CN111985717A - Safety early warning method and device, safety early warning equipment and storage medium - Google Patents
Safety early warning method and device, safety early warning equipment and storage medium Download PDFInfo
- Publication number
- CN111985717A CN111985717A CN202010858884.XA CN202010858884A CN111985717A CN 111985717 A CN111985717 A CN 111985717A CN 202010858884 A CN202010858884 A CN 202010858884A CN 111985717 A CN111985717 A CN 111985717A
- Authority
- CN
- China
- Prior art keywords
- real
- distance
- time
- safety
- predicted
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 69
- 238000003860 storage Methods 0.000 title claims description 8
- 239000013598 vector Substances 0.000 claims abstract description 74
- 238000012417 linear regression Methods 0.000 claims abstract description 27
- 230000006399 behavior Effects 0.000 claims description 91
- 238000012549 training Methods 0.000 claims description 19
- 238000010801 machine learning Methods 0.000 claims description 15
- 238000012706 support-vector machine Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 description 14
- 238000004519 manufacturing process Methods 0.000 description 8
- 230000000007 visual effect Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000003111 delayed effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
- G01S17/06—Systems determining position data of a target
- G01S17/08—Systems determining position data of a target for measuring distance only
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The method comprises the steps of obtaining the distance between a monitored object and an obstacle, and obtaining real-time action data of the monitored object in a specified time period when the distance between the monitored object and the obstacle is smaller than a preset distance; according to the real-time action data and the real-time distance of the specified time period, respectively obtaining predicted action data and a predicted distance of a preset future moment after the specified time period through a linear regression algorithm; combining the predicted action data and the predicted distance of the preset future moment and the real-time action data and the real-time distance of the appointed time period into a predicted behavior vector; inputting the predicted behavior vector into a trained safety judgment model to obtain a safety judgment result; and when the safety judgment result is dangerous, early warning is carried out. The purposes of predicting the behavior of the staff and warning in advance are achieved, and safety early warning can be fully achieved.
Description
Technical Field
The present application relates to the field of security technologies, and in particular, to a security early warning method, an apparatus, a security early warning device, and a storage medium.
Background
With the continuous acceleration of the industrialization process of China, China is the first industrial country in the world. Meanwhile, various production accidents emerge endlessly, once a safety accident occurs, the production line is halted slightly, enterprises suffer loss, and the life and health of staff are endangered seriously. Therefore, how to make the production safety more strict has become an issue facing enterprises. Although there are strict safety regulations and real-time video monitoring and other safeguards, real-time video monitoring is delayed and not enough to predict danger, and cannot completely guarantee the absolute safety of production line staff.
Therefore, a safety early warning method capable of predicting staff behaviors and giving warning in advance is urgently needed to reduce or eliminate production accidents of a production line.
Disclosure of Invention
In order to solve the problems, the application provides a safety early warning method, a safety early warning device and a storage medium, and solves the technical problem that the behavior of an employee cannot be predicted and warning cannot be performed in advance in the prior art.
In a first aspect, the present application provides a safety precaution method, including:
the method comprises the steps of obtaining the real-time distance between a monitored object and an obstacle, and obtaining real-time action data of the monitored object in a specified time period when the real-time distance between the monitored object and the obstacle is smaller than a preset distance;
according to the real-time action data and the real-time distance of the specified time period, respectively obtaining predicted action data and a predicted distance of a preset future moment after the specified time period through a linear regression algorithm;
combining the predicted action data and the predicted distance of the preset future moment and the real-time action data and the real-time distance of the appointed time period into a predicted behavior vector;
inputting the predicted behavior vector into a trained safety judgment model to obtain a safety judgment result;
and when the safety judgment result is dangerous, early warning is carried out.
According to an embodiment of the present application, preferably, in the safety precaution method, acquiring a real-time distance between a monitoring object and an obstacle, and acquiring real-time action data of the monitoring object in a specified time period when the real-time distance between the monitoring object and the obstacle is smaller than a preset distance, the method includes the following steps:
the method comprises the steps of obtaining real-time distances between all parts of a body of a monitored object and an obstacle, and obtaining real-time action data of the monitored object in a specified time period when the minimum value of the real-time distances between all parts of the body of the monitored object and the obstacle is smaller than a preset distance.
According to an embodiment of the application, preferably, in the safety precaution method, the step of obtaining predicted action data of a preset future moment after the specified time period by a linear regression algorithm according to the real-time action data of the specified time period includes the following steps:
according to the real-time action data of the specified time period, establishing an action prediction model for describing the corresponding relation between the action data and the time through a linear regression algorithm;
and obtaining predicted action data of a preset future moment after the specified time period according to the action prediction model.
According to an embodiment of the present application, preferably, in the safety precaution method, the step of obtaining the predicted distance of the preset future time after the specified time period by using a linear regression algorithm according to the real-time distance of the specified time period includes the following steps:
respectively establishing a distance prediction model for describing the corresponding relation between each part of the body of the monitored object and the distance and time of the obstacle through a linear regression algorithm according to the real-time distance between each part of the body of the monitored object and the obstacle in the specified time period;
and obtaining the predicted distance between each part of the body of the monitored object and the obstacle at a preset future moment after the specified time period according to the distance prediction model.
According to an embodiment of the present application, preferably, in the above safety precaution method, the safety judgment model is constructed by the following steps:
acquiring different historical behavior vectors;
according to a preset safety standard, performing safety judgment on different historical behavior vectors to obtain corresponding historical safety judgment results;
and performing machine learning training on different historical behavior vectors and the historical safety judgment results corresponding to the different historical behavior vectors to obtain the safety judgment model.
According to an embodiment of the present application, preferably, in the safety precaution method, machine learning training is performed on different historical behavior vectors and the historical safety determination results corresponding to the different historical behavior vectors to obtain the safety determination model, and the method includes the following steps:
performing machine learning training on different historical behavior vectors and the corresponding historical safety judgment results by using a support vector machine algorithm to establish an initial safety judgment model;
determining initial safety judgment results corresponding to different historical behavior vectors according to the initial safety judgment model, and determining the correctness of each initial safety judgment result according to the comparison result of each initial safety judgment result and the corresponding historical safety judgment result; when the current initial safety judgment result is the same as the corresponding historical safety judgment result, the current initial safety judgment result is correct;
calculating the accuracy of the initial safety judgment result according to the accuracy of each initial safety judgment result, and comparing the accuracy with a preset threshold:
when the accuracy is greater than or equal to the preset threshold, taking the initial safety judgment model as the final safety judgment model;
and when the accuracy is smaller than the preset threshold value, returning to the step of performing machine learning training on different historical behavior vectors and the historical safety judgment results corresponding to the different historical behavior vectors by using a support vector machine algorithm so as to perform machine learning training again.
In a second aspect, the present application provides a safety precaution device, the device comprising:
the real-time data acquisition module is used for acquiring the real-time distance between a monitored object and an obstacle and acquiring real-time action data of the monitored object in a specified time period when the real-time distance between the monitored object and the obstacle is smaller than a preset distance;
the behavior prediction module is used for obtaining predicted action data and predicted distance of a preset future moment after the specified time period through a linear regression algorithm according to the real-time action data and the real-time distance of the specified time period;
the behavior vector combination module is used for combining the predicted action data and the predicted distance at the preset future moment and the real-time action data and the real-time distance of the specified time period into a predicted behavior vector;
the safety judgment module is used for inputting the predicted behavior vector into a trained safety judgment model to obtain a safety judgment result;
and the early warning module is used for carrying out early warning when the safety judgment result is dangerous.
In a third aspect, the present application provides a safety precaution device, including a memory, a controller, a distance sensor, a motion sensor, and an alarm;
the distance sensor is used for acquiring the real-time distance between a monitored object and an obstacle;
the motion sensor is used for acquiring real-time motion data of the monitored object in a specified time period;
the memory stores a program, and when the program is executed by the controller, the program executes the safety warning method according to any one of the first aspect to control the alarm to warn according to the data collected by the distance sensor and the motion sensor.
According to the embodiment of the application, preferably, in the safety precaution device, the safety precaution device is a wearable device.
In a fourth aspect, the present application provides a storage medium storing a computer program, executable by one or more processors, for implementing the safety precaution method according to any one of the first aspect.
Compared with the prior art, one or more embodiments in the above scheme can have the following advantages or beneficial effects:
the method comprises the steps of obtaining the distance between a monitored object and an obstacle, and obtaining real-time action data of the monitored object in a specified time period when the distance between the monitored object and the obstacle is smaller than a preset distance; according to the real-time action data and the real-time distance of the specified time period, respectively obtaining predicted action data and a predicted distance of a preset future moment after the specified time period through a linear regression algorithm; combining the predicted action data and the predicted distance of the preset future moment and the real-time action data and the real-time distance of the appointed time period into a predicted behavior vector; inputting the predicted behavior vector into a trained safety judgment model to obtain a safety judgment result; and when the safety judgment result is dangerous, early warning is carried out. The method predicts the behavior data at a certain future moment according to the real-time behavior data of the monitored object, inputs the real-time data and the predicted data into the trained safety judgment model for judgment, achieves the purposes of predicting the behavior of the staff and warning in advance, and can fully realize safety early warning.
Drawings
The present application will be described in more detail hereinafter on the basis of embodiments and with reference to the accompanying drawings:
fig. 1 is a schematic flow chart of a safety warning method according to an embodiment of the present disclosure;
fig. 2 is a schematic view of a construction process of a safety determination model according to an embodiment of the present application;
fig. 3 is another schematic flow chart of a safety warning method according to an embodiment of the present disclosure;
fig. 4 is a connection block diagram of a safety precaution device according to an embodiment of the present disclosure;
fig. 5 is a connection block diagram of a safety precaution device according to an embodiment of the present application;
in the drawings, like parts are designated with like reference numerals, and the drawings are not drawn to scale.
Detailed Description
The following detailed description will be provided with reference to the accompanying drawings and embodiments, so that how to apply the technical means to solve the technical problems and achieve the corresponding technical effects can be fully understood and implemented. The embodiments and various features in the embodiments of the present application can be combined with each other without conflict, and the formed technical solutions are all within the scope of protection of the present application.
Example one
Referring to fig. 1, the present embodiment provides a safety precaution method, including:
step S101: the method comprises the steps of obtaining the real-time distance between a monitored object and an obstacle, and obtaining real-time action data of the monitored object in a specified time period when the real-time distance between the monitored object and the obstacle is smaller than a preset distance.
Specifically, the method includes the steps of obtaining the distance between each part of the body of a monitored object and an obstacle, and obtaining real-time action data of the monitored object in a specified time period when the minimum value of the distances between each part of the body of the monitored object and the obstacle is smaller than a preset distance.
In this embodiment, the above-mentioned real-time motion data and real-time distance may be acquired by (but not limited to) a wearable device.
The monitoring object is provided with wearable equipment, the wearing equipment is a labor protection glove, a labor protection shoe, a work clothes, a safety helmet and the like, and each set of equipment corresponds to one another.
The wearable device is provided with the action sensors and the distance sensors corresponding to all parts of the body, the action sensors acquire action data of the human body according to the positions of all parts of the human body, the distance sensors comprise infrared distance measuring instruments and can acquire the distance between all parts of the human body and the obstacle, and in the embodiment, the action data and the distance between all parts of the body and the obstacle form behavior data of the monitored object.
The obstacles include equipment, vehicles, and other personnel in the production line.
The preset distance is an absolute safety distance and is set according to the actual situation and the safety standard of the actual post.
The real-time action data of the monitoring object in the specified time period at least comprises the real-time action data of the beginning and the ending of the specified time period so as to form a complete action segment.
Moreover, since the real-time distance between the monitoring object and the obstacle is always acquired, the real-time distance in the specified time period is acquired at the same time as the real-time action is acquired.
Step S102: and according to the real-time action data and the real-time distance of the specified time period, obtaining predicted action data and predicted distance of a preset future moment after the specified time period through a linear regression algorithm.
It should be noted that the overall motion trajectory of the monitored object may be complex and may not be accurately predicted, but the motion trajectory of a certain portion may be regarded as linear in a short period of time, so that a linear regression algorithm may be used to predict behavior data at a future time.
Specifically, in step S102, the step of obtaining predicted motion data of a preset future time after the specified time period by using a linear regression algorithm according to the real-time motion data of the specified time period includes the following steps:
according to the real-time action data of the specified time period, establishing an action prediction model for describing the corresponding relation between the action data and the time through a linear regression algorithm;
and obtaining predicted action data of a preset future moment after the specified time period according to the action prediction model.
In step S102, the step of obtaining the predicted distance of the preset future time after the specified time period by using a linear regression algorithm according to the real-time distance of the specified time period includes the following steps:
respectively establishing a distance prediction model for describing the corresponding relation between each part of the body of the monitored object and the distance and time of the obstacle through a linear regression algorithm according to the real-time distance between each part of the body of the monitored object and the obstacle in the specified time period;
and obtaining the predicted distance between each part of the body of the monitored object and the obstacle at a preset future moment after the specified time period according to the distance prediction model.
The motion prediction model is a linear relation between the motion data and the time of the monitored object, the distance prediction model is a linear relation between the distance between each part of the monitored object and the obstacle and the time of the monitored object, and the predicted motion data and the predicted distance corresponding to the preset future time can be respectively calculated by substituting the preset future time into the linear relation. This approach may allow for prediction of motion data and distance at a future time. The method can predict what action the monitoring object does, and can also predict whether the monitoring object is close to the obstacle or far away from the obstacle, so that the prediction result is more accurate.
Step S103: and combining the predicted action data and the predicted distance of the preset future moment and the real-time action data and the real-time distance of the specified time period into a predicted behavior vector.
Specifically, the predicted motion data at the preset future time and the real-time motion data of the specified time period form a predicted motion vector, the predicted distance at the preset future time and the real-time distance of the specified time period form a predicted distance vector, and the motion vector and the distance vector are combined into a predicted behavior vector, namely, a predicted behavior segment.
Step S104: and inputting the predicted behavior vector into a trained safety judgment model to obtain a safety judgment result.
Specifically, the predicted behavior vector is input into a trained safety judgment model, and a safety judgment result can be obtained. That is, the linear regression algorithm is used based on the previous period (first preset time T)1To a second preset time T2) Real-time motion data (constructed real-time motion vector d)0) And the real-time distance (the constructed real-time distance vector p)0) To predict future T3Motion data d of time1And a distance p1Then, the predicted motion vector (predicted motion vector d)0+d1+p0+p1) And substituting the safety judgment model with the safety judgment model to predict whether the staff behaviors generate danger or not.
Meanwhile, real-time data and prediction data are combined, and the effect of accurate prediction can be achieved.
Because the process of acquiring the motion data by the motion sensor and the process of acquiring the distance data by the distance sensor are delayed and need a certain time, by the method in the embodiment, the prediction of the behavior at the preset future moment is finished before the actual arrival at the preset future moment, and the safety judgment is carried out, so that the danger is relieved, and the occurrence of safety accidents is greatly reduced.
As shown in fig. 2, the safety determination model is constructed by the following steps:
(a) acquiring different historical behavior vectors;
(b) according to a preset safety standard, performing safety judgment on different historical behavior vectors to obtain corresponding historical safety judgment results;
(c) and performing machine learning training on different historical behavior vectors and the historical safety judgment results corresponding to the different historical behavior vectors to obtain the safety judgment model.
And different historical behavior vectors are collected according to the historical behaviors of the monitored object.
It should be noted that after different historical behavior vectors (training data) are obtained, the training data may be subjected to big data cleaning, and after operations such as removing some data noise and smoothing some abnormal data, usable historical data may be obtained to improve the accuracy of the training data.
The preset safety standard is determined according to different posts and working environments thereof in practical situations, for example, certain posts relate to equipment running at high speed, the safety standards corresponding to the posts are strict, and for the posts only relating to computer operation, the safety standards corresponding to the posts are loose.
That is, historical behavior data of the monitored object is collected to form a behavior vector set Mk i[a1,a2,...,an]Wherein k is the position of the monitoring object, i is the number of the monitoring object, anIs the nth behavior vector. According to a preset safety standard, a safety behavior mode and a dangerous behavior mode (namely a historical safety judgment result) are defined for the first time, and a safety behavior label S and a dangerous label D are given.
Wherein the step of performing machine learning training on the different historical behavior vectors and the historical safety judgment results corresponding thereto to obtain the safety judgment model comprises the steps of:
(a) performing machine learning training on different historical behavior vectors and corresponding historical safety judgment results by using a support vector machine algorithm to establish an initial safety judgment model;
(b) determining initial safety judgment results corresponding to different historical behavior vectors according to the initial safety judgment model, and determining the correctness of each initial safety judgment result according to the comparison result of each initial safety judgment result and the corresponding historical safety judgment result; when the current initial safety judgment result is the same as the corresponding historical safety judgment result, the current initial safety judgment result is correct;
(c) calculating the accuracy of the initial safety judgment result according to the accuracy of each initial safety judgment result, and comparing the accuracy with a preset threshold:
when the accuracy is greater than or equal to the preset threshold, taking the initial safety judgment model as the final safety judgment model;
and when the accuracy is smaller than the preset threshold value, returning to the step of performing machine learning training on different historical behavior vectors and the historical safety judgment results corresponding to the different historical behavior vectors by using a support vector machine algorithm so as to perform machine learning training again.
Specifically, the accuracy of the initial safety judgment model is calculated according to the historical safety judgment result (judged according to the preset safety standard) and the initial safety judgment result (judged according to the initial safety judgment model) corresponding to each historical behavior vector. And comparing the accuracy with a preset threshold, and only when the accuracy is less than or equal to the preset threshold, taking the current initial safety judgment model as a final safety judgment model to be put into use.
Illustratively, the preset threshold is 95%, which can be changed according to the actual situation and the post requirement.
It should be noted that the safety determination model may be trained by using various methods, such as Support Vector Machine (SVM) algorithm, multiple linear regression, neural network, and the like, and this embodiment only provides a training process of the SVM algorithm.
Step S105: and when the safety judgment result is dangerous, early warning is carried out.
Specifically, when the safety judgment result is dangerous, at least one of a voice early warning, a vibration early warning and a vision early warning is adopted for early warning.
The voice alarm used for voice early warning is arranged on the shoulder of the wearable device and the position, close to the human ear, of the helmet at equal distance.
The vibration alarm used for the vibration early warning is arranged at sensitive parts such as hands of the wearable equipment.
The visual alarm used for visual early warning is arranged on the back, the chest, the outer side of the big arm and other parts of the wearable equipment to provide early warning for other staff.
In addition to determining the predicted behavior vector of the monitored object as safe S and dangerous D, the dangerous behavior may be further classified into three levels from low to high, i.e., D1, D2 and D3, as required. Correspondingly, the output of the safety judgment model is divided into S, D1, D2 and D3. Different danger levels correspond to different early warning modes and emergency measures. The low level is fed back through the alarm device of the wearable device, the middle level suspends the related device, and the high level suspends the related production line.
Referring to fig. 3, another flow chart of the safety precaution method is also provided in this embodiment.
The embodiment provides a safety early warning method, which comprises the steps of obtaining the distance between a monitored object and an obstacle, and obtaining real-time action data of the monitored object in a specified time period when the distance between the monitored object and the obstacle is smaller than a preset distance; according to the real-time action data and the real-time distance of the specified time period, respectively obtaining predicted action data and a predicted distance of a preset future moment after the specified time period through a linear regression algorithm; combining the predicted action data and the predicted distance of the preset future moment and the real-time action data and the real-time distance of the appointed time period into a predicted behavior vector; inputting the predicted behavior vector into a trained safety judgment model to obtain a safety judgment result; and when the safety judgment result is dangerous, early warning is carried out. The method predicts the behavior data at a certain future moment according to the real-time behavior data of the monitored object, inputs the real-time data and the predicted data into the trained safety judgment model for judgment, achieves the purposes of predicting the behavior of the staff and warning in advance, and can fully realize safety early warning.
Example two
Referring to fig. 4, the present embodiment provides a safety precaution device 100, including: the system comprises a real-time data acquisition module 101, a behavior prediction module 102, a behavior vector combination module 103, a safety judgment module 104 and an early warning module 105.
The real-time data acquisition module 101 is configured to acquire a real-time distance between a monitored object and an obstacle, and acquire real-time action data of the monitored object in a specified time period when the real-time distance between the monitored object and the obstacle is smaller than a preset distance;
the behavior prediction module 102 is configured to obtain predicted motion data and a predicted distance at a preset future time after the specified time period by a linear regression algorithm according to the real-time motion data and the real-time distance of the specified time period;
the behavior vector combination module 103 is configured to combine the predicted motion data and the predicted distance at the preset future time and the real-time motion data and the real-time distance at the specified time period into a predicted behavior vector;
the safety judgment module 104 is used for inputting the predicted behavior vector into a trained safety judgment model to obtain a safety judgment result;
and the early warning module 105 is used for early warning when the safety judgment result is dangerous.
The real-time data acquisition module 101 acquires a real-time distance between a monitored object and an obstacle, and acquires real-time action data of the monitored object in a specified time period when the real-time distance between the monitored object and the obstacle is smaller than a preset distance; the behavior prediction module 102 obtains predicted motion data and predicted distance of a preset future moment after the specified time period through a linear regression algorithm according to the real-time motion data and the real-time distance of the specified time period; the behavior vector combination module 103 combines the predicted action data and the predicted distance at the preset future moment and the real-time action data and the real-time distance of the specified time period into a predicted behavior vector; the safety judgment module 104 inputs the predicted behavior vector into a trained safety judgment model to obtain a safety judgment result; and the early warning module 105 carries out early warning when the safety judgment result is dangerous.
The specific embodiment process of the above method steps can be referred to as embodiment one, and the details of this embodiment are not repeated herein.
EXAMPLE III
Referring to fig. 5, the present embodiment provides a safety precaution device 200, including: memory 201, controller 202, distance sensor 203, motion sensor 204 and alarm 205.
The memory 201 stores a computer program, which when executed by the controller 202 implements the safety warning method according to the first embodiment to control the alarm 205 to warn according to the data collected by the distance sensor 203 and the motion sensor 204.
The controller 202 is configured to perform all or part of the steps of the safety precaution method according to the first embodiment. The memory 201 is used to store various types of data, which may include, for example, instructions for any application or method in the safety precaution device, as well as application-related data.
The Memory 201 may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk or optical disk.
The controller 202 may be implemented by a controller, a microcontroller or other electronic components, and is used to execute the safety precaution method described in the first embodiment.
And the distance sensor 203 is connected with the controller 202 and is used for acquiring the real-time distance between the monitored object and the obstacle. Specifically, the distance sensor 203 is configured to collect real-time distances between each part of the body of the monitoring subject and the obstacle. The distance sensor 203 includes an infrared distance meter, and can obtain the distance between each part of the human body and the obstacle.
And the motion sensor 204 is connected with the controller 202 and is used for collecting real-time motion data of the monitored object in a specified time period.
The safety precaution device 200 may be, but is not limited to, a wearable device.
The motion sensor 204 and the distance sensor 203 are provided on the wearable device at positions corresponding to respective parts of the body of the monitoring subject. The motion sensor 204 acquires motion data of the human body based on the positions of the respective parts of the human body.
And the alarm 205 is connected with the controller 202, and the alarm 205 comprises a voice alarm, a vibration alarm and a visual alarm.
Wherein, audible alarm sets up in the shoulder of wearable equipment, the helmet equidistance people ear nearer position.
The vibration alarm is arranged on sensitive parts such as hands of the wearable device.
Visual alarm sets up in positions such as wearable equipment's back, chest, big arm outside to provide the warning for other staff.
It is understood that the safety precaution device 200 may also include an input/output (I/O) interface, and a communication module. The communication module comprises a Bluetooth assembly, a WiFi assembly and a 5G assembly, and can transmit real-time distance and real-time action data to the server in real time according to actual use scenes and communication conditions.
The specific embodiment of the method for performing the safety precaution based on the above devices has been described in detail in the first embodiment, and is not described herein again.
Example four
The present embodiments provide a computer readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application mall, etc., having stored thereon a computer program which, when executed by a processor, may implement the method steps of:
step S101: the method comprises the steps of obtaining a real-time distance between a monitored object and an obstacle, and obtaining a real-time behavior vector of the monitored object in a specified time period when the real-time distance between the monitored object and the obstacle is smaller than a preset distance;
step S102: according to the real-time action data and the real-time distance of the specified time period, respectively obtaining predicted action data and a predicted distance of a preset future moment after the specified time period through a linear regression algorithm;
step S103: combining the predicted action data and the predicted distance of the preset future moment and the real-time action data and the real-time distance of the appointed time period into a predicted behavior vector;
step S104: inputting the predicted behavior vector into a trained safety judgment model to obtain a safety judgment result;
step S105: and when the safety judgment result is dangerous, early warning is carried out.
The specific embodiment process of the above method steps can be referred to as embodiment one, and the details of this embodiment are not repeated herein.
In summary, according to the safety pre-warning method, the safety pre-warning device, the safety pre-warning apparatus and the storage medium provided by the present application, the method includes acquiring a distance between a monitored object and an obstacle, and acquiring real-time action data of the monitored object in a specified time period when the distance between the monitored object and the obstacle is smaller than a preset distance; according to the real-time action data and the real-time distance of the specified time period, respectively obtaining predicted action data and a predicted distance of a preset future moment after the specified time period through a linear regression algorithm; combining the predicted action data and the predicted distance of the preset future moment and the real-time action data and the real-time distance of the appointed time period into a predicted behavior vector; inputting the predicted behavior vector into a trained safety judgment model to obtain a safety judgment result; and when the safety judgment result is dangerous, early warning is carried out. The method predicts the behavior data at a certain future moment according to the real-time behavior data of the monitored object, inputs the real-time data and the predicted data into the trained safety judgment model for judgment, achieves the purposes of predicting the behavior of the staff and warning in advance, and can fully realize safety early warning.
In the embodiments provided in the present application, it should be understood that the disclosed method can be implemented in other ways. The above-described method embodiments are merely illustrative.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Although the embodiments disclosed in the present application are described above, the descriptions are only for the convenience of understanding the present application, and are not intended to limit the present application. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the disclosure as defined by the appended claims.
Claims (10)
1. A safety precaution method, the method comprising:
the method comprises the steps of obtaining the real-time distance between a monitored object and an obstacle, and obtaining real-time action data of the monitored object in a specified time period when the real-time distance between the monitored object and the obstacle is smaller than a preset distance;
according to the real-time action data and the real-time distance of the specified time period, respectively obtaining predicted action data and a predicted distance of a preset future moment after the specified time period through a linear regression algorithm;
combining the predicted action data and the predicted distance of the preset future moment and the real-time action data and the real-time distance of the appointed time period into a predicted behavior vector;
inputting the predicted behavior vector into a trained safety judgment model to obtain a safety judgment result;
and when the safety judgment result is dangerous, early warning is carried out.
2. The method according to claim 1, wherein the step of obtaining the real-time distance between a monitored object and an obstacle and obtaining the real-time action data of the monitored object in a specified time period when the real-time distance between the monitored object and the obstacle is less than a preset distance comprises the following steps:
the method comprises the steps of obtaining real-time distances between all parts of a body of a monitored object and an obstacle, and obtaining real-time action data of the monitored object in a specified time period when the minimum value of the real-time distances between all parts of the body of the monitored object and the obstacle is smaller than a preset distance.
3. The method according to claim 1, wherein the step of obtaining the predicted motion data of the preset future time after the specified time period by a linear regression algorithm according to the real-time motion data of the specified time period comprises the following steps:
according to the real-time action data of the specified time period, establishing an action prediction model for describing the corresponding relation between the action data and the time through a linear regression algorithm;
and obtaining predicted action data of a preset future moment after the specified time period according to the action prediction model.
4. The method according to claim 2, wherein the step of obtaining the predicted distance of the preset future time after the specified time period by a linear regression algorithm according to the real-time distance of the specified time period comprises the steps of:
respectively establishing a distance prediction model for describing the corresponding relation between each part of the body of the monitored object and the distance and time of the obstacle through a linear regression algorithm according to the real-time distance between each part of the body of the monitored object and the obstacle in the specified time period;
and obtaining the predicted distance between each part of the body of the monitored object and the obstacle at a preset future moment after the specified time period according to the distance prediction model.
5. The method of claim 1, wherein the safety decision model is constructed by:
acquiring different historical behavior vectors;
according to a preset safety standard, performing safety judgment on different historical behavior vectors to obtain corresponding historical safety judgment results;
and performing machine learning training on different historical behavior vectors and the historical safety judgment results corresponding to the different historical behavior vectors to obtain the safety judgment model.
6. The method of claim 5, wherein performing machine learning training on different historical behavior vectors and their corresponding historical security decision results to obtain the security decision model comprises:
performing machine learning training on different historical behavior vectors and the corresponding historical safety judgment results by using a support vector machine algorithm to establish an initial safety judgment model;
determining initial safety judgment results corresponding to different historical behavior vectors according to the initial safety judgment model, and determining the correctness of each initial safety judgment result according to the comparison result of each initial safety judgment result and the corresponding historical safety judgment result; when the current initial safety judgment result is the same as the corresponding historical safety judgment result, the current initial safety judgment result is correct;
calculating the accuracy of the initial safety judgment result according to the accuracy of each initial safety judgment result, and comparing the accuracy with a preset threshold:
when the accuracy is greater than or equal to the preset threshold, taking the initial safety judgment model as the final safety judgment model;
and when the accuracy is smaller than the preset threshold value, returning to the step of performing machine learning training on different historical behavior vectors and the historical safety judgment results corresponding to the different historical behavior vectors by using a support vector machine algorithm so as to perform machine learning training again.
7. A safety precaution device, comprising:
the real-time data acquisition module is used for acquiring the real-time distance between a monitored object and an obstacle and acquiring real-time action data of the monitored object in a specified time period when the real-time distance between the monitored object and the obstacle is smaller than a preset distance;
the behavior prediction module is used for obtaining predicted action data and predicted distance of a preset future moment after the specified time period through a linear regression algorithm according to the real-time action data and the real-time distance of the specified time period;
the behavior vector combination module is used for combining the predicted action data and the predicted distance at the preset future moment and the real-time action data and the real-time distance of the specified time period into a predicted behavior vector;
the safety judgment module is used for inputting the predicted behavior vector into a trained safety judgment model to obtain a safety judgment result;
and the early warning module is used for carrying out early warning when the safety judgment result is dangerous.
8. The safety early warning equipment is characterized by comprising a memory, a controller, a distance sensor, a motion sensor and an alarm;
the distance sensor is used for acquiring the real-time distance between a monitored object and an obstacle;
the motion sensor is used for acquiring real-time motion data of the monitored object in a specified time period;
the memory stores a program which, when executed by the controller, executes the safety warning method according to any one of claims 1 to 6 to control the alarm to warn according to the data collected by the distance sensor and the motion sensor.
9. The safety precaution device of claim 8, wherein the safety precaution device is a wearable device.
10. A storage medium storing a computer program executable by one or more processors for implementing a safety precaution method as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010858884.XA CN111985717A (en) | 2020-08-24 | 2020-08-24 | Safety early warning method and device, safety early warning equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010858884.XA CN111985717A (en) | 2020-08-24 | 2020-08-24 | Safety early warning method and device, safety early warning equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111985717A true CN111985717A (en) | 2020-11-24 |
Family
ID=73443158
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010858884.XA Pending CN111985717A (en) | 2020-08-24 | 2020-08-24 | Safety early warning method and device, safety early warning equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111985717A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112863125A (en) * | 2020-12-24 | 2021-05-28 | 珠海新天地科技有限公司 | Intelligent alarm method |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20170067319A (en) * | 2015-12-08 | 2017-06-16 | 한국건설기술연구원 | Intelligence structure safety monitoring system for collecting timing- synchronized sensor data, and method for the same |
| CN109095355A (en) * | 2018-11-07 | 2018-12-28 | 徐州重型机械有限公司 | Working space collision-proof method and system, detecting devices and control equipment |
| CN109269556A (en) * | 2018-09-06 | 2019-01-25 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of equipment Risk method for early warning, device, terminal device and storage medium |
| CN109859447A (en) * | 2019-01-30 | 2019-06-07 | 广州轨道交通建设监理有限公司 | Method, controller and the system of security protection in a kind of construction site |
| CN110223489A (en) * | 2019-05-17 | 2019-09-10 | 中电投工程研究检测评定中心有限公司 | A kind of monitoring method and device of engineering object |
| CN110293968A (en) * | 2019-06-18 | 2019-10-01 | 百度在线网络技术（北京）有限公司 | Control method, device, equipment and the readable storage medium storing program for executing of automatic driving vehicle |
| CN110570690A (en) * | 2019-09-20 | 2019-12-13 | 珠海云航智能技术有限公司 | ship navigation risk early warning method and device, terminal device and storage medium |
| CN110689041A (en) * | 2019-08-20 | 2020-01-14 | 陈羽旻 | Multi-target behavior action recognition and prediction method, electronic equipment and storage medium |
| CN111144263A (en) * | 2019-12-20 | 2020-05-12 | 山东大学 | Construction worker high-fall accident early warning method and device |
| CN111275923A (en) * | 2020-01-22 | 2020-06-12 | 清华大学 | Man-machine collision early warning method and system for construction site |
| CN111392619A (en) * | 2020-03-25 | 2020-07-10 | 广东博智林机器人有限公司 | Tower crane early warning method, device and system and storage medium |
-
2020
- 2020-08-24 CN CN202010858884.XA patent/CN111985717A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20170067319A (en) * | 2015-12-08 | 2017-06-16 | 한국건설기술연구원 | Intelligence structure safety monitoring system for collecting timing- synchronized sensor data, and method for the same |
| CN109269556A (en) * | 2018-09-06 | 2019-01-25 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of equipment Risk method for early warning, device, terminal device and storage medium |
| CN109095355A (en) * | 2018-11-07 | 2018-12-28 | 徐州重型机械有限公司 | Working space collision-proof method and system, detecting devices and control equipment |
| CN109859447A (en) * | 2019-01-30 | 2019-06-07 | 广州轨道交通建设监理有限公司 | Method, controller and the system of security protection in a kind of construction site |
| CN110223489A (en) * | 2019-05-17 | 2019-09-10 | 中电投工程研究检测评定中心有限公司 | A kind of monitoring method and device of engineering object |
| CN110293968A (en) * | 2019-06-18 | 2019-10-01 | 百度在线网络技术（北京）有限公司 | Control method, device, equipment and the readable storage medium storing program for executing of automatic driving vehicle |
| CN110689041A (en) * | 2019-08-20 | 2020-01-14 | 陈羽旻 | Multi-target behavior action recognition and prediction method, electronic equipment and storage medium |
| CN110570690A (en) * | 2019-09-20 | 2019-12-13 | 珠海云航智能技术有限公司 | ship navigation risk early warning method and device, terminal device and storage medium |
| CN111144263A (en) * | 2019-12-20 | 2020-05-12 | 山东大学 | Construction worker high-fall accident early warning method and device |
| CN111275923A (en) * | 2020-01-22 | 2020-06-12 | 清华大学 | Man-machine collision early warning method and system for construction site |
| CN111392619A (en) * | 2020-03-25 | 2020-07-10 | 广东博智林机器人有限公司 | Tower crane early warning method, device and system and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112863125A (en) * | 2020-12-24 | 2021-05-28 | 珠海新天地科技有限公司 | Intelligent alarm method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108628281B (en) | Abnormality detection system and abnormality detection method | |
| CN107103733B (en) | One kind falling down alarm method, device and equipment | |
| US9183176B2 (en) | Method and apparatus for providing driver-customized vehicle service | |
| US11216757B2 (en) | Worker management device | |
| JP6444851B2 (en) | Control device having learning function for detecting cause of noise generation | |
| CN109001649A (en) | A kind of power supply smart diagnostic system and guard method | |
| CN111126153B (en) | Safety monitoring method, system, server and storage medium based on deep learning | |
| CN113724105A (en) | Building construction site monitoring system and monitoring method thereof | |
| KR101985161B1 (en) | Intelligent safety management system for reducing damages of construction site | |
| JP2014178861A (en) | Abnormal driving action detection device | |
| EP3088269B1 (en) | Method, system, and computer program product for monitoring a driver of a vehicle | |
| CN112884199A (en) | Method and device for predicting faults of hydropower station equipment, computer equipment and storage medium | |
| CN107764318A (en) | Method for detecting abnormality and Related product | |
| JP2020042785A (en) | Method, apparatus, device and storage medium for identifying passenger state in unmanned vehicle | |
| CN111985717A (en) | Safety early warning method and device, safety early warning equipment and storage medium | |
| Simeone et al. | Cloud-based platform for intelligent healthcare monitoring and risk prevention in hazardous manufacturing contexts | |
| CN108803690A (en) | Numerical control device | |
| CN116909235A (en) | Intelligent factory monitoring method, intelligent factory monitoring system and electronic equipment | |
| Wang et al. | Integrated and automated Systems for Safe Construction Sites | |
| CN115338867A (en) | Fault state monitoring method, device and equipment for mobile robot | |
| CN113569785A (en) | Driving state sensing method and device | |
| CN117407573B (en) | Visual security data processing method and system | |
| CN113108794B (en) | Position identification method, device, equipment and computer readable storage medium | |
| AU2021105041A4 (en) | Method and equipment for judging safety of operating personnel | |
| RU2790331C1 (en) | Method for determining an anomaly in a cyber-physical system |
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 |