CN119085735B - A sensor data analysis system for underwater explosion detection - Google Patents
A sensor data analysis system for underwater explosion detection Download PDFInfo
- Publication number
- CN119085735B CN119085735B CN202411570731.XA CN202411570731A CN119085735B CN 119085735 B CN119085735 B CN 119085735B CN 202411570731 A CN202411570731 A CN 202411570731A CN 119085735 B CN119085735 B CN 119085735B
- Authority
- CN
- China
- Prior art keywords
- sensor
- data
- real
- time
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D18/00—Testing or calibrating apparatus or arrangements provided for in groups G01D1/00 - G01D15/00
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D2218/00—Indexing scheme relating to details of testing or calibration
- G01D2218/10—Testing of sensors or measuring arrangements
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Algebra (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention relates to the technical field of sensor data analysis, in particular to a sensor data analysis system for underwater explosion detection, which comprises an information acquisition module, an underwater model construction module, a characteristic association analysis module, a real-time data analysis module and an abnormality confirmation module, wherein the data acquired by a sensor in a normal state and the data acquired by the sensor after the underwater explosion occur are respectively analyzed to determine a normal integral association value and a phenomenon integral association value of the sensor, the real-time phenomenon association value calculation and the real-time normal association value calculation are performed on the real-time acquired sensor data, the equipment trust value of the sensor is determined based on the real-time phenomenon association value and the real-time normal association value, the abnormal sensor is determined by the equipment trust value, and the accuracy of the sensor data acquisition for the underwater explosion detection is improved by data fusion and characteristic analysis in multi-source equipment.
Description
Technical Field
The invention relates to the technical field of sensor data analysis, in particular to a sensor data analysis system for underwater explosion detection.
Background
Underwater explosions are a common marine disaster that has serious impact on marine environments and human activities. Therefore, timely and accurate detection of underwater blast events is critical to preventing and mitigating their effects.
The prior art CN112557500A discloses a nondestructive testing system and method for an underwater elastic wave full wave field, wherein the system comprises an excitation component, a force sensor, a detection component and a data analysis module, wherein the excitation component is used for applying impact force to the surface of an underwater structure to be tested to excite the elastic wave field, the force sensor is used for measuring impact force information of the excitation component, the detection component is used for sensing elastic wave full wave field information of the surface of the structure to be tested in X, Y and Z directions and pressure wave field information of water on the surface of the structure to be tested, and the data analysis module is used for carrying out inversion analysis on the impact force information, the elastic wave full wave field information and the pressure wave field information to obtain a damage model corresponding to the structure to be tested.
When detecting underwater explosion, because the sensor is in an underwater environment, the sensor is usually operated and maintained in a fixed period time, but when the sensor is in an initial period of failure, the data offset degree is low, the system does not detect the abnormality of the sensor in time, at this time, the system can analyze the data acquired by the abnormal sensor as normal data, so that errors occur in the data analysis result, and the accuracy of the system analysis result is further reduced.
Disclosure of Invention
The invention aims to solve the problems in the background art, and provides a sensor data analysis system for underwater explosion detection.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
a sensor data analysis system for underwater explosion detection, comprising:
the information acquisition module is used for acquiring underwater information of the target detection area and transmitting the underwater information to the underwater model construction module, wherein the underwater information comprises sensor information and water area information;
the underwater model building module is used for building an underwater model, wherein the underwater model comprises a three-dimensional coordinate system and a position data packet, the sensor position in sensor information is obtained, the sensor position is marked in the three-dimensional coordinate system, the position coordinate of the sensor is determined, then the position data packet between adjacent sensors is determined based on the position coordinate, and the position data packet comprises a position distance and a position angle;
The characteristic association analysis module is used for calculating the data characteristics of the sensor, wherein the data characteristics comprise a normal state integral association value and a phenomenon integral association value, the normal state integral association value refers to an obtained target sensor and an adjacent combination thereof, the association value of two normal state data in the adjacent combination is calculated, then the association value of the adjacent combination of the target sensor is comprehensively processed, and the processing result is marked as a normal state integral association value;
The phenomenon integral association value comprises a forward integral association value and a reverse integral association value, a transmission direction is set between adjacent sensors, the transmission direction comprises forward transmission and reverse transmission, phenomenon data acquired by the sensors are divided into forward data and reverse data according to the energy transmission direction, a target sensor and an adjacent combination thereof are selected, the forward data and the reverse data in the adjacent combination are respectively acquired, the forward association value and the reverse association value are obtained through calculation, and then the forward association value and the reverse association value in the adjacent combination of the target sensor are respectively and comprehensively processed with a position data packet to obtain the forward integral association value and the reverse integral association value;
the real-time data analysis module is used for dividing the real-time acquisition data into real-time normal state data and real-time phenomenon data, determining the transmission direction of the sensor based on the real-time phenomenon data, calculating a real-time phenomenon association value, taking the real-time normal state data, calculating the real-time normal state association value, and comprehensively calculating the real-time phenomenon association value and the real-time normal state association value to obtain the equipment trust value of the sensor;
the abnormal confirmation module is used for determining the abnormal sensor according to the equipment trust value of the sensor, generating an abnormal signal, transmitting the abnormal signal to the terminal equipment of the staff, and confirming the fault of the abnormal sensor by the staff.
As a further aspect of the present invention, a method for calculating a location data packet includes:
s1, arbitrarily selecting one position as a reference position in a target detection area, setting a three-dimensional coordinate system by taking the reference position as an origin, and marking the position coordinates of the sensors as Gi (xi, yi, zi) based on the position where each sensor is placed, wherein i represents the numbers corresponding to different sensors;
S2, arbitrarily selecting two sensors a and b, acquiring position coordinates Ga and Gb of the two sensors, wherein a and b belong to i, obtaining a position distance Dab between the sensor a and the sensor b by using a distance formula, ;
S3, based on the formula againAndRespectively obtain the position and the angleAndAngle of positionAndBinding with the position distance Dab and integrating to obtain position data package Wab (Wa, wb) of sensor a and sensor b, wherein,,;
Wherein, The position of sensor b is described with reference to sensor a,The position of sensor a is described with reference to sensor b.
As a further scheme of the invention, the calculation method of the normal state integral association value comprises the following steps:
the method comprises the steps of SS1, acquiring sensor data of a target detection area in a normal state, marking the sensor data as normal data NU, randomly selecting one sensor as a target sensor based on an underwater model, respectively combining the target sensor with adjacent sensors, and marking the combination as inter-adjacent combination;
SS2, acquiring normal data in each inter-neighbor combination, calculating a correlation value of each inter-neighbor combination by using a Pearson correlation coefficient algorithm, and marking a calculation result as Rj, wherein j represents different inter-neighbor combinations;
SS3 acquiring the position distance Dj of two sensors in the inter-adjacent combination, and then based on a formula Obtaining a normal state overall association value Tr of the target sensor, wherein J represents the total number of the inter-neighbor combinations of the target sensor,To influence the coefficients.
As a further aspect of the present invention, a method for calculating a forward correlation value includes:
SS4, acquiring sensor data of a target detection area after underwater explosion occurs, marking the sensor data as phenomenon data, and setting a transmission direction between adjacent sensors, wherein the transmission direction comprises forward transmission and reverse transmission;
SS5, dividing the phenomenon data into forward data and reverse data according to the position and transmission direction of the underwater explosion, wherein the forward data refers to the phenomenon data collected during forward transmission, and the reverse data refers to the phenomenon data collected during reverse transmission;
And SS6, randomly selecting one sensor again as a target sensor, acquiring an inter-neighbor combination of the target sensor, extracting forward data in the inter-neighbor combination, calculating a correlation value between the forward data in the inter-neighbor combination by using a Pearson correlation coefficient algorithm, marking the correlation value as a forward correlation value ZRm, wherein M represents numbers of different inter-neighbor combinations in the target sensor, and M E [1, M ] represents the total number of the inter-neighbor combinations of the target sensor.
As a further aspect of the present invention, a method for calculating a forward overall correlation value includes:
SS7, acquiring position data packets corresponding to two sensors in the inter-neighbor combination, and acquiring corresponding position angles based on the transmission direction;
SS8 utilizing the formula A forward overall correlation value Zr for each target sensor is obtained, wherein,,Dm is the position distance between two sensors in the inter-neighbor combination m,Indicating the corresponding position angle of the inter-neighbor combination in forward transmission,Representing the lateral influence coefficient in the forward transmission,Representing the longitudinal influence coefficient at the time of forward transmission,Indicating the overall correction factor at the time of forward transmission.
As a further aspect of the present invention, a method for calculating a reverse global correlation value includes:
According to the processing method in the steps SS6 to SS8, the reverse data in the inter-neighbor combinations of the target sensor are obtained, the correlation value of the reverse data in each inter-neighbor combination is calculated, the calculation result is marked as a reverse correlation value NRm, and the corresponding position angle is obtained based on the transmission direction Combining the inverse correlation value with the position angle, and utilizing the formulaA reverse global correlation value Nr of the target sensor is determined,Representing the lateral influence coefficient in the reverse transmission,Representing the longitudinal influence coefficient at the time of reverse transmission,Indicating the overall correction factor at the time of reverse transmission.
As a further scheme of the invention, the method for calculating the trust value of the equipment comprises the following steps:
ST1, comparing the real-time acquisition data with threshold data, dividing the real-time acquisition data into real-time normal data and real-time phenomenon data according to a comparison result, storing the data if the real-time acquisition data is the real-time normal data, and determining the explosion position of underwater explosion if the real-time acquisition data is the real-time phenomenon data;
ST2, determining the transmission direction of energy among the sensors according to the underwater explosion occurrence position, and then determining a phenomenon integral association value Xr of each sensor according to the transmission direction, wherein the phenomenon integral association value Xr comprises a forward integral association value Zr and a reverse integral association value Nr;
ST3, randomly selecting one sensor as a target sensor, acquiring an inter-adjacent combination of the target sensor, and then marking the real-time phenomenon data as a real-time phenomenon correlation value GX of the target sensor according to a calculation method of a phenomenon integral correlation value based on real-time phenomenon data in each sensor;
ST4, taking the time for determining the real-time phenomenon data as node time, acquiring real-time normal state data acquired by the target sensor and the sensors in the adjacent combination before the node time, and marking the calculation result as a real-time normal state association value GS of the target sensor according to a calculation method of a normal state integral association value;
ST5 after which the formula is used Obtaining the equipment trust value RE of the target sensor, c 1E (0, 1) and c 2E (0, 1).
As a further aspect of the present invention, a method of determining an abnormality sensor includes:
Comparing the equipment trust value with a standard trust threshold, if the equipment trust value is smaller than the standard trust threshold, marking the corresponding sensor as an abnormal sensor, otherwise, marking the corresponding sensor as a normal sensor if the equipment trust value is larger than or equal to the standard trust threshold;
when the abnormal sensor is detected, an abnormal signal is generated, the position of the abnormal sensor is obtained at the same time, the abnormal signal and the position of the abnormal sensor are transmitted to the terminal equipment of the staff at the same time, and the staff confirms the fault of the abnormal sensor.
Compared with the prior art, the invention has the advantages that:
According to the invention, the data collected by the sensor in the normal state and the data collected by the sensor after the underwater explosion are respectively analyzed, meanwhile, according to the data association between adjacent sensors, the integral association value of the sensor in the normal state and the integral association value of the data between adjacent sensors after the underwater explosion are respectively calculated, the normal integral association value and the phenomenon integral association value are determined, then the real-time phenomenon association value calculation and the real-time normal association value calculation are carried out on the data of the sensor collected in real time, the equipment trust value of the sensor is determined based on the real-time phenomenon association value and the real-time normal association value, the abnormal sensor is determined by the equipment trust value, and the accuracy of the sensor data collection for the underwater explosion detection is improved through the data fusion and the feature analysis in the multi-source equipment, and meanwhile, the equipment fault diagnosis response efficiency is further improved.
Drawings
Fig. 1 is a schematic diagram of a system structure according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments.
Referring to fig. 1, a sensor data analysis system for underwater explosion detection includes an information acquisition module, an underwater model construction module, a feature correlation analysis module, a real-time data analysis module, and an anomaly confirmation module;
The information acquisition module is used for acquiring underwater information of a target detection area, wherein the underwater information comprises sensor information and water area information, the sensor information comprises the number, the positions, the types and the corresponding equipment precision of sensors placed in the target detection area, the water area information comprises the information such as the depth of the target detection area, the pressure and the flow rate of each position and the like, the target detection water area refers to an area for detecting underwater explosion by using the sensors, and the information acquisition module is in unidirectional communication connection with the underwater model building module;
The underwater model construction module is used for acquiring sensor information, determining the relative positions among the sensors based on the sensor placement positions in the sensor information, and constructing an underwater model of a target detection area according to the relative position relation among all the sensors, wherein the specific underwater model construction method comprises the following steps:
s1, arbitrarily selecting one position as a reference position in a target detection area, setting a three-dimensional coordinate system by taking the reference position as an origin, and marking the position coordinates of the sensors as Gi (xi, yi, zi) based on the position where each sensor is placed, wherein i represents the numbers corresponding to different sensors;
S2, arbitrarily selecting two sensors a and b, acquiring position coordinates Ga and Gb of the two sensors, wherein a and b belong to i, and then obtaining a position distance Dab between the sensor a and the sensor b by using a distance formula, specifically, ;
S3, based on the formula againAndRespectively obtain the position and the angleAndThen the position and angle areAndBinding with the position distance Dab and integrating to obtain position data package Wab (Wa, wb) of sensor a and sensor b, wherein,,;
It should be further noted that,The position of sensor b is described with reference to sensor a,Representing the position of sensor a with sensor b as a reference point;
S4, processing the position data packets between all adjacent sensors according to the processing methods in the steps S2 and S3, merging the three-dimensional coordinate system and the position data packets, and marking as an underwater model;
the underwater model building module is in bidirectional communication connection with the characteristic association analysis module;
the characteristic association analysis module is used for determining the data characteristics of the sensor on the basis of the underwater model, wherein the data characteristics comprise a normal state integral association value and a phenomenon integral association value, and the method for determining the data characteristics of the sensor comprises the following steps:
For a normal global association value:
SS1, acquiring sensor data of a target detection area in a normal state, marking the sensor data as normal data NU, arbitrarily selecting one sensor as a target sensor based on an underwater model, respectively combining the target sensor with adjacent sensors, and marking the target sensor as an adjacent combination, for example, selecting a sensor 1 as the target sensor, wherein the adjacent sensors on the upper side, the lower side, the left side and the right side of the sensor 1 are respectively 11, 12, 13 and 14, and 4 groups of adjacent combinations of the sensor 1 exist at the moment, namely (1, 11), (1, 12), (1, 13) and (1, 14);
SS2, acquiring normal data in each inter-neighbor combination, calculating a correlation value of each inter-neighbor combination by using a pearson correlation coefficient algorithm, and marking a calculation result as Rj, wherein j represents different inter-neighbor combinations, the pearson correlation coefficient algorithm is the prior art, and redundant description is omitted here;
SS3 acquiring the position distance Dj of two sensors in the inter-adjacent combination, and then based on a formula Obtaining a normal state overall association value Tr of the target sensor, wherein J represents the total number of the inter-neighbor combinations of the target sensor,In order to influence the coefficient of the coefficient,The specific value is obtained by big data operation by a person skilled in the art;
Then sequentially taking all the sensors as target sensors, and processing according to the steps SS1 to SS3 to obtain a normal integral association value of each sensor;
Global correlation value for a phenomenon:
The phenomenon overall association value comprises a forward overall association value and a reverse overall association value, and the specific calculation method comprises the following steps:
SS4, acquiring sensor data of the target detection area after underwater explosion occurs, marking the sensor data as phenomenon data, setting transmission directions between adjacent sensors, wherein the transmission directions comprise forward transmission and reverse transmission, for example, for sensor a and sensor b, marking the direction of energy transmission from the sensor a position to the sensor b position as forward transmission, otherwise, reverse transmission, and when the underwater explosion occurs, if the energy is transmitted from the sensor a position to the sensor b position, the transmission direction is forward transmission, and if the energy is transmitted from the sensor b position to the sensor a position, the transmission direction is reverse transmission;
SS5, dividing the phenomenon data into forward data and reverse data according to the position and transmission direction of the underwater explosion;
Further, the forward data refers to phenomenon data collected during forward transmission, and the reverse data refers to phenomenon data collected during reverse transmission;
SS6, randomly selecting a sensor again as a target sensor, acquiring an inter-neighbor combination of the target sensor, extracting forward data in the inter-neighbor combination, calculating a correlation value between the forward data in the inter-neighbor combination by using a Pearson correlation coefficient algorithm, marking the correlation value as a forward correlation value ZRm, wherein M represents numbers of different inter-neighbor combinations in the target sensor, and M is [1, M ] and M represents the total number of the inter-neighbor combinations of the target sensor;
SS7, acquiring position data packets corresponding to two sensors in the inter-neighbor combination, and acquiring corresponding position angles based on the transmission direction;
In addition, regarding the correspondence between the transmission direction and the position angle, for example, for the sensor a and the sensor b in the inter-adjacent combination, if the energy is transmitted from the sensor a position to the sensor b position as the forward direction and the energy is transmitted from the sensor b position to the sensor a position as the reverse direction, the position angle is selected when the energy is transmitted in the forward direction Conversely, if the reverse transmission is performed, the position and angle are selected;
SS8 after which the formula is usedA forward overall correlation value Zr for each target sensor is obtained, wherein,,Dm is the position distance between two sensors in the inter-neighbor combination m,Indicating the corresponding position angle of the inter-neighbor combination in forward transmission,Representing the lateral influence coefficient in the forward transmission,Representing the longitudinal influence coefficient at the time of forward transmission,Representing the overall correction factor at the time of forward transmission,、AndThe specific values of (2) are obtained by those skilled in the art after big data operation;
Then according to the processing method in the steps SS6 to SS8, the reverse data in the inter-neighbor combinations of the target sensor are obtained, the correlation value of the reverse data in each inter-neighbor combination is calculated, the calculation result is marked as a reverse correlation value NRm, and the corresponding position angle is obtained based on the transmission direction Combining the inverse correlation value with the position angle, and utilizing the formulaA reverse global correlation value Nr of the target sensor is determined,Representing the lateral influence coefficient in the reverse transmission,Representing the longitudinal influence coefficient at the time of reverse transmission,Representing the overall correction factor at the time of reverse transmission,、AndThe specific values of (2) are obtained by those skilled in the art after big data operation;
Sequentially taking all the sensors as target sensors according to the processing methods in the steps SS6 to SS8 to obtain a forward overall correlation value Zr and a reverse overall correlation value Nr of each sensor;
then the characteristic association analysis module is in unidirectional communication connection with the real-time data analysis module;
The real-time data analysis module is used for analyzing data acquired by the sensors in the target detection area in real time and determining the data trust value of each sensor, and the specific device trust value determining method comprises the following steps:
ST1, comparing the real-time acquisition data with threshold data, dividing the real-time acquisition data into real-time normal data and real-time phenomenon data according to a comparison result, storing the data if the real-time acquisition data is the real-time normal data, and determining the explosion position of underwater explosion if the real-time acquisition data is the real-time phenomenon data;
The threshold value data are set by a person skilled in the art through big data experience, and it is further explained that the real-time normal state data refer to sensor data collected in real time in a normal state of a target detection area, and the real-time phenomenon data refer to sensor data collected in real time after underwater explosion occurs in the target detection area;
ST2, determining the transmission direction of energy among the sensors according to the underwater explosion occurrence position, and then determining the phenomenon integral association value Xr of each sensor according to the transmission direction, for example, if the energy is transmitted in the forward direction between two adjacent sensors, the phenomenon integral association values of the two sensors are both selected to be the forward integral association values at the moment, otherwise, if the energy is transmitted in the reverse direction between the two adjacent sensors, the phenomenon integral association values of the two sensors are both selected to be the reverse integral association values at the moment;
ST3, randomly selecting one sensor as a target sensor, acquiring an inter-adjacent combination of the target sensor, and then marking the real-time phenomenon data as a real-time phenomenon correlation value GX of the target sensor according to a calculation method of a phenomenon integral correlation value based on real-time phenomenon data in each sensor;
ST4, taking the time for determining the real-time phenomenon data as node time, acquiring real-time normal state data acquired by the target sensor and the sensors in the adjacent combination before the node time, and marking the calculation result as a real-time normal state association value GS of the target sensor according to a calculation method of a normal state integral association value;
ST5 after which the formula is used Obtaining equipment trust values RE, c 1E (0, 1), c 2E (0, 1) of the target sensor, and obtaining specific values of c1 and c2 by big data operation of a person skilled in the art;
It should be further noted that, when the device trust value is larger, the accuracy rate of the data collected by the target sensor is indicated to be effective data is higher, otherwise, when the device trust value is smaller, the accuracy rate of the data collected by the target sensor is indicated to be effective data is lower, and the probability of abnormal faults of the target sensor is greater;
the real-time data analysis module transmits the equipment trust value of the sensor to the abnormality confirmation module;
The abnormal confirmation module is used for receiving the equipment trust value of the sensor, comparing the equipment trust value with a standard trust threshold, marking the corresponding sensor as an abnormal sensor if the equipment trust value is smaller than the standard trust threshold, otherwise, marking the corresponding sensor as a normal sensor if the equipment trust value is larger than or equal to the standard trust threshold, wherein the standard trust threshold is obtained by a person skilled in the art after big data operation;
when the abnormal sensor is detected, an abnormal signal is generated, the position of the abnormal sensor is obtained at the same time, the abnormal signal and the position of the abnormal sensor are transmitted to the terminal equipment of the staff at the same time, and the staff confirms the fault of the abnormal sensor.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should make equivalent substitutions or modifications according to the technical scheme of the present invention and the inventive concept thereof, and should be covered by the scope of the present invention.
Claims (2)
1. A sensor data analysis system for underwater explosion detection, comprising:
the information acquisition module is used for acquiring underwater information of the target detection area and transmitting the underwater information to the underwater model construction module, wherein the underwater information comprises sensor information and water area information;
The underwater model construction module is used for constructing an underwater model, wherein the underwater model comprises a three-dimensional coordinate system and a position data packet, the sensor position in sensor information is acquired, the sensor position is marked in the three-dimensional coordinate system, the position coordinates of the sensors are determined, then the position data packet between adjacent sensors is determined based on the position coordinates, the position data packet comprises a position distance and a position angle, and the specific position data packet calculation method comprises the following steps:
s1, arbitrarily selecting one position as a reference position in a target detection area, setting a three-dimensional coordinate system by taking the reference position as an origin, and marking the position coordinates of the sensors as Gi (xi, yi, zi) based on the position where each sensor is placed, wherein i represents the numbers corresponding to different sensors;
S2, arbitrarily selecting two sensors a and b, acquiring position coordinates Ga and Gb of the two sensors, wherein a and b belong to i, obtaining a position distance Dab between the sensor a and the sensor b by using a distance formula, ;
S3, based on the formula againAndRespectively obtain the position and the angleAndAngle of positionAndBinding with the position distance Dab respectively, integrating, obtaining a position data packet Wab (Wa, wb) of the sensor a and the sensor b, wherein wa= = -a =,Dab),Wb=(,Dab);
Wherein, The position of sensor b is described with reference to sensor a,Representing the position of sensor a with sensor b as a reference point;
The characteristic association analysis module is used for calculating the data characteristic of the sensor, wherein the data characteristic comprises a normal state integral association value and a phenomenon integral association value, the normal state integral association value is obtained from the target sensor and the adjacent combination thereof, the association value of two normal state data in the adjacent combination is calculated, then the association value of the adjacent combination of the target sensor is comprehensively processed, and the processing result is marked as the normal state integral association value, and the calculation method of the normal state integral association value comprises the following steps:
the method comprises the steps of SS1, acquiring sensor data of a target detection area in a normal state, marking the sensor data as normal data NU, randomly selecting one sensor as a target sensor based on an underwater model, respectively combining the target sensor with adjacent sensors, and marking the combination as inter-adjacent combination;
SS2, acquiring normal data in each inter-neighbor combination, calculating a correlation value of each inter-neighbor combination by using a Pearson correlation coefficient algorithm, and marking a calculation result as Rj, wherein j represents different inter-neighbor combinations;
SS3 acquiring the position distance Dj of two sensors in the inter-adjacent combination, and then based on a formula Obtaining a normal state overall association value Tr of the target sensor, wherein J represents the total number of the inter-neighbor combinations of the target sensor,Is an influence coefficient;
The phenomenon integral association value comprises a forward integral association value and a reverse integral association value, a transmission direction is set between adjacent sensors, the transmission direction comprises forward transmission and reverse transmission, phenomenon data acquired by the sensors are divided into forward data and reverse data according to the energy transmission direction, a target sensor and an adjacent combination thereof are selected, the forward data and the reverse data in the adjacent combination are respectively acquired, the forward association value and the reverse association value are obtained through calculation, and then the forward association value and the reverse association value in the adjacent combination of the target sensor are respectively and comprehensively processed with a position data packet to obtain the forward integral association value and the reverse integral association value;
the method for calculating the forward integral association value and the reverse integral association value comprises the following steps:
SS4, acquiring sensor data of a target detection area after underwater explosion occurs, marking the sensor data as phenomenon data, and setting a transmission direction between adjacent sensors, wherein the transmission direction comprises forward transmission and reverse transmission;
SS5, dividing the phenomenon data into forward data and reverse data according to the position and transmission direction of the underwater explosion, wherein the forward data refers to the phenomenon data collected during forward transmission, and the reverse data refers to the phenomenon data collected during reverse transmission;
SS6, randomly selecting a sensor again as a target sensor, acquiring an inter-neighbor combination of the target sensor, extracting forward data in the inter-neighbor combination, calculating a correlation value between the forward data in the inter-neighbor combination by using a Pearson correlation coefficient algorithm, marking the correlation value as a forward correlation value ZRm, wherein M represents numbers of different inter-neighbor combinations in the target sensor, and M is [1, M ] and M represents the total number of the inter-neighbor combinations of the target sensor;
SS7, acquiring position data packets corresponding to two sensors in the inter-neighbor combination, and acquiring corresponding position angles based on the transmission direction;
SS8 utilizing the formula A forward overall correlation value Zr for each target sensor is obtained, wherein,,Dm is the position distance between two sensors in the inter-neighbor combination m,Indicating the corresponding position angle of the inter-neighbor combination in forward transmission,Representing the lateral influence coefficient in the forward transmission,Representing the longitudinal influence coefficient at the time of forward transmission,Representing the overall correction coefficient at the time of forward transmission;
According to the processing method in the steps SS6 to SS8, the reverse data in the inter-neighbor combinations of the target sensor are obtained, the correlation value of the reverse data in each inter-neighbor combination is calculated, the calculation result is marked as a reverse correlation value NRm, and the corresponding position angle is obtained based on the transmission direction Combining the inverse correlation value with the position angle, and utilizing the formulaA reverse global correlation value Nr of the target sensor is determined,Representing the lateral influence coefficient in the reverse transmission,Representing the longitudinal influence coefficient at the time of reverse transmission,Representing the overall correction coefficient during reverse transmission;
the real-time data analysis module is used for dividing real-time acquisition data into real-time normal state data and real-time phenomenon data, determining the transmission direction of the sensor based on the real-time phenomenon data, calculating a real-time phenomenon association value, taking the real-time normal state data, calculating the real-time normal state association value, and comprehensively calculating the real-time phenomenon association value and the real-time normal state association value to obtain the equipment trust value of the sensor, wherein the equipment trust value calculating method specifically comprises the following steps:
ST1, comparing the real-time acquisition data with threshold data, dividing the real-time acquisition data into real-time normal data and real-time phenomenon data according to a comparison result, storing the data if the real-time acquisition data is the real-time normal data, and determining the explosion position of underwater explosion if the real-time acquisition data is the real-time phenomenon data;
ST2, determining the transmission direction of energy among the sensors according to the underwater explosion occurrence position, and then determining a phenomenon integral association value Xr of each sensor according to the transmission direction, wherein the phenomenon integral association value Xr comprises a forward integral association value Zr and a reverse integral association value Nr;
ST3, randomly selecting one sensor as a target sensor, acquiring an inter-adjacent combination of the target sensor, and then marking the real-time phenomenon data as a real-time phenomenon correlation value GX of the target sensor according to a calculation method of a phenomenon integral correlation value based on real-time phenomenon data in each sensor;
ST4, taking the time for determining the real-time phenomenon data as node time, acquiring real-time normal state data acquired by the target sensor and the sensors in the adjacent combination before the node time, and marking the calculation result as a real-time normal state association value GS of the target sensor according to a calculation method of a normal state integral association value;
ST5 after which the formula is used Obtaining a device trust value RE of a target sensor, c 1E (0, 1) and c 2E (0, 1);
the abnormal confirmation module is used for determining the abnormal sensor according to the equipment trust value of the sensor, generating an abnormal signal, transmitting the abnormal signal to the terminal equipment of the staff, and confirming the fault of the abnormal sensor by the staff.
2. A sensor data analysis system for underwater explosion detection as claimed in claim 1, wherein the method of determining the anomaly sensor comprises:
Comparing the equipment trust value with a standard trust threshold, if the equipment trust value is smaller than the standard trust threshold, marking the corresponding sensor as an abnormal sensor, otherwise, marking the corresponding sensor as a normal sensor if the equipment trust value is larger than or equal to the standard trust threshold;
when the abnormal sensor is detected, an abnormal signal is generated, the position of the abnormal sensor is obtained at the same time, the abnormal signal and the position of the abnormal sensor are transmitted to the terminal equipment of the staff at the same time, and the staff confirms the fault of the abnormal sensor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411570731.XA CN119085735B (en) | 2024-11-06 | 2024-11-06 | A sensor data analysis system for underwater explosion detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411570731.XA CN119085735B (en) | 2024-11-06 | 2024-11-06 | A sensor data analysis system for underwater explosion detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119085735A CN119085735A (en) | 2024-12-06 |
| CN119085735B true CN119085735B (en) | 2025-02-21 |
Family
ID=93667680
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411570731.XA Active CN119085735B (en) | 2024-11-06 | 2024-11-06 | A sensor data analysis system for underwater explosion detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119085735B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013144126A2 (en) * | 2012-03-28 | 2013-10-03 | Dassault Aviation | Method for determining a state of credibility of measurements made by sensors of an aircraft and corresponding system |
| WO2020245968A1 (en) * | 2019-06-06 | 2020-12-10 | 三菱電機株式会社 | Abnormality sign detection device, abnormality sign detection method, and abnormality sign detection program |
Family Cites Families (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE3323519A1 (en) * | 1983-06-30 | 1985-01-10 | Diehl GmbH & Co, 8500 Nürnberg | METHOD FOR OBTAINING A IGNITION SIGNAL AND SENSOR IGNITION ARRANGEMENT WITH SEVERAL DETECTORS |
| DE602008001963D1 (en) * | 2008-02-28 | 2010-09-09 | Sap Ag | Credibility assessment of sensor data from wireless sensor networks for business applications |
| CN101556651B (en) * | 2009-04-15 | 2011-02-16 | 北京航空航天大学 | Multi-source data fusion method in clustering wireless sensor network |
| CN102970698A (en) * | 2012-11-02 | 2013-03-13 | 北京邮电大学 | Fault detection method of wireless sensor network |
| US10037689B2 (en) * | 2015-03-24 | 2018-07-31 | Donald Warren Taylor | Apparatus and system to manage monitored vehicular flow rate |
| CN104537220A (en) * | 2014-12-18 | 2015-04-22 | 华北电力大学（保定） | Fault diagnosis method based on principal component analysis and D-S evidence theory |
| CN108763681B (en) * | 2018-05-16 | 2022-01-28 | 华北水利水电大学 | Hydrogen engine fault diagnosis system and method based on FOA-GRNN fusion algorithm |
| CN110458366A (en) * | 2019-08-16 | 2019-11-15 | 郑州中粮科研设计院有限公司 | Grain storage and transportation process dust explosion Risk Pre-control system and assessment method for early warning |
| CN113532499B (en) * | 2021-07-15 | 2022-08-30 | 中国科学院深圳先进技术研究院 | Sensor security detection method and device for unmanned system and storage medium |
| CN114021405B (en) * | 2021-11-04 | 2022-09-30 | 大连理工大学 | Fabricated plate girder bridge hinge joint damage detection method based on transverse deflection influence line |
| KR102459503B1 (en) * | 2022-06-09 | 2022-10-27 | 베스트 주식회사 | Monitoring area abnormality monitoring system using dual sensor and method thereof |
| CN117634555A (en) * | 2023-10-19 | 2024-03-01 | 哈尔滨工业大学 | Numerical sensor reliability self-assessment method and system based on motion constraint Transformer |
| CN117725513B (en) * | 2024-02-07 | 2024-05-14 | 青岛哈尔滨工程大学创新发展中心 | AUV propeller real-time reliability evaluation system and method |
| CN118274906A (en) * | 2024-04-17 | 2024-07-02 | 深圳先闻科技有限公司 | Processing method and device for multi-sensor environment data and computer equipment |
| CN118687632B (en) * | 2024-08-28 | 2024-10-25 | 山东理工职业学院 | A coal mine electromechanical equipment operating status monitoring system based on data analysis |
| CN118885744B (en) * | 2024-09-24 | 2024-12-31 | 山东海纳智能装备科技股份有限公司 | Online monitoring method and system for deformation of mine filling body |
-
2024
- 2024-11-06 CN CN202411570731.XA patent/CN119085735B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013144126A2 (en) * | 2012-03-28 | 2013-10-03 | Dassault Aviation | Method for determining a state of credibility of measurements made by sensors of an aircraft and corresponding system |
| WO2020245968A1 (en) * | 2019-06-06 | 2020-12-10 | 三菱電機株式会社 | Abnormality sign detection device, abnormality sign detection method, and abnormality sign detection program |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119085735A (en) | 2024-12-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9310345B2 (en) | Sensor system, computer, and machine | |
| US10884404B2 (en) | Method of predicting plant data and apparatus using the same | |
| CN103776654A (en) | Method for diagnosing faults of multi-sensor information fusion | |
| CN103776480A (en) | Small-fault detection method and device based on multiple moving average | |
| CN105277968B (en) | A kind of automatic excitation control method and device in earthquake stimulation source | |
| CN110398775B (en) | Method and system for picking up the first arrival of signal fluctuation of microseismic event in tunnel water inrush disaster | |
| Moeinifard et al. | Lost vibration test data recovery using convolutional neural network: a case study | |
| CN104316167B (en) | Anomaly Detection Method of Structural Response under Low Signal-to-Noise Ratio | |
| KR101724152B1 (en) | Extraction method of dispersion curves for impact source localization estimating of loose parts | |
| CN111027721A (en) | A system fault location method | |
| CN119085735B (en) | A sensor data analysis system for underwater explosion detection | |
| CN115100819B (en) | Landslide hazard early warning method and device based on big data analysis and electronic equipment | |
| CN118689116B (en) | An intelligent control method for a multifunctional hydraulic chuck clamping system | |
| CN113613278A (en) | Gate monitoring method and system based on Beidou, computer equipment and storage medium | |
| CN109458924A (en) | Resistance value alertness grid deformation test system and method based on ten axle sensors | |
| CN102323049A (en) | Structural abnormality detection method based on consistent data replacement under incomplete data | |
| CN118997996A (en) | Wind turbine blade health monitoring method based on Lamb wave and active-passive fusion | |
| CN112150851B (en) | Testing method and device for geomagnetic detector | |
| CN109861859B (en) | Multi-Agent system fault detection method based on side inspection comprehensive judgment | |
| CN114584395B (en) | Big data safety protection system and method based on network safety | |
| CN112859002B (en) | Acoustic emission source positioning method and system | |
| CN104462770B (en) | Signal reconstruction method taking sensor performance degradation into consideration | |
| CN115390099B (en) | Maximum Joint Chi-Square Troubleshooting Method Based on Odd-Even Vector Projection | |
| CN118868418B (en) | Integrated line intelligent monitoring system and method | |
| CN118395382B (en) | Power transformer fault detection method and system based on data analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |