Represents the 1st, 2nd, 3rd... dangerous accidents existing in the tunnel, and m is a positive integer.

3. The method for automatic tunnel monitoring based on the Internet of Things according to claim 1, characterized in that: The specific steps of calculating the danger threshold of each dangerous accident according to the danger data of dangerous accidents in history in S200 are: S201, collect h records of each dangerous accident in history, extract the environmental data when each dangerous accident occurred in history, and set the types of the extracted environmental data to be {H1, H2, H3...H j }, H1, H2, H3...H j It represents the 1st, 2nd, 3rd, ... jth environmental data collected when each dangerous accident occurs, where j is a positive integer; S202, draw a bar graph using the values ​​of j kinds of environmental data before and after each dangerous accident in history, compare the environmental data bar graphs before and after the dangerous accident in history, extract the environmental data types with different environmental data values, compare the j record bar graphs of the same dangerous accident and extract the environmental data types with different values, and obtain j sets of environmental data types; compare the j types of environmental data, select the environmental data types that exist in the j sets of environmental data types as the dangerous data of each dangerous accident, and construct the dangerous data set of each dangerous accident as {H_w1, H_w2, H_w3...H_w k }, H_w1, H_w2, H_w3...H_w k It is represented by the 1st, 2nd, 3rd, ... kth hazard data of each selected dangerous accident, where k is a positive integer; S203, collecting the danger data value W_z of each dangerous accident in history, and calculating the danger threshold of each dangerous accident based on the historical danger data, the formula is: W_c=W_z i -W In the formula, Th represents the danger threshold for each dangerous accident, h represents the number of each dangerous accident in the collected history, and W represents the average value of all types of dangerous data for each dangerous accident; k represents the number of types of dangerous data for each dangerous accident, W_c represents the compensation value of the dangerous data for each dangerous accident, W_z represents the value of the dangerous data for each dangerous accident, and i ranges from 1 to k; S204, calculating the danger thresholds of m types of dangerous accidents in history, and obtaining the danger threshold of each dangerous accident as {Th1, Th2, Th3...Th m }, Th1, Th2, Th3...Th m It is expressed as the calculated danger thresholds of the 1st, 2nd, 3rd...mth dangerous accidents.

4. The method for automatic tunnel monitoring based on the Internet of Things according to claim 1, characterized in that: The specific steps for judging potential safety hazards for each dangerous accident in real time according to the danger threshold in S300 and issuing early warnings are as follows: S301. Collect the value of the dangerous data for each dangerous accident in real time {W_s1, W_s2, W_s3...W_s k }, W_s1, W_s2, W_s3...W_s k The real-time collected hazard data of the 1st, 2nd, 3rd, ... kth dangerous accidents are represented. The real-time collected hazard data are weighted using the compensation value of each hazard data calculated in S203. The formula is: W_d = W_s - W_c In the formula, W_d represents the real-time dangerous data value after weight processing, W_c represents the compensation value of each dangerous data, and W_s represents the real-time collected value of each dangerous data; S302. Use the dangerous data after weight processing to calculate the average value of each dangerous accident in real time and judge whether there are potential safety hazards for each dangerous accident. The formula is: In the formula, W_a represents the average value of the real-time dangerous data after weight processing, W_d represents the real-time dangerous data value after weight processing, and k is the number of types of dangerous data collected in real time; When the dangerous data with the largest change after a dangerous accident occurs in the history increases, when W_a ≥ Th, it is judged that there are potential safety hazards for the corresponding dangerous accident, and a potential safety hazard warning signal is issued; when W_a < Th, it is judged that there are no potential safety hazards for the corresponding dangerous accident; When the dangerous data with the largest change after a dangerous accident occurs in the history decreases, when W_a > Th, it is judged that there are no potential safety hazards for the corresponding dangerous accident, and a potential safety hazard warning signal is issued; when W_a ≤ Th, it is judged that there are potential safety hazards for the corresponding dangerous accident.

5. The method for automatic tunnel monitoring based on the Internet of Things according to claim 1, characterized in that: The specific steps for formulating corresponding potential safety hazard handling plans in S500 are as follows: S501. When the potential safety hazards in the early warning do not have an interaction relationship, select the measures taken when each dangerous accident occurred in the history to make the dangerous data corresponding to the potential safety hazard tend to approach the danger threshold, and finally stop processing after crossing the danger threshold to make the tunnel operate normally; S502. When the potential safety hazards in the early warning have an interaction relationship, calculate the absolute value of the difference between the average value of the real-time dangerous data of the potential safety hazards with an interaction relationship and the danger threshold. The formula is: cc = |W_a - Th| In the formula, cc is the absolute value of the difference between the average value of the real-time dangerous data and the danger threshold, W_a represents the average value of the real-time dangerous data, and Th represents the danger threshold; calculate for each potential safety hazard in the accident impact set to obtain v cc values, sort the v cc values from largest to smallest, and process the corresponding potential safety hazards according to the sorting of the cc values.

6. An Internet of Things-based tunnel automation monitoring system using an Internet of Things-based tunnel automation monitoring method according to any one of claims 1 to 5, characterized in that: The tunnel automatic monitoring system includes a data collection module, a threshold calculation module, an early warning judgment module, an impact relationship judgment module, and a plan formulation module; The data collection module is used to collect the environmental data when dangerous accidents occur in the tunnel in the history and classify the dangerous accidents; The threshold calculation module is used to analyze the environmental data when dangerous accidents occurred in history, extract the danger data of each dangerous accident, and calculate the danger threshold of each dangerous accident using the danger data in history; The early warning judgment module is used to collect the danger data in the tunnel in real time, and after weighting each kind of danger data, calculate the average value of the real-time danger data, and after comparing it with the danger threshold, judge whether there is a safety hazard in the real-time tunnel and issue an early warning; The influence relationship judgment module is used to find the difference in the history of the same hazard data after judging that there is a safety hazard in the tunnel and issuing an early warning, and to judge whether each safety hazard has a mutual influence relationship; The solution formulation module is used to formulate different safety hazard handling solutions according to whether each safety hazard obtained by judgment has a mutual influence relationship.

7. The tunnel automation monitoring system based on the Internet of Things according to claim 6 is characterized in that: The data collection module includes a historical data collection unit and a dangerous accident classification unit; The historical data collection unit is used to collect environmental data of dangerous accidents that occurred in the tunnel in the past; The dangerous accident classification unit is used to extract the characteristics of each dangerous accident based on the environmental data when the dangerous accidents occurred in history, and classify the dangerous accidents according to the characteristics.

8. The tunnel automation monitoring system based on the Internet of Things according to claim 6 is characterized in that: The threshold value calculation module includes a danger data search unit, a threshold value calculation unit and a compensation value calculation unit; The danger data search unit is used to analyze the environmental data of dangerous accidents that occurred in the tunnel in the past, draw a bar graph, and search for the danger data of each dangerous accident; The threshold value calculation unit is used to calculate the danger threshold value of each dangerous accident according to the searched danger data; The compensation value calculation unit is used to calculate the compensation value of each risk data weight according to the average value of the risk data in history when calculating the risk threshold.

9. The tunnel automation monitoring system based on the Internet of Things according to claim 6 is characterized in that: The impact relationship judgment module includes a safety hazard screening unit and a danger data difference judgment unit; The potential safety hazard screening unit is used to compare the danger data in the potential safety hazard warnings and screen the potential safety hazard with the same danger data; The risk data difference judgment unit is used to calculate the difference of the same risk data in the screened safety hazards, judge the sign of the difference, and judge whether the safety hazards have a mutual influence relationship based on the similarities and differences of the difference signs.

Images