CN114997682A

CN114997682A - Construction site safety monitoring system and method based on big data

Info

Publication number: CN114997682A
Application number: CN202210676272.8A
Authority: CN
Inventors: 徐会君
Original assignee: Individual
Current assignee: Individual
Priority date: 2022-06-15
Filing date: 2022-06-15
Publication date: 2022-09-02
Anticipated expiration: 2042-06-15
Also published as: CN114997682B

Abstract

The invention provides a construction site safety monitoring system and method based on big data, wherein the system comprises the following steps: the data acquisition module is used for acquiring construction data of a construction site and classifying the construction data; the data analysis module is used for carrying out abnormity detection on the classified construction data; the alarm module is used for determining an alarm type based on the abnormal item and carrying out alarm operation; the safety analysis module is used for determining actual construction action information of a construction site based on the abnormal construction data; the safety evaluation module is used for determining the difference between the actual construction action information and the standard construction action information; and the responsibility tracing module is used for acquiring the key event information of the abnormal project, determining the target responsible party and determining the accident responsibility degree of the target responsible party based on the difference. The construction site is strictly and safely monitored, corresponding alarm operation is timely carried out when abnormal conditions occur, measures can be timely taken conveniently, the accident rate is reduced, and safe and reliable operation of the construction site is ensured.

Description

Construction site safety monitoring system and method based on big data

Technical Field

The invention relates to the technical field of monitoring and data processing, in particular to a construction site safety monitoring system and method based on big data.

Background

At present, along with the rapid development of the economy of China, the building industry is rapidly developed, and more high-rise buildings lead to the rising of the frequency of various accidents, various illegal operations and other uncertainties of the construction phenomena;

the traditional safety monitoring and management are realized by the guidance of managers on management sites, the quality and the state of the managers affect the final management effect, the accident frequency cannot be effectively reduced, and meanwhile, because a manual supervision mode is adopted, hidden dangers are not found timely, so that immeasurable loss is caused;

therefore, the invention provides a construction site safety monitoring system and method based on big data.

Disclosure of Invention

The invention provides a construction site safety monitoring system and method based on big data, which are used for realizing strict safety monitoring on a construction site by acquiring construction data of the construction site in real time and analyzing the construction data, and carrying out corresponding alarm operation in time when abnormal conditions occur, so that measures can be taken in time conveniently, the occurrence rate of accidents is reduced, and safe and reliable operation of the construction site is ensured.

The invention provides a construction site safety monitoring system based on big data, which comprises:

the data acquisition module is used for acquiring construction data of a construction site in real time and classifying the construction data;

the data analysis module is used for carrying out abnormity detection on the classified construction data based on a preset abnormity detection model and determining an abnormal item based on a detection result;

the alarm module is used for determining an alarm type based on the abnormal item and carrying out alarm operation based on the alarm type;

the safety analysis module is used for calling abnormal construction data corresponding to the abnormal project based on an alarm result after alarm operation and determining actual construction action information of the construction site based on the abnormal construction data;

the safety evaluation module is used for calling a construction standard monitoring index to process the actual construction action information and determining the difference degree of the actual construction action information relative to the standard construction action information;

and the responsibility tracing module is used for acquiring the key event information of the abnormal project, matching the key event information with the construction project declaration material, determining a target responsibility party and determining the accident responsibility degree of the target responsibility party based on the difference degree.

Preferably, a job site safety monitoring system based on big data, data acquisition module includes:

the data acquisition point determining unit is used for acquiring a construction map of a construction site and determining a target area set for acquiring data of the construction site based on the construction map, wherein the target area set comprises at least one construction area;

the positioning unit is used for determining the geographic position coordinates of each area in the target area set and setting a preset data acquisition device in each area based on the geographic position coordinates;

the data acquisition unit is used for carrying out image pre-acquisition on construction sites of all areas based on the preset data acquisition device and adjusting the acquisition angle of the preset data acquisition device based on a pre-acquisition result;

the data acquisition unit is used for acquiring construction images of construction sites of all areas through the preset data acquisition device based on the adjustment result, wherein the construction images comprise buildings, construction workers and construction environments;

and the data format conversion unit is used for determining the image parameters of the construction image and carrying out format conversion on the construction image based on the image parameters to obtain the construction data of the construction site.

Preferably, a job site safety monitoring system based on big data, data format conversion unit includes:

the data acquisition subunit is used for acquiring the obtained construction data of the construction site and grouping the construction data to obtain N groups of sub-construction data;

the link construction subunit is used for acquiring communication addresses of the preset data acquisition device and the management terminal and constructing a data transmission link based on the communication addresses;

the data transmission subunit is used for determining the transmission sequence of the N groups of sub-construction data and transmitting the N groups of sub-construction data to a management terminal through the data transmission link based on the transmission sequence;

the data storage subunit is used for combining the received N groups of sub-construction data and determining the byte value of the combined construction data;

and the data storage subunit is used for determining the space capacity for storing the construction data based on the byte value, matching a target storage space from a preset storage space based on the space capacity, and storing the construction data in the target storage space.

the data acquisition unit is used for acquiring the acquired construction data of the construction site and determining an acquisition index when the data acquisition is carried out on the construction site;

the data classification unit is used for clustering the construction data based on the acquisition indexes and obtaining a clustering center of each type of construction data based on a clustering result;

the classification checking unit is used for extracting target characteristics of a clustering center of each type of construction data and respectively determining the matching degree of the target characteristics and corresponding acquisition indexes;

and the comparison unit is used for judging that the construction data are qualified in classification when the matching degree is greater than or equal to a preset matching degree value, otherwise, judging that the construction data are unqualified in classification, and reclassifying the construction data until the matching degree is greater than or equal to the preset matching degree value.

Preferably, a job site safety monitoring system based on big data, the data analysis module includes:

the system comprises an evaluation index acquisition unit, a construction safety monitoring unit and a construction safety monitoring unit, wherein the evaluation index acquisition unit is used for acquiring safety monitoring projects of a construction site and determining construction safety standards of the safety monitoring projects, at least one safety monitoring project is provided, and the construction safety standard corresponding to each safety monitoring project is at least one;

the sample data acquisition unit is used for acquiring benchmark construction data corresponding to the safety monitoring project based on the construction safety standard and calling a preset abnormal detection model;

the model training unit is used for determining the importance degree value of the construction safety standard and sequentially extracting the characteristic sequence in the reference construction data based on the importance degree value;

the model training unit is used for correspondingly packing the safety monitoring items, the importance degree values of the construction safety standards and the characteristic sequences in the reference construction data one by one, and training the data layer in the preset abnormal detection model based on the packing result to obtain a standard abnormal detection model;

the data input unit is used for acquiring the classified construction data and inputting the classified construction data into the standard anomaly detection model for processing;

the data processing unit is used for respectively determining a target value of each type of construction data based on the standard anomaly detection model and determining a data state change trend of a corresponding safety monitoring project based on the target value;

the anomaly detection unit is used for determining a safety parameter range corresponding to each construction safety standard in a safety monitoring project and determining the target quantity of the target value of each type of construction data in the safety parameter range based on the data state change trend;

the anomaly detection unit is used for determining a risk threshold of a safety monitoring project corresponding to each type of construction data based on the target quantity and comparing the risk threshold with a preset risk value;

if the risk threshold value is larger than or equal to the preset risk value, determining a target safety monitoring project corresponding to the construction data of the current category, and judging the target safety monitoring project as an abnormal project;

otherwise, judging that the safety monitoring project corresponding to each type of construction data is not abnormal.

Preferably, a job site safety monitoring system based on big data, the anomaly detection unit includes:

the project acquisition subunit is used for acquiring the abnormal project and determining the project attribute of the abnormal project;

the risk source positioning subunit is used for determining the project type of the abnormal project based on the project attribute and acquiring the construction data corresponding to the abnormal project;

the risk source positioning subunit is used for determining the structural characteristics of the abnormal items based on the item types and determining the risk sources of the abnormal items according to the structural characteristics based on the construction data;

the risk source positioning subunit is further configured to determine specific position coordinates of the risk source in the abnormal item, and complete positioning of the risk source based on the specific position coordinates.

the information acquisition subunit is used for acquiring the abnormal project, determining a project identifier of the abnormal project, and calling the recorded data of the abnormal project through big data based on the project identifier;

the information acquisition subunit is further configured to determine a construction progress of the abnormal project, and retrieve phase data information stored in a management terminal of the abnormal project based on the construction progress, where the phase data information is proportional to the construction progress;

and the reason judging subunit is used for determining project parameters related to the abnormal project based on the record data and the stage data information, and determining a target risk reason of the abnormal project based on the project parameters.

Preferably, a job site safety monitoring system based on big data, alarm module includes:

the project acquisition unit is used for acquiring the abnormal project and determining project characteristics of the abnormal project;

the item type determining unit is used for matching the item characteristics with a preset item type list and determining the target type of the abnormal item based on a matching result;

the alarm mode determining unit is used for extracting the type identifier of the target type and determining a target alarm mode for the abnormal item based on the type identifier;

the risk level determining unit is used for retrieving the construction data of the abnormal project and determining risk factors of the abnormal project with risks based on the construction data;

the risk level determining unit is used for determining the cause and effect relationship between the risk factors and the abnormal items and constructing an adjacency matrix based on the cause and effect relationship;

the risk level determination unit is used for constructing a relationship network based on the adjacency matrix, determining the centrality of each node based on the relationship network, and obtaining the weight value of the risk factor based on the centrality;

the risk level determining unit is used for constructing an evaluation system of the risk level of the abnormal item based on the risk factors and determining a risk coefficient of each risk factor in the evaluation system based on the weight value, wherein the risk coefficient is in direct proportion to the weight value;

the risk level determining unit is used for determining the sub risk levels of the abnormal items for each risk factor based on the risk coefficients, and integrating the sub risk levels based on the weight values to obtain the final risk level of the abnormal item;

and the alarm unit is used for determining the alarm grade for alarming the abnormal project in the target alarm mode based on the final risk grade and carrying out alarm operation with a management terminal on the construction site based on the alarm grade.

Preferably, the job site safety monitoring system based on big data, the risk level determining unit includes:

a result obtaining subunit, configured to obtain a final risk level of the abnormal item, obtain a project name of the abnormal item, and generate a risk level evaluation report based on the project name and the final risk level;

the notification subunit is used for transmitting the risk level evaluation report to a management terminal, and the management terminal matches a target prevention and control measure from a preset prevention and control measure library based on the risk level evaluation report;

and the issuing subunit is used for issuing the target prevention and control measures to an intelligent terminal of a worker and providing the worker for prevention and control work.

Preferably, a construction site safety monitoring method based on big data includes:

step 1: collecting construction data of a construction site in real time, and classifying the construction data;

step 2: performing anomaly detection on the classified construction data based on a preset anomaly detection model, and determining an anomaly item based on a detection result;

and 3, step 3: determining an alarm type based on the abnormal item, and performing alarm operation based on the alarm type;

and 4, step 4: calling abnormal construction data corresponding to the abnormal project based on an alarm result after alarm operation, and determining actual construction action information of the construction site based on the abnormal construction data;

and 5: calling a construction standard monitoring index to process the actual construction action information, and determining the difference degree of the actual construction action information relative to standard construction action information;

step 6: acquiring key event information of an abnormal project, matching the key event information with construction project declaration materials, determining a target responsible party, and determining the accident responsibility degree of the target responsible party based on the difference degree.

Compared with the prior art, the invention provides a construction site safety monitoring system and method based on big data, which has the following beneficial effects:

1. the invention provides a construction site safety monitoring system based on big data, which realizes the strict safety monitoring of a construction site by acquiring construction data of the construction site in real time and analyzing the construction data, and carries out corresponding alarm operation in time when an abnormal condition occurs, thereby facilitating the taking of measures in time, reducing the occurrence rate of accidents, and simultaneously determining the difference degree of actual construction action and standard construction action according to abnormal construction data corresponding to an abnormal project, thereby realizing the determination of the responsible party of the abnormal project according to the difference degree, realizing the accurate determination of the degree of the responsible party, and ensuring the safe and reliable operation of the construction site.

2. The invention provides a construction site safety monitoring system based on big data, which can accurately and effectively judge abnormal projects by analyzing construction data of a construction site, and can select alarm levels with different degrees according to the severity of abnormal conditions of the abnormal projects, thereby improving the alarm rigidness of the construction site, facilitating a management terminal to take corresponding prevention and control measures in time, and improving the safety monitoring strength of the construction site.

3. The invention provides a construction site safety monitoring system based on big data, which realizes strict and effective monitoring on each safety monitoring project in a construction site by comprehensively acquiring and analyzing construction data of the construction site, and timely determines the project type of an abnormal project and carries out corresponding alarm and prevention and control when abnormal conditions exist in the construction site, thereby ensuring the safety of the construction site and improving the safety factor of the construction site.

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 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 block diagram of a big data based safety monitoring system for a construction site according to an embodiment of the present invention;

FIG. 2 is a block diagram of a data collection module in a big data based safety monitoring system for a construction site according to an embodiment of the present invention;

fig. 3 is a flowchart of a construction site safety monitoring method based on big data 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 should be understood that they are presented herein only to illustrate and explain the present invention and not to limit the present invention.

Example 1:

the embodiment provides a job site safety monitoring system based on big data, as shown in fig. 1, including:

and the responsibility tracing module is used for acquiring the key event information of the abnormal project, matching the key event information with the construction project declaration material, determining a target responsible party and determining the accident responsibility degree of the target responsible party based on the difference degree.

In this embodiment, the construction data refers to the wearing condition of protective equipment such as a helmet of a worker at a construction site, the operating condition of construction machine hardware, the operating condition of a construction vehicle, the construction site environment, the building condition of a building, and the like.

In this embodiment, the preset anomaly detection model is set in advance and is used for analyzing the construction data, so as to determine whether potential safety hazards exist in the construction site.

In this embodiment, the abnormal project refers to a construction project that does not meet the construction safety requirement, and includes an operation condition of a constructor, an operation condition of a machine, and an environment condition of a construction site.

In the embodiment, the alarm type refers to that different abnormal items correspond to different alarm modes, so that the management terminal can find corresponding abnormal conditions in time conveniently.

In this embodiment, the alarm operation includes simultaneous alarm at a construction site and a management terminal.

In this embodiment, the abnormal construction data refers to construction data corresponding to an abnormal project in a construction site, and specifically includes a construction progress of the abnormal project, a current construction state, a construction standard according to in a construction process, and the like.

In this embodiment, the actual construction action information refers to the operation steps of an abnormal project in the construction process in the construction site and the specification degree of each step, and specifically includes the order of use of materials, the standard of use, the number of use, whether each construction step is performed according to the construction requirement, and the like.

In the embodiment, the construction standard monitoring index is set in advance and is suitable for a reference basis for measuring whether each construction action meets the requirement or not.

In this embodiment, the standard construction action information refers to a corresponding construction behavior when the standard monitoring index is satisfied, and is in accordance with the construction requirement.

In this embodiment, the difference degree refers to the deviation between the actual construction action information and the standard construction action information, and the larger the difference degree is, the more the actual construction action information does not meet the construction standard monitoring index.

In this embodiment, the key event information refers to the project type of the abnormal project, the current construction step and the construction progress of the abnormal project, and the like.

In this embodiment, the construction project declaration material is set in advance, and is a record of the construction project performed before the construction.

In this embodiment, the target responsible party refers to a main responsible person who causes an abnormality in the current abnormal project, specifically, a construction worker or a contractor, and the like.

In this embodiment, determining the accident responsibility degree of the target responsible party based on the difference degree means that when the difference degree is larger, it indicates that the current construction standard of the abnormal project is less qualified to the construction requirement, that is, the degree of abnormality of the abnormal project is larger, and meanwhile, the larger the difference degree is, it indicates that the result is more serious, that is, the larger the difference degree is, the greater the accident responsibility is.

The beneficial effects of the above technical scheme are: the construction data of the construction site are collected in real time and analyzed, so that the construction site is strictly and safely monitored, corresponding alarm operation is timely carried out when abnormal conditions occur, measures are convenient to take timely, the occurrence rate of accidents is reduced, meanwhile, the difference degree of actual construction actions and standard construction actions is determined according to the abnormal construction data corresponding to abnormal projects, accordingly, the responsibility party of the abnormal projects is determined according to the difference degree, the accuracy judgment of the responsibility degree of the responsibility party is realized, and the safe and reliable operation of the construction site is ensured.

Example 2:

on the basis of embodiment 1, this embodiment provides a job site safety monitoring system based on big data, as shown in fig. 2, the data acquisition module includes:

In this embodiment, the construction map refers to the distribution of areas used to characterize the construction site, and is convenient for determining the area currently being constructed in the construction site, and the like.

In this embodiment, the target area set refers to a plurality of current construction sites where data collection is required.

In this embodiment, the geographic location coordinates refer to the specific distribution locations of different construction areas on the construction site.

In this embodiment, the preset data acquisition device is a camera and is used for acquiring a construction image of a construction site.

In this embodiment, the pre-collection refers to performing testability image collection on the construction site through the preset data collection device, so as to determine whether the installation angle of the preset data collection device is qualified.

In this embodiment, the image parameter refers to the subject matter recorded in the construction image.

The beneficial effects of the above technical scheme are: the method has the advantages that the region needing data acquisition in the construction site is accurately positioned according to the construction map of the construction site, so that the required construction data can be acquired, the acquired moral data are accurate and reliable through adjusting the preset installation angle of the data acquisition device, the acquired construction image is converted into the corresponding construction data, the accuracy of construction data acquisition is realized, and the construction site is strictly monitored safely.

Example 3:

on the basis of embodiment 2, this embodiment provides a job site safety monitoring system based on big data, and the data format conversion unit includes:

In this embodiment, the sub-construction data refers to a plurality of data segments in the construction data obtained by splitting the acquired construction data.

In this embodiment, the transmission sequence is used to characterize the transmission sequence of different sub-construction data in the data transmission link.

In this embodiment, the byte value is used to characterize the size of the construction data content.

In this embodiment, the preset storage space is set in advance, and is used by the management terminal to store construction data of different byte sizes.

In this embodiment, the target storage space refers to a storage space suitable for storing the current construction data, and is a part of the preset storage space.

The beneficial effects of the above technical scheme are: the communication addresses of the preset data acquisition device and the management terminal are determined, so that a data transmission link between the preset data acquisition device and the management terminal is accurately constructed, the construction data is split, the transmission speed in the data transmission link is improved, meanwhile, the management terminal determines the byte value of the construction data, so that the construction data is accurately and effectively stored according to the byte value of the construction data, and convenience and guarantee are provided for accurately analyzing the safety condition of a construction site.

Example 4:

on the basis of embodiment 1, this embodiment provides a job site safety monitoring system based on big data, and the data acquisition module includes:

In this embodiment, the acquisition index refers to a data type to be taken which is known in advance when data acquisition is performed on a construction site.

In this embodiment, the clustering process refers to classifying the construction data having the same characteristics.

In this embodiment, the cluster center is used to represent the data characteristics of the construction data of the current category, and the construction data of the same category shares the current cluster center.

In this embodiment, the target feature refers to a specific value of a cluster center and a feature such as a data type.

In this embodiment, the preset matching degree value is set in advance, and is used to determine whether the classification of the construction data is qualified, or may be modified.

The beneficial effects of the above technical scheme are: the method has the advantages that accurate and effective clustering processing on the construction data is realized by determining the acquisition indexes of the construction data, so that the classification accuracy of the construction data is guaranteed, and meanwhile, after classification is finished, the classification result is accurately and effectively verified by matching the target characteristics of each type of construction data with the corresponding acquisition indexes, so that the accuracy and reliability of the classification of the construction data are improved, and a guarantee is provided for realizing strict safety monitoring on a construction site.

Example 5:

on the basis of embodiment 1, this embodiment provides a job site safety monitoring system based on big data, and the data analysis module includes:

the sample data acquisition unit is used for acquiring benchmark construction data corresponding to the safety monitoring project based on the construction safety standard and calling a preset anomaly detection model;

the model training unit is used for determining an importance degree value of the construction safety standard and sequentially extracting a characteristic sequence in the reference construction data based on the importance degree value;

the anomaly detection unit is used for determining a risk threshold value of a safety monitoring project corresponding to each type of construction data based on the target quantity and comparing the risk threshold value with a preset risk value;

otherwise, judging that the safety monitoring project corresponding to each type of construction data is abnormal.

In this embodiment, the safety monitoring project refers to a service category for performing safety monitoring on a construction site, specifically, an operation behavior of a worker, a building condition of a building, and a construction environment of the construction site.

In this embodiment, the construction safety standard refers to standard monitoring data corresponding to each safety monitoring project, and specifically, a worker must wear a safety helmet and the like.

In this embodiment, the reference construction data refers to construction data corresponding to the safety monitoring project under a qualified condition.

In this embodiment, the feature sequence refers to a key data segment that can indicate a value and attribute information of the reference construction data in the reference construction data.

In this embodiment, the standard anomaly detection model refers to a final anomaly detection model obtained by training a preset anomaly detection model.

In this embodiment, the target value refers to a value size corresponding to each type of construction data.

In this embodiment, the data state change trend refers to a specific change condition of a value of each type of construction data.

In this embodiment, the safety parameter range refers to a value range corresponding to safety construction data corresponding to a safety monitoring project, and it is determined that the project is not dangerous within the value range.

In this embodiment, the target quantity refers to the quantity of the construction data having a value within the safety parameter range in each type of construction data.

In this embodiment, the risk threshold refers to a degree of risk of the safety monitoring project corresponding to the current construction data.

In this embodiment, the preset risk value is set in advance, and is used to measure whether the risk value of the current safety monitoring project meets the standard of determining as an abnormal project.

The beneficial effects of the above technical scheme are: the method comprises the steps of determining the types of projects needing to be subjected to safety monitoring on a construction site, determining the construction safety standard of each safety monitoring project, accurately and reliably training a preset abnormal detection model, and analyzing collected construction data through the trained abnormal detection model, so that the safety monitoring projects with potential safety hazards in the construction site are accurately and timely judged, and convenience and guarantee are provided for ensuring safe and reliable operation of the construction site.

Example 6:

on the basis of embodiment 5, this embodiment provides a job site safety monitoring system based on big data, and the anomaly detection unit includes:

In this embodiment, the item attribute refers to an item category of an abnormal item and a corresponding item feature.

In this embodiment, the structural feature refers to a structural feature of an abnormal item or a connection relationship between devices, or the like.

In this embodiment, the risk source refers to a source location causing an abnormality of a different project.

In this embodiment, the specific location coordinates refer to the specific distribution of the risk sources in the abnormal item.

The beneficial effects of the above technical scheme are: the method and the device have the advantages that the project attributes of the abnormal projects are determined, so that the project types of the abnormal projects are accurately and effectively acquired, secondly, the structural features of the abnormal projects are effectively judged through the project types, so that the risk sources and the corresponding specific positions of the abnormal projects are accurately acquired, the safety and reliability of the construction site are guaranteed, and convenience is brought to timely prevention and control measures.

Example 7:

and the reason judging subunit is used for determining project parameters related to the abnormal project based on the record materials and the phase data information, and determining a target risk reason of the abnormal project based on the project parameters.

In this embodiment, the item identifier is a tag label used to tag different items, and the type of the current item can be determined quickly and accurately through the identifier.

In this embodiment, the documentation refers to the construction materials stored in the management terminal before the construction of the abnormal project, specifically, the type of the construction equipment and the list of the workers involved in the construction.

In this embodiment, the phase data information refers to that the construction condition of the construction site is synchronously updated at the management terminal according to the construction progress of the construction site.

In this embodiment, the project parameters include the current progress of the abnormal project, the specific construction equipment and the corresponding worker information

In this embodiment, the target risk cause refers to a root cause that causes a risk or an abnormality of an abnormal item.

The beneficial effects of the above technical scheme are: by determining the recorded data of the abnormal project and the phase data information synchronously updated with the construction progress at the management terminal, the target risk reason of the abnormal project is accurately and effectively analyzed, so that the abnormal project is conveniently and timely taken with precautionary measures, and convenience is provided for guaranteeing safe and orderly operation of a construction site.

Example 8:

on the basis of embodiment 1, this embodiment provides a job site safety monitoring system based on big data, and alarm module includes:

the project acquisition unit is used for acquiring the abnormal projects and determining project characteristics of the abnormal projects;

a risk level determining unit, which is used for retrieving the construction data of the abnormal project and determining risk factors of the abnormal project based on the construction data, wherein the risk factors are not unique;

In this embodiment, the project characteristics refer to project characteristics of an abnormal project, including project construction attributes, operation characteristics, and the like.

In this embodiment, the preset item type list is set in advance and is used for storing item types of different construction items.

In this embodiment, the target type refers to the item type of the abnormal item.

In this embodiment, the type identifier refers to a tag label for tagging different item types, and one item type corresponds to one identifier.

In this embodiment, the target alarm mode refers to an alarm mode suitable for alarming a current abnormal item, and different types of abnormal items correspond to different alarm modes.

In this embodiment, the risk factor refers to a main factor causing an abnormal item to be abnormal or to be at risk.

In this embodiment, the adjacency matrix refers to a one-dimensional array for storing all data of the risk factors, and a two-dimensional array for storing data of the cause-effect relationship (edge or arc) between the risk factors and the abnormal item, and this two-dimensional array is called the adjacency matrix.

In this embodiment, the relationship network is used to characterize the association relationship between different risk factors.

In this embodiment, the centrality refers to the weight of different risk factors in the risk of causing an abnormal item.

In this embodiment, the risk factor is a measure of the risk of different risk factors.

In this embodiment, the sub-risk level refers to the risk level caused by different risk factors to the abnormal item.

The beneficial effects of the above technical scheme are: the corresponding alarm mode is matched according to the project type by determining the project type of the abnormal project, then the risk grade of the abnormal project is accurately and effectively judged through a risk evaluation system, the alarm operation is carried out by calling the matched alarm grade according to the risk grade, the rigor degree of safety monitoring of the construction site is improved, the abnormal project of the construction site is conveniently found in time, corresponding prevention and control measures are taken according to the risk grade for prevention and control, and the safe and orderly operation of the construction site is guaranteed.

Example 9:

on the basis of embodiment 8, this embodiment provides a job site safety monitoring system based on big data, and the risk level determination unit includes:

In this embodiment, the project name refers to the name of an abnormal project, specifically, "building," "worker operation behavior," and the like.

In this embodiment, the preset prevention and control measure library is set in advance and is used for storing the prevention and control measures corresponding to different risk levels.

In this embodiment, the target prevention and control measure refers to a prevention and control measure suitable for solving the current abnormal item risk fan, and is one or more combinations in a preset prevention and control measure library.

The beneficial effects of the above technical scheme are: corresponding risk grade evaluation reports are generated by determining the project names of the abnormal projects, and the abnormal projects are subjected to prevention and control operation by matching corresponding prevention and control measures according to the risk grade evaluation reports, so that the efficiency of dealing with emergency situations of a construction site is improved, the safety of the construction site is conveniently ensured, and the safety factor of the construction site is improved.

Example 10:

the embodiment provides a construction site safety monitoring method based on big data, as shown in fig. 3, including:

and 2, step: performing anomaly detection on the classified construction data based on a preset anomaly detection model, and determining an anomaly item based on a detection result;

and step 3: determining an alarm type based on the abnormal item, and performing alarm operation based on the alarm type;

Example 11:

on the basis of embodiment 8, this embodiment provides a job site safety monitoring system based on big data, and obtaining a final risk level of the abnormal item includes:

when the abnormal project is a scaffold on a construction site, the specific steps of determining the final risk level of the scaffold are as follows:

the method comprises the following steps of obtaining the average wind speed of a construction site, calculating the wind load of the construction site based on the average wind speed, and calculating the vertical rod bending moment value of the scaffold based on the wind load, wherein the method comprises the following specific steps:

calculating the wind load of the construction site according to the following formula:

wherein α represents a wind load of the construction site; mu represents an error factor, and the value range is (0.02, 0.05); beta represents the wind vibration coefficient, and the value range is (0.9, 1.2); delta represents the height change coefficient of the wind pressure, and the value range is (0.4, 3);

the value range of the factor of the wind load body type of the scaffold is (0.8, 1.5); ρ represents an air density value of a construction site; v represents an average wind speed at the construction site;

calculating the vertical rod bending moment value of the scaffold according to the following formula:

wherein M represents a vertical rod bending moment value of the scaffold; l represents the longitudinal distance between the upright stanchions of the scaffold; d represents the transverse distance between the upright stanchions of the scaffold; a represents a constant, generally 10;

comparing the calculated bending moment value with a preset bending moment value;

if the bending moment value is smaller than or equal to the preset bending moment value, judging that the scaffold can bear the wind load of a construction site;

otherwise, judging that the wind load of the construction site can damage the scaffold, and performing alarm operation.

In this embodiment, wind load refers to the pressure of the air flow against the scaffolding.

In this embodiment, the wind vibration coefficient means that the effect of wind on a building is irregular, and the wind pressure is constantly changed along with the turbulence change of the wind speed and the wind direction.

In this embodiment, the height variation coefficient of the pressure is a coefficient that reflects the rule of variation of the wind pressure with different sites, landforms, and heights.

In this embodiment, the scaffold wind load size coefficient refers to the degree of influence of the scaffold on the wind load.

In this embodiment, the bending moment value refers to the degree to which the scaffolding bends under the action of wind load.

In this embodiment, the wind speed and air density values are detected by specialized machinery or sensors.

The beneficial effects of the above technical scheme are: by analyzing the scaffold in the construction site, calculating the wind load of the construction site according to the wind speed of the construction site and calculating the bending moment value of the scaffold under the action of the wind according to the wind load, the risk of the scaffold generated by the wind of the construction site is accurately and effectively analyzed, and the alarm operation is performed when the bending moment value reaches the preset bending moment value, so that the strength and the accuracy of safety monitoring of the construction site are improved.

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

1. The utility model provides a job site safety monitoring system based on big data which characterized in that includes:

2. The big data-based construction site safety monitoring system according to claim 1, wherein the data acquisition module comprises:

3. The big data-based construction site safety monitoring system as claimed in claim 2, wherein the data format conversion unit comprises:

4. The big data-based construction site safety monitoring system according to claim 1, wherein the data acquisition module comprises:

and the comparison unit is used for judging that the construction data are qualified when the matching degree is greater than or equal to a preset matching degree value, otherwise, judging that the construction data are unqualified, and reclassifying the construction data until the matching degree is greater than or equal to the preset matching degree value.

5. The big data-based construction site safety monitoring system as claimed in claim 1, wherein the data analysis module comprises:

6. The big data-based safety monitoring system for construction sites as claimed in claim 5, wherein the abnormality detection unit comprises:

the risk source positioning subunit is used for determining the structural characteristics of the abnormal project based on the project type and determining the risk source of the abnormal project according to the structural characteristics based on the construction data;

7. The big data-based construction site safety monitoring system according to claim 5, wherein the abnormality detection unit comprises:

8. The big data-based construction site safety monitoring system as claimed in claim 1, wherein the alarm module comprises:

the alarm mode determining unit is used for extracting the type identifier of the target type and determining the target alarm mode for the abnormal item based on the type identifier;

9. The big data-based job site safety monitoring system according to claim 8, wherein the risk level determination unit comprises:

10. A construction site safety monitoring method based on big data is characterized by comprising the following steps: