CN115358494B - Danger early warning method for subway shield underpass construction - Google Patents
Danger early warning method for subway shield underpass construction Download PDFInfo
- Publication number
- CN115358494B CN115358494B CN202211283629.2A CN202211283629A CN115358494B CN 115358494 B CN115358494 B CN 115358494B CN 202211283629 A CN202211283629 A CN 202211283629A CN 115358494 B CN115358494 B CN 115358494B
- Authority
- CN
- China
- Prior art keywords
- danger
- moment
- construction
- information
- early warning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000010276 construction Methods 0.000 title claims abstract description 114
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000004458 analytical method Methods 0.000 claims abstract description 41
- 238000005516 engineering process Methods 0.000 claims abstract description 12
- 238000012544 monitoring process Methods 0.000 claims description 37
- 230000004044 response Effects 0.000 claims description 20
- 239000013598 vector Substances 0.000 claims description 13
- 238000013058 risk prediction model Methods 0.000 claims description 11
- 230000035515 penetration Effects 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 10
- 230000005641 tunneling Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 7
- 230000009286 beneficial effect Effects 0.000 description 8
- 238000006243 chemical reaction Methods 0.000 description 6
- 230000007613 environmental effect Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 238000009412 basement excavation Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 239000011435 rock Substances 0.000 description 3
- 239000004576 sand Substances 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 230000032683 aging Effects 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000012502 risk assessment Methods 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 239000002893 slag Substances 0.000 description 1
- 239000011573 trace mineral Substances 0.000 description 1
- 235000013619 trace mineral Nutrition 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Excavating Of Shafts Or Tunnels (AREA)
Abstract
The invention provides a danger early warning method for subway shield underpass construction, which comprises the following steps: acquiring actual data information of the underground shield underpass construction; performing pre-analysis prediction on a second moment based on actual data information of a first moment in each adjacent moment; comparing the analysis prediction result with the actual data information at the second moment, determining the adjustment information corresponding to the adjacent moments, setting a possible danger label for the adjustment information, and executing a first early warning operation; carrying out hazard calibration on the acquired actual data information at each moment, and constructing a first hazard prediction model for the underground shield to pass through based on a digital twin technology; and optimizing the first danger prediction model based on the adjustment information at the adjacent moment and the possible danger label, predicting the possible danger in the continuous construction, and executing corresponding second early warning operation. Carry out first early warning to probably dangerous label, carry out the second early warning to probably dangerous that exists, the danger that exists is in time effectually reminded, improves the efficiency of construction.
Description
Technical Field
The invention relates to the technical field of danger early warning, in particular to a danger early warning method for underground shield underpass construction.
Background
The subway shield construction refers to a subway construction method for constructing a tunnel under the condition that tunnel excavation and slag discharge are carried out by using a special machine for underground tunnel excavation while the underground tunnel excavation is carried out, the excavated rock surface and surrounding rocks are fixed in time, meanwhile, duct pieces are assembled in a shield tail to form a lining, grouting is carried out in time, and the tunnel is constructed as far as possible without disturbing the surrounding rocks.
However, in recent years, safety accidents in subway shield construction have appeared in a blowout manner, so that dangerous sources in subway shield construction are effectively prevented, and the prevention of the safety accidents is a priority for subway shield construction.
Although a related method for predicting danger exists at present, the danger cannot be warned in an early warning manner in time, so that the danger cannot be effectively handled in time when the danger really occurs, and the construction efficiency is low.
Therefore, the invention provides a danger early warning method for underground shield underpass construction.
Disclosure of Invention
The invention provides a danger early warning method for subway shield underpass construction, which is used for carrying out first early warning on a possible danger label and carrying out second early warning on possible dangers by analyzing and adjusting underpass construction information at adjacent moments, and can effectively remind the existing dangers in time and improve the construction efficiency.
The invention provides a danger early warning method for subway shield underpass construction, which comprises the following steps:
step 1: acquiring actual data information of each adjacent moment in the construction process of the subway shield underpass;
step 2: performing pre-analysis prediction on a second moment based on actual data information of a first moment in each adjacent moment to obtain an analysis prediction result;
and step 3: comparing the analysis prediction result with the actual data information at the second moment, determining adjustment information corresponding to adjacent moments, setting a possible danger label to the corresponding adjustment information, and executing a first early warning operation based on the set possible danger label;
and 4, step 4: carrying out hazard calibration on the acquired actual data information at each moment, and constructing a first hazard prediction model of the underground shield penetration based on a digital twinning technology;
and 5: and optimizing the first danger prediction model based on the adjustment information at the adjacent moment and the possible danger label, predicting the possible danger existing in the continuous construction, and executing corresponding second early warning operation.
Preferably, gather the actual data information of every adjacent moment in the subway shield under-penetration work progress, include:
monitoring a construction result of a target area in the process of underpass construction of the subway shield machine to obtain a first monitoring result;
when the subway shield machine is in underpass construction, monitoring the working operation of the subway shield machine to obtain a second monitoring result;
and acquiring a first monitoring result and a second monitoring result at the same time, and acquiring actual data information at adjacent times.
Preferably, the obtaining the first monitoring result and the second monitoring result at the same time and the actual data information at adjacent times includes:
carrying out result denoising processing on the obtained first monitoring result and the second monitoring result at the same time;
and obtaining actual data information at adjacent moments according to the denoising processing result.
Preferably, comparing the analysis prediction result with the actual data information at the second time, determining adjustment information corresponding to adjacent times, setting a possible danger label to the corresponding adjustment information, and executing a first warning operation based on the set possible danger label, including:
acquiring a construction project plan and a construction estimation result of the pre-determined underground shield underpass construction, simulating the construction project plan and the construction estimation result, and acquiring ideal information at each moment;
acquiring actual data information corresponding to a first moment in adjacent moments and actual data information corresponding to a second moment in a previous adjacent moment;
acquiring a first time line corresponding to the ideal starting time of a first time in adjacent moments and acquiring a second time line based on the ideal starting time of a second time in the previous adjacent moment;
constructing and obtaining a first ideal loss array of a first time line and a second ideal loss array of a second time line based on the obtained ideal loss factor of the subway shield machine at each moment;
according to the first ideal loss array, carrying out first adjustment on actual data information corresponding to a first moment in adjacent moments to obtain first information, and meanwhile, according to the second ideal loss array, carrying out second adjustment on actual data information corresponding to a second moment in the previous adjacent moments to obtain second information;
comparing the first information with first ideal information at the corresponding moment to obtain a first danger response result, and simultaneously comparing the second information with second ideal information at the corresponding moment to obtain a second danger response result;
analyzing all first danger response results and second danger response results before the second moment in the corresponding adjacent moments to obtain the association factor of each adjacent moment before the second moment in the corresponding adjacent moments;
performing pre-analysis prediction on a second moment in the corresponding adjacent moments by combining actual data information of the first moment in the corresponding adjacent moments based on the correlation factors to obtain analysis prediction results;
splitting and comparing the analysis prediction result with actual data information corresponding to a second moment in adjacent moments according to the subway shield machine and a construction area of the subway shield machine;
according to the splitting comparison result, obtaining a first error data set related to the subway shield machine and a second error data set related to a construction area of the subway shield machine;
obtaining adjustment information based on the first error data set and the second error data set;
inputting the first error data set and the second error data set into an error analysis model, outputting error weights of different error data in different data sets, and calibrating the error weights on corresponding error data in the adjustment information;
respectively analyzing the data state of each error data, and distributing a corresponding preset danger value to each data state from a danger setting database, thereby setting a possible danger label for each adjustment index in the corresponding adjustment information;
and setting a first early warning event for each possible dangerous label based on a danger-early warning database, and executing corresponding first early warning operation based on the first early warning event.
Preferably, the ideal information includes: ideal operation parameters, ideal loss factors and ideal construction conditions of a target area of the subway shield machine.
Preferably, the analyzing the data state of each error data, and assigning a corresponding preset risk value to each data state from the risk setting database, and further setting a possible risk label for each adjustment index in the corresponding adjustment information, includes:
determining the data state of the corresponding error data according to the error weight and the data type of each error data;
matching a preset danger value consistent with the data state based on the danger setting database;
calibrating a preset danger value for each error data in the adjustment information, and determining a danger level by combining the calibrated error weight;
dividing the adjustment information according to the category of the acquired data information, and determining a danger sequence of each division result based on danger levels;
meanwhile, the number of first indexes of each division result is determined based on the category of the acquired data information, and the index label setting state of each first index is obtained based on the danger sequence;
when the setting state of the index tag is 0, judging that no danger tag is required to be set corresponding to the first index;
and when the setting state of the index tag is not 0, judging that a possible danger tag needs to be set corresponding to the first index.
Preferably, the method for calibrating the dangers of the acquired actual data information at each moment and constructing a first danger prediction model of the subway shield under penetration based on the digital twin technology comprises the following steps:
carrying out hazard calibration on the acquired actual data information at each moment based on a hazard calibration model;
and constructing a first risk prediction model for the subway shield to pass downwards based on a digital twin technology and by combining the acquisition result at each moment and the risk calibration result at each moment.
Preferably, the first risk prediction model is optimized based on adjustment information at adjacent time and a possible risk label, a risk possibly existing in the continuous construction is predicted, and a corresponding second early warning operation is performed, including:
based on a vector analysis model, obtaining adjustment information of adjacent moments and an optimized vector corresponding to a possible danger label;
optimizing the first risk prediction model based on the optimization vectors corresponding to all adjacent moments before the continuous construction moment, and predicting the possible risks in the continuous construction;
and continuously setting a second early warning event to the possible danger matching based on the danger-early warning database, and executing corresponding second early warning operation based on the second early warning event.
Preferably, calibrating a preset risk value for each error data in the adjustment information, and determining a risk level by combining the calibrated error weight, includes:
acquiring a data set which belongs to the same index as the corresponding error data;
calculating the danger level Y corresponding to the data error;
wherein Y1 represents a preset danger value calibrated by a corresponding data error; y2 represents the error weight calibrated by the corresponding data error;
a first standard conversion coefficient representing a preset risk value;
a second standard conversion coefficient representing a weight to the error; n1 represents the number of first error data in the data set; n2 represents the number of second error data in the data set;
representing an influence factor of the corresponding i1 th first error data on the corresponding error data;
representing an influence factor of the corresponding i2 th second error data on the corresponding error data; n1 is greater than n2, and the second error data is data of the first error data; []Representing a rounding symbol.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
fig. 1 is a flowchart of a danger early warning method for subway shield underpass construction in an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
Example 1:
the invention provides a danger early warning method for subway shield underpass construction, which comprises the following steps as shown in figure 1:
step 1: acquiring actual data information of each adjacent moment in the subway shield underpass construction process;
step 2: pre-analyzing and predicting the second moment based on the actual data information of the first moment in each adjacent moment to obtain an analysis and prediction result;
and step 3: comparing the analysis prediction result with the actual data information at the second moment, determining adjustment information corresponding to adjacent moments, setting a possible danger label to the corresponding adjustment information, and executing a first early warning operation based on the set possible danger label;
and 4, step 4: carrying out hazard calibration on the acquired actual data information at each moment, and constructing a first hazard prediction model of the underground shield penetration based on a digital twinning technology;
and 5: and optimizing the first danger prediction model based on the adjustment information at the adjacent moment and the possible danger label, predicting the possible danger existing in the continuous construction, and executing corresponding second early warning operation.
In this embodiment, the actual data information refers to the acquired subway shield underpass construction results at the previous time and the next time of the adjacent time, and the parameters and the environmental parameters of each operating machine of the subway shield machine, and includes: the construction result image, the cutter head working image, the shield bearing pressure value, the cutter head working data, the environmental water, soil and sand content proportion, the number of high buildings and the number of environmental pipelines.
In this embodiment, the pre-analysis prediction refers to prediction of the construction operation information data at the second time by analyzing the construction operation information data at the first time.
In this embodiment, the adjustment information refers to a difference between the pre-analysis prediction result for the second time instant and the actual data information in the adjacent time instant.
And data change difference and trend information between adjacent moments are obtained through the first analysis prediction and the comprehensive analysis of the actual information data at the second moment, so that the purpose of optimizing prediction is achieved, and the purpose of optimizing the model is mainly achieved.
In this embodiment, the possible danger label refers to a label that is made based on the specific content of the adjustment information at each time and is added to the adjustment information that may cause danger, for example, the adjustment information at the corresponding time has dangers 1 and 2, for example, when the actual result data at the time 2 is analyzed, there is no danger situation, but when the prediction result data at the time 2 is predicted, there is a danger situation, and at this time, the corresponding adjustment information sets a label corresponding to the danger situation.
In this embodiment, the risk calibration refers to the judgment of the dangerous situation occurring during the underground construction of the iron shield by analyzing the information data acquired in real time, that is, determining the possible danger according to the acquired data at the moment, and then performing calibration, and the analysis of the information data may be performed based on the analysis of a risk analysis model, and the risk analysis model is obtained by training samples based on different information data and the possible danger corresponding to the information data.
In this embodiment, the first risk prediction model is a model constructed for the underground shield tunneling construction condition at each moment based on a digital twinning technology, so as to achieve the purpose of accurately grasping the underground shield tunneling construction condition at that moment.
In this embodiment, the predicted continuation of construction time occurs after the optimization model.
In this embodiment, the first and second early warning operations are obtained based on matching a danger-early warning database, and the danger-early warning database includes various possible danger labels, possible danger situations, and a matching early warning manner.
The working principle and the beneficial effects of the technical scheme are as follows: through analyzing, adjusting the construction information of wearing down to adjacent constantly, carry out first early warning to probably dangerous label, simultaneously, still carry out the second early warning to probably dangerous that exists, danger that can in time effectual warning exists improves the efficiency of construction.
Example 2:
on the basis of the above embodiment 1, the method for acquiring actual data information of each adjacent moment in the underground shield tunneling construction process includes:
monitoring a construction result of a target area in the process of downward penetration construction of the subway shield machine to obtain a first monitoring result;
when the subway shield machine is in underpass construction, monitoring the working operation of the subway shield machine to obtain a second monitoring result;
and acquiring a first monitoring result and a second monitoring result at the same time, and acquiring actual data information at adjacent times.
In this embodiment, the actual data information refers to the subway shield penetration construction result and the parameter and the environmental parameter of each operating machine of the subway shield machine at the previous moment and the next moment of the adjacent moment extracted from the first monitoring result and the second monitoring result, and includes: the construction result image, the cutter head working image, the shield bearing pressure value, the cutter head working data, the environmental water, soil and sand content proportion, the number of high buildings in the environment and the number of environmental pipelines.
The working principle and the beneficial effects of the technical scheme are as follows: data monitoring is carried out on the construction result and the operation condition of the subway shield machine, accurate understanding of the underground penetration construction condition of the subway shield at adjacent moments is guaranteed, the purpose of predicting the dangerous condition possibly occurring at the moment of continuing construction is achieved, a foundation is provided for a follow-up accurate matching early warning mode, and construction efficiency is indirectly improved.
Example 3:
on the basis of the foregoing embodiment 2, acquiring a first monitoring result and a second monitoring result at the same time, and acquiring actual data information at adjacent times includes:
carrying out result denoising processing on the obtained first monitoring result and the second monitoring result at the same time;
and obtaining actual data information at adjacent moments according to the denoising processing result.
In this embodiment, the denoising processing refers to a processing mode of reducing noise interference on the first monitoring result and the second monitoring result at the same time of acquisition in order that the acquired data has no interference.
In this embodiment, adjacent time instants refer to adjacent time instants, for example, there are time instants 1, 2, and 3, time instants 1 and 2 are adjacent time instants, and time instants 2 and 3 are adjacent time instants.
The working principle and the beneficial effects of the technical scheme are as follows: by denoising the acquired first monitoring result and the second monitoring result at the same time, the redundancy and invalid parts in the data are reduced, so that the data can be utilized to the maximum extent on the basis of small cache space, and an effective basis is provided for subsequent danger prediction.
Example 4:
on the basis of the foregoing embodiment 1, comparing the analysis prediction result with the actual data information at the second time, determining adjustment information between corresponding adjacent times, setting a possible danger label to the corresponding adjustment information, and executing a first warning operation based on the set possible danger label, where the method includes:
acquiring a construction project plan and a construction estimation result of the pre-determined underground shield underpass construction, simulating the construction project plan and the construction estimation result, and acquiring ideal information at each moment;
acquiring actual data information corresponding to a first moment in adjacent moments and actual data information corresponding to a second moment in a previous adjacent moment;
acquiring a first time line corresponding to the ideal starting time of a first time in adjacent moments and acquiring a second time line based on the ideal starting time of a second time in the previous adjacent moment;
constructing and obtaining a first ideal loss array of a first time line and a second ideal loss array of a second time line based on the obtained ideal loss factor of the subway shield machine at each moment;
according to the first ideal loss array, carrying out first adjustment on actual data information corresponding to a first moment in adjacent moments to obtain first information, and meanwhile, according to a second ideal loss array, carrying out second adjustment on actual data information corresponding to a second moment in the previous adjacent moments to obtain second information;
comparing the first information with first ideal information at the corresponding moment to obtain a first danger response result, and simultaneously comparing the second information with second ideal information at the corresponding moment to obtain a second danger response result;
analyzing all first danger response results and second danger response results before the second moment in the corresponding adjacent moments to obtain the association factors of each adjacent moment before the second moment in the corresponding adjacent moments;
performing pre-analysis prediction on a second moment in the corresponding adjacent moments by combining actual data information of the first moment in the corresponding adjacent moments based on the correlation factors to obtain analysis prediction results;
splitting and comparing the analysis prediction result with actual data information corresponding to a second moment in adjacent moments according to the subway shield machine and a construction area of the subway shield machine;
according to the splitting comparison result, obtaining a first error data set related to the subway shield machine and a second error data set related to a construction area of the subway shield machine;
obtaining adjustment information based on the first error dataset and the second error dataset;
inputting the first error data set and the second error data set into an error analysis model, outputting error weights of different error data in different data sets, and calibrating the error weights on corresponding error data in the adjustment information;
respectively analyzing the data state of each error data, and distributing a corresponding preset danger value to each data state from a danger setting database, thereby setting a possible danger label for each adjustment index in the corresponding adjustment information;
and setting a first early warning event for each possible dangerous label based on a danger-early warning database, and executing corresponding first early warning operation based on the first early warning event.
Preferably, the ideal information includes: ideal operation parameters, ideal loss factors and ideal construction conditions of a target area of the subway shield machine.
In this embodiment, the ideal information at each time refers to the construction result and the working condition data information of the subway shield underpass construction corresponding to each time when the subway shield underpass construction is performed under an ideal condition.
In this embodiment, the first time line refers to a construction time line from the ideal starting time to the first time point of the adjacent time points, where the subway shield downward penetration construction starts.
In this embodiment, the second time line refers to a construction time line from a second time point in the previous adjacent time point, where the subway shield underpass construction starts based on the ideal starting time point, the first time line is one more time point than the second time line, and the first time point is before the second time point in the same adjacent time point.
In this embodiment, the ideal loss factor refers to a factor that causes reasonable loss of the subway shield machine when the subway shield machine normally performs the underpass construction, and includes: normal wear of the subway shield machine, cutter head aging, shield aging and corrosion of trace elements in the environment to the subway shield machine.
In this embodiment, the first ideal loss array refers to an array formed by all ideal loss factors of the subway shield machine at each moment in the first timeline.
In this embodiment, the second ideal loss array refers to an array formed by all ideal loss factors of the subway shield machine at each moment in the second timeline, and the loss factor of the second ideal loss array is less than that of the first ideal loss array by one moment.
In this embodiment, the first adjustment refers to removing the influence of the ideal loss factor from the actual data at the first time in the adjacent times, so as to achieve the purposes of reducing the ideal loss interference on the real-time data information and predicting the construction risk more accurately, for example, the actual data is 0.8, and after the first adjustment is performed, 1 is obtained, that is, the interference of the ideal loss on the actual data is removed.
In this embodiment, the second adjustment refers to removing an influence of the ideal loss factor from the actual data at the second time in the adjacent times, so as to achieve the purposes of reducing the ideal loss interference on the real-time data information and predicting the construction risk more accurately, for example, the actual data is 0.8, and after the second adjustment, 1 is obtained, that is, the interference of the ideal loss on the actual data is removed.
In this embodiment, the first danger response result refers to a response result of danger in the subway shield underpass construction at the first moment to actual data information at the first moment, that is, a dangerous situation that may exist in the process.
In this embodiment, the second dangerous response result refers to a response result of a danger in the subway shield underpassing construction at the second time to actual data information at the second time, that is, a dangerous situation that may exist in the process.
In this embodiment, the association factor refers to a factor that obtains a continuous influence association of the first risk response result on the second risk response result by corresponding to all the first risk response results and the second risk response results before the second time in the adjacent time, where the first time and the second time in each adjacent time before the second time may have a risk influence factor, for example, the existence of the risk factor 1 in time 1 may cause the existence of the risk factor 2 in time 1, and the risk factor 1 in time 1 may continue to increase the risk at time 2.
In this embodiment, the first error data set refers to an error data set obtained by splitting the analysis prediction result and the actual data information corresponding to the second time in the adjacent time according to the subway shield machine itself and comparing the split result with the data related to the subway shield machine itself, where the data related to the subway shield machine itself includes: the shield bears the pressure value and the cutter head working data.
In this embodiment, the second error data set refers to an error data set obtained by splitting the analysis prediction result and the actual data information corresponding to the second time in the adjacent times according to the construction area of the subway shield machine and comparing the analysis prediction result with the data related to the construction area of the subway shield machine, where the data related to the construction area of the subway shield machine includes: the water-soil-sand content proportion of the region and the number of the pipelines of the region.
In this embodiment, the adjustment information refers to the first error data set and the second error data set.
In this embodiment, the error analysis model refers to a case where errors may occur in the first error data set and the second error data set respectively through training of the historical error data sets and their corresponding error weights.
In this embodiment, the data state refers to various determined parameters of the data at the time, such as data error, error weight, data type, and the like.
In this embodiment, the risk setting database includes data states and corresponding preset risk values, and the preset risk values corresponding to different data states may be different or the same.
In this embodiment, the preset risk value refers to a preset risk value for setting a possible risk label for each adjustment index in the adjustment information and comparing and judging whether a risk may occur to a data state of each error data.
In this embodiment, the dangerous tag may be, for example, a tag that the subway shield machine itself may have a fault abnormality or the like, or a dangerous tag that the construction environment may have a collapse, a water leakage or the like.
In this embodiment, the danger tag is a set possibility of danger, and different warnings are configured for different tags.
The working principle and the beneficial effects of the technical scheme are as follows: the actual data information of the subway shield underpass construction at the first moment and the second moment in the adjacent moments is analyzed to obtain the correlation factor of each adjacent moment, the second moment is analyzed and predicted, error analysis is combined to obtain the adjustment information and set possible dangerous labels, the dangerous condition which possibly occurs at the time of continuing the construction is predicted, the related early warning operation is reasonably matched for different labels, the effect of effective reminding is facilitated, and the construction efficiency is effectively improved.
Example 5:
on the basis of the foregoing embodiment 4, respectively analyzing the data state of each error data, and assigning a corresponding preset risk value to each data state from the risk setting database, and further setting a possible risk label for each adjustment index in the corresponding adjustment information, includes:
determining the data state of the corresponding error data according to the error weight and the data type of each error data;
matching a preset danger value consistent with the data state based on the danger setting database;
calibrating a preset danger value for each error data in the adjustment information, and determining a danger level by combining the calibrated error weight;
dividing the adjustment information according to the category of the acquired data information, and determining a danger sequence of each division result based on danger levels;
meanwhile, the number of first indexes of each division result is determined based on the category of the acquired data information, and the index label setting state of each first index is obtained based on the danger sequence;
when the setting state of the index tag is 0, judging that no danger tag is required to be set corresponding to the first index;
and when the setting state of the index tag is not 0, judging that a possible danger tag needs to be set corresponding to the first index.
In this embodiment, the type of the collected data information refers to a type formed according to different attributes of the data information when data collection is performed, where the attributes may be divided according to dynamic attributes (devices on the subway shield machine whose displacement may change) and static attributes (devices on the subway shield machine whose displacement does not change), for example, the dynamic attributes include cutterhead working data, and the static attributes include shield bearing pressure values.
In this embodiment, the adjustment information includes data 1, 2, 3, 4, and 5, and after being divided according to categories, category 1 is obtained: data 1, 3, 4, and taking the danger levels of the data 1, 3, 4 as corresponding sequence values to obtain a danger sequence, wherein the category 2: data 2 and 5, and obtaining the danger sequence according to the danger level of the data 2 and 5 as the corresponding sequence value.
At this time, when the number of indexes included in the category 1 and the number of indexes included in the category 2 are determined, if the data 1 and 3 belong to the same index, the sequence values corresponding to the data 1 and 3 are obtained from the danger sequence to set the state of the index tag, and the category 1 includes an image acquisition index and a sound acquisition index;
if the index 1 is an image acquisition index, the index 2 is a sound acquisition index, the corresponding data 1 in the category 1 is sound acquisition data, and the data 3 and 4 are image acquisition data, at this time, the tag setting state of the index 1 can be determined by the sequence value corresponding to the data 1, and is related to the danger alarm output mode, and the tag setting state of the index 2 is determined according to the sequence values corresponding to the data 3 and 4.
The working principle and the beneficial effects of the technical scheme are as follows: through the analysis to adjustment information, set up probably dangerous label to every first index, conveniently carry out the early warning according to probably dangerous label and remind, guarantee the effective progress of construction.
Example 6:
on the basis of the embodiment 1, the method for calibrating the danger of the acquired actual data information at each moment and constructing the first danger prediction model of the underground shield tunneling based on the digital twin technology comprises the following steps:
carrying out hazard calibration on the acquired actual data information at each moment based on a hazard calibration model;
and constructing a first risk prediction model for the underground shield to penetrate through based on a digital twin technology and by combining the acquisition result at each moment and the risk calibration result at each moment.
In this embodiment, the risk calibration model refers to a method for determining that a risk may occur in the collected actual data information at each time through training of corresponding risk calibration of the historical data information.
The working principle and the beneficial effects of the technical scheme are as follows: by means of risk calibration of information data acquired in real time, a first risk prediction model for subway shield downward penetration is constructed based on a digital twinning technology, and accuracy of follow-up early warning and reminding is improved.
Example 7:
on the basis of the above embodiment 1, the first risk prediction model is optimized based on adjustment information at adjacent time and a possible risk label, a risk possibly existing in the continued construction is predicted, and a corresponding second early warning operation is performed, including:
based on a vector analysis model, obtaining adjustment information of adjacent moments and an optimized vector corresponding to a possible danger label;
optimizing the first risk prediction model based on the optimization vectors corresponding to all adjacent moments before the continuous construction moment, and predicting the possible risks in the continuous construction;
and continuously setting a second early warning event to the possible danger matching based on the danger-early warning database, and executing corresponding second early warning operation based on the second early warning event.
In this embodiment, the vector analysis model refers to a model that is trained based on historical adjustment information and possible danger labels and converts adjustment information and possible danger labels at adjacent time points into an optimization vector.
In this embodiment, the optimization vector is derived based on a combination of the model versus both the adjustment information and the possible threat signatures.
In this embodiment, the second warning event refers to an instruction or the like that can control execution of the warning operation.
The working principle and the beneficial effects of the technical scheme are as follows: the risk is predicted by carrying out vector optimization on the adjustment information and the possible dangerous labels at adjacent moments, and effective early warning operation is executed to set an event to the risk, so that the construction efficiency is further ensured.
Example 8:
on the basis of the above embodiment 5, calibrating a preset risk value for each error data in the adjustment information, and determining a risk level by combining the calibrated error weight, including:
acquiring a data set which belongs to the same index as the corresponding error data;
calculating the danger level Y corresponding to the data error;
wherein Y1 represents a preset danger value calibrated by a corresponding data error; y2 represents the error weight calibrated by the corresponding data error;
a first standard conversion coefficient representing a preset risk value;
a second standard conversion coefficient representing a weight to the error; n1 represents the number of first error data in the data set; n2 represents the number of second error data in the data set;
representing an influence factor of the corresponding i1 st first error data on the corresponding error data;
representing an influence factor of the corresponding i2 th second error data on the corresponding error data; n1 is greater than n2, and the second error data is data of the first error data; []Representing the rounding symbol.
In this embodiment, the first standard conversion coefficient refers to a coefficient that can convert a preset risk value into a numerical value in the same unit as the risk level, thereby achieving the purpose of convenient calculation.
In this embodiment, the second standard conversion coefficient refers to a coefficient that can convert the error weight into a value in the same unit as the risk level, thereby achieving the purpose of convenient calculation.
In this embodiment, a data set that belongs to the same index as the corresponding error data is called, mainly to determine the influence of the data set on the error data, and to ensure the accuracy of the calculation of the risk level.
In this embodiment, for example, a value of n2 is 2, a value of n1 is 1, and n1 is at least 2, it should be noted that the second error data corresponding to n2 is obtained based on n1/2 data obtained after the first error data is sorted from large to small according to the influence factor of the corresponding error data, that is, the obtained data has a larger influence factor.
In the embodiment shown in the above-mentioned figure,
and with
Has a value range of [0,1 ]]But in the normal case, however,
is greater than
In (1).
The working principle and the beneficial effects of the technical scheme are as follows: through the accurate calculation to danger level, and then to adjustment information analysis, the dangerous condition that probably takes place at the time of the prediction continuation construction provides the effective basis for follow-up accurate matching early warning incident.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (7)
1. A danger early warning method for underground shield underpass construction is characterized by comprising the following steps:
step 1: acquiring actual data information of each adjacent moment in the construction process of the subway shield underpass;
step 2: performing pre-analysis prediction on a second moment based on actual data information of a first moment in each adjacent moment to obtain an analysis prediction result;
and 3, step 3: comparing the analysis prediction result with the actual data information at the second moment, determining adjustment information corresponding to adjacent moments, setting danger labels for the corresponding adjustment information, and executing first early warning operation based on the set danger labels;
and 4, step 4: carrying out hazard calibration on the acquired actual data information at each moment, and constructing a first hazard prediction model of the underground shield penetration based on a digital twinning technology;
and 5: optimizing the first risk prediction model based on the adjustment information and the risk label at the adjacent moment, predicting the risk existing in the continuous construction, and executing corresponding second early warning operation;
wherein, step 3, include:
acquiring a construction project plan and a construction estimation result of the pre-determined underground shield underpass construction, simulating the construction project plan and the construction estimation result, and acquiring ideal information at each moment;
acquiring actual data information corresponding to a first moment in adjacent moments and actual data information corresponding to a second moment in previous adjacent moments;
acquiring a first time line corresponding to a first moment in adjacent moments based on the ideal starting moment and acquiring a second time line corresponding to a second moment in the previous adjacent moment based on the ideal starting moment;
constructing and obtaining a first ideal loss array of a first time line and a second ideal loss array of a second time line based on the obtained ideal loss factor of the subway shield machine at each moment;
according to the first ideal loss array, carrying out first adjustment on actual data information corresponding to a first moment in adjacent moments to obtain first information, and meanwhile, according to a second ideal loss array, carrying out second adjustment on actual data information corresponding to a second moment in the previous adjacent moments to obtain second information;
comparing the first information with first ideal information at the corresponding moment to obtain a first danger response result, and simultaneously comparing the second information with second ideal information at the corresponding moment to obtain a second danger response result;
analyzing all first danger response results and second danger response results before the second moment in the corresponding adjacent moments to obtain the association factors of each adjacent moment before the second moment in the corresponding adjacent moments;
performing pre-analysis prediction on a second moment in the corresponding adjacent moments by combining actual data information of the first moment in the corresponding adjacent moments based on the correlation factors to obtain analysis prediction results;
splitting and comparing the analysis prediction result with actual data information corresponding to a second moment in adjacent moments according to the subway shield machine and a construction area of the subway shield machine;
according to the splitting comparison result, obtaining a first error data set related to the subway shield machine and a second error data set related to a construction area of the subway shield machine;
obtaining adjustment information based on the first error dataset and the second error dataset;
inputting the first error data set and the second error data set into an error analysis model, outputting error weights of different error data in different data sets, and calibrating the error weights on corresponding error data in the adjustment information;
respectively analyzing the data state of each error data, distributing a corresponding preset danger value to each data state from a danger setting database, and further setting a danger label for each adjustment index in corresponding adjustment information;
and setting a first early warning event for each dangerous label based on a danger-early warning database, and executing corresponding first early warning operation based on the first early warning event.
2. The method for early warning of the danger in the underground shield tunneling construction according to claim 1, wherein the step of collecting the actual data information of each adjacent moment in the underground shield tunneling construction process comprises the following steps:
monitoring a construction result of a target area in the process of downward penetration construction of the subway shield machine to obtain a first monitoring result;
when the subway shield machine is in underpass construction, monitoring the working operation of the subway shield machine to obtain a second monitoring result;
and acquiring a first monitoring result and a second monitoring result at the same time, and acquiring actual data information at adjacent times.
3. The method for pre-warning the danger in the underground shield tunneling construction according to claim 2, wherein the step of obtaining the first monitoring result and the second monitoring result at the same time and obtaining the actual data information at the adjacent time comprises the steps of:
carrying out result denoising processing on the obtained first monitoring result and the second monitoring result at the same time;
and obtaining actual data information at adjacent moments according to the denoising processing result.
4. The method for warning the danger in the underground shield tunneling construction according to claim 1, wherein the ideal information includes: ideal operation parameters, ideal loss factors and ideal construction conditions of a target area of the subway shield machine.
5. The method for warning dangers during shield tunneling of subways as recited in claim 1, wherein the step of analyzing the data state of each error data, assigning a corresponding preset danger value to each data state from a danger setting database, and setting a danger label for each adjustment index in the corresponding adjustment information comprises the steps of:
determining the data state of the corresponding error data according to the error weight and the data type of each error data;
matching a preset danger value consistent with the data state based on the danger setting database;
calibrating a preset danger value for each error data in the adjustment information, and determining a danger level by combining the calibrated error weight;
dividing the adjustment information according to the category of the acquired data information, and determining a danger sequence of each division result based on a danger level;
meanwhile, the number of first indexes of each division result is determined based on the category of the acquired data information, and the index label setting state of each first index is obtained based on the danger sequence;
when the setting state of the index tag is 0, judging that no danger tag is required to be set corresponding to the first index;
and when the setting state of the index tag is not 0, judging that a danger tag needs to be set corresponding to the first index.
6. The method for danger early warning in subway shield underpass construction according to claim 1, wherein the steps of carrying out danger calibration on the acquired actual data information at each moment and constructing a first danger prediction model of subway shield underpass based on a digital twin technology comprise:
carrying out hazard calibration on the acquired actual data information at each moment based on a hazard calibration model;
and constructing a first risk prediction model for the underground shield to penetrate through based on a digital twin technology and by combining the acquisition result at each moment and the risk calibration result at each moment.
7. The method for danger early warning in subway shield underpass construction according to claim 1, wherein the first danger prediction model is optimized based on adjustment information and danger labels at adjacent moments, and the danger existing in the continued construction is predicted, and a corresponding second early warning operation is performed, and the method comprises:
based on a vector analysis model, obtaining adjustment information of adjacent moments and an optimized vector corresponding to a danger label;
optimizing the first risk prediction model based on the optimization vectors corresponding to all adjacent moments before the continuous construction moment, and predicting the risks existing in the continuous construction;
and continuously setting a second early warning event for the existing danger matching based on a danger-early warning database, and executing corresponding second early warning operation based on the second early warning event.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211283629.2A CN115358494B (en) | 2022-10-20 | 2022-10-20 | Danger early warning method for subway shield underpass construction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211283629.2A CN115358494B (en) | 2022-10-20 | 2022-10-20 | Danger early warning method for subway shield underpass construction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115358494A CN115358494A (en) | 2022-11-18 |
| CN115358494B true CN115358494B (en) | 2023-01-06 |
Family
ID=84008256
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211283629.2A Active CN115358494B (en) | 2022-10-20 | 2022-10-20 | Danger early warning method for subway shield underpass construction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115358494B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117235874B (en) * | 2023-11-14 | 2024-02-20 | 中电建铁路建设投资集团有限公司 | Track deformation prediction method and system based on shield tunneling |
| CN117646657B (en) * | 2024-01-30 | 2024-04-16 | 中电建铁路建设投资集团有限公司 | Monitoring and early warning system for slurry shield downward penetrating technology |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012082676A (en) * | 2011-04-11 | 2012-04-26 | Takenaka Komuten Co Ltd | Displacement controlling method |
| CN111058855B (en) * | 2019-11-11 | 2021-03-16 | 北京住总集团有限责任公司 | Deformation control method and evaluation system for shield underpassing structure |
| CN111636891B (en) * | 2020-06-08 | 2022-04-08 | 中铁高新工业股份有限公司 | Real-time shield attitude prediction system and construction method of prediction model |
| CN111985804B (en) * | 2020-08-18 | 2021-09-10 | 华中科技大学 | Shield approaching existing tunnel safety evaluation method based on data mining and data fusion |
| CN112418683A (en) * | 2020-11-26 | 2021-02-26 | 华中科技大学 | Construction risk evaluation method for shield underpass existing structure |
| CN113362469B (en) * | 2021-08-09 | 2021-10-08 | 长沙市轨道交通三号线建设发展有限公司 | Shield tunnel construction early warning method integrating city building information and stratum structure |
| CN114329810B (en) * | 2021-11-16 | 2024-04-16 | 中国水利水电科学研究院 | Real-time prediction method for working posture of shield tunneling machine based on big data |
| CN114000907A (en) * | 2021-12-10 | 2022-02-01 | 重庆邮电大学 | Mine ventilation equipment intelligent regulation and control system based on digital twin technology |
| CN114881440A (en) * | 2022-04-26 | 2022-08-09 | 济南交通发展投资有限公司 | Risk control method and system for shield tunnel to pass through high-speed railway bridge downwards |
-
2022
- 2022-10-20 CN CN202211283629.2A patent/CN115358494B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115358494A (en) | 2022-11-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115358494B (en) | Danger early warning method for subway shield underpass construction | |
| Guo et al. | Assessment of rockburst risk using multivariate adaptive regression splines and deep forest model | |
| CN111222683B (en) | PCA-KNN-based comprehensive grading prediction method for TBM construction surrounding rock | |
| CN112462736B (en) | Wind turbine generator fault diagnosis method based on data analysis | |
| CN108470095A (en) | TBM based on data-driven radial basis function model promotes force prediction method | |
| WO2016034945A2 (en) | Stuck pipe prediction | |
| CN115455791B (en) | Method for improving landslide displacement prediction accuracy based on numerical simulation technology | |
| CN108376293B (en) | ZJ17 cigarette equipment maintenance intelligent prediction method based on fuzzy mathematics improved analytic hierarchy process | |
| CN110348510B (en) | Data preprocessing method based on staged characteristics of deepwater oil and gas drilling process | |
| CN113190902B (en) | Prediction method and system for earth surface displacement caused by tunnel construction | |
| CN108536980B (en) | Gas detector discrete site selection optimization method considering reliability factor | |
| CN116152674A (en) | Dam unmanned aerial vehicle image crack intelligent recognition method based on improved U-Net model | |
| CN116777085B (en) | Coal mine water damage prediction system based on data analysis and machine learning technology | |
| CN116894213A (en) | Method for identifying working condition of excavator and working condition identifying device of excavator | |
| CN116797017A (en) | TBM construction risk evaluation method and system based on fuzzy mathematical theory | |
| CN116295230A (en) | Intelligent monitoring system for deformation of weak surrounding rock of shallow-buried large-section tunnel | |
| CN113657515B (en) | Classification method for judging and improving surrounding rock grade of FMC model tunnel based on rock opportunity sense parameters | |
| CN111899119B (en) | Intelligent alarm suppression method and system for coal-fired power plant | |
| CN113482595B (en) | Drilling overflow early warning method, system, equipment and storage medium | |
| CN114382490A (en) | Shield tunneling machine cutter head wear assessment and prediction method | |
| CN113158562A (en) | TBM rock machine mapping construction method and system based on physical constraint and data mining | |
| Wu et al. | Multisource information fusion for real-time prediction and multiobjective optimization of large-diameter slurry shield attitude | |
| CN116562433B (en) | TBM hob life prediction method and system based on CSM-GRU model | |
| CN111594197B (en) | Tunnel broken section advanced intelligent sensing method based on TBM rock machine information | |
| CN118395193B (en) | Slope instability prediction method and system based on artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |