Safety monitoring method and system for underground space

Abstract

The invention relates to the field of data processing, in particular to an underground space safety monitoring method and system, and the method comprises the steps: obtaining historical pressure data at a pipeline interface, extracting a corresponding data sequence at the same moment in a preset period range, and fitting a hyperplane; based on the vertical distance between the pressure data and the hyperplane, calculating a periodic index of each moment, obtaining data of a preset time period before the real-time pressure data, and calculating the importance degree of each moment in the preset time period; and according to the periodicity index and the importance degree, obtaining a weight value of the data in a preset time period, taking the weight value as a weight in a weighted average algorithm to predict the water consumption demand of the resident, and performing early warning by using a difference between a predicted value and an actual value. The real abnormal condition can be identified more accurately by comprehensively considering the importance degree and the periodicity index, false alarms caused by normal periodicity fluctuation are reduced, and the accuracy and reliability of abnormal detection are improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and more particularly to a method and system for monitoring the safety of an underground space. Background Art

[0002] In the rapidly developing urbanization process, underground space, as a valuable urban resource, has become a key focus of urban planning and management, ensuring its safety and stability. Water supply pipelines, as the core infrastructure of underground spaces, bear the heavy responsibility of providing residents with drinking water. Water supply mains are typically laid out in underground pipe corridors. Due to the cramped space and poor ventilation within these corridors, operators often conduct regular inspections and maintenance, making it difficult to monitor potential hazards in the underground pipelines in real time. If water seepage or leakage in the pipelines is not promptly addressed, it poses a potential threat to the overall stability of the underground space structure, exacerbating the risk of unsafe accidents. Therefore, it is necessary to monitor changes in underground pipeline data in real time to detect anomalies and warn of potential risks, thereby ensuring the safety of underground space structures.

[0003] A Chinese patent application, published under the publication number CN117252042A, discloses a comprehensive bearing capacity assessment system and method for urban underground spaces. The system includes a foundation bearing capacity detector equipped with a sensor monitoring unit, an edge computing gateway analysis module, and a bearing capacity assessment module. The system collects relevant environmental data and performs comparative analysis and BIM 3D modeling analysis on the collected data. If the compression modulus or liquid index exceeds a preset safety limit, a bearing capacity assessment is performed. If the limit remains within the preset safety limit, BIM 3D modeling analysis of changes in the building's underground environment is performed.

[0004] The application document uses BIM 3D modeling and analysis of environmental data to assist personnel in promptly identifying local environmental changes and potential safety risks caused by construction. This provides a basis for construction personnel to optimize the construction process, enhances the timeliness of construction process supervision, and ensures construction safety. However, due to the current high demand for water from residents during peak hours in the morning and evening, pipeline pressure is affected by fluctuations in water consumption, which often manifest as normal periodic fluctuations. Relying solely on local data and ignoring these normal periodic fluctuations can lead to misinterpretation of data by the pressure monitoring system, making it difficult to accurately identify potential risks in underground pipeline corridors, thereby threatening the safety of underground spaces. Summary of the Invention

[0005] In order to solve the problem that due to the high water demand of residents during the peak hours in the morning and evening, the pressure in the pipeline will be affected by the fluctuation of water consumption. Relying solely on local data and ignoring such normal periodic fluctuations will cause the pressure monitoring system to misjudge the data. The present invention provides solutions in the following aspects.

[0006] In a first aspect, a safety monitoring method for underground space includes: obtaining historical pressure data at a pipeline interface, extracting a data sequence at the same moment within a preset period range based on the historical pressure data and fitting a hyperplane; calculating a periodicity index at each moment based on the vertical distance between the pressure data corresponding to any moment and the hyperplane, obtaining data for a preset period before the real-time pressure data, and calculating the importance of each moment within the preset period; calculating a weight value of the pressure data within the preset period based on the periodicity index and the importance, using a weighted average algorithm to use the weight value as the weight of the pressure data for weighting to predict residents' water demand, and using the difference between the predicted value and the actual value for early warning.

[0007] The results are as follows: By combining periodic analysis of historical pressure data with importance assessment of real-time data, the system can more accurately predict residential water demand, improving the accuracy and reliability of predictions, reducing false alarms caused by normal periodic fluctuations, and ensuring that the system can still accurately predict even complex water use patterns. By fitting a hyperplane and calculating periodic indicators, the system can adapt to different water use patterns and periodic changes. Even during peak water use periods, the system can use the hyperplane fitted to historical data to assess whether the current pressure data conforms to the expected periodic pattern, thereby avoiding unnecessary alarms caused by normal fluctuations. By calculating the importance and weight of each moment within a preset time period, the system can monitor changes in pressure data in real time and use the difference between predicted and actual values ​​to issue warnings. This real-time monitoring and warning mechanism can promptly detect potential anomalies, such as pipeline leaks or pressure anomalies, so that timely maintenance measures can be taken.

[0008] Preferably, extracting a data sequence at the same time within a preset period range based on historical pressure data and fitting a hyperplane includes: Taking any moment as the target moment, traverse the pressure data of the same target moment within a historical week and construct a pressure data matrix. At the same time, construct a time index matrix based on the time index. Use the least squares method to fit the pressure data matrix and the time index matrix to obtain the hyperplane.

[0009] The effect is that by traversing the pressure data at the same target moment within a week, the pressure change trend and cyclical characteristics at that moment can be captured. Using the least squares method to fit a hyperplane, a mathematical model can be established that can more accurately predict the pressure data at the current target moment. The least squares hyperplane not only considers the pressure data at the current target moment, but also integrates the data at the same moment within a week. This fitting method based on historical data can better capture the long-term trends and cyclical changes in pressure data, thereby enhancing the model's generalization ability.

[0010] Preferably, the periodic indicators include: Calculate the average vertical distance between the pressure data and the hyperplane at the same time within the preset period range to obtain the average level within the preset period range; Calculate the absolute deviation between the vertical distance between the pressure data at the current moment and the hyperplane and the average level, and use a negative exponential function to exponentially decay the absolute deviation to obtain the periodicity index at the current moment.

[0011] Preferably, the importance level includes: Take any moment as the target moment, obtain the pressure data in the local period before the target moment, and calculate the pressure in the local period. The sum of squares of the pressure data between the moment and other moments is calculated for the local period except the moment The pressure data at other moments other than the moment are the same as the pressure data at the local period except the moment The mean of the sum of squares of the pressure data at each moment other than the target moment is obtained to obtain the standard deviation of the pressure data; the ratio between the sum of squares of the difference and the standard deviation is normalized to obtain the first pressure data in the local period before the target moment. The importance of a moment.

[0012] The effect is: by evaluating the difference between the pressure data at each moment and other moments, as well as the degree of fluctuation of the pressure data within a local period, abnormal moments can be identified more accurately, misjudgments can be reduced, and the system can be ensured to promptly detect and handle potential abnormal situations; it can effectively distinguish between normal fluctuations and abnormal fluctuations, and even during peak water usage periods, it can avoid triggering unnecessary alarms due to normal fluctuations, ensuring that the system maintains stable performance in the face of complex water usage patterns and periodic fluctuations, and reducing maintenance costs and resource waste caused by misjudgments.

[0013] Preferably, the importance level also includes: Take any moment as the target moment, obtain the pressure data in the local period before the target moment, and calculate the pressure of the local time. The pressure data at each moment is the same as that in the local period except the The difference between the mean pressure data of each other moment is calculated, and the difference is added to the mean pressure data of the local time period except the first moment. Normalize the ratio of the standard deviation of the pressure data at each other moment to obtain the pressure data at the local period before the target moment. The importance of a moment.

[0014] The effect is that by evaluating the difference between the pressure data at each moment and the mean of other moments in the local period, combined with the ratio of standard deviations, abnormal moments can be identified more accurately, ensuring that the system can detect and handle potential abnormal situations in a timely manner.

[0015] Preferably, the weight value includes: Taking any moment as the target moment, the ratio between the importance of the target moment and the periodic index is calculated, and normalized to obtain the weight value of the pressure data corresponding to the target moment.

[0016] Preferably, the weight value further includes: Taking any moment as the target moment, calculate the ratio between the importance of the target moment and the periodic index to obtain the abnormality degree of the target moment; The product of the inverse of the difference between the pressure data at the target moment and the pressure data at the moment before the target moment and the abnormality degree is normalized and used as the weight value of the pressure data corresponding to the target moment.

[0017] The effect is that by calculating the ratio between the importance of a target moment and its periodicity index, we can more accurately assess whether the pressure data at that moment is abnormal. The importance reflects the difference between the pressure data at that moment and other moments, while the periodicity index reflects the similarity between the pressure data at that moment and the same period in history. A weight value is calculated for each target moment, reflecting its relative importance in the overall monitoring process. This helps prioritize and focus on moments that may contain abnormal information, improving overall monitoring and maintenance efficiency.

[0018] Preferably, the method of using the difference between the predicted value and the actual value to issue an early warning includes: The absolute difference between the predicted value and the actual monitored value of the pressure data at the current moment is normalized as the abnormality degree at the current moment; In response to the abnormality level at the current moment being greater than the warning coefficient, a warning message is sent to the monitoring center to remind the underground pipeline corridor that there is a safety risk in the corresponding pipeline and that timely maintenance is required. Otherwise, the underground pipeline corridor is safe.

[0019] In a second aspect, a safety monitoring system for an underground space includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned safety monitoring method for the underground space is implemented.

[0020] The present invention has the following effects: 1. This invention can more accurately identify true anomalies by comprehensively considering both importance and periodicity indicators. This approach not only considers the difference between the current pressure data and other times, but also historical periodic patterns and trends in adjacent times. This reduces false alarms caused by normal periodic fluctuations and improves the accuracy and reliability of anomaly detection.

[0021] 2. The present invention can effectively distinguish normal fluctuations from abnormal fluctuations by introducing periodic indicators. During peak water usage periods, the system can also evaluate whether the current pressure data conforms to the expected periodic pattern through the hyperplane fitted by historical data, thereby avoiding unnecessary alarms caused by normal fluctuations. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the following detailed description with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an illustrative and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 This is a method flow chart of steps S1 to S3 in a method for safety monitoring of an underground space according to an embodiment of the present invention.

[0023] Figure 2 This is a structural block diagram of an underground space safety monitoring system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work shall fall within the scope of protection of the present invention.

[0025] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0026] Specific implementation scenario: By installing intelligent pressure monitors at key nodes of underground pipelines, such as interfaces and main pipeline branches, real-time pressure data at pipeline interfaces can be obtained. These locations are key areas in the pipeline system that are more sensitive to pressure changes.

[0027] Reference Figure 1 A safety monitoring method for underground space includes steps S1 to S3, which are specifically as follows: S1: Obtain historical pressure data at the pipeline interface, extract the data sequence at the same time within a preset period range based on the historical pressure data, and fit a hyperplane.

[0028] In this embodiment, the preset sensor collects data once a minute to ensure that small changes can be captured, so as to facilitate timely detection of abnormal situations.

[0029] Taking any moment as the target moment, traverse the pressure data of the same target moment within a historical week and construct a pressure data matrix. At the same time, construct a time index matrix based on the time index. Use the least squares method to fit the pressure data matrix and the time index matrix to obtain the hyperplane.

[0030] It should be noted that since the actual water supply main pipeline is deployed in the underground space corridor of residential buildings, the internal pressure of the pipeline is affected by the daily water usage patterns of residents. During peak hours in the morning and evening, the pipeline pressure often fluctuates due to the sharp increase in water consumption. This fluctuation is normal and has obvious regularity.

[0031] Therefore, if pressure data fluctuates at a certain moment, it is important to consider whether this fluctuation is a normal change caused by daily water use patterns or a fluctuation caused by an abnormal situation. The closer the pressure data at a certain moment is to the historical trend curve representing normal behavior fitted by the pressure data of the same period in history, and the smaller the difference between this distance and the mean absolute distance of each pressure data from the fitted curve during the same period in history, it means that the change at that moment is consistent with historical normal behavior, and the periodicity indicator is considered to be larger.

[0032] S2: Calculate the periodicity index at each moment based on the vertical distance between the corresponding pressure data and the hyperplane at any moment, obtain the data of the preset period before the real-time pressure data, and calculate the importance of each moment in the preset period.

[0033] For example, for any moment, traverse historical moments to obtain corresponding pressure data at the same moment within a historical preset period, and set the following traversal formula: ; in, Indicates the number of days traversed within the preset period, Represents the index of the days within the preset period range, Indicates the A moment, Indicates the total number of minutes in a day, .

[0034] In this embodiment, the preset period range is one week, and the implementer can adjust it according to the specific situation, such as two weeks, one month, etc.

[0035] Calculate periodic indicators at any time, including: Taking any moment as the target moment, calculate the vertical distance between the pressure data point at the target moment and the fitted hyperplane; calculate the mean of the vertical distances between the corresponding data points and the fitted hyperplane within the preset period range before the target moment; calculate the absolute difference between the vertical distance at the target moment and the mean of the vertical distances within the preset period range before, and use the exponential function to correct the absolute difference to obtain the periodic index of the target moment.

[0036] Specifically, the periodic indicators satisfy the following relationship: ; Where, Indicates the Periodic indicators at each moment, Indicates the The vertical distance between the data point and the hyperplane at each moment, Indicates the The preset period range is set before the moment. Indicates the Days ago The vertical distance between the data point and the hyperplane at each moment, Represented by natural numbers An exponential function with base .

[0037] That is to say, Indicates the The vertical distance between the data point and the hyperplane at the moment, The absolute difference between the mean of the vertical distance between the corresponding data point and the hyperplane at the same moment within the preset period before the moment. The smaller the value, the better. The more consistent the pressure data corresponding to a moment is with the changing trend of the same moment in the historical period, that is, the pressure data at the current moment conforms to the expected periodic pattern, and the moment is considered to have strong periodicity.

[0038] In addition, another embodiment further includes: Taking any moment as the target moment, calculate the average of the absolute deviations between the pressure data at the target moment and the pressure data at the same moment within the preset period range, and use the exponential function to correct the average of the absolute deviations to obtain the periodic index of the target moment.

[0039] Specifically, the periodic indicators satisfy the following relationship: ; Where, Indicates the Periodic indicators at each moment, Indicates the The preset period range is set before the moment. Indicates the Pressure data at each moment, Indicates the Days ago Pressure data at each moment, Represented by natural numbers An exponential function with base .

[0040] That is to say, It reflects the mean difference between the pressure data at the target moment and the pressure data at the same moment within the previously preset period range. The smaller the mean difference, the more consistent it is with the characteristics of periodic changes and the stronger the periodicity. The larger the periodicity index, the more consistent the change trend of the pressure data at the current moment is with the pressure data at the same historical moment, that is, the pressure change at the current moment conforms to the historical periodic pattern. Conversely, the smaller the periodicity index, the more inconsistent the change trend of the pressure data at the current moment is with the pressure data at the same historical moment, that is, there may be an abnormal situation at the current moment.

[0041] It's important to note that due to long-term exposure to damp and poorly ventilated environments, pipeline materials may experience minor water seepage due to corrosion at the joints, or ruptures caused by rust and blockage. If the pipelines are not promptly inspected and cleaned of water seepage, long-term water seepage can affect the stability of underground structures (due to reduced concrete reinforcement strength, foundation settlement, and other issues). In practice, water seepage or leakage in pipelines can cause unstable water flow. When the water flow rate changes, the pressure inside the pipeline will also fluctuate, resulting in a distribution pattern that differs significantly from the normal stable pressure.

[0042] Therefore, the importance of each moment is evaluated by considering the changing characteristics of the pressure data within the time series. If a moment shows data that is significantly different from that of other moments in the period, it means that there may be potential abnormalities at that moment that cause abnormal fluctuations in the pressure data, and the current moment is considered to be more important.

[0043] Specifically, obtain the importance, including: Take any moment as the target moment, obtain the pressure data in the local period before the target moment, and calculate the pressure in the local period. The sum of squares of the pressure data between the moment and other moments is calculated for the local period except the moment The pressure data at other moments other than the moment are the same as the pressure data at the local period except the moment The mean of the sum of squares of the pressure data at each moment other than the target moment is obtained to obtain the standard deviation of the pressure data; the ratio between the sum of squares of the difference and the standard deviation is normalized to obtain the first pressure data in the local period before the target moment. The importance of a moment.

[0044] In this embodiment, the local time period is set to 10 data, excluding the target time.

[0045] Specifically, the importance satisfies the following relationship: ; Where, Indicates the number of the local time period at the current moment The importance of a moment, Indicates the number of moments in the local period of the current moment, Indicates the time index value within the local time period at the current time. Indicates the number of the local time period at the current moment The corresponding pressure data at each moment, Indicates the number of the local time period at the current moment The corresponding pressure data at each moment, Indicates that the current local time period is The other moments correspond to the mean pressure data, Represents the standard normalization function.

[0046] That is to say, Indicates that in the current local time period, The sum of the squares of the pressure data corresponding to a moment and the pressure data corresponding to each moment except this moment. The larger the value, the The greater the difference between the corresponding pressure data at one moment and other moments; Indicates that the current local time period is The standard deviation of the pressure data at other moments other than the first moment, the smaller the value, the more stable the pressure data changes at other moments in the local period. In this case, if the first moment The greater the difference between the pressure data at the first moment and the pressure data at other moments, the greater the difference between the first moment and the pressure data at other moments. If there may be anomalies in the pressure data at a certain moment, then this moment is considered important.

[0047] In addition, another embodiment further includes: Take any moment as the target moment, obtain the pressure data in the local period before the target moment, and calculate the pressure of the local time. The pressure data at each moment is the same as that in the local period except the The difference between the mean pressure data of each other moment is calculated, and the difference is added to the mean pressure data of the local time period except the first moment. Normalize the ratio of the standard deviation of the pressure data at each other moment to obtain the pressure data at the local period before the target moment. The importance of a moment.

[0048] Specifically, the importance satisfies the following relationship: ; For example, Indicates the number of the local time period at the current moment The importance of a moment, Indicates the number of the local time period at the current moment The corresponding pressure data at each moment, Indicates that the current local time period is The other moments correspond to the mean pressure data, Indicates that the current local time period is The standard deviation of the pressure data at each other moment, Represents the standard normalization function.

[0049] It's important to note that once the periodic indicators at each moment are determined, it's possible to determine whether the pressure data changes at that moment are consistent with fluctuations in historical daily water use patterns. If the data at a particular moment exhibits significant fluctuations within a localized period, and this fluctuation is inconsistent with historical daily water use patterns, this indicates a possible anomaly in the data at that moment and warrants special attention.

[0050] Therefore, the two indicators are combined to dynamically adjust the weight value, so that those moments that are considered to have possible abnormalities receive greater attention when weighting, thereby enhancing the sensitivity to potential abnormal situations and reducing the sensitivity of data with normal pattern fluctuations, making the current moment prediction value more in line with the actual pipeline situation.

[0051] S3: Calculate the weight value of the pressure data within the preset time period based on the periodic indicators and importance. Use the weighted average algorithm to take the weight value as the weight of the pressure data and perform weighting to predict the water demand of residents. Use the difference between the predicted value and the actual value to issue an early warning.

[0052] The weight values ​​include: Taking any moment as the target moment, the ratio between the importance of the target moment and the periodic index is calculated, and normalized to obtain the weight value of the pressure data corresponding to the target moment.

[0053] Specifically, the weight value satisfies the following relationship: ; Where, Indicates the number of the local time period at the current moment The weight value of the pressure data corresponding to each moment, Indicates the number of the local time period at the current moment The importance of a moment, Indicates the number of the local time period at the current moment Periodic indicators at each moment, Represents the standard normalization function.

[0054] In addition, another embodiment also includes: Taking any moment as the target moment, calculate the ratio between the importance of the target moment and the periodic index to obtain the abnormality degree of the target moment; The product of the inverse of the difference between the pressure data at the target moment and the pressure data at the moment before the target moment and the abnormality degree is normalized and used as the weight value of the pressure data corresponding to the target moment.

[0055] Specifically, the weight value satisfies the following relationship: ; Where, Indicates the number of the local time period at the current moment The weight value of the pressure data corresponding to each moment, Indicates the number of the local time period at the current moment The importance of a moment, Indicates the number of the local time period at the current moment Periodic indicators at each moment, Indicates the number of the local time period at the current moment The corresponding pressure data at each moment, Indicates the number of the local time period at the current moment The corresponding pressure data at each moment, Represents the standard normalization function.

[0056] The absolute difference between the predicted value and the actual monitored value of the pressure data at the current moment is normalized as the abnormality degree at the current moment; In response to the abnormality level at the current moment being greater than the warning coefficient, a warning message is sent to the monitoring center to remind the underground pipeline corridor that there is a safety risk in the corresponding pipeline and that timely maintenance is required. Otherwise, the underground pipeline corridor is safe.

[0057] In this embodiment, the warning coefficient is 0.75.

[0058] The present invention also provides a safety monitoring system for underground space. Figure 2 As shown, the system includes a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, a safety monitoring method for underground space according to the first aspect of the present invention is implemented.

[0059] The system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and therefore will not be described in detail here.

[0060] In the present invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, the computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application, module, or both. Any such computer storage medium can be part of, accessible to, or connectable to a device. Any application or module described in the present invention can be implemented by computer-readable / executable instructions stored or otherwise retained by such a computer-readable medium.

[0061] In the description of this specification, "multiple" and "several" mean at least two, such as two, three or more, unless otherwise clearly defined.

[0062] While several embodiments of the present invention have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Numerous modifications, variations, and alternatives will occur to those skilled in the art without departing from the concept and spirit of the present invention. It should be understood that various alternatives to the embodiments of the present invention described herein may be employed in practicing the present invention.

Claims

1. A safety monitoring method for underground space, characterized in that: include: Obtain historical pressure data at the pipeline interface, extract the data sequence at the same time within a preset period based on the historical pressure data, and fit a hyperplane; Calculate the periodicity index at each moment based on the vertical distance between the corresponding pressure data at any moment and the hyperplane, obtain the data of the preset period before the real-time pressure data, and calculate the importance of each moment in the preset period; Based on periodic indicators and importance, the weight value of the pressure data within the preset period is calculated. Using the weighted average algorithm, the weight value is used as the weight of the pressure data for weighting to predict residents' water demand and use the difference between the predicted value and the actual value for early warning.

2. A method for monitoring underground space safety according to claim 1, characterized in that: Extract the data sequence at the same time within the preset period range based on the historical pressure data and fit the hyperplane, including: Taking any moment as the target moment, traverse the pressure data of the same target moment within a historical week and construct a pressure data matrix. At the same time, construct a time index matrix based on the time index. Use the least squares method to fit the pressure data matrix and the time index matrix to obtain the hyperplane.

3. The underground space safety monitoring method according to claim 1, characterized in that: The cyclical indicators include: Calculate the average vertical distance between the pressure data and the hyperplane at the same time within the preset period range to obtain the average level within the preset period range; Calculate the absolute deviation between the vertical distance between the pressure data at the current moment and the hyperplane and the average level, and use a negative exponential function to exponentially decay the absolute deviation to obtain the periodicity index at the current moment.

4. The underground space safety monitoring method according to claim 1, characterized in that: The degree of importance includes: Take any moment as the target moment, obtain the pressure data in the local period before the target moment, and calculate the pressure in the local period. The sum of squares of the pressure data between the moment and other moments is calculated for the local period except the moment The pressure data at other moments other than the moment are the same as the pressure data at the local period except the moment The mean of the sum of squares of the pressure data at each moment other than the target moment is obtained to obtain the standard deviation of the pressure data; the ratio between the sum of squares of the difference and the standard deviation is normalized to obtain the first pressure data in the local period before the target moment. The importance of a moment.

5. The underground space safety monitoring method according to claim 1, characterized in that: The importance level also includes: Take any moment as the target moment, obtain the pressure data in the local period before the target moment, and calculate the pressure of the local time. The pressure data at each moment is the same as that in the local period except the The difference between the mean pressure data of each other moment is calculated, and the difference is added to the mean pressure data of the local time period except the first moment. Normalize the ratio of the standard deviation of the pressure data at each other moment to obtain the pressure data at the local period before the target moment. The importance of a moment.

6. The underground space safety monitoring method according to claim 1, characterized in that: The weight values ​​include: Taking any moment as the target moment, the ratio between the importance of the target moment and the periodic index is calculated, and normalized to obtain the weight value of the pressure data corresponding to the target moment.

7. The underground space safety monitoring method according to claim 1, characterized in that: The weight value also includes: Taking any moment as the target moment, calculate the ratio between the importance of the target moment and the periodic index to obtain the abnormality degree of the target moment; The product of the inverse of the difference between the pressure data at the target moment and the pressure data at the moment before the target moment and the abnormality degree is normalized and used as the weight value of the pressure data corresponding to the target moment.

8. The underground space safety monitoring method according to claim 1, characterized in that: The method of using the difference between the predicted value and the actual value to issue an early warning includes: The absolute difference between the predicted value and the actual monitored value of the pressure data at the current moment is normalized as the abnormality degree at the current moment; In response to the abnormality level at the current moment being greater than the warning coefficient, a warning message is sent to the monitoring center to remind the underground pipeline corridor that there is a safety risk in the corresponding pipeline and that timely maintenance is required. Otherwise, the underground pipeline corridor is safe.

9. A safety monitoring system for underground space, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the underground space safety monitoring method according to any one of claims 1 to 7 is implemented.

Images