CN110706453A - Safety clothing danger signal identification system and method - Google Patents
Safety clothing danger signal identification system and method Download PDFInfo
- Publication number
- CN110706453A CN110706453A CN201911110668.0A CN201911110668A CN110706453A CN 110706453 A CN110706453 A CN 110706453A CN 201911110668 A CN201911110668 A CN 201911110668A CN 110706453 A CN110706453 A CN 110706453A
- Authority
- CN
- China
- Prior art keywords
- signal
- sound
- voice
- safety
- decision
- 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 79
- 238000001514 detection method Methods 0.000 claims abstract description 35
- 230000005540 biological transmission Effects 0.000 claims abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000006243 chemical reaction Methods 0.000 claims abstract description 17
- 238000012806 monitoring device Methods 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims description 25
- 230000001133 acceleration Effects 0.000 claims description 21
- 238000001035 drying Methods 0.000 claims description 12
- 230000004927 fusion Effects 0.000 claims description 9
- 238000007405 data analysis Methods 0.000 claims description 8
- 230000005236 sound signal Effects 0.000 claims description 8
- 238000003066 decision tree Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000011478 gradient descent method Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 6
- 238000012706 support-vector machine Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 3
- 238000012417 linear regression Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 230000004044 response Effects 0.000 claims 1
- 208000014674 injury Diseases 0.000 description 9
- 230000006378 damage Effects 0.000 description 8
- 208000027418 Wounds and injury Diseases 0.000 description 7
- 208000012260 Accidental injury Diseases 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000005180 public health Effects 0.000 description 2
- 206010028813 Nausea Diseases 0.000 description 1
- 206010028980 Neoplasm Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 208000026106 cerebrovascular disease Diseases 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 208000019622 heart disease Diseases 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 230000008693 nausea Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 208000023504 respiratory system disease Diseases 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Alarm Systems (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The invention discloses a system and a method for identifying danger signals of safety clothing, wherein the system comprises a main trigger device worn on a person, and a sound detection device and a danger signal monitoring device which are installed on the safety clothing, wherein the main trigger device comprises a first micro-processing unit, a three-axis accelerometer, a three-axis gyroscope, a pressure sensor and a first Bluetooth transmission module; the sound detection device comprises a second micro-processing unit, a double-microphone array, a conversion module and a second Bluetooth transmission module. According to the invention, the behavior state information of the operation personnel in the dangerous occasions is recorded according to the information collected by the safety clothing worn by the operation personnel in the dangerous occasions, so that the operation personnel is monitored and protected, the potential safety hazard is reduced, and the safety of the personnel is improved.
Description
Technical Field
The invention relates to a safety clothing danger signal identification system and a method, and belongs to the technical field of data monitoring.
Background
With the rapid development of economy, injuries have become important public health problems threatening the health of people. According to statistics, each kind of injury occurs about 2 hundred million times every year in China, the number of dead people is about 70 million, and accounts for about 9 percent of the total number of dead people, and the death is the fifth cause of nausea, tumor, cerebrovascular disease, respiratory system disease and heart disease.
Injuries are divided by intent into accidental injuries, conscious injuries and violence and other kills, with the greatest proportion of accidental injuries. According to WHO organization estimates, along with the acceleration of urbanization processes and population mobility, death caused by injuries worldwide will increase by 65%, up to 840 thousands, and the threat caused by accidental injuries will be in a continuously rising trend.
The accidental injury caused by the dangerous signals cannot be correctly distinguished, so that the serious threat to the health of people is caused, and the heavy burden is also brought to the society. How to avoid accidental injury has become a public health issue, and many times the injury is not directly from the danger itself, but the danger signal cannot be correctly identified, so the prevention should be based on the injury, and the danger signal is identified when the danger is not generated. In recent years, with the continuous enrichment of multi-modal information and the great development of deep learning technology, more and more researchers begin to research the danger signal identification technology, strive to improve the danger signal identification accuracy, reduce the harm to people through means such as prediction, reminding, alarm and remedy, and the like, and the technology has good application value and wide market prospect.
Disclosure of Invention
The invention aims to provide a safety clothing danger signal identification system and a method, which can record the behavior state information of operators in dangerous occasions, thereby realizing monitoring and protection of the operators, reducing the potential safety hazard and improving the safety of the operators.
The technical scheme of the invention is as follows: a safety suit danger signal identification system comprises a main trigger device worn on a person, and a sound detection device and a danger signal monitoring device which are installed on a safety suit, wherein the main trigger device comprises a first micro-processing unit, a three-axis accelerometer, a three-axis gyroscope, a pressure sensor and a first Bluetooth transmission module; the sound detection device comprises a second micro-processing unit, a double-microphone array, a conversion module and a second Bluetooth transmission module, wherein the double-microphone array, the conversion module and the second Bluetooth transmission module are electrically connected with the second micro-processing unit; the danger signal detection device comprises a receiving module, a calculation module and an analysis module, and is in wireless communication connection with the first Bluetooth transmission module and the second Bluetooth transmission module through the receiving module respectively.
Further, the sound detection device is arranged on the shoulder of the safety suit, and the danger signal monitoring device is arranged on the waist of the safety suit.
Meanwhile, the invention also provides a safety clothing danger signal identification method, which comprises the following steps:
s1, acquiring triggering information, position information and sound information of personnel;
s2, designing an independent trigger method according to the trigger information: acquiring acceleration, angular velocity and joint point pressure data of personnel by using a main trigger device, filtering the acquired data by using an FIR filter to obtain effective measurement signals, performing data fusion on the de-noised acceleration, angular velocity and joint point pressure data by using a gradient descent method to obtain a target function, and taking the target function as a main decision-making function and the method as a main decision-making method;
s3, designing a voice recognition decision method by using a deep learning method according to the voice information: firstly, collecting voice information of personnel by using a voice detection device, converting a voice analog signal into a digital signal by using a conversion module, performing drying treatment on the voice digital signal by using a wavelet threshold drying method to obtain an effective voice signal, extracting short-time energy, short-time average zero-crossing rate, Mel cepstrum coefficient and linear prediction cepstrum coefficient of the voice signal, and finally performing data analysis on the voice characteristics by using a decision tree support vector machine to obtain a dangerous person voice signal target function, wherein the target function is used as an auxiliary decision function and is used as an auxiliary decision method;
s4, designing a final decision method according to the main decision method and the auxiliary decision method: and (5) fusing and judging the results of the main decision method and the auxiliary decision method by using a linear programming equation.
The main decision method comprises the following steps:
the method comprises the following steps: acquisition of the acceleration a of a person using a main triggering devicex、ay、azAngular velocity ωx、ωy、ωzAnd magnetic strength mx、my、mz；
Step two: for the collected acceleration ax、ay、azAngular velocity wx、wy、wzAnd magnetic strength m, filtering by using an FIR filter to obtain an effective measurement signal;
step three: and (3) establishing a navigation coordinate system and a carrier coordinate system, wherein the rotation matrix is as follows:
where ψ is the yaw angle, ρ is the pitch angle, and θ is the roll angle. Is recorded as:
the three attitude angles are:
attitude quaternion q ═ q (q0 q1 q2 q3)TAngular velocity omega of gyroscopex、ωy、ωzThe satisfied relationship is:
the relationship between the attitude quaternion and the attitude matrix can be expressed as:
the relationship between the triaxial accelerometer and the pitch angle and the roll angle is as follows:
[axayaz]T＝[g·sinθcosρ -g·sinρ -g·cosθcosρ]T
the relationship between the triaxial magnetometer and the yaw angle is as follows:
step four: carrying out data fusion on the denoised acceleration, angular velocity and magnetic strength data by using a gradient descent method, wherein an iterative formula is as follows:
the objective function is obtained as:
this objective function is taken as the main decision method.
The assistant decision method comprises the following steps:
the method comprises the following steps: collecting voice information of personnel by using a voice detection device (2);
step two: converting the sound analog signal into a sound digital signal through a conversion module (22);
step three: carrying out drying reduction on the sound digital signal by using a wavelet threshold drying method to obtain an effective sound signal;
step four: extracting short-time energy of sound signalsShort time average zero crossing rate
Melezi pedigreeA number MFCC and a linear prediction cepstral coefficient LPCC;
step five: and carrying out data analysis on the sound characteristics by using a decision tree support vector machine to obtain a dangerous person sound signal identification result delta, wherein 0 is a non-dangerous signal, 1 is a dangerous signal, and the identification result delta is used as an auxiliary decision method.
The final decision method is to use a linear programming equation to fuse and judge the results of the main decision method and the auxiliary decision method; the linear regression equation is: y ═ w1f(q)+w2δ, where w1 and w2 are weights, may be adjusted as appropriate, and are set here to 10 and 1, respectively.
Due to the adoption of the technical scheme, the invention has the advantages that: according to the invention, the behavior state information of the operation personnel in the dangerous occasions is recorded according to the information collected by the safety clothing worn by the operation personnel in the dangerous occasions, so that the operation personnel is monitored and protected, the potential safety hazard is reduced, and the safety of the personnel is improved.
Drawings
FIG. 1 is a schematic structural view of the present invention;
FIG. 2 is a schematic structural diagram of a main trigger device according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a sound detection device according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a danger signal monitoring apparatus according to an embodiment of the present invention;
FIG. 5 is a schematic flow diagram of the present invention;
FIG. 6 is a flow chart illustrating a primary decision method of the present invention;
FIG. 7 is a flow chart of an aid decision method of the present invention;
fig. 8 is a flow chart illustrating data analysis of sound characteristics according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the accompanying drawings and examples.
The embodiment of the invention comprises the following steps: the safety suit danger signal identification system is shown in fig. 1-4, and comprises a main trigger device 1 worn on a person, and a sound detection device 2 and a danger signal monitoring device 3 which are installed on the safety suit, wherein the main trigger device 1 comprises a first micro-processing unit 10, a three-axis accelerometer 11, a three-axis gyroscope 12, a pressure sensor 13 and a first bluetooth transmission module 14, and the three-axis accelerometer 11, the three-axis gyroscope 12, the pressure sensor 13 and the first bluetooth transmission module 14 are all electrically connected with the first micro-processing unit 10; the sound detection device 2 comprises a second micro-processing unit 20, a dual-microphone array 21, a conversion module 22 and a second bluetooth transmission module 23, wherein the dual-microphone array 21, the conversion module 22 and the second bluetooth transmission module 23 are all electrically connected with the second micro-processing unit 20; the danger signal detection device 3 comprises a receiving module 30, a calculating module 31 and an analyzing module 32, and the danger signal detection device 3 is in wireless communication connection with the first bluetooth transmission module 14 and the second bluetooth transmission module 23 through the receiving module 30.
The functions of the above components are explained as follows:
the main trigger device 1 is used for acquiring the posture information of personnel;
the voice detection device 2 is used for acquiring voice information of a person;
and the danger signal monitoring device 3 is used for fusing the posture information and the sound information of the personnel, calculating the real-time state of the personnel, and judging the danger degree of the personnel by utilizing deep learning and multi-mode information fusion.
In the implementation, the main trigger device 1 is worn on the body of a worker in a dangerous occasion and is used for acquiring attitude information such as acceleration, direction, pressure and the like of the worker; the sound detection device 2 is arranged on the shoulder of the safety clothing and used for acquiring and processing sound information of personnel. The danger signal monitoring device 3 is mounted on the waist of the safety suit and used for fusing posture information and sound information of personnel, calculating the real-time state of the personnel and judging the danger degree of the personnel according to the state.
As shown in fig. 2, the main trigger device 1 includes:
a micro-processing unit 10 for processing the acquired attitude information;
the three-axis accelerometer 11 is used for acquiring X, Y, Z acceleration information of a person in three directions, and if acceleration greater than a set value is generated, the main trigger device 1 is triggered to enter an excitation state and a trigger signal is sent out;
the three-axis gyroscope 12 is used for acquiring angular speed and direction information of personnel;
a pressure sensor 13 for detecting a pressure state of each joint point;
a bluetooth transmission module 14, configured to send acceleration information, angular velocity information, and pressure information to the danger signal detection apparatus 3, where these pieces of information are collectively referred to as trigger information;
the pressure state of each joint point comprises: neck pressure, shoulder pressure, elbow pressure, hip pressure, knee pressure, and foot pressure information.
The direction information includes: angular velocity variation, corner offset, and equilibrium position offset.
As shown in fig. 3, the sound detection device 2 includes:
a micro-processing unit 20 for processing the acquired voice information;
the dual-microphone array 21 is used for acquiring human voice information;
a conversion module 22, configured to convert an analog signal acquired by the dual-microphone array 21 into a digital signal;
and the Bluetooth transmission module 23 is configured to send the human voice information to the danger signal detection device 3.
In the embodiment, the dual microphone array 21 collects the voice of the person, and then transmits the voice signal to the conversion module 22 for analog-to-digital conversion, the micro processing unit 20 packages the received digital voice signal and transmits the digital voice signal to the bluetooth transmission module 23, and the bluetooth transmission module 23 transmits the voice signal to the danger signal detection apparatus 3.
As shown in fig. 4, the danger signal detecting apparatus 3 includes:
a receiving module 30, configured to receive the trigger signal, the positioning signal, and the sound signal;
the calculation module 31 is used for calculating triggering information, position information and sound information of personnel;
and the analysis module 32 is used for carrying out data fusion on the triggering information and the sound information of the personnel, and analyzing and identifying the state of the personnel.
In specific implementation, a person wears a safety suit with a main trigger device 1, a sound detection device 2 and a danger signal detection device 3. The main trigger device 1 collects attitude information such as acceleration, direction and pressure, and sends the information to the dangerous signal detection device 3 through the Bluetooth transmission module 13. The sound detection device 2 collects sound signals, converts the signals into digital signals through the conversion module 22, and sends information to the danger signal detection device 3 through the Bluetooth module 23. The danger signal detection device 3 performs data analysis and status judgment on the received information.
As shown in fig. 5, an embodiment of the present invention further provides a method for identifying a danger signal of a safety suit, including the following steps:
s1, acquiring triggering information, position information and sound information of personnel;
s2, designing an independent trigger method according to the trigger information: acquiring acceleration, angular velocity and joint point pressure data of a person by using a main trigger device 1, filtering the acquired data by using an FIR filter to obtain effective measurement signals, performing data fusion on the de-noised acceleration, angular velocity and joint point pressure data by using a gradient descent method to obtain a target function, and taking the target function as a main decision-making function and the method as a main decision-making method;
s3, designing a voice recognition decision method by using a deep learning method according to the voice information: firstly, a voice detection device 2 is used for collecting voice information of personnel, then a voice analog signal is converted into a digital signal through a conversion module 22, the voice digital signal is subjected to drying treatment by using a wavelet threshold value drying method to obtain an effective voice signal, the short-time energy, the short-time average zero-crossing rate, the Mel cepstrum coefficient and the linear prediction cepstrum coefficient of the voice signal are extracted, finally, a decision tree support vector machine is used for carrying out data analysis on the voice characteristics to obtain a target function of the voice signal of the dangerous person, the target function is used as an auxiliary decision function, and the method is used as an auxiliary decision method;
s4, designing a final decision method according to the main decision method and the auxiliary decision method: and (5) fusing and judging the results of the main decision method and the auxiliary decision method by using a linear programming equation.
As shown in fig. 6, the main decision method comprises the following steps:
the method comprises the following steps: acquisition of the acceleration a of the person using the main triggering device 1x、ay、azAngular velocity ωx、ωy、ωzAnd magnetic strength mx、my、mz；
Step two: for the collected acceleration ax、ay、azAngular velocity wx、wy、wzAnd magnetic strength m, filtering by using an FIR filter to obtain an effective measurement signal;
step three: and (3) establishing a navigation coordinate system and a carrier coordinate system, wherein the rotation matrix is as follows:
where ψ is the yaw angle, ρ is the pitch angle, and θ is the roll angle. Is recorded as:
the three attitude angles are:
attitude quaternion q ═ q (q0 q1 q2 q3)TAngular velocity omega of gyroscopex、ωy、ωzThe satisfied relationship is:
the relationship between the attitude quaternion and the attitude matrix can be expressed as:
the relationship between the triaxial accelerometer and the pitch angle and the roll angle is as follows:
[axayaz]T＝[g·sinθcosρ -g·sinρ -g·cosθcosρ]T
the relationship between the triaxial magnetometer and the yaw angle is as follows:
step four: carrying out data fusion on the denoised acceleration, angular velocity and magnetic strength data by using a gradient descent method, wherein an iterative formula is as follows:
the objective function is obtained as:
this objective function is taken as the main decision method.
As shown in fig. 7, the assistant decision method comprises the following steps:
the method comprises the following steps: collecting voice information of a person by using a voice detection device 2;
step two: converting the sound analog signal into a sound digital signal through the conversion module 22;
step three: carrying out drying reduction on the sound digital signal by using a wavelet threshold drying method to obtain an effective sound signal;
step four: extracting short-time energy of sound signals
Short time average zero crossing rate
Mel cepstral coefficients MFCC and linear prediction cepstral coefficients LPCC;
step five: and (3) carrying out data analysis on the sound characteristics by using a decision tree support vector machine, and referring to fig. 8, the analysis processing process comprises the following steps: and (3) extracting features by frames, carrying out self-adaptive segmentation, carrying out DT-SVM abnormal detection and identification results to obtain a dangerous human voice signal identification result delta, wherein 0 is a non-dangerous signal, 1 is a dangerous signal, and the identification result delta is used as an auxiliary decision method.
The final decision method is to use a linear programming equation to fuse and judge the results of the main decision method and the auxiliary decision method; the linear regression equation is: y ═ w1f(q)+w2δ, where w1 and w2 are weights, may be adjusted as appropriate, and are set here to 10 and 1, respectively.
In the embodiment of the invention, the collected data are analyzed according to the posture information and the sound signals collected by the safety suit worn by the testing personnel, and the safety state of the personnel is evaluated, so that the personnel are monitored in real time, the risk degree of bearing danger is reduced, and the efficiency of safety guarantee is improved.
In addition, the security suit danger signal identification method based on multi-modal information fusion and deep learning provided by the embodiment of the invention is described in detail, a specific example is applied in the text to explain the principle and the implementation of the invention, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (6)
1. The utility model provides a safety clothing danger signal identification system, includes main trigger device (1) of dress on one's body and installs sound detection device (2) and danger signal monitoring devices (3) on the safety clothing, its characterized in that: the main trigger device (1) comprises a first micro-processing unit (10), a three-axis accelerometer (11), a three-axis gyroscope (12), a pressure sensor (13) and a first Bluetooth transmission module (14), wherein the three-axis accelerometer (11), the three-axis gyroscope (12), the pressure sensor (13) and the first Bluetooth transmission module (14) are electrically connected with the first micro-processing unit (10); the sound detection device (2) comprises a second micro-processing unit (20), a double-microphone array (21), a conversion module (22) and a second Bluetooth transmission module (23), wherein the double-microphone array (21), the conversion module (22) and the second Bluetooth transmission module (23) are electrically connected with the second micro-processing unit (20); the danger signal detection device (3) comprises a receiving module (30), a calculating module (31) and an analyzing module (32), and the danger signal detection device (3) is in wireless communication connection with the first Bluetooth transmission module (14) and the second Bluetooth transmission module (23) through the receiving module (30).
2. The safety suit hazard signal identification system of claim 1, wherein: the sound detection device (2) is arranged on the shoulder of the safety suit, and the danger signal monitoring device (3) is arranged on the waist of the safety suit.
3. A safety clothing danger signal identification method is characterized by comprising the following steps:
s1, acquiring triggering information, position information and sound information of personnel;
s2, designing an independent trigger method according to the trigger information: acquiring acceleration, angular velocity and joint point pressure data of a person by using a main trigger device (1), filtering the acquired data by using an FIR (finite impulse response) filter to obtain effective measurement signals, performing data fusion on the de-noised acceleration, angular velocity and joint point pressure data by using a gradient descent method to obtain a target function, and taking the target function as a main decision-making function and the method as a main decision-making method;
s3, designing a voice recognition decision method by using a deep learning method according to the voice information: firstly, a voice detection device (2) is used for collecting voice information of personnel, then a voice analog signal is converted into a digital signal through a conversion module (22), a wavelet threshold value drying method is applied to the voice digital signal for drying treatment, an effective voice signal is obtained, short-time energy, a short-time average zero-crossing rate, a Mel cepstrum coefficient and a linear prediction cepstrum coefficient of the voice signal are extracted, finally, a decision tree support vector machine is used for carrying out data analysis on the voice characteristics, a dangerous person voice signal target function is obtained, the target function is used as an auxiliary decision function, and the method is used as an auxiliary decision method;
s4, designing a final decision method according to the main decision method and the auxiliary decision method: and (5) fusing and judging the results of the main decision method and the auxiliary decision method by using a linear programming equation.
4. The method for identifying danger signals for safety suits according to claim 3, characterized in that: the main decision making method comprises the following steps:
the method comprises the following steps: using a main trigger device (1) to detect the acceleration a of a personx、ay、azAngular velocity ωx、ωy、ωzAnd magnetic strength mx、my、mz；
Step two: for the collected acceleration ax、ay、azAngular velocity wx、wy、wzAnd magnetic strength m, filtering by using an FIR filter to obtain an effective measurement signal;
step three: and (3) establishing a navigation coordinate system and a carrier coordinate system, wherein the rotation matrix is as follows:
where ψ is the yaw angle, ρ is the pitch angle, and θ is the roll angle. Is recorded as:
the three attitude angles are:
attitude quaternion q ═ q (q0 q1 q2 q3)TAngular velocity omega of gyroscopex、ωy、ωzThe satisfied relationship is:
the relationship between the attitude quaternion and the attitude matrix can be expressed as:
the relationship between the triaxial accelerometer and the pitch angle and the roll angle is as follows:
[axayaz]T＝[g·sinθcosρ -g·sinρ -g·cosθcosρ]T
the relationship between the triaxial magnetometer and the yaw angle is as follows:
step four: carrying out data fusion on the denoised acceleration, angular velocity and magnetic strength data by using a gradient descent method, wherein an iterative formula is as follows:
the objective function is obtained as:
this objective function is taken as the main decision method.
5. The method for identifying danger signals for safety suits according to claim 3, characterized in that: the assistant decision method comprises the following steps:
the method comprises the following steps: collecting voice information of personnel by using a voice detection device (2);
step two: converting the sound analog signal into a sound digital signal through a conversion module (22);
step three: carrying out drying reduction on the sound digital signal by using a wavelet threshold drying method to obtain an effective sound signal;
step four: extracting short-time energy of sound signals
Short time average zero crossing rate
Mel cepstral coefficients MFCC and linear prediction cepstral coefficients LPCC;
step five: and carrying out data analysis on the sound characteristics by using a decision tree support vector machine to obtain a dangerous person sound signal identification result delta, wherein 0 is a non-dangerous signal, 1 is a dangerous signal, and the identification result delta is used as an auxiliary decision method.
6. The method for identifying danger signals for safety suits according to claim 3, characterized in that: the final decision method is to use a linear programming equation to fuse and judge the results of the main decision method and the auxiliary decision method; the linear regression equation is: y ═ w1f(q)+w2δ, where w1 and w2 are weights.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911110668.0A CN110706453A (en) | 2019-11-14 | 2019-11-14 | Safety clothing danger signal identification system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911110668.0A CN110706453A (en) | 2019-11-14 | 2019-11-14 | Safety clothing danger signal identification system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110706453A true CN110706453A (en) | 2020-01-17 |
Family
ID=69206037
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911110668.0A Pending CN110706453A (en) | 2019-11-14 | 2019-11-14 | Safety clothing danger signal identification system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110706453A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111192434A (en) * | 2020-01-19 | 2020-05-22 | 中国建筑第四工程局有限公司 | Safety protective clothing recognition system and method based on multi-mode perception |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104224182A (en) * | 2014-03-31 | 2014-12-24 | 桂林电子科技大学 | Method and device for monitoring human tumbling |
| CN104700564A (en) * | 2013-12-06 | 2015-06-10 | 深圳市豪恩安全科技有限公司 | Falling detection device and method |
| CN106403945A (en) * | 2016-10-20 | 2017-02-15 | 北京航空航天大学 | Low-cost object attitude monitoring system and method |
| KR101810783B1 (en) * | 2016-07-22 | 2018-01-25 | 전규상 | Sound and Motion Pattern Recognition Based Dangerous Situation Detection and Automatic SOS Request Wearable Device |
| CN109074716A (en) * | 2016-04-19 | 2018-12-21 | 帝人株式会社 | The article for having warning system |
| CN210515602U (en) * | 2019-11-14 | 2020-05-12 | 中国建筑第四工程局有限公司 | Safety clothing danger signal identification system |
-
2019
- 2019-11-14 CN CN201911110668.0A patent/CN110706453A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104700564A (en) * | 2013-12-06 | 2015-06-10 | 深圳市豪恩安全科技有限公司 | Falling detection device and method |
| CN104224182A (en) * | 2014-03-31 | 2014-12-24 | 桂林电子科技大学 | Method and device for monitoring human tumbling |
| CN109074716A (en) * | 2016-04-19 | 2018-12-21 | 帝人株式会社 | The article for having warning system |
| KR101810783B1 (en) * | 2016-07-22 | 2018-01-25 | 전규상 | Sound and Motion Pattern Recognition Based Dangerous Situation Detection and Automatic SOS Request Wearable Device |
| CN106403945A (en) * | 2016-10-20 | 2017-02-15 | 北京航空航天大学 | Low-cost object attitude monitoring system and method |
| CN210515602U (en) * | 2019-11-14 | 2020-05-12 | 中国建筑第四工程局有限公司 | Safety clothing danger signal identification system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111192434A (en) * | 2020-01-19 | 2020-05-22 | 中国建筑第四工程局有限公司 | Safety protective clothing recognition system and method based on multi-mode perception |
| CN111192434B (en) * | 2020-01-19 | 2024-02-09 | 中国建筑第四工程局有限公司 | Multi-mode perception based safety protection suit identification system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103976739B (en) | It is wearable to fall down dynamic realtime detection method and device | |
| Tong et al. | HMM-based human fall detection and prediction method using tri-axial accelerometer | |
| Wang et al. | Human activity recognition with user-free accelerometers in the sensor networks | |
| CN108509897A (en) | A kind of human posture recognition method and system | |
| WO2017125094A1 (en) | Body fall smart control system and method therefor | |
| CN107358248B (en) | Method for improving falling detection system precision | |
| Otanasap | Pre-impact fall detection based on wearable device using dynamic threshold model | |
| CN201691930U (en) | Human movement state monitoring device | |
| CN104297519B (en) | Human motion gesture recognition method and mobile terminal | |
| CN111178155B (en) | Gait feature extraction and gait recognition method based on inertial sensor | |
| CN210515602U (en) | Safety clothing danger signal identification system | |
| CN105989694A (en) | Human body falling-down detection method based on three-axis acceleration sensor | |
| CN106650300B (en) | Old man monitoring system and method based on extreme learning machine | |
| CN108958482B (en) | Similarity action recognition device and method based on convolutional neural network | |
| Hung et al. | Activity recognition with sensors on mobile devices | |
| CN110706453A (en) | Safety clothing danger signal identification system and method | |
| Shi et al. | Fall detection system based on inertial mems sensors: Analysis design and realization | |
| Su et al. | A multi-sensor based pre-impact fall detection system with a hierarchical classifier | |
| EP2313814B1 (en) | A method, device, and computer program product for event detection while preventing misclassification | |
| Ye et al. | Research of fall detection and alarm applications for the elderly | |
| Ketabdar et al. | Fall and emergency detection with mobile phones | |
| CN107643908A (en) | Voice application trigger control method, device and terminal | |
| CN113342166A (en) | Cervical vertebra movement identification method and system based on earphone for protecting privacy | |
| CN113400309A (en) | Motion state identification method of upper limb assistance exoskeleton robot | |
| Kau et al. | A smart phone-based pocket fall accident detection 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 |