Ship lock main body deep foundation pit construction water level monitoring system and method

Abstract

The invention provides a ship lock main body deep foundation pit construction water level monitoring system and method which are suitable for the field of deep foundation pit construction, and a large hydro-junction water drain gate deep foundation pit construction safety control system comprises a water level monitoring module, a water level monitoring data transmission and receiving module, a water level monitoring data processing module and a water level monitoring early warning module. The invention discloses a ship lock body deep foundation pit construction water level monitoring method. The method comprises the steps of water level monitoring point position arrangement, water level monitoring data obtaining, monitoring data primary processing, single water level monitoring point position data analysis, overall water level distribution data analysis and water level early warning implementation. According to the method, monitoring data of the upstream water level of the ship lock body deep foundation pit are analyzed and processed, the water level change of the ship lock body deep foundation pit can be better predicted, construction safety is guaranteed, and the method can be widely applied to the field of deep foundation pit construction.

Description

Technical Field

[0001] The invention relates to a water level monitoring system and method for deep foundation pit construction of a ship lock main body, and is applicable to the field of deep foundation pit construction. Background Art

[0002] In modern engineering construction, deep foundation pit construction is a difficult task, especially in the construction process of water conservancy projects such as the main body of the ship lock, the change of water level has an important impact on the stability of the foundation pit and the safety of construction. Therefore, it is particularly necessary to establish an efficient water level monitoring system. Traditional water level monitoring methods mostly rely on manual measurement, which is not only time-consuming and labor-intensive, but also difficult to achieve real-time monitoring, which can easily lead to missed measurements and data lags. With the advancement of sensor technology and communication technology, a water level monitoring system based on the Internet of Things technology has emerged. This system can realize automated water level monitoring, provide real-time data and perform data analysis, thereby reducing construction risks and improving construction efficiency.

[0003] During the construction of deep foundation pits, water level monitoring requires not only high-precision sensors, but also effective data processing and analysis methods to identify potential safety hazards in a timely manner. Based on this, a water level monitoring module is used to obtain water level data in real time by arranging multiple water level monitoring points, and the data is transmitted to the processing center through the data transmission and receiving module. The data processing module will perform preliminary processing on the monitoring data, including outlier identification and supplementation, to ensure the accuracy and reliability of the data.

[0004] At the same time, there are many problems in the field of water level monitoring during the construction of the deep foundation pit of the main body of the ship lock. The main problems are: 1) The data of the water level monitoring points arranged near the deep foundation pit are distorted; the reason for this phenomenon is that there are frequent pumping and releasing operations during the construction of the deep foundation pit, which leads to irregular changes in the water level around the deep foundation pit, which also leads to very abnormal water level monitoring data near the deep foundation pit, and it is very difficult to analyze; 2) The change of the water level during the construction of the deep foundation pit of the main body of the ship lock is closely related to the change of the water level upstream, so in order to obtain the real change of the water level during the construction of the deep foundation pit, it is possible to arrange monitoring points upstream to analyze and process the data, and then The data from the upstream water level monitoring points show two obvious characteristics. Feature 1 is that the water level monitoring data for a single monitoring point shows obvious periodic changes. The main reason for this is the influence of periodic factors, such as the influence of tides, repeated changes during the day and night, etc. Feature 2 is that at the same monitoring time, the monitoring data obtained from the continuous monitoring point arrangement often presents a more complex nonlinear situation. The main reason is that the influencing factors are too complex, mainly including the impact of rainfall, reservoir scheduling, hydrological and meteorological factors, etc. In data processing, it is necessary to choose reasonable processing methods for these factors in order to better utilize the monitoring data to achieve the purpose of construction control.

[0005] In summary, in order to overcome the above problems, it is urgent to develop a more comprehensive and intelligent water level monitoring system and method for the deep foundation pit construction of the main body of the lock. Summary of the invention

[0006] The purpose of the present invention is to propose a water level monitoring system and method for the deep foundation pit construction of a ship lock body, in view of the current urgent need for a more comprehensive and intelligent water level monitoring system and method for the deep foundation pit construction of a ship lock body.

[0007] The purpose of the present invention can be achieved by adopting the following technical solutions:

[0008] A method for monitoring water level during construction of a deep foundation pit of a ship lock main body, characterized in that the method comprises the following steps:

[0009] S101 Arrange water level monitoring points;

[0010] The arrangement of water level monitoring points includes arranging a total of n water level monitoring points in sequence from far to near at a certain interval L1 upstream of the water level of the deep foundation pit of the ship lock body, marked as J i , i = 1 ~ n, and J i Distance from deep foundation pit L i , the distance L i Calculated by formula (1);

[0011] L i =L1×(n+1-j) (1)

[0012] S102 obtains water level monitoring data;

[0013] The water level monitoring data is obtained, including the water level monitoring points J arranged i , obtain monitoring data at fixed time intervals. Suppose that m monitoring data have been obtained and the time for obtaining monitoring data is T j , j = 1 ~ m, time T j Corresponding water level monitoring point J i The monitoring data obtained is expressed as J ij , for water level monitoring point J i The monitoring data set obtained is C i ={J ij |j=1~m};

[0014] S103 Preliminary processing of monitoring data;

[0015] The preliminary processing of the monitoring data includes obtaining a data set C i Preliminary data processing, including identification and supplementation of missing values ​​and identification and supplementation of outliers;

[0016] S104 Data analysis of a single water level monitoring point;

[0017] The data analysis of a single water level monitoring point includes the following steps: i The monitoring data set obtained is C i ={J ij |j=1~m}, and perform data analysis to obtain the water level monitoring point J i Future time T j+1 ~T j+x The predicted value of J i(j+1) ~J i(j+x) ;

[0018] S105 Data analysis of overall water level distribution;

[0019] The data analysis of the overall water level distribution includes obtaining the future time T y , the monitoring data set of all monitoring points from y = (j+1) to (j+x) is C y ={J iy |i=1~n}, construct the future time T y The analysis model of monitoring data and obtain the future time T y Water level monitoring prediction value of deep foundation pit (n+1)y ;

[0020] Implementation of S106 water level warning;

[0021] The implementation of the water level warning includes combining the obtained future time T y Water level monitoring prediction value of deep foundation pit (n+1)y Conduct early warning analysis based on the early warning standards to obtain early warning results, and decide whether to issue an early warning based on the early warning results.

[0022] Furthermore, in the above step S103, the identification and supplementation of the outliers are performed by using a moving average method, and the steps of using the moving average method to identify and supplement the outliers are as follows:

[0023] a) Calculate the moving average M;

[0024] b) Examine the actual value S and the moving average value M, and determine whether it is an abnormal value according to formula (2);

[0025]

[0026] c) If it is judged as an outlier, it is deleted and supplemented with a moving average M.

[0027] Furthermore, in the above step S104, the data analysis is performed to obtain the water level monitoring point J iFuture time T j+1 ~T j+x The predicted value of J i(j+1) ~J i(j+x) The steps are:

[0028] a) For monitoring point J i The monitoring data set C i ={J ij |j=1~m} for preprocessing, wherein the preprocessing includes data normalization, and the preprocessing includes dividing the monitoring data set into a training set and a test set;

[0029] b) constructing a recurrent neural network prediction model, wherein the recurrent neural network prediction model adopts a hyperbolic tangent scaling linear function, and the expression of the hyperbolic tangent scaling linear function is formula (3),

[0030]

[0031] In the formula, a is a parameter with a value range of 0.01 to 1;

[0032] In order to better fit the periodic characteristics of changes in a single monitoring data, the selection of a recurrent neural network is conducive to better capturing the time dependency in the data. At the same time, the hyperbolic tangent scaling linear function is selected due to its typical nonlinear characteristics, smoothness and scale adjustment characteristics. Typical nonlinear characteristics can better capture periodically changing data. Parameter a provides the scale adjustment characteristics of the hyperbolic tangent scaling linear function, which can be obtained through methods such as cross-validation in actual use.

[0033] c) Use the training set data to train the recurrent neural network prediction model, use the test set data to test and optimize the recurrent neural network prediction model, and finally obtain an applicable model;

[0034] d) Using the applicable model to obtain the future time T j+1 ~T j+x The predicted value of J i(j+1) ~J i(j+x) .

[0035] Furthermore, in the above step S105, the future time T is constructed y The analysis model of monitoring data and obtain the future time T y Water level monitoring prediction value of deep foundation pit (n+1)y The steps are:

[0036] a) For future time T y , the monitoring data set of all monitoring points at this time is obtained as C y ={J iy |i=1~n};

[0037] b) Construct input and output data sets, where the input data is the monitoring point J i Distance from deep foundation pit L i , the corresponding output data is J iy ;

[0038] c) Construct BP neural network model M y , the model M y An enhanced Gaussian activation function is used, and the expression of the enhanced Gaussian activation function is formula (4);

[0039]

[0040] Where α is the enhanced response coefficient, and α≥1.01;

[0041] In order to better fit the data distribution characteristics (complex nonlinearity) of the overall monitoring point data at a time, the enhanced Gaussian activation function is selected to better fit the change characteristics of the data. At the same time, the enhanced corresponding coefficient α is introduced, and α≥1.01 is required to increase the nonlinear characteristics of the function, so that it can perform better in complex nonlinear problems;

[0042] d) placing the output data set into the BP neural network model M y Carry out model training and optimization in the process and obtain the final optimized model;

[0043] e) L i = 0 is input into the final optimized model to obtain the future time T y Water level monitoring prediction value of deep foundation pit (n+1)y .

[0044] Furthermore, in the above step S106, the warning standard includes a time threshold T 阈值 and monitoring data threshold J 阈值 The above-mentioned early warning analysis to obtain the early warning result is to use formula (2) to perform early warning analysis and obtain the early warning result.

[0045]

[0046] Where, T 阈值 is the time threshold, J 阈值 is the monitoring data threshold;

[0047] The main consideration here is the actual construction. On the one hand, the impact of water level must be considered. If it exceeds the set threshold, an alarm will be issued. However, in actual problems, some monitoring points are far away, and it takes a long time to reach the vicinity of the deep foundation pit. Therefore, it is necessary to comprehensively consider the impact of both time and water level monitoring values ​​to determine the early warning standard, which will be more reasonable.

[0048] A water level monitoring system for deep foundation pit construction of a ship lock body, specifically comprising a water level monitoring module, a water level monitoring data transmission and receiving module, a water level monitoring data processing module and a water level monitoring early warning module, wherein the water level monitoring module is used to monitor the water level and obtain water level monitoring data, the water level monitoring data transmission and receiving module is used to receive the water level monitoring data and transmit it to the water level monitoring data processing module, the water level monitoring data processing module is used to process the obtained water level monitoring data and obtain an early warning result, and transmit the early warning result to the water level monitoring early warning module, and the water level monitoring early warning module performs corresponding operations according to the received early warning result.

[0049] The present invention has the following beneficial effects: 1) In order to solve the problem of irregular changes and data distortion of water level monitoring data around the deep foundation pit of the ship lock, the method arranges monitoring points upstream, analyzes and studies the data of the upstream monitoring points, and then obtains the predicted value of the water level around the deep foundation pit; 2) In view of the obvious characteristics of the data presented by the upstream water level monitoring points, an activation function that is more in line with the law of data change is selected in data processing to improve the fitting generalization ability of the model; 3) Based on the obtained prediction data and the current status of the deep foundation pit construction of the ship lock body, an early warning method that is more in line with the actual situation on site is formulated. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a flow chart of a method for monitoring water level during construction of a deep foundation pit of a ship lock body according to the present invention; DETAILED DESCRIPTION

[0051] The specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings; it should be understood that the specific embodiments given here are only used to illustrate and explain the present invention and cannot be used to limit the present invention.

[0052] The following is a specific embodiment of a water level monitoring system and method for the deep foundation pit construction of a ship lock body.

[0053] A method for monitoring water level during construction of a deep foundation pit of a ship lock main body, characterized in that the method comprises the following steps:

[0054] S101 Arrange water level monitoring points;

[0055] The arrangement of water level monitoring points includes arranging a total of n water level monitoring points in sequence from far to near at a certain interval L1 upstream of the water level of the deep foundation pit of the ship lock body, marked as J i , i = 1 ~ n, and J i Distance from deep foundation pit L i , the distance L i Calculated by formula (1);

[0056] L i =L1×(n+1-j) (1)

[0057] S102 obtains water level monitoring data;

[0058] The water level monitoring data is obtained, including the water level monitoring points J arranged i , obtain monitoring data at fixed time intervals. Suppose that m monitoring data have been obtained and the time for obtaining monitoring data is T j , j = 1 ~ m, time T j Corresponding water level monitoring point J i The monitoring data obtained is expressed as J ij , for water level monitoring point J i The monitoring data set obtained is C i ={J ij |j=1~m};

[0059] S103 Preliminary processing of monitoring data;

[0060] The preliminary processing of the monitoring data includes obtaining a data set C i Preliminary data processing, including identification and supplementation of missing values ​​and identification and supplementation of outliers;

[0061] S104 Data analysis of a single water level monitoring point;

[0062] The data analysis of a single water level monitoring point includes the following steps: i The monitoring data set obtained is C i ={J ij |j=1~m}, and perform data analysis to obtain the water level monitoring point J i Future time T j+1 ~T j+x The predicted value of J i(j+1) ~J i(j+x) ;

[0063] S105 Data analysis of overall water level distribution;

[0064] The data analysis of the overall water level distribution includes obtaining the future time T y , the monitoring data set of all monitoring points from y = (j+1) to (j+x) is C y ={J iy |i=1~n}, construct the future time T y The analysis model of monitoring data and obtain the future time T y Water level monitoring prediction value of deep foundation pit (n+1)y ;

[0065] Implementation of S106 water level warning;

[0066] The implementation of the water level warning includes combining the obtained future time T y Water level monitoring prediction value of deep foundation pit (n+1)y Conduct early warning analysis based on the early warning standards to obtain early warning results, and decide whether to issue an early warning based on the early warning results.

[0067] Furthermore, in the above step S103, the identification and supplementation of the outliers are performed by using a moving average method, and the steps of using the moving average method to identify and supplement the outliers are as follows:

[0068] a) Calculate the moving average M;

[0069] b) Examine the actual value S and the moving average value M, and determine whether it is an abnormal value according to formula (2);

[0070]

[0071] c) If it is judged as an outlier, it is deleted and supplemented with a moving average M.

[0072] Furthermore, in the above step S104, the data analysis is performed to obtain the monitoring point J i Future time T j+1 ~T j+x The predicted value of J i(j+1) ~J i(j+x) The steps are:

[0073] a) For monitoring point J i The monitoring data set C i ={J ij |j=1~m} for preprocessing, wherein the preprocessing includes data normalization, and the preprocessing includes dividing the monitoring data set into a training set and a test set;

[0074] b) constructing a recurrent neural network prediction model, wherein the recurrent neural network prediction model adopts a hyperbolic tangent scaling linear function, and the expression of the hyperbolic tangent scaling linear function is formula (3),

[0075]

[0076] In the formula, a is a parameter with a value range of 0.01 to 1;

[0077] In order to better fit the periodic characteristics of changes in a single monitoring data, the selection of a recurrent neural network is conducive to better capturing the time dependency in the data. At the same time, the hyperbolic tangent scaling linear function is selected due to its typical nonlinear characteristics, smoothness and scale adjustment characteristics. Typical nonlinear characteristics can better capture periodically changing data. Parameter a provides the scale adjustment characteristics of the hyperbolic tangent scaling linear function, which can be obtained through methods such as cross-validation in actual use.

[0078] c) Use the training set data to train the recurrent neural network prediction model, use the test set data to test and optimize the recurrent neural network prediction model, and finally obtain an applicable model;

[0079] d) Using the applicable model to obtain the future time T j+1 ~T j+x The predicted value of J i(j+1) ~J i(j+x) .

[0080] Furthermore, in the above step S105, the future time T is constructed y The analysis model of monitoring data and obtain the future time T y Water level monitoring prediction value of deep foundation pit (n+1)y The steps are:

[0081] a) For future time T y , the monitoring data set of all monitoring points at this time is obtained as C y ={J iy |i=1~n};

[0082] b) Construct input and output data sets, where the input data is the monitoring point J i Distance from deep foundation pit L i , the corresponding output data is J iy ;

[0083] c) Construct BP neural network model M y , the model M y An enhanced Gaussian activation function is used, and the expression of the enhanced Gaussian activation function is formula (4);

[0084]

[0085] Where α is the enhanced response coefficient, and α≥1.01;

[0086] In order to better fit the data distribution characteristics (complex nonlinearity) of the overall monitoring point data at a time, the enhanced Gaussian activation function is selected to better fit the change characteristics of the data. At the same time, the enhanced corresponding coefficient α is introduced, and α≥1.01 is required to increase the nonlinear characteristics of the function, so that it can perform better in complex nonlinear problems;

[0087] d) placing the output data set into the BP neural network model M y Carry out model training and optimization in the process and obtain the final optimized model;

[0088] e) L i = 0 is input into the final optimized model to obtain the future time T y Water level monitoring prediction value of deep foundation pit (n+1)y .

[0089] Furthermore, in the above step S106, the warning standard includes a time threshold T 阈值 and monitoring data threshold J 阈值 The above-mentioned early warning analysis to obtain the early warning result is to use formula (2) to perform early warning analysis and obtain the early warning result.

[0090]

[0091] Where, T 阈值 is the time threshold, J 阈值 is the monitoring data threshold;

[0092] The main consideration here is the actual construction. On the one hand, the impact of water level must be considered. If it exceeds the set threshold, an alarm will be issued. However, in actual problems, some monitoring points are far away, and it takes a long time to reach the vicinity of the deep foundation pit. Therefore, it is necessary to comprehensively consider the impact of both time and water level monitoring values ​​to determine the early warning standard, which will be more reasonable.

[0093] A water level monitoring system for deep foundation pit construction of a ship lock body, specifically comprising a water level monitoring module, a water level monitoring data transmission and receiving module, a water level monitoring data processing module and a water level monitoring early warning module, wherein the water level monitoring module is used to monitor the water level and obtain water level monitoring data, the water level monitoring data transmission and receiving module is used to receive the water level monitoring data and transmit it to the water level monitoring data processing module, the water level monitoring data processing module is used to process the obtained water level monitoring data and obtain an early warning result, and transmit the early warning result to the water level monitoring early warning module, and the water level monitoring early warning module performs corresponding operations according to the received early warning result.

[0094] In the above embodiment, a large-scale water conservancy hub sluice gate deep foundation pit construction safety control system includes a water level monitoring module, a water level monitoring data transmission and receiving module, a water level monitoring data processing module and a water level monitoring early warning module; a ship lock main body deep foundation pit construction water level monitoring method, including the arrangement of water level monitoring points, the acquisition of water level monitoring data, the preliminary processing of monitoring data, the data analysis of a single water level monitoring point, the data analysis of the overall water level distribution and the realization of water level early warning; the method can better predict the water level changes of the ship lock main body deep foundation pit by analyzing and processing the monitoring data of the upstream water level of the ship lock main body deep foundation pit, thereby ensuring the construction safety, and can be widely used in the field of deep foundation pit construction.

[0095] The above description is a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for monitoring water level during construction of a deep foundation pit of a ship lock, characterized in that: The monitoring method comprises the following steps: S101 Arrange water level monitoring points; S102 obtains water level monitoring data; S103 Preliminary processing of monitoring data; S104 Data analysis of a single water level monitoring point; S105 Data analysis of overall water level distribution; Implementation of S106 water level warning; The arrangement of water level monitoring points includes arranging a total of n water level monitoring points in sequence from far to near at a certain interval L1 upstream of the water level of the deep foundation pit of the ship lock body, marked as J i , i = 1 ~ n, and J i Distance from deep foundation pit L i , the distance L i Calculated by formula (1); L i =L1×(n+1-j) (1) The water level monitoring data is obtained, including the water level monitoring points J arranged i , obtain monitoring data at fixed time intervals. Suppose that m monitoring data have been obtained and the time for obtaining monitoring data is T j , j = 1 ~ m, time T j Corresponding water level monitoring point J i The monitoring data obtained is expressed as J ij , for water level monitoring point J i The monitoring data set obtained is C i ={J ij |j=1~m}; The preliminary processing of the monitoring data includes obtaining a data set C i Preliminary data processing, including identification and supplementation of missing values ​​and identification and supplementation of outliers; The data analysis of a single water level monitoring point includes the following steps: i The monitoring data set C i ={J ij |j=1~m} to analyze the data and obtain the water level monitoring point J i Future time T j+1 ~T j+x The predicted value of J i(j+1) ~J i(j+x) ; The data analysis of the overall water level distribution includes obtaining the future time T y , the monitoring data set of all monitoring points from y = (j+1) to (j+x) is C y ={J iy |i=1~n}, construct the future time T y The analysis model of monitoring data and obtain the future time T y Water level monitoring prediction value of deep foundation pit (n+1)y ; The realization of the water level warning includes combining the water level monitoring prediction value J (n+1)y Conduct early warning analysis based on the early warning standards to obtain early warning results, and decide whether to issue an early warning based on the early warning results.

2. A method for monitoring water level during construction of a deep foundation pit of a ship lock body according to claim 1, characterized in that: In step S103, the identification and supplementation of the outliers are performed by using a moving average method. The steps of using the moving average method to identify and supplement the outliers are as follows: a) Calculate the moving average M; b) Examine the actual value S and the moving average value M, and determine whether it is an abnormal value according to formula (2); c) If it is judged as an outlier, it is deleted and supplemented with a moving average M.

3. A method for monitoring water level during construction of a deep foundation pit of a ship lock body according to claim 1, characterized in that: In step S104, the water level monitoring point J is obtained. i Future time T j+1 ~T j+x The predicted value of J i(j+1) ~J i(j+x) The steps are: a) For monitoring point J i The monitoring data set C i ={J ij |j=1~m} for preprocessing, wherein the preprocessing includes data normalization, and the preprocessing includes dividing the monitoring data set into a training set and a test set; b) constructing a recurrent neural network prediction model, wherein the recurrent neural network prediction model adopts a hyperbolic tangent scaling linear function, and the expression of the hyperbolic tangent scaling linear function is formula (3), In the formula, a is a parameter with a value range of 0.01 to 1; c) Use the training set data to train the recurrent neural network prediction model, use the test set data to test and optimize the recurrent neural network prediction model, and finally obtain an applicable model; d) Using the applicable model to obtain the future time T j+1 ~T j+x The predicted value of J i(j+1) ~J i(j+x) .

4. A method for monitoring water level during construction of a deep foundation pit of a ship lock body according to claim 1, characterized in that: In step S105, the future time T is constructed y The analysis model of monitoring data and obtain the future time T y Water level monitoring prediction value of deep foundation pit (n+1)y The steps are: a) For future time T y , the monitoring data set of all monitoring points at this time is obtained as C y ={J iy |i=1~n}; b) Construct input and output data sets, where the input data is the monitoring point J i Distance from deep foundation pit L i , the corresponding output data is J iy ; c) Construct BP neural network model M y , the M y An enhanced Gaussian activation function is used, and the expression of the enhanced Gaussian activation function is formula (4); Where α is the enhanced response coefficient, and α≥1.01; d) placing the output data set into the BP neural network model M y Carry out model training and optimization in the process and obtain the final optimized model; e) L i = 0 is input into the final optimized model to obtain the future time T y Water level monitoring prediction value of deep foundation pit (n+1)y .

5. A method for monitoring water level during construction of a deep foundation pit of a ship lock body according to claim 1, characterized in that: In step S106, the warning criteria include a time threshold T 阈值 and monitoring data threshold J 阈值 The early warning analysis obtains the early warning result by using formula (2) to perform early warning analysis and obtain the early warning result. Where, T 阈值 is the time threshold, J 阈值 is the monitoring data threshold.

6. A water level monitoring system for deep foundation pit construction of a ship lock body, used in the water level monitoring method for deep foundation pit construction of a ship lock body as claimed in any one of claims 1 to 5, characterized in that: Specifically, it includes a water level monitoring module, a water level monitoring data transmission and receiving module, a water level monitoring data processing module and a water level monitoring early warning module. The water level monitoring module is used to monitor the water level and obtain water level monitoring data. The water level monitoring data transmission and receiving module is used to receive water level monitoring data and transmit it to the water level monitoring data processing module. The water level monitoring data processing module is used to process the obtained water level monitoring data and obtain early warning results, and pass the early warning results to the water level monitoring early warning module. The water level monitoring early warning module performs corresponding operations according to the received early warning results.

Images