CN116934262B - Construction safety supervision system and method based on artificial intelligence - Google Patents
Construction safety supervision system and method based on artificial intelligence Download PDFInfo
- Publication number
- CN116934262B CN116934262B CN202310925926.0A CN202310925926A CN116934262B CN 116934262 B CN116934262 B CN 116934262B CN 202310925926 A CN202310925926 A CN 202310925926A CN 116934262 B CN116934262 B CN 116934262B
- Authority
- CN
- China
- Prior art keywords
- construction
- area
- constructed
- probability
- unit
- 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 232
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 18
- 230000002159 abnormal effect Effects 0.000 claims abstract description 51
- 238000001514 detection method Methods 0.000 claims abstract description 35
- 238000005096 rolling process Methods 0.000 claims abstract description 35
- 238000004458 analytical method Methods 0.000 claims abstract description 17
- 230000005856 abnormality Effects 0.000 claims description 36
- 238000012216 screening Methods 0.000 claims description 25
- 238000012544 monitoring process Methods 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000006467 substitution reaction Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
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
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
-
- 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
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Computer Security & Cryptography (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to the technical field of construction safety supervision, in particular to an artificial intelligence-based construction safety supervision system and method, comprising the following steps: the construction area detection module, the construction information acquisition module, the database, the risk range analysis module and the construction safety supervision module detect the ground flatness of the current area to be constructed through the construction area detection module, the construction information acquisition module acquires the ground detection information and the construction abnormal information of the area subjected to historical construction, all acquired data are stored through the database, the risk area is screened out in the current area to be constructed through the risk range analysis module, the construction safety supervision is carried out on the mechanical equipment used for construction through the construction safety supervision module, the problem of rolling is timely warned and reminded when the mechanical equipment enters the risk area, the problem of rolling caused by rugged ground of the construction area in hydraulic engineering construction is reduced, and the safety of hydraulic engineering construction is improved.
Description
Technical Field
The invention relates to the technical field of construction safety supervision, in particular to a construction safety supervision system and method based on artificial intelligence.
Background
With the progress of technology, the construction quality of the hydraulic engineering is guaranteed, but the safety problem is not thoroughly solved, the safety supervision work in the water conservancy construction process is always the key point of the hydraulic engineering, the construction cost can be reduced, the economic benefit and the social benefit of construction enterprises are improved, the overall planning of water resources is realized, and the steady and coordinated development of the water conservancy industry is promoted;
however, there is a certain potential safety hazard in the existing hydraulic engineering construction, which may cause construction safety accidents, for example: in the construction environment of hydraulic engineering, the ground is mostly rugged, so that mechanical equipment for construction works unstably, safety accidents such as rolling over and turning over of the mechanical equipment are easy to occur, a certain safety risk exists, equipment problems should be paid attention to a construction area where equipment rolling over is easy to occur so as to prevent the occurrence of the safety accidents, safety supervision and reminding work are not performed in advance when the mechanical equipment is in a part of risky area, the problem that rolling over of the mechanical equipment is caused by rugged ground in the construction area cannot be effectively avoided, and the safety of hydraulic engineering construction cannot be improved.
Therefore, there is a need for an artificial intelligence based construction safety supervision system and method to solve the above problems.
Disclosure of Invention
The invention aims to provide an artificial intelligence-based construction safety supervision system and method, which are used for solving the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: a construction safety supervision system based on artificial intelligence, the system comprising: the system comprises a construction area detection module, a construction information acquisition module, a database, a risk range analysis module and a construction safety supervision module;
the output end of the construction area detection module is connected with the input end of the construction information acquisition module, the output end of the construction information acquisition module is connected with the input end of the database, the output end of the database is connected with the input end of the risk range analysis module, and the output end of the risk range analysis module is connected with the input end of the construction safety supervision module;
the construction area detection module is used for detecting the ground flatness of the current area to be constructed and transmitting the detection result to the database;
the construction information acquisition module is used for acquiring ground detection information and construction abnormality information of a region subjected to historical construction and transmitting all acquired data into the database;
the database is used for storing all received data;
the risk range analysis module is used for screening out a risk area from the area to be constructed currently;
the construction safety supervision module is used for carrying out construction safety supervision on mechanical equipment for construction.
Further, the construction area detection module comprises a ground leveling detection unit and a construction area dividing unit;
the output end of the construction area dividing unit is connected with the input end of the ground leveling detection unit;
the construction area dividing unit is used for dividing the current area to be constructed into a plurality of areas at random, and the plurality of areas form a finished area to be constructed;
the ground flatness detection unit is used for detecting flatness of the ground of the currently divided area to be constructed by using a flatness detector, marking the ground flatness of different areas by using a deep learning algorithm, and acquiring a ground flatness data set as a test set;
the ground flatness of different areas is marked by using an artificial intelligence technology, so that the method is beneficial to quickly integrating the test data of the whole area to be constructed so as to input the test data into a corresponding model.
Further, the construction information acquisition module comprises an area information acquisition unit and a history abnormal information acquisition unit;
the input end of the area information acquisition unit is connected with the output end of the ground leveling detection unit, and the output ends of the area information acquisition unit and the historical abnormal information acquisition unit are connected with the input end of the database;
the area information acquisition unit is used for acquiring the ground flatness of an area which is constructed in the past;
the historical abnormal information acquisition unit is used for acquiring the number of times that mechanical equipment rolls over in the past in the corresponding constructed area.
Further, the risk range analysis module comprises an abnormality prediction model building unit, an abnormality probability prediction unit and a risk region screening unit;
the input end of the abnormal prediction model establishing unit is connected with the output end of the database, the output end of the abnormal prediction model establishing unit is connected with the input end of the abnormal probability predicting unit, and the output end of the abnormal probability predicting unit is connected with the input end of the risk area screening unit;
the abnormal prediction model building unit is used for analyzing the probability of the rolling over of the mechanical equipment in the constructed area and building a construction abnormal prediction model by combining the ground flatness and probability information;
the abnormal probability prediction unit is used for inputting the ground flatness data in the test set into the construction abnormal prediction model and predicting the probability of occurrence of rolling of mechanical equipment in the current area to be constructed;
the risk area screening unit is used for comparing the predicted probability and screening the risk area from the current area to be constructed.
Further, the construction safety supervision module comprises a construction equipment monitoring unit and a risk early warning unit;
the output end of the construction equipment monitoring unit is connected with the input end of the risk early warning unit, and the input end of the risk early warning unit is connected with the output end of the risk area screening unit;
the construction equipment monitoring unit is used for monitoring the position of the mechanical equipment in real time after the construction of the current area to be constructed is started;
the risk early warning unit is used for sending an alarm signal to the monitoring terminal when the mechanical equipment is monitored to be in the risk area, and reminding of the problem of rolling over of the mechanical equipment.
An artificial intelligence-based construction safety supervision method comprises the following steps:
z1: detecting the ground flatness of the current area to be constructed;
z2: collecting ground detection information and construction abnormality information of a region subjected to historical construction;
z3: building a construction abnormality prediction model, and predicting construction abnormality probability of the classified area;
z4: comparing construction abnormal probability, and screening out a risk area from the current area to be constructed;
z5: and when the mechanical equipment for construction is in the dangerous area, carrying out construction safety supervision on the mechanical equipment.
Further, in step Z1: dividing the current area to be constructed into k areas randomly, detecting the ground flatness of the k areas by using a flatness detector, and obtaining a ground flatness set of the k areas to be constructed currently as Q= { Q 1 ，Q 2 ，…，Q i ，…，Q k }。
Further, in step Z2: the ground flatness set of the area where the previous construction is collected is M= { M 1 ，M 2 ，…，M f The number of times of mechanical equipment rolling in the past of the corresponding constructed area is set as C= { C 1 ，C 2 ，…，C f And (3) wherein, the elements in C are not 0, and f represents the number of the collected areas which are constructed in the past.
Further, in step Z3: according to the formulaCalculating the construction anomaly probability of a randomly constructed area as P j Obtaining a construction anomaly probability set of P= { P for f constructed areas 1 ，P 2 ，…，P f J=1, 2, …, f, j represents the j-th constructed area, C j Representing the number of times the mechanical equipment has been rolled over in the past for the jth constructed region, and obtaining a training data set as { (M) 1 ，P 1 )，(M 2 ，P 2 )，…，(M j ，P j )，…，(M f ，P f ) Training ofPerforming straight line fitting on the training data set, and establishing a construction anomaly prediction model: />Wherein (1)>And->Representing fitting coefficients by solving +.>And->Obtaining a final construction abnormality prediction model, and respectively solving the following formulas>And->
Wherein M is j Represents the ground flatness of the jth constructed area, will Q i Substituting the construction anomaly prediction model to let x=q i Predicting and obtaining the construction abnormality probability Y of the ith area to be constructed currently i ，Substituting the ground flatness of the k areas to be constructed currently into a construction anomaly prediction model to obtain the k areas to be constructed currentlyThe construction anomaly probability set is Y= { Y 1 ，Y 2 ，…，Y i ，…，Y k }, wherein Q i Representing the ground flatness of the ith area to be constructed currently;
in order to judge the probability that the rolling abnormality phenomenon of the mechanical equipment occurs in the current area to be constructed, historical rolling abnormality data of the mechanical equipment and ground flatness data of the area where the mechanical equipment is located when the rolling occurs are acquired and analyzed through a big data technology, the data are combined to form data points which are used as training samples for building a construction abnormality prediction model, a construction abnormality prediction model is built by using a least square method, the purpose is to predict the probability that the rolling abnormality phenomenon of the mechanical equipment occurs in the area with different current flatness, and the prediction abnormality probability of the mechanical equipment rolling occurs in combination with the historical actual data is favorable for improving the accuracy of a prediction result.
Further, in step Z4: comparing construction anomaly probabilities of k areas to be constructed currently, arranging the construction anomaly probabilities in a sequence from large to small, and dividing the k areas into n categories according to the construction anomaly probability, wherein the construction anomaly probabilities of all areas in the former category are larger than those of the latter category, and acquiring a random classification result, wherein the construction anomaly probability mean value set of each area in the n categories is S= { S 1 ，S 2 ，…，S a ，…，S n -selecting an optimal classification result according to the following formula:
wherein L is e Representing the difference degree of construction abnormality probability of n-type region in the e-th classification result, S a Representing the construction abnormal probability mean value of an a-th class region in n classes in the e-th class classification result, obtaining the difference degree of the construction abnormal probability of the n-class region in different classification results through the same calculation mode, comparing the difference degree, selecting the classification result with the largest difference degree as the optimal classification result, and screening out the region to be constructed of the first class in the optimal classification result as the risk region;
after the construction abnormal probabilities of different areas are predicted, the areas with larger risks are screened out according to probability data, and the safety supervision work is performed when the mechanical equipment enters the areas with larger risks, so that the problems that the construction areas are uneven and the mechanical equipment rolls over easily are reminded in time, the phenomenon that the mechanical equipment rolls over due to rugged ground of the construction areas in hydraulic engineering construction is reduced, and the safety of hydraulic engineering construction is improved;
when screening the risk areas, the areas are divided into different types according to the abnormal probability, and the optimal classification result is selected to classify the areas with the most similar abnormal probability into one type, so that the to-be-constructed areas with the larger abnormal probability are selected to be used as the risk areas, the selected risk areas are generally more prone to the problem of rolling over of mechanical equipment, the mechanical equipment in the risk areas selected by the method is early warned, and the effective degree and the value for reminding of the problem of rolling over of the mechanical equipment are improved.
Further, in step Z5: after the construction of the current area to be constructed is started, the position of the mechanical equipment is monitored in real time, and when the mechanical equipment is monitored to be in the risk area, an alarm signal is sent to the monitoring terminal to remind the attention of the problem of rolling over of the mechanical equipment.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, the safety supervision is carried out on the mechanical equipment in the construction process, so that the probability of construction safety accidents is reduced; the method comprises the steps of collecting and analyzing historical mechanical equipment rolling abnormal data and ground flatness data of an area where mechanical equipment is located when rolling occurs through a big data technology, combining the data to form data points, using the data points as training samples for building a construction abnormal prediction model, building the construction abnormal prediction model by using a least square method, predicting the probability that the mechanical equipment rolling abnormal occurs in the area with different current flatness, and predicting the abnormal probability by combining the actual data of the mechanical equipment rolling occurring in the history, so that the accuracy of a prediction result is improved;
after the construction abnormal probabilities of different areas are predicted, the areas with larger risks are screened out according to probability data, safety supervision work is done in advance when mechanical equipment enters the areas with larger risks, the problems that the construction areas are uneven and the mechanical equipment rolls over easily are reminded in time, the phenomenon that the mechanical equipment rolls over due to uneven ground of the construction areas in hydraulic engineering construction is reduced, and the safety of hydraulic engineering construction is improved;
when the risk areas are screened, the areas are divided into different types according to the abnormal probability, and the optimal classification result is selected, so that the areas with the most similar abnormal probability are classified, the areas to be constructed with the larger abnormal probability are favorable for being selected as the risk areas, the mechanical equipment in the risk areas selected by the method is early warned, and the effective degree and the value for reminding the attention of the problem of rolling of the mechanical equipment are improved.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a block diagram of an artificial intelligence based construction safety supervision system of the present invention;
FIG. 2 is a flow chart of a construction safety supervision method based on artificial intelligence of the invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
The invention is further described below with reference to fig. 1-2 and the specific embodiments.
Embodiment one:
as shown in fig. 1, the present embodiment provides an artificial intelligence based construction safety supervision system, which includes: the system comprises a construction area detection module, a construction information acquisition module, a database, a risk range analysis module and a construction safety supervision module;
the output end of the construction area detection module is connected with the input end of the construction information acquisition module, the output end of the construction information acquisition module is connected with the input end of the database, the output end of the database is connected with the input end of the risk range analysis module, and the output end of the risk range analysis module is connected with the input end of the construction safety supervision module;
the construction area detection module is used for detecting the ground flatness of the current area to be constructed and transmitting the detection result to the database;
the construction information acquisition module is used for acquiring ground detection information and construction abnormality information of the area subjected to historical construction and transmitting all acquired data into the database;
the database is used for storing all received data;
the risk range analysis module is used for screening out a risk area from the area to be constructed currently;
the construction safety supervision module is used for carrying out construction safety supervision on mechanical equipment for construction.
The construction area detection module comprises a ground leveling detection unit and a construction area dividing unit;
the output end of the construction area dividing unit is connected with the input end of the ground leveling detecting unit;
the construction area dividing unit is used for dividing the current area to be constructed into a plurality of areas at random;
the ground flatness detection unit is used for detecting flatness of the ground of the currently divided area to be constructed by using a flatness detector, marking the ground flatness of different areas through a deep learning algorithm, and acquiring a ground flatness data set as a test set.
The construction information acquisition module comprises an area information acquisition unit and a history abnormal information acquisition unit;
the input end of the regional information acquisition unit is connected with the output end of the ground leveling detection unit, and the output ends of the regional information acquisition unit and the historical abnormal information acquisition unit are connected with the input end of the database;
the area information acquisition unit is used for acquiring the ground flatness of the area which is constructed in the past;
the historical abnormal information acquisition unit is used for acquiring the number of times that mechanical equipment rolls over in the past in the corresponding constructed area.
The risk range analysis module comprises an abnormality prediction model establishment unit, an abnormality probability prediction unit and a risk region screening unit;
the input end of the abnormal prediction model establishing unit is connected with the output end of the database, the output end of the abnormal prediction model establishing unit is connected with the input end of the abnormal probability predicting unit, and the output end of the abnormal probability predicting unit is connected with the input end of the risk area screening unit;
the abnormal prediction model building unit is used for analyzing the probability of the rolling over of the mechanical equipment in the constructed area and building a construction abnormal prediction model by combining the ground flatness and probability information;
the abnormal probability prediction unit is used for inputting the ground flatness data in the test set into the construction abnormal prediction model and predicting the probability of occurrence of rolling over of mechanical equipment in the current area to be constructed;
the risk area screening unit is used for comparing the predicted probability and screening the risk area from the current area to be constructed.
The construction safety supervision module comprises a construction equipment monitoring unit and a risk early warning unit;
the output end of the construction equipment monitoring unit is connected with the input end of the risk early warning unit, and the input end of the risk early warning unit is connected with the output end of the risk area screening unit;
the construction equipment monitoring unit is used for monitoring the position of the mechanical equipment in real time after the construction of the current area to be constructed is started;
the risk early warning unit is used for sending an alarm signal to the monitoring terminal when the mechanical equipment is monitored to be in the risk area, and reminding of the problem of rolling over of the mechanical equipment.
Embodiment two:
as shown in fig. 2, the present embodiment provides an artificial intelligence based construction safety supervision method, which is implemented based on the supervision system in the embodiment, and specifically includes the following steps:
z1: detecting the ground flatness of the current area to be constructed, randomly dividing the current area to be constructed into k areas, detecting the ground flatness of the k areas by using a flatness detector, and obtaining a ground flatness set of the k areas to be constructed currently as Q= { Q 1 ，Q 2 ，…，Q i ，…，Q k }，
The flatness is measured as follows:
taking a random area as an example, selecting a horizontal plane as a reference plane, and detecting that the set of vertical distances from m points of the corresponding area to the reference plane is d= { d 1 ，d 2 ，…，d m Measure the flatness Q of the corresponding area in a mode of calculating standard deviation i ObtainingThe ground flatness of different areas is obtained in the same mode, and the larger the standard deviation is, the smaller the ground flatness of the corresponding area is judged, namely the more uneven the ground is;
for example: the current area to be constructed is randomly divided into 7 areas, the flatness detector is used for detecting the flatness of the ground in the 7 areas, and the set of the flatness of the ground in the 7 areas to be constructed is Q= { Q 1 ，Q 2 ，Q 3 ，Q 4 ，Q 5 ，Q 6 ，Q 7 }＝{0.31，0.25，0.55，0.96，0.36，0.72，0.63}；
Z2: collecting ground detection information and construction abnormality information of a region subjected to historical construction, wherein the ground flatness set of the region subjected to previous construction is M= { M 1 ，M 2 ，…，M f The number of times of mechanical equipment rolling in the past of the corresponding constructed area is set as C= { C 1 ，C 2 ，…，C f Wherein, the elements in C are not 0, f represents the number of the collected areas which are constructed in the past;
z3: building a construction abnormality prediction model, predicting construction abnormality probability of the classified area, and according to a formulaCalculating the construction anomaly probability of a randomly constructed area as P j Obtaining a construction anomaly probability set of P= { P for f constructed areas 1 ，P 2 ，…，P f J=1, 2, …, f, j represents the j-th constructed area, C j Representing the number of times the mechanical equipment has been rolled over in the past for the jth constructed region, and obtaining a training data set as { (M) 1 ，P 1 )，(M 2 ，P 2 )，…，(M j ，P j )，…，(M f ，P f ) Performing straight line fitting on the training data set, and establishing a construction anomaly prediction model:wherein (1)>And->Representing fitting coefficients by solving +.>And->Obtaining a final construction abnormality prediction model, and respectively solving the following formulas>And->
Wherein M is j Representing the ground flatness of the j-th constructed area;
for example: the ground flatness set of the area where the previous construction is collected is M= { M 1 ，M 2 ，M 3 ，M 4 ，M 5 The number of times of mechanical equipment rolling in the corresponding constructed area is C= { C = {0.69,0.72,0.23,0.15,0.35}, and the number of times of mechanical equipment rolling in the past is C= { C 1 ，C 2 ，C 3 ，C 4 ，C 5 The construction anomaly probability set of the 5 constructed areas is calculated as P= { P 1 ，P 2 ，P 3 ，P 4 ，P 5 The training data set is obtained as { (M) = { (0.16,0.08,0.24,0.32,0.20 } 1 ，P 1 )，(M 2 ，P 2 )，(M 3 ，P 3 )，(M 4 ，P 4 )，(M 5 ，P 5 ) The training data set is subjected to straight line fitting to establish a construction anomaly prediction model = { (0.69,0.16), (0.72,0.08), (0.23,0.24), (0.15,0.32), (0.35,0.20) }:calculated->Yielding y= -0.31x+0.33;
will Q i Substituting the construction anomaly prediction model to let x=q i Predicting and obtaining the construction abnormality probability Y of the ith area to be constructed currently i ，Substituting the ground flatness of the k areas to be constructed currently into a construction anomaly prediction model to predict that the construction anomaly probability set of the k areas to be constructed currently is Y= { Y 1 ，Y 2 ，…，Y i ，…，Y k And } wherein,Q i representing the ground flatness of the ith area to be constructed currently;
substituting to obtain a construction anomaly probability set of the k areas to be constructed currently as Y= { Y 1 ，Y 2 ，Y 3 ，Y 4 ，Y 5 ，Y 6 ，Y 7 }＝{0.23，0.25，0.16，0.03，0.22，0.11，0.13}；
Z4: comparing construction anomaly probabilities, screening out risk areas in the current areas to be constructed, comparing the construction anomaly probabilities of k areas to be constructed, arranging the construction anomaly probabilities in the order from large to small, dividing the k areas into n=3 types according to the construction anomaly probability, wherein the construction anomaly probabilities of all areas in the former type are larger than those in the latter type, obtaining a random classification result, wherein the construction anomaly probability sets of each area in the 3 types are {0.25,0.23}, {0.22,0.16,0.13}, and {0.11,0.03}, and the construction anomaly probability average value set of each area is S= { S 1 ，S 2 ，S 3 } = {0.24,0.17,0.07}, the optimal classification result is selected according to the following formula:
obtaining the difference L of construction abnormality probabilities of 3 types of areas in the corresponding classification result e ≈0.07，S a The construction anomaly probability mean value of the a-th class region in the n-th class is represented in the e-th class classification result, the difference degree of the construction anomaly probability of the n-th class region in different classification results is obtained through the same calculation mode, the difference degree is compared, the classification result with the largest difference degree is selected as the optimal classification result, and the optimal classification result is obtained: the construction anomaly probability sets of each type of region in the 3 types are {0.25,0.23,0.22}, {0.16,0.13,0.11}, and {0.03}, and the region to be constructed of the first type, namely the first, the second and the fifth regions are risk regions;
z5: after the construction of the current area to be constructed is started, the position of the mechanical equipment is monitored in real time, and when the mechanical equipment is monitored to be in the risk area, an alarm signal is sent to the monitoring terminal to remind the attention of the problem of rolling over of the mechanical equipment.
Finally, it should be noted that: the foregoing is merely a preferred example of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (5)
1. An artificial intelligence based construction safety supervision system, which is characterized in that: the system comprises: the system comprises a construction area detection module, a construction information acquisition module, a database, a risk range analysis module and a construction safety supervision module;
the output end of the construction area detection module is connected with the input end of the construction information acquisition module, the output end of the construction information acquisition module is connected with the input end of the database, the output end of the database is connected with the input end of the risk range analysis module, and the output end of the risk range analysis module is connected with the input end of the construction safety supervision module;
the construction area detection module is used for detecting the ground flatness of the current area to be constructed and transmitting the detection result to the database;
the construction information acquisition module is used for acquiring ground detection information and construction abnormality information of a region subjected to historical construction and transmitting all acquired data into the database;
the database is used for storing all received data;
the risk range analysis module is used for screening out a risk area from the area to be constructed currently;
the construction safety supervision module is used for carrying out construction safety supervision on mechanical equipment for construction;
the construction area detection module comprises a ground leveling detection unit and a construction area dividing unit;
the output end of the construction area dividing unit is connected with the input end of the ground leveling detection unit;
the construction area dividing unit is used for dividing the current area to be constructed into a plurality of areas at random;
the ground flatness detection unit is used for detecting flatness of the ground of the currently divided area to be constructed by using a flatness detector, marking the ground flatness of different areas by using a deep learning algorithm, and acquiring a ground flatness data set as a test set;
the risk range analysis module comprises an abnormality prediction model establishment unit, an abnormality probability prediction unit and a risk region screening unit;
the input end of the abnormal prediction model establishing unit is connected with the output end of the database, the output end of the abnormal prediction model establishing unit is connected with the input end of the abnormal probability predicting unit, and the output end of the abnormal probability predicting unit is connected with the input end of the risk area screening unit;
the abnormal prediction model building unit is used for analyzing the probability of the rolling over of the mechanical equipment in the constructed area and building a construction abnormal prediction model by combining the ground flatness and probability information;
the abnormal probability prediction unit is used for inputting the ground flatness data in the test set into the construction abnormal prediction model and predicting the probability of occurrence of rolling of mechanical equipment in the current area to be constructed;
the risk area screening unit is used for comparing the predicted probability and screening a risk area from the current area to be constructed;
dividing the current area to be constructed into k areas randomly, detecting the ground flatness of the k areas by using a flatness detector, and obtaining a ground flatness set of the k areas to be constructed currently as Q= { Q 1 ，Q 2 ，…，Q i ，…，Q k }；
The ground flatness set of the area where the previous construction is collected is M= { M 1 ，M 2 ，…，M f The number of times of mechanical equipment rolling in the past of the corresponding constructed area is set as C= { C 1 ，C 2 ，…，C f Wherein, the elements in C are not 0, f represents the number of the collected areas which are constructed in the past;
according to the formulaCalculating the construction anomaly probability of a randomly constructed area as P j Obtaining a construction anomaly probability set of P= { P for f constructed areas 1 ，P 2 ，…，P f J=1, 2, …, f, j represents the j-th constructed area, C j Representing the number of times the mechanical equipment has been rolled over in the past for the jth constructed region, and obtaining a training data set as { (M) 1 ，P 1 )，(M 2 ，P 2 )，…，(M j ，P j )，…，(M f ，P f ) Performing straight line fitting on the training data set, and establishing a construction anomaly prediction model: />Wherein (1)>And->Representing fitting coefficients by solving +.>And->Obtaining a final construction abnormality prediction model, and respectively solving the following formulas>And->
Wherein M is j Represents the ground flatness of the jth constructed area, will Q i Substituting the construction anomaly prediction model to let x=q i Predicting and obtaining the construction abnormality probability Y of the ith area to be constructed currently i ， Substituting the ground flatness of the k areas to be constructed currently into a construction anomaly prediction model to predict that the construction anomaly probability set of the k areas to be constructed currently is Y= { Y 1 ，Y 2 ，…，Y i ，…，Y k }, wherein Q i Representing the ground flatness of the ith area to be constructed currently;
comparing construction anomaly probabilities of k areas to be constructed currently, arranging the construction anomaly probabilities in order from large to small, dividing the k areas into n classes according to the construction anomaly probability, and obtaining a random classification result, wherein the construction anomaly probability average value set of each class of area in the n classes is S= { S 1 ，S 2 ，…，S a ，…，S n -selecting an optimal classification result according to the following formula:
wherein L is e Representing the difference degree of construction abnormality probability of n-type region in the e-th classification result, S a And (3) representing the construction anomaly probability mean value of the a-th class region in the n-th class in the e-th class classification result, obtaining the difference degree of the construction anomaly probabilities of the n-th class region in different classification results through the same calculation mode, comparing the difference degrees, selecting the classification result with the largest difference degree as the optimal classification result, and screening the to-be-constructed region of the first class in the optimal classification result as the risk region.
2. An artificial intelligence based construction safety supervision system according to claim 1, wherein: the construction information acquisition module comprises an area information acquisition unit and a history abnormal information acquisition unit;
the input end of the area information acquisition unit is connected with the output end of the ground leveling detection unit, and the output ends of the area information acquisition unit and the historical abnormal information acquisition unit are connected with the input end of the database;
the area information acquisition unit is used for acquiring the ground flatness of an area which is constructed in the past;
the historical abnormal information acquisition unit is used for acquiring the number of times that mechanical equipment rolls over in the past in the corresponding constructed area.
3. An artificial intelligence based construction safety supervision system according to claim 1, wherein: the construction safety supervision module comprises a construction equipment monitoring unit and a risk early warning unit;
the output end of the construction equipment monitoring unit is connected with the input end of the risk early warning unit, and the input end of the risk early warning unit is connected with the output end of the risk area screening unit;
the construction equipment monitoring unit is used for monitoring the position of the mechanical equipment in real time after the construction of the current area to be constructed is started;
the risk early warning unit is used for sending an alarm signal to the monitoring terminal when the mechanical equipment is monitored to be in the risk area, and reminding of the problem of rolling over of the mechanical equipment.
4. The construction safety supervision method based on artificial intelligence is characterized by comprising the following steps of: the method comprises the following steps:
z1: detecting the ground flatness of the current area to be constructed;
z2: collecting ground detection information and construction abnormality information of a region subjected to historical construction;
z3: building a construction abnormality prediction model, and predicting construction abnormality probability of the classified area;
z4: comparing construction abnormal probability, and screening out a risk area from the current area to be constructed;
z5: when the mechanical equipment for construction is in the risk area, carrying out construction safety supervision on the mechanical equipment;
in step Z1: dividing the current area to be constructed into k areas randomly, detecting the ground flatness of the k areas by using a flatness detector, and obtaining a ground flatness set of the k areas to be constructed currently as Q= { Q 1 ，Q 2 ，…，Q i ，…，Q k }；
In step Z2: the ground flatness set of the area where the previous construction is collected is M= { M 1 ，
M 2 ，…，M f The number of times of mechanical equipment rolling in the past of the corresponding constructed area is set as C= { C 1 ，C 2 ，…，C f Wherein, the elements in C are not 0, f represents the number of the collected areas which are constructed in the past;
in step Z3: according to the formulaCalculating the construction anomaly probability of a randomly constructed area as P j Obtaining a construction anomaly probability set of P= { P for f constructed areas 1 ，P 2 ，…，P f J=1, 2, …, f, j represents the j-th constructed area, C j Representing the number of times the mechanical equipment has been rolled over in the past for the jth constructed region, and obtaining a training data set as { (M) 1 ，P 1 )，(M 2 ，P 2 )，…，(M j ，P j )，…，(M f ，P f ) Performing straight line fitting on the training data set, and establishing a construction anomaly prediction model: />Wherein (1)>And->Representing fitting coefficients by solving +.>And->Obtaining a final construction abnormality prediction model, and respectively solving the following formulas>And->
Wherein M is j Represents the ground flatness of the jth constructed area, will Q i Substitution construction anomaly prediction modelLet x=q i Predicting and obtaining the construction abnormality probability Y of the ith area to be constructed currently i ， Substituting the ground flatness of the k areas to be constructed currently into a construction anomaly prediction model to predict that the construction anomaly probability set of the k areas to be constructed currently is Y= { Y 1 ，Y 2 ，…，Y i ，…，Y k }, wherein Q i Representing the ground flatness of the ith area to be constructed currently;
in step Z4: comparing construction anomaly probabilities of k areas to be constructed currently, arranging the construction anomaly probabilities in order from large to small, dividing the k areas into n classes according to the construction anomaly probability, and obtaining a random classification result, wherein the construction anomaly probability average value set of each class of area in the n classes is S= { S 1 ，S 2 ，…，S a ，…，S n -selecting an optimal classification result according to the following formula:
wherein L is e Representing the difference degree of construction abnormality probability of n-type region in the e-th classification result, S a And (3) representing the construction anomaly probability mean value of the a-th class region in the n-th class in the e-th class classification result, obtaining the difference degree of the construction anomaly probabilities of the n-th class region in different classification results through the same calculation mode, comparing the difference degrees, selecting the classification result with the largest difference degree as the optimal classification result, and screening the to-be-constructed region of the first class in the optimal classification result as the risk region.
5. The construction safety supervision method based on artificial intelligence according to claim 4, wherein the construction safety supervision method comprises the following steps: in step Z5: after the construction of the current area to be constructed is started, the position of the mechanical equipment is monitored in real time, and when the mechanical equipment is monitored to be in the risk area, an alarm signal is sent to the monitoring terminal to remind the attention of the problem of rolling over of the mechanical equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310925926.0A CN116934262B (en) | 2023-07-26 | 2023-07-26 | Construction safety supervision system and method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310925926.0A CN116934262B (en) | 2023-07-26 | 2023-07-26 | Construction safety supervision system and method based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116934262A CN116934262A (en) | 2023-10-24 |
| CN116934262B true CN116934262B (en) | 2024-02-02 |
Family
ID=88380322
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310925926.0A Active CN116934262B (en) | 2023-07-26 | 2023-07-26 | Construction safety supervision system and method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116934262B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117437598B (en) * | 2023-12-13 | 2024-02-27 | 山东大莱龙铁路有限责任公司 | Intelligent protection system for construction safety of adjacent business line |
| CN117609742B (en) * | 2024-01-24 | 2024-03-26 | 中建安装集团有限公司 | Side slope construction supervision system and method for realizing intelligent management |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016090883A1 (en) * | 2014-12-12 | 2016-06-16 | 中国矿业大学 | Stope roof separation layer water disaster advanced forecasting method based on multi-source information integration |
| CN106593534A (en) * | 2016-12-18 | 2017-04-26 | 河北科技大学 | Intelligent tunnel construction security monitoring system |
| CN109544051A (en) * | 2019-01-25 | 2019-03-29 | 中铁三局集团广东建设工程有限公司 | A kind of construction management application platform based on BIM technology application |
| CN110533292A (en) * | 2019-07-26 | 2019-12-03 | 合肥森弗卡电子科技有限公司 | A kind of safety technological guard method based on outlying district construction |
| CN116010826A (en) * | 2022-12-28 | 2023-04-25 | 嘉兴市叁壹工程检测有限公司 | Construction safety early warning method and system for building engineering |
-
2023
- 2023-07-26 CN CN202310925926.0A patent/CN116934262B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016090883A1 (en) * | 2014-12-12 | 2016-06-16 | 中国矿业大学 | Stope roof separation layer water disaster advanced forecasting method based on multi-source information integration |
| CN106593534A (en) * | 2016-12-18 | 2017-04-26 | 河北科技大学 | Intelligent tunnel construction security monitoring system |
| CN109544051A (en) * | 2019-01-25 | 2019-03-29 | 中铁三局集团广东建设工程有限公司 | A kind of construction management application platform based on BIM technology application |
| CN110533292A (en) * | 2019-07-26 | 2019-12-03 | 合肥森弗卡电子科技有限公司 | A kind of safety technological guard method based on outlying district construction |
| CN116010826A (en) * | 2022-12-28 | 2023-04-25 | 嘉兴市叁壹工程检测有限公司 | Construction safety early warning method and system for building engineering |
Non-Patent Citations (2)
| Title |
|---|
| 公路隧道施工安全风险管理研究;喇英阁;;智能城市(第03期);全文 * |
| 铁路施工安全管理中风险预警机制的建立;于江;;建筑技术开发(第11期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116934262A (en) | 2023-10-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116934262B (en) | Construction safety supervision system and method based on artificial intelligence | |
| US11335179B1 (en) | Water environment risk prediction and early warning method | |
| CN111798127B (en) | Chemical industry park inspection robot path optimization system based on dynamic fire risk intelligent assessment | |
| CN115578015B (en) | Sewage treatment whole process supervision method, system and storage medium based on Internet of things | |
| CN108257114A (en) | A kind of transmission facility defect inspection method based on deep learning | |
| CN116975378B (en) | Equipment environment monitoring method and system based on big data | |
| CN114894411B (en) | Bridge health monitoring method and system based on wireless sensor network | |
| CN107436277A (en) | The single index data quality control method differentiated based on similarity distance | |
| CN111625988A (en) | Bridge health management analysis and prediction system and method based on deep learning | |
| CN113762329A (en) | Method and system for constructing state prediction model of large rolling mill | |
| CN109472075B (en) | Base station performance analysis method and system | |
| US20240142063A1 (en) | Method for troubleshooting potential safety hazards of compressor in smart gas pipeline network and internet of things system thereof | |
| CN116881749B (en) | Pollution site construction monitoring method and system | |
| CN116105802B (en) | Underground facility safety monitoring and early warning method based on Internet of things | |
| CN114201374A (en) | Operation and maintenance time sequence data anomaly detection method and system based on hybrid machine learning | |
| CN115524002B (en) | Operation state early warning method, system and storage medium of power plant rotating equipment | |
| RU2687848C1 (en) | Method and system of vibration monitoring of industrial safety of dynamic equipment of hazardous production facilities | |
| CN117151478B (en) | Chemical enterprise risk early warning method and system based on convolutional neural network | |
| CN116614366B (en) | Industrial Internet optimization method and system based on edge calculation | |
| CN117744945A (en) | Environment monitoring system of hazardous chemical park | |
| CN110533061B (en) | Remote operation and maintenance service platform based on cloud | |
| CN116665401A (en) | Accident prevention alarm system for chemical production | |
| CN114445041B (en) | Method and system for emergency treatment of in-transit accidents of hazardous chemical substances | |
| CN113361730B (en) | Risk early warning method, device, equipment and medium for maintenance plan | |
| CN113673600A (en) | Industrial signal abnormity early warning method, system, storage medium and computing equipment |
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 |