Method and device for intelligently judging sealing failure of shield tail

Abstract

The invention discloses a shield tail sealing failure intelligent judgment method and device. The method comprises the steps that gap data of a duct piece and a tail shield, external soil mass pressure data and grease state data are obtained; inputting the gap data into a shield attitude abnormity early warning model, and outputting a first prediction result; inputting the external soil body pressure data into an external soil body abnormity early warning model, and outputting a second prediction result; the external soil body abnormity early warning model is used for determining an external soil body pressure sudden change turning point; inputting the grease state data into a grease abnormity early warning model, and outputting a third prediction result; the grease abnormity early warning model is used for determining whether the grease contains water, whether the grease temperature is abnormal and whether the grease pressure is abnormal according to the grease state data; and based on a Bayesian algorithm, carrying out fusion processing on the first prediction result, the second prediction result and the third prediction result, and outputting a comprehensive prediction result. The early warning accuracy of the shield tail sealing failure can be improved.

Description

Technical Field

[0001] The invention relates to the field of shield machine technology, and in particular to a shield tail seal failure intelligent judgment method and device. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention recited in the claims. No admission is made that the description herein is prior art by inclusion in this section.

[0003] The shield tail sealing system generally includes tail seals, grease injection systems, slurry stop plates, etc. The shield tail sealing system is a key component of the shield machine. Failure of the seal may cause external mud and groundwater to flow into the tunnel, causing ground collapse and casualties. The buried depth of the shield machine, the posture of the tail shield, the external soil pressure, the grease injection of the shield tail cavity, the wear of the tail brush, etc. all affect the sealing effect. If not diagnosed and warned in time, it will cause sealing failure and leakage.

[0004] The existing systems for diagnosing the failure of the shield tail seal mainly analyze the original data of the shield machine or the parameters collected by the sensing terminal and propose warning rules. For example, by analyzing the grease injection system of the shield machine, the pressure of each cavity and branch is aggregated, and the real-time warning is combined with the amount of grease. The real-time warning is only for the grease injection system, resulting in the early warning scheme being unable to effectively reflect the effect of the shield tail seal and having no guiding significance for the site. For another example, the technology of processing and detecting anomalies of the pressure data of the shield tail seal system through time series segmentation and unsupervised learning methods only focuses on the pressure data of the shield tail seal, ignoring the influence of various actual factors in the field work, resulting in a high error rate in judging the failure of the shield tail seal. Summary of the invention

[0005] The embodiment of the present invention provides an intelligent judgment method for failure of a shield tail seal, which is used to comprehensively consider multi-dimensional information such as tail shield posture, external soil pressure, and grease injection quality, monitor the shield tail seal state in all directions and at multiple angles, realize intelligent diagnosis and accurate early warning of failure of the shield tail seal, and ensure safe excavation of the equipment in complex working conditions. The method includes:

[0006] Obtain the gap data between the segment and the tail shield, external soil pressure data, and grease status data;

[0007] The gap data between the segment and the tail shield is input into the shield attitude abnormality warning model, and the first prediction result is output; the shield attitude abnormality warning model is used to: determine the uniformity of the shield tail gap distribution at multiple points on the circumference of the tail shield according to the gap data between the segment and the tail shield; determine the first prediction result according to the uniformity of the shield tail gap distribution; the first prediction result reflects the degree of extrusion of the shield tail brush;

[0008] The external soil pressure data is input into the external soil anomaly warning model, and a second prediction result is output; the external soil anomaly warning model is used to: determine first external soil pressure data of a sudden change in external soil pressure according to the external soil pressure data, and determine a second prediction result according to the first external soil pressure data; the second prediction result reflects the influence of the external soil pressure on the sealing performance of the shield tail;

[0009] The grease status data is input into the grease abnormality early warning model, and a third prediction result is output; the grease abnormality early warning model is used to: determine the third prediction result by using the results of whether the grease contains water, whether the grease temperature is abnormal, and whether the grease pressure is abnormal determined by the grease status data; the third prediction result reflects the influence of the grease status on the sealing performance of the shield tail;

[0010] Based on the Bayesian algorithm, the first prediction result, the second prediction result and the third prediction result are fused and processed to output a comprehensive prediction result; the comprehensive prediction result includes no risk, grease spillage, leakage risk level, and leakage location.

[0011] The embodiment of the present invention also provides a shield tail seal failure intelligent judgment device, which is used to comprehensively consider multi-dimensional information such as tail shield posture, external soil pressure, grease injection quality, etc., to monitor the shield tail seal state in all directions and at multiple angles, realize intelligent diagnosis and accurate early warning of shield tail seal failure, and ensure safe excavation of equipment in complex working conditions. The device includes:

[0012] Data acquisition module, used to obtain the gap data between the segment and the tail shield, external soil pressure data, and grease status data;

[0013] The shield attitude abnormality warning module is used to input the gap data between the pipe segment and the tail shield into the shield attitude abnormality warning model and output the first prediction result; the shield attitude abnormality warning model is used to: determine the uniformity of the shield tail gap distribution at multiple points on the circumference of the tail shield according to the gap data between the pipe segment and the tail shield; determine the first prediction result according to the uniformity of the shield tail gap distribution; the first prediction result reflects the degree of extrusion of the shield tail brush;

[0014] The external soil abnormality warning module is used to input the external soil pressure data into the external soil abnormality warning model and output the second prediction result; the external soil abnormality warning model is used to: determine the first external soil pressure data of the external soil pressure mutation according to the external soil pressure data, and determine the second prediction result according to the first external soil pressure data; the second prediction result reflects the influence of the external soil pressure on the sealing performance of the shield tail;

[0015] The grease state abnormality warning module is used to input the grease state data into the grease abnormality warning model and output the third prediction result; the grease abnormality warning model is used to: determine the third prediction result by using the results of whether the grease contains water, whether the grease temperature is abnormal, and whether the grease pressure is abnormal determined by the grease state data; the third prediction result reflects the influence of the grease state on the sealing performance of the shield tail;

[0016] The fusion processing module is used to fuse the first prediction result, the second prediction result and the third prediction result based on the Bayesian algorithm, and output a comprehensive prediction result; the comprehensive prediction result includes no risk, grease spillage, leakage risk level, and leakage location.

[0017] An embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned shield tail seal failure intelligent judgment method when executing the computer program.

[0018] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned shield tail seal failure intelligent judgment method is implemented.

[0019] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the above-mentioned shield tail seal failure intelligent judgment method is implemented.

[0020] In the embodiment of the present invention, the gap data between the pipe segment and the tail shield, the external soil pressure data and the grease status data are obtained, and the corresponding data are processed by using the independently operated shield posture abnormality warning model, the external soil abnormality warning model and the grease abnormality warning model respectively. The influence of the tail shield posture, the external soil pressure, the shield tail cavity state, and the shield tail sealing grease injection on the sealing effect are comprehensively considered, and the shield tail sealing state is monitored in all directions and at multiple angles. The intelligent diagnosis and evaluation of the shield tail sealing failure with multi-information fusion is realized, which greatly improves the warning accuracy of the shield tail sealing failure and can provide timely and accurate warning information for construction personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0022] Figure 1It is a flow chart of the intelligent judgment method of the failure of the shield tail seal in the embodiment of the present invention;

[0023] Figure 2 Schematic diagram of uniform distribution of shield tail gap in an embodiment of the present invention;

[0024] Figure 3 Schematic diagram of an excessively large shield tail gap in an embodiment of the present invention;

[0025] Figure 4 Schematic diagram of the flow of the change point monitoring algorithm in an embodiment of the present invention;

[0026] Figure 5 It is a schematic diagram of the process of abnormal grease pressure warning in an embodiment of the present invention;

[0027] Figure 6 It is a diagram showing an example of an intelligent method for judging failure of a shield tail seal in an embodiment of the present invention;

[0028] Figure 7 It is another example diagram of the intelligent judgment method of the failure of the shield tail seal in the embodiment of the present invention;

[0029] Figure 8 Schematic diagram of a shield tail seal failure intelligent judgment device in an embodiment of the present invention. DETAILED DESCRIPTION

[0030] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0031] In view of the defects in the prior art, the embodiments of the present invention propose a multi-system coupled shield tail seal failure intelligent judgment method and device to solve the problems of unclear diagnosis and inaccurate early warning of shield tail seal failure in the prior art, aiming to identify the risk of seal failure, optimize construction decisions, and ensure the safe excavation of the shield machine.

[0032] Figure 1 FIG. 1 is a flow chart of an intelligent method for determining failure of a shield tail seal according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0033] Step 101, obtaining gap data between the segment and the tail shield, external soil pressure data and grease status data;

[0034] Step 102, inputting the clearance data between the segment and the tail shield into the shield attitude abnormality warning model, and outputting a first prediction result; the shield attitude abnormality warning model is used to: determine the uniformity of the shield tail clearance distribution at multiple points on the circumference of the tail shield according to the clearance data between the segment and the tail shield; and determine the first prediction result according to the uniformity of the shield tail clearance distribution;

[0035] Step 103: input the external soil pressure data into the external soil abnormality early warning model, and output a second prediction result; the external soil abnormality early warning model is used to: determine first external soil pressure data of a sudden change in external soil pressure according to the external soil pressure data, and determine the second prediction result according to the first external soil pressure data;

[0036] Step 104: input the grease status data into the grease abnormality warning model, and output a third prediction result; the grease abnormality warning model is used to: determine the third prediction result by using the results of whether the grease contains water, whether the grease temperature is abnormal, and whether the grease pressure is abnormal determined by the grease status data;

[0037] Step 105: Based on the Bayesian algorithm, the first prediction result, the second prediction result and the third prediction result are fused and processed to output a comprehensive prediction result; the comprehensive prediction result includes no risk, grease spillage, leakage risk level, and leakage location.

[0038] from Figure 1 It can be seen from the process shown that in the embodiment of the present invention, the gap data between the pipe segment and the tail shield, the external soil pressure data and the grease status data are obtained, and the corresponding data are processed by using the independently running shield posture abnormality warning model, the external soil abnormality warning model and the grease abnormality warning model respectively. The influence of the tail shield posture, the external soil pressure, the shield tail cavity state, and the shield tail seal grease injection on the sealing effect is comprehensively considered, and the shield tail sealing state is monitored in all directions and at multiple angles. The intelligent diagnosis and evaluation of the shield tail seal failure with multi-information fusion is realized, which greatly improves the warning accuracy of the shield tail seal failure and can provide timely and accurate warning information for construction personnel.

[0039] During the tunneling process of the shield machine, the stability and reliability of the shield tail sealing system are key factors in ensuring the safety of tunnel construction. However, due to the complexity and particularity of the environment in which the shield tail sealing system is located, it is difficult to directly observe and accurately judge the leakage of the shield tail seal, which poses a potential risk to construction safety. In the embodiment of the present invention, sensors are installed in multiple locations. For example, a laser sensor is installed at the junction of the tail shield and the pipe segment to measure the shield tail gap, and a sensing monitoring sensor is installed in the shield tail sealing cavity to obtain parameters such as grease pressure, grease temperature, and moisture content in the cavity. The multi-system coupled shield tail seal failure intelligent judgment method in the embodiment of the present invention comprehensively considers the influence of the tail shield posture, external soil pressure, shield tail cavity state parameters, and shield tail seal grease injection parameters on the sealing effect, and forms multiple independent models for parallel operation based on the coupling between the sub-models, so as to realize the intelligent judgment and evaluation of shield tail seal failure with multi-information fusion, and provide timely and accurate early warning information for construction personnel, which has important guiding significance for the site.

[0040] In step 101, the gap data between the segment and the tail shield, the external soil pressure data and the grease status data are obtained.

[0041] Preferably, the gap data between the segment and the tail shield detected by the first sensor, the external soil pressure data detected by the second sensor, and the grease status data detected by the third sensor are obtained; the first sensor is installed at the junction of the tail shield and the segment; the second sensor is installed at the position where the shield tail is in direct contact with the surrounding soil; the third sensor is installed in the shield tail sealing cavity, and the grease status data reflects the moisture content, temperature and pressure of the grease.

[0042] For example, obtain the gap data collected by the laser sensor, the external soil pressure data collected by the mud pressure sensor, the grease temperature data and grease pressure data collected by the temperature and pressure sensor, etc.

[0043] These sensors communicate directly or indirectly with the server, which ultimately performs calculations based on the sensor data acquired in real time.

[0044] In one embodiment, after obtaining the gap data between the pipe segment and the tail shield detected by the first sensor, the external soil pressure data detected by the second sensor, and the grease state data detected by the third sensor, the following may also be included:

[0045] The gap data between the pipe segment and the tail shield detected by the first sensor, the external soil pressure data detected by the second sensor, and the grease status data detected by the third sensor are preprocessed as follows:

[0046] Sliding average filtering and outlier removal.

[0047] In this example, the acquired data is processed by sliding average filtering and outlier removal to improve the data quality.

[0048] In step 102, the gap data between the segment and the tail shield is input into the shield attitude abnormality warning model, and the first prediction result is output; the shield attitude abnormality warning model is used to: determine the shield tail gap distribution uniformity of multiple points on the circumference of the tail shield according to the gap data between the segment and the tail shield; determine the first prediction result according to the shield tail gap distribution uniformity. In the embodiment of the present invention, the first prediction result reflects the degree of extrusion of the shield tail brush.

[0049] Among them, a shield posture abnormality warning model is pre-built, and the shield posture abnormality warning model is used to predict whether the shield posture is abnormal, and then predict the leakage risk.

[0050] The uniformity of the shield tail gap distribution at multiple points on the circumference of the tail shield is determined based on the gap data between the segment and the tail shield. It is mainly to determine the size of the shield tail gap measured at different positions in the entire circumferential direction of the shield machine's tail shield. By comparing the gap values ​​at different positions, it can be determined whether the shield machine has shifted or whether the segment has deformed.

[0051] The gap data between the segment and the tail shield may include a gap value and a monitoring position. In one embodiment, the shield posture abnormality warning model is specifically used for:

[0052] Determine the shield tail gap value at each point on the circumference of the tail shield according to the gap value and monitoring position;

[0053] According to the average value and standard deviation of the shield tail gap value at each point, the shield tail gap distribution uniformity of multiple points on the circumference of the tail shield is determined; the distribution uniformity includes uniform distribution and uneven distribution;

[0054] When the distribution is uneven, the relative height difference between the segment and the shield tail seal is calculated based on the deviation between the tail shield and the segment on the axis;

[0055] A first prediction result is determined according to the relative height difference.

[0056] The change of shield posture directly affects the shield tail gap. The gap between the shield tail seal and the segment is calculated based on the shield tail gap to indirectly reflect the degree of extrusion of the shield tail brush. The specific modeling ideas of the present invention are as follows:

[0057] 1) Traverse the maximum value point of the shield tail gap to determine whether the tail shield posture has a large deviation;

[0058] 2) Given the tail shield diameter, segment diameter, and shield tail seal brush related design parameters, calculate the height difference at the junction of the segment and the shield tail seal through the deviation angle α between the tail shield and the segment center

[0059] 3) When the height difference h is less than the set threshold, a seal leakage warning is issued.

[0060] During implementation, based on the gap between the pipe segment and the tail shield detected by the first sensor, the shield tail gap value of each point on the circumference of the tail shield is calculated by detecting the position, and the extreme points of the current gap are traversed to accurately depict the relative position relationship between the tail shield and the pipe segment. When the shield tail gap is evenly distributed, it is considered that the shield posture here has no leakage risk for the shield tail seal. When the shield tail gap has a large deviation in the horizontal or vertical direction, the relative height difference between the pipe segment and the shield tail seal is calculated based on the deviation of the tail shield and the pipe segment on the axis, so as to reflect the degree of extrusion of the shield tail brush, and then realize the early warning assessment of the leakage risk.

[0061] Figure 2 FIG. 1 is a schematic diagram of a uniform distribution of the shield tail gap in an embodiment of the present invention. Figure 2 As shown, when the center of the tail shield is coaxial with the center of the segment, the gaps at the upper, lower, left and right parts of the shield tail are evenly distributed, the shield tail sealing brush will stick to the segment, the shield tail sealing cavity is filled with grease, and the sealing effect is good.

[0062] Figure 3Schematic diagram of the shield tail gap being too large in an embodiment of the present invention. Figure 3 As shown in the figure, when the shield posture is offset, the center of the tail shield is no longer coaxial with the center of the segment, and the gap between the shield tail is too large or too small, the shield tail sealing brush will separate from the segment, causing the shield tail seal to fail, which is very likely to cause sealing failure and mud leakage.

[0063] In step 103, the external soil pressure data is input into the external soil abnormality early warning model, and a second prediction result is output; the external soil abnormality early warning model is used to: determine the first external soil pressure data of the external soil pressure mutation according to the external soil pressure data, and determine the second prediction result according to the first external soil pressure data of the external soil pressure mutation. In the embodiment of the present invention, the second prediction result reflects the influence of the external soil pressure on the sealing performance of the shield tail.

[0064] The external soil pressure has a decisive influence on the shield tail sealing effect. When the external soil pressure increases suddenly, the risk of shield tail seal leakage is greatly increased. In view of the external soil pressure, the change point detection algorithm (Pruned Exact Linear Time, PELT algorithm) is used to capture the sudden increase and decrease moments of the external soil pressure. Based on the precise time division and efficient load attenuation mechanism, the subtle changes in the pressure data of the mud water cavity at the shield tail can be keenly captured, and the key turning points of sudden increase or decrease in pressure can be identified. The embodiment of the present invention closely combines the dynamic monitoring capability of the PELT algorithm with the immediate impact of the external soil pressure on the shield tail sealing effect, and realizes the accurate assessment of the risk of shield tail seal leakage.

[0065] The change point detection algorithm in the embodiment of the present invention minimizes the cost function through dynamic programming, and then finds the optimal change segmentation point, that is, the anomaly detection point. Figure 4 is a flow chart of a change point monitoring algorithm in an embodiment of the present invention, with reference to Figure 4 In the embodiment of the present invention, the external soil abnormality early warning model is specifically used for:

[0066] Divide the external soil pressure data into multiple segments according to the detection time;

[0067] Calculate the difference, fluctuation rate and mean of the external soil pressure data within each segment;

[0068] Then, the mean square error is used as the cost function to measure the deviation between the mean value and the true value in the current interval of the input test time series; specifically, the difference, volatility and mean of the external soil pressure data in each segment are used to calculate the minimum cost function of the external soil pressure data in each segment according to the following formula:

[0069]

[0070] Where L(t',t) is the cost of the time interval [t',t], i represents the time interval [t',t], y i is the difference or fluctuation rate of the test time series (external soil pressure data) in the time interval [t', t], μ [t',t] is the mean value of the external soil pressure data in the interval [t', t]; the cost function is minimized by dynamic programming according to the following formula:

[0071]

[0072] Where C(t) represents the minimum cost from time point 0 to time point t, C(t′) represents the minimum cost from time point 0 to time point t′, and L(t′,t) is the cost of [t′,t].

[0073] The second prediction result is determined according to the minimum cost function of the external soil pressure data in each segment.

[0074] In this example, based on the PELT algorithm, pruning technology is used to reduce the amount of calculation, which can effectively eliminate those parts that cannot become the optimal solution in the dynamic programming process, thereby greatly reducing the amount of calculation and improving the efficiency and accuracy of change point detection.

[0075] In step 104, the grease state data is input into the grease abnormality warning model, and a third prediction result is output; the grease abnormality warning model is used to determine the third prediction result by using the results of whether the grease contains water, whether the grease temperature is abnormal, and whether the grease pressure is abnormal determined from the grease state data. In the embodiment of the present invention, the third prediction result reflects the influence of the grease state on the sealing performance of the shield tail.

[0076] The grease abnormality warning model mainly performs comprehensive warning judgment on the grease moisture content, grease temperature and grease pressure in the shield tail sealing cavity, and may include grease temperature abnormality warning algorithm, grease moisture content abnormality warning algorithm and grease pressure abnormality warning algorithm.

[0077] In one embodiment, the grease status data includes grease moisture content data, grease temperature data, and grease pressure data;

[0078] The grease abnormality early warning model is specifically used for:

[0079] Determine whether the grease contains water based on the grease moisture content data; when water is detected in the grease, issue an early warning message immediately;

[0080] According to the grease temperature data, determine whether the grease temperature exceeds a first preset value; when the grease temperature exceeds the first preset value, immediately issue a warning message;

[0081] The grease pressure data of a single monitoring point in the shield tail sealing cavity in different tail brush cavities are eliminated for abnormal values, and the grease pressure data at the time of grease injection in the shield tail sealing cavity are eliminated to obtain the grease pressure data after eliminating abnormalities;

[0082] A change point detection algorithm is used to determine abnormal data in the grease pressure data after the abnormalities are eliminated, the abnormal data is screened out, and the current sealing chamber grease pressure abnormality monitoring position is output.

[0083] Among them, whether the grease contains water, whether the grease temperature exceeds the first preset value and the current abnormal grease pressure monitoring position in the sealing chamber are combined to form a third prediction result.

[0084] During implementation, the oil moisture content abnormal warning algorithm is used for the oil moisture content data. If water is detected in the oil, an early warning signal is immediately issued. The specific judgment formula is as follows:

[0085]

[0086] In the formula, f water Indicates the warning result of oil and fat water content.

[0087] Grease and water are significant signs of shield tail seal failure, and immediate measures must be taken to prevent further damage and ensure the safety of shield construction.

[0088] For the grease temperature, the grease temperature abnormal warning algorithm is used to directly monitor the grease temperature data collected by the sensor integrated module. If the grease temperature exceeds the preset threshold range, an early warning is triggered immediately. The specific judgment formula is as follows:

[0089]

[0090] In the formula, f temp Indicates the grease temperature warning result, and T indicates temperature.

[0091] Too high a temperature means that the grease is overheated, affecting the sealing performance; too low a temperature may indicate that the sensor is abnormal or the grease is in poor condition, ensuring a timely response to prevent sensor failure.

[0092] For grease pressure, an abnormal grease pressure warning algorithm is used to detect abnormal grease pressure at a single monitoring point in the shield tail seal cavity in different tail brush cavities. The grease injection moment in the shield tail seal cavity is eliminated, and the leakage risk of the current monitoring point is comprehensively evaluated by combining the simulated leakage mechanism of the shield tail seal and the abnormal detection results of each cavity. For specific algorithms, refer to Figure 4 , Figure 5 , Figure 5The figure is a flow chart of the abnormal grease pressure warning in the embodiment of the present invention. The abnormal grease pressure warning algorithm first calculates the difference, volatility, and mean of the pressure in the shield tail sealing cavity, and then combines the pressure to form a 4-dimensional feature as the input of the abnormal change point PELT algorithm (the principle of the PELT algorithm is consistent with the external soil pressure), and finally outputs the abnormal point of the current sealing cavity and the current monitoring point.

[0093] Specifically, the difference is used to measure the changes between adjacent observations in the time series data (grease pressure data is sorted by acquisition time), which can represent the instantaneous change of the shield tail seal grease pressure data in time. The specific calculation formula is as follows:

[0094] ΔP t =P t -P t-1

[0095] Where ΔP t is the difference value at time point t, P t is the shield tail seal pressure value at time t, P t-1 is the shield tail sealing pressure value at time t-1.

[0096] The volatility is used to reflect the stability and change range of data over a period of time. It can measure the stability of the trend change of the shield tail seal grease pressure over a certain period of time. The specific calculation formula is as follows:

[0097]

[0098] Where μ is the average value of the shield tail seal grease pressure over time, P i is the shield tail seal pressure value at the i-th time point, N is the total number of samples in time. var is the variance of the shield tail seal pressure, vol is the volatility of the shield tail seal pressure

[0099] Figure 5 In the process, the abnormal grease pressure data of the front cavity and the rear cavity are counted by the change point abnormality detection unit respectively, and the grease pressure data at the time of grease injection are eliminated to obtain a series of abnormal monitoring points of the front cavity and the rear cavity. Finally, a comprehensive judgment is made to output the leakage risk assessment result of the current monitoring point.

[0100] Finally, in step 105, based on the Bayesian algorithm, the first prediction result, the second prediction result and the third prediction result are fused and processed to output a comprehensive prediction result; the comprehensive prediction result includes no risk, grease spillage, leakage risk level, and leakage location.

[0101] In one embodiment, based on the Bayesian algorithm, the first prediction result, the second prediction result and the third prediction result are fused and processed to output a comprehensive prediction result, which may include:

[0102] Based on the Bayesian algorithm, the posterior probabilities of the shield attitude abnormality warning model, the external soil abnormality warning model and the grease abnormality warning model are calculated using the pre-set prior probabilities of the shield attitude abnormality warning model, the external soil abnormality warning model and the grease abnormality warning model.

[0103] According to the posterior probabilities of the shield posture abnormality warning model, the external soil abnormality warning model and the grease abnormality warning model and the first prediction result, the second prediction result and the third prediction result, a comprehensive prediction result is output.

[0104] Figure 6 FIG. 1 is an example of an intelligent judgment method for failure of the shield tail seal in an embodiment of the present invention, referring to Figure 6 The acquired data is preprocessed by outlier removal, filling, sliding average filtering, etc., and is processed by the shield posture abnormality warning model M1, the external soil abnormality warning model M2, and the shield tail sealing cavity grease abnormality warning model M3. Finally, the fusion decision is output based on the Bayesian algorithm to send the leakage risk. When outputting the fusion decision based on the Bayesian algorithm, the prior probability P(M) of the shield posture abnormality warning model M1, the external soil abnormality warning model M2, and the grease abnormality warning model M3 can be set in advance based on expert experience. i ), and then use Bayes' theorem to calculate the posterior probability P(M i / F):

[0105]

[0106] Among them, P(F / M i ) is the model M i The likelihood of P(F) is the marginal likelihood. The warning result of the final fusion decision is the weighted sum of each warning model:

[0107]

[0108] Among them, W i is the warning result of the model, and Warn is the final result.

[0109] The early warning results of each sub-model are organically integrated through the Bayesian algorithm, and the correlation between the sub-models is fully considered to achieve comprehensive decision-making for shield tail seal failure diagnosis based on multi-information fusion. The accuracy of the shield tail seal leakage risk warning is significantly improved, and it can be migrated and applied in a variety of complex working conditions and multiple equipment, which has important guiding significance for the site.

[0110] Figure 7 FIG. 2 is another example of an intelligent method for determining failure of a shield tail seal in an embodiment of the present invention. Figure 7As shown, based on the shield posture abnormal warning model, the shield tail gap determines the status of the shield tail and the pipe segment; based on the external soil pressure monitoring device, that is, using the external soil abnormal warning model, mud pressure, and formula, the mud water cavity state is determined; based on the shield tail sealing state monitoring system, that is, using the grease abnormal warning model to comprehensively process the grease pressure, grease moisture content, and grease temperature, the shield tail sealing cavity state is determined by the corresponding formula, and finally the comprehensive processing structure is output to output the shield tail sealing cavity leakage risk assessment result, including no risk, grease overflow and leakage risk. It should be noted that the input parameters in the embodiment of the present invention include but are not limited to grease injection parameters, shield tail posture parameters, shield tail cavity state parameters, external soil pressure parameters, etc., among which the constructed change point detection algorithm can be replaced by a more appropriate method, and can be processed by a machine learning model and can be replaced at will.

[0111] To sum up, compared with the prior art, the embodiment of the present invention provides a multi-system coupled shield tail seal failure intelligent judgment method, which comprehensively considers the influence of multiple factors on the shield tail seal effect, can accurately warn of the risk of shield tail seal failure leakage, and provide suggestions for the main driver on grease injection and grouting, thereby reducing potential safety hazards and ensuring the safe excavation of the shield machine.

[0112] The present invention also provides a shield tail seal failure intelligent judgment device, as described in the following embodiments. Since the principle of the device to solve the problem is similar to the shield tail seal failure intelligent judgment method, the implementation of the device can refer to the implementation of the shield tail seal failure intelligent judgment method, and the repeated parts will not be repeated.

[0113] Figure 8 Schematic diagram of the intelligent judgment device for failure of the shield tail seal in an embodiment of the present invention. Figure 8 As shown, the shield tail seal failure intelligent judgment device 800 includes:

[0114] The data acquisition module 801 is used to acquire the gap data between the segment and the tail shield, the external soil pressure data and the grease status data;

[0115] The shield attitude abnormality warning module 802 is used to input the gap data between the segment and the tail shield into the shield attitude abnormality warning model, and output a first prediction result; the shield attitude abnormality warning model is used to: determine the uniformity of the shield tail gap distribution at multiple points on the circumference of the tail shield according to the gap data between the segment and the tail shield; determine the first prediction result according to the uniformity of the shield tail gap distribution;

[0116] The external soil abnormality warning module 803 is used to input the external soil pressure data into the external soil abnormality warning model and output the second prediction result; the external soil abnormality warning model is used to: determine the first external soil pressure data of the external soil pressure sudden change according to the external soil pressure data, and determine the second prediction result according to the first external soil pressure data;

[0117] The grease state abnormality warning module 804 is used to input the grease state data into the grease abnormality warning model and output a third prediction result; the grease abnormality warning model is used to determine the third prediction result by using the results of whether the grease contains water, whether the grease temperature is abnormal, and whether the grease pressure is abnormal determined from the grease state data;

[0118] The fusion processing module 805 is used to fuse the first prediction result, the second prediction result and the third prediction result based on the Bayesian algorithm, and output a comprehensive prediction result; the comprehensive prediction result includes no risk, grease spillage, leakage risk level, and leakage location.

[0119] In one embodiment, the data acquisition module 801 is specifically used to: obtain the gap data between the pipe segment and the tail shield detected by the first sensor, the external soil pressure data detected by the second sensor, and the grease status data detected by the third sensor; the first sensor is installed at the junction of the tail shield and the pipe segment; the second sensor is installed at the position where the shield tail is in direct contact with the surrounding soil; the third sensor is installed in the shield tail sealing cavity, and the grease status data reflects the moisture content, temperature, and pressure of the grease.

[0120] In one embodiment, the gap data between the segment and the tail shield includes a gap value and a monitoring position;

[0121] The shield machine posture abnormal warning module 802 is specifically used for:

[0122] The shield tail gap value of each point on the circumference of the tail shield is determined according to the gap value and the monitoring position; the shield tail gap distribution uniformity of multiple points on the circumference of the tail shield is determined according to the average value and standard deviation of the shield tail gap value of each point; the distribution uniformity includes uniform distribution and uneven distribution; when the distribution is uneven, the relative height difference between the pipe segment and the shield tail seal is calculated according to the deviation of the tail shield and the pipe segment on the axis; and the first prediction result is determined according to the relative height difference.

[0123] In one embodiment, the external soil abnormality warning module 803 is specifically used for:

[0124] Divide the external soil pressure data into multiple segments according to the detection time;

[0125] Calculate the difference, fluctuation rate and mean of the external soil pressure data within each segment;

[0126] Using the difference, fluctuation rate and mean of the external soil pressure data in each segment, the minimum cost function of the external soil pressure data in each segment is calculated according to the following formula:

[0127]

[0128] Where L(t',t) is the cost of the time interval [t',t], i represents the time interval [t',t], y i is the difference or fluctuation rate of the external soil pressure data in the time interval [t', t], μ [t',t] is the mean value of the external soil pressure data in the interval [t', t]; the cost function is minimized by dynamic programming according to the following formula:

[0129] C(t)=m t′＜ i t n(C(t′)+L(t′,t));

[0130] Where C(t) represents the minimum cost from time point 0 to time point t, C(t′) represents the minimum cost from time point 0 to time point t′, and L(t′,t) is the cost of [t′,t].

[0131] The second prediction result is determined according to the minimum cost function of the external soil pressure data in each segment.

[0132] In one embodiment, the grease status data includes grease moisture content data, grease temperature data, and grease pressure data;

[0133] The abnormal grease status warning module 804 is specifically used for:

[0134] Determine whether the grease contains water based on the grease moisture content data; when water is detected in the grease, issue an early warning message immediately;

[0135] According to the grease temperature data, determine whether the grease temperature exceeds a first preset value; when the grease temperature exceeds the first preset value, immediately issue a warning message;

[0136] The grease pressure data of a single monitoring point in the shield tail sealing cavity in different tail brush cavities are eliminated for abnormal values, and the grease pressure data at the time of grease injection in the shield tail sealing cavity are eliminated to obtain the grease pressure data after eliminating abnormalities;

[0137] A change point detection algorithm is used to determine abnormal data in the grease pressure data after the abnormalities are eliminated, the abnormal data is screened out, and the current sealing chamber grease pressure abnormality monitoring position is output.

[0138] In one embodiment, the fusion processing module 805 is specifically used for:

[0139] Based on the Bayesian algorithm, the posterior probabilities of the shield attitude abnormality warning model, the external soil abnormality warning model and the grease abnormality warning model are calculated using the pre-set prior probabilities of the shield attitude abnormality warning model, the external soil abnormality warning model and the grease abnormality warning model.

[0140] According to the posterior probabilities of the shield posture abnormality warning model, the external soil abnormality warning model and the grease abnormality warning model and the first prediction result, the second prediction result and the third prediction result, a comprehensive prediction result is output.

[0141] In one embodiment, the apparatus 800 may further include:

[0142] The data preprocessing module is used to perform the following preprocessing on the gap data between the segment and the tail shield detected by the first sensor, the external soil pressure data detected by the second sensor, and the grease status data detected by the third sensor after the data acquisition module 801 acquires the gap data between the segment and the tail shield detected by the first sensor, the external soil pressure data detected by the second sensor, and the grease status data detected by the third sensor:

[0143] Sliding average filtering and outlier removal.

[0144] An embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned shield tail seal failure intelligent judgment method when executing the computer program.

[0145] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned shield tail seal failure intelligent judgment method is implemented.

[0146] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the above-mentioned shield tail seal failure intelligent judgment method is implemented.

[0147] In the embodiment of the present invention, sensors are arranged at the junction of the tail shield and the segment, at the position where the shield tail is in direct contact with the surrounding soil, and in the shield tail sealing cavity to obtain the gap data between the segment and the tail shield, the external soil pressure data and the grease status data, and the corresponding data are processed by using the independently operated shield posture abnormality warning model, the external soil abnormality warning model and the grease abnormality warning model, respectively. The influence of the tail shield posture, the external soil pressure, the shield tail cavity state, and the shield tail sealing grease injection on the sealing effect is comprehensively considered, and the shield tail sealing state is monitored in all directions and at multiple angles, realizing the intelligent diagnosis and evaluation of the shield tail sealing failure with multi-information fusion, which greatly improves the warning accuracy of the shield tail sealing failure and can provide timely and accurate warning information for construction personnel.

[0148] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0149] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0150] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0151] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0152] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An intelligent judgment method for shield tail seal failure, characterized in that: include: Obtain the gap data between the segment and the tail shield, the external soil pressure data and the grease status data; Input the gap data between the segment and the tail shield into the shield attitude abnormality warning model, and output the first prediction result; the shield attitude abnormality warning model is used to: determine the shield tail gap distribution uniformity of multiple points on the circumference of the tail shield according to the gap data between the segment and the tail shield; determine the first prediction result according to the shield tail gap distribution uniformity; The external soil pressure data is input into the external soil abnormality early warning model, and a second prediction result is output; the external soil abnormality early warning model is used to: determine first external soil pressure data of a sudden change in external soil pressure according to the external soil pressure data, and determine the second prediction result according to the first external soil pressure data; The grease status data is input into the grease abnormality early warning model, and a third prediction result is output; the grease abnormality early warning model is used to determine the third prediction result by using the results of whether the grease contains water, whether the grease temperature is abnormal, and whether the grease pressure is abnormal determined by the grease status data; Based on the Bayesian algorithm, the first prediction result, the second prediction result and the third prediction result are fused and processed to output a comprehensive prediction result; the comprehensive prediction result includes no risk, grease spillage, leakage risk level, and leakage location.

2. The shield tail seal failure intelligent judgment method according to claim 1, characterized in that: Obtain the gap data between the segment and the tail shield, external soil pressure data, and grease status data, including: The gap data between the segment and the tail shield detected by the first sensor, the external soil pressure data detected by the second sensor, and the grease status data detected by the third sensor are obtained; the first sensor is installed at the junction of the tail shield and the segment; the second sensor is installed at the position where the shield tail is in direct contact with the surrounding soil; the third sensor is installed in the sealing cavity of the shield tail, and the grease status data reflects the moisture content, temperature and pressure of the grease.

3. The shield tail seal failure intelligent judgment method according to claim 1, characterized in that: The gap data between the segment and the tail shield includes a gap value and a monitoring position; The shield machine posture abnormal warning model is specifically used for: Determine the shield tail gap value at each point on the circumference of the tail shield according to the gap value and monitoring position; According to the average value and standard deviation of the shield tail gap value at each point, the shield tail gap distribution uniformity of multiple points on the circumference of the tail shield is determined; the distribution uniformity includes uniform distribution and uneven distribution; When the distribution is uneven, the relative height difference between the segment and the shield tail seal is calculated based on the deviation between the tail shield and the segment on the axis; A first prediction result is determined according to the relative height difference.

4. The shield tail seal failure intelligent judgment method according to claim 1, characterized in that: The external soil anomaly early warning model is specifically used for: Divide the external soil pressure data into multiple segments according to the detection time; Calculate the difference, fluctuation rate and mean of the external soil pressure data within each segment; Using the difference, fluctuation rate and mean of the external soil pressure data in each segment, the minimum cost function of the external soil pressure data in each segment is calculated according to the following formula: Where L(t',t) is the cost of the time interval [t',t], i represents the time interval [t',t], y i is the difference or fluctuation rate of the external soil pressure data in the time interval [t', t], μ [t',t] is the mean value of the external soil pressure data in the interval [t', t]; the cost function is minimized by dynamic programming according to the following formula: Where C(t) represents the minimum cost from time point 0 to time point t, C(t′) represents the minimum cost from time point 0 to time point t′, and L(t′,t) is the cost of [t′,t]. The second prediction result is determined according to the minimum cost function of the external soil pressure data in each segment.

5. The shield tail seal failure intelligent judgment method according to claim 1, characterized in that: Grease status data includes grease moisture content data, grease temperature data, and grease pressure data; The grease abnormality early warning model is specifically used for: Determine whether the oil contains water according to the oil moisture content data; When water is detected in the grease, an early warning message is immediately issued; Determining whether the grease temperature exceeds a first preset value according to the grease temperature data; When the grease temperature exceeds the first preset value, an early warning message is immediately issued; The grease pressure data of a single monitoring point in the shield tail sealing cavity in different tail brush cavities are eliminated for abnormal values, and the grease pressure data at the time of grease injection in the shield tail sealing cavity are eliminated to obtain the grease pressure data after eliminating abnormalities; A change point detection algorithm is used to determine abnormal data in the grease pressure data after the abnormalities are eliminated, the abnormal data is screened out, and the current sealing chamber grease pressure abnormality monitoring position is output.

6. The shield tail seal failure intelligent judgment method according to claim 1, characterized in that: Based on the Bayesian algorithm, the first prediction result, the second prediction result and the third prediction result are fused and processed to output a comprehensive prediction result, including: Based on the Bayesian algorithm, the posterior probabilities of the shield attitude abnormality warning model, the external soil abnormality warning model and the grease abnormality warning model are calculated using the pre-set prior probabilities of the shield attitude abnormality warning model, the external soil abnormality warning model and the grease abnormality warning model. According to the posterior probabilities of the shield posture abnormality warning model, the external soil abnormality warning model and the grease abnormality warning model and the first prediction result, the second prediction result and the third prediction result, a comprehensive prediction result is output.

7. The intelligent judgment method for shield tail seal failure according to claim 1 is characterized in that: After obtaining the gap data between the pipe segment and the tail shield detected by the first sensor, the external soil pressure data detected by the second sensor, and the grease state data detected by the third sensor, it also includes: The gap data between the pipe segment and the tail shield detected by the first sensor, the external soil pressure data detected by the second sensor, and the grease status data detected by the third sensor are preprocessed as follows: Sliding average filtering and outlier removal.

8. An intelligent judgment device for shield tail seal failure, characterized in that: include: Data acquisition module, used to obtain the gap data between the segment and the tail shield, external soil pressure data and grease status data; The shield attitude abnormality warning module is used to input the gap data between the segment and the tail shield into the shield attitude abnormality warning model and output the first prediction result; the shield attitude abnormality warning model is used to: determine the uniformity of the shield tail gap distribution at multiple points on the circumference of the tail shield according to the gap data between the segment and the tail shield; determine the first prediction result according to the uniformity of the shield tail gap distribution; The external soil abnormality warning module is used to input the external soil pressure data into the external soil abnormality warning model and output the second prediction result; the external soil abnormality warning model is used to: determine the first external soil pressure data of the external soil pressure sudden change according to the external soil pressure data, and determine the second prediction result according to the first external soil pressure data; The grease state abnormality warning module is used to input the grease state data into the grease abnormality warning model and output a third prediction result; the grease abnormality warning model is used to: determine the third prediction result by using the results of whether the grease contains water, whether the grease temperature is abnormal, and whether the grease pressure is abnormal determined by the grease state data; The fusion processing module is used to fuse the first prediction result, the second prediction result and the third prediction result based on the Bayesian algorithm, and output a comprehensive prediction result; the comprehensive prediction result includes no risk, grease spillage, leakage risk level, and leakage location.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the shield tail seal failure intelligent judgment method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the shield tail seal failure intelligent judgment method according to any one of claims 1 to 7 is implemented.

11. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the shield tail seal failure intelligent judgment method according to any one of claims 1 to 7 is implemented.

Images