CN116679331A - Pole tower offset monitoring method and system based on polling Beidou RTK positioning and LSTM auxiliary calculation - Google Patents
Pole tower offset monitoring method and system based on polling Beidou RTK positioning and LSTM auxiliary calculation Download PDFInfo
- Publication number
- CN116679331A CN116679331A CN202310461912.8A CN202310461912A CN116679331A CN 116679331 A CN116679331 A CN 116679331A CN 202310461912 A CN202310461912 A CN 202310461912A CN 116679331 A CN116679331 A CN 116679331A
- Authority
- CN
- China
- Prior art keywords
- polling
- beidou
- module
- lstm
- neural network
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 37
- 238000004364 calculation method Methods 0.000 title claims abstract description 34
- 238000000034 method Methods 0.000 title claims abstract description 15
- 238000003062 neural network model Methods 0.000 claims abstract description 43
- 230000007613 environmental effect Effects 0.000 claims abstract description 25
- 238000004891 communication Methods 0.000 claims abstract description 24
- 238000001914 filtration Methods 0.000 claims abstract description 24
- 238000012549 training Methods 0.000 claims abstract description 17
- 230000000977 initiatory effect Effects 0.000 claims abstract description 10
- 238000004806 packaging method and process Methods 0.000 claims abstract description 6
- 238000005259 measurement Methods 0.000 claims description 17
- 239000011159 matrix material Substances 0.000 claims description 16
- 238000012790 confirmation Methods 0.000 claims description 11
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 7
- 208000028257 Joubert syndrome with oculorenal defect Diseases 0.000 claims description 6
- 239000005433 ionosphere Substances 0.000 claims description 5
- 230000004044 response Effects 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 3
- DMBHHRLKUKUOEG-UHFFFAOYSA-N diphenylamine Chemical compound C=1C=CC=CC=1NC1=CC=CC=C1 DMBHHRLKUKUOEG-UHFFFAOYSA-N 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 2
- 230000007547 defect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- LIWAQLJGPBVORC-UHFFFAOYSA-N ethylmethylamine Chemical compound CCNC LIWAQLJGPBVORC-UHFFFAOYSA-N 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- 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
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/01—Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/13—Receivers
- G01S19/14—Receivers specially adapted for specific applications
-
- 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
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
- G01S19/43—Determining position using carrier phase measurements, e.g. kinematic positioning; using long or short baseline interferometry
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention discloses a tower offset monitoring method and system based on polling Beidou RTK positioning and LSTM auxiliary calculation, wherein the method comprises the following steps: receiving Beidou satellite message, and converting the Beidou satellite message into an original observation data format through de-mediation and expansion; packaging the identity information and the environmental sensor information of the current Beidou terminal with the streaming original observation data by a communication protocol and transmitting the data; sequentially initiating a polling request to each Beidou terminal; carrying out single-point positioning calculation on the received data, and obtaining a floating point solution of RTK positioning based on Kalman filtering; constructing and training an LSTM neural network model; inputting the feature data to be detected into the trained LSTM neural network model to obtain coordinate information of the corresponding Beidou terminal, and calculating the tower deflection condition through the anti-sporadic threshold judgment to realize the monitoring of the tower deflection. The invention reduces the overall power consumption of the tower offset monitoring, reduces the resolving error and improves the accuracy and efficiency of the tower offset monitoring.
Description
Technical Field
The invention relates to the technical field of tower detection, in particular to a tower offset monitoring method and system based on polling Beidou RTK positioning and LSTM auxiliary calculation.
Background
The transmission towers play an important role in the task of transmitting power, most towers are distributed in areas frequently suffered from geological disasters, such as wild mountain tops and landslide, so that the capsizing inspection of the transmission towers is an important item, the offset of the transmission towers in a certain time is an important index, the common monitoring modes such as unmanned aerial vehicle monitoring, manual inspection and the like have the problems of high consumption of manpower and material resources, high cost and the like, and some enterprises monitor by adopting RTK positioning, but the integrated RTK terminals are high in cost and power consumption, and the low-cost RTK terminals have the problems of low fixing rate, instability and the like. The traditional low-cost RTK receiver adopts a Kalman filtering algorithm to obtain a floating solution, and then is fast fixed through an LAMBDA algorithm, and then the method has some defects, such as unstable precision when the terminal is powered on again, fast reduction of the success rate of fixation after the terminal moves, and the like.
Disclosure of Invention
In order to overcome the defects and shortcomings in the prior art, the invention provides a tower offset monitoring method and system based on polling Beidou RTK positioning and LSTM auxiliary resolving, and a neural network model is used for enabling resolving logic to be suitable for a tower use scene, so that resolving errors are reduced, and low-cost and high-efficiency monitoring of tower offset is realized.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
a tower offset monitoring method based on polling Beidou RTK positioning and LSTM auxiliary calculation comprises the following steps:
receiving Beidou satellite message, and converting the Beidou satellite message into an original observation data format through de-mediation and expansion;
after receiving the polling confirmation request, carrying out communication protocol packaging on the identity information of the current Beidou terminal, the environmental sensor information and the original observation data which flow in, and carrying out data transmission;
sequentially initiating a polling request to each Beidou terminal, initiating a polling confirmation request to the corresponding terminal again after receiving a polling response of the Beidou terminal, and opening a data receiving channel;
carrying out single-point positioning calculation on the received data to obtain a single-point solution after calculation, and obtaining a floating point solution of RTK positioning based on Kalman filtering;
constructing an LSTM neural network model, taking output signal characteristics of an environmental sensor and floating point characteristics obtained based on extended Kalman filtering as inputs of the LSTM neural network model, taking the Beidou terminal coordinates as expected outputs of the LSTM neural network model, and training the constructed LSTM neural network model;
inputting the feature data to be detected into the trained LSTM neural network model to obtain coordinate information of the corresponding Beidou terminal, judging through the anti-sporadic threshold value, further calculating the tower deflection condition, and monitoring the tower deflection.
As a preferable technical scheme, a polling request is initiated to each Beidou terminal in turn, and the following polling protocol is adopted:
when each Beidou terminal respectively accesses the network, a polling list is formed successively according to the time of address allocation, and the Beidou terminal which is allocated with the address at last is positioned at the head of the polling list, and the Beidou terminal which is allocated with the address at first is positioned at the tail of the polling list;
if the polling list does not detect the existence of the mark, the polling is ended, and the next polling is re-entered;
the polling list is expressed as:
pol＝{y 1 : 1 ,y 2 : 2 ,…,y n : n }
wherein n represents the number of the Beidou polling terminals and y n Beidou terminal address representing polling, l n Representing the mark corresponding to the Beidou terminal address.
As a preferred technical solution, performing single-point positioning calculation on received data to obtain a single-point solution after calculation, which specifically includes:
and carrying out single-point positioning through a pseudo-range error equation constructed by the reference satellite and each observation satellite, wherein the formula is as follows:
wherein ,as pseudorange residuals δx k 、δy k 、δz k Offset of single point positioning result relative to last epoch, < >>Respectively obtaining the first three coefficients obtained by Taylor series expansion of the geometric distance of the star and the ground at the approximate coordinates of the measuring station, wherein c is the light speed and δt k To monitor the node receiving module clock difference, δt p For satellite clock error>Single point location estimate representing last epoch, < >>Is electricError of separation layer>Is a tropospheric error, if the receiver module is a single frequency module, then +.>Is built by a global Broadcast ionosphere model Broadcast model, if the receiving module is a dual-frequency module, the receiving module is +.>Obtained by ionosphere-Free linear combination Iono Free LC algorithm.
As a preferable technical solution, the kalman filter adopts extended kalman filter, which is specifically expressed as follows:
wherein , and Pk Is the current epoch t k To-be-estimated state vector of (c) and its variance-covariance matrix, (-) and (+) represent the before and after extended kalman filter measurement update, H (x) and R k Conversion vector of measurement model, corresponding partial derivative matrix and variance-covariance matrix of corresponding error, y k Representing the observable measurement, +.>Representing observable measurements and extended Kalman filterAnd the residual error obtained after the conversion of the measurement model before the wave measurement update is adopted, and I is an identity matrix.
As the preferable technical scheme, through preventing sporadic threshold value judgement and then push away the pole tower skew condition, realize the monitoring to pole tower skew, specifically include:
and judging the threshold value and the duration time of the environmental feature, if the duration time and the variation of the environmental feature under different epochs are within the set threshold value range, differentiating the output result of the epoch neural network from the previous result to form a tower offset, and if the output result is not within the range, recording that the epoch result is not used.
The invention also provides a tower offset monitoring system based on the polling Beidou RTK positioning and LSTM auxiliary calculation, which comprises the following steps: the system comprises a Beidou terminal, a communication module, a central control module, a CORS module, a resolving module, a neural network model building module and a neural network model training module;
the Beidou terminal is used for receiving Beidou satellite telegrams, converting the Beidou satellite telegrams into an original observation data format through de-mediation and expansion, and transmitting the Beidou satellite telegrams to the communication module;
the communication module is used for packaging the identity information of the Beidou terminal, the environmental sensor information and the original observation data which flow in through a communication protocol after receiving the polling confirmation request and transmitting the data;
the central control module is used for sequentially initiating a polling request to each Beidou terminal, initiating a polling confirmation request to the corresponding Beidou terminal again after receiving a Beidou terminal polling response, and opening a data receiving channel;
the resolving module is used for carrying out single-point positioning resolving on received data to obtain resolved single-point solutions, the resolved single-point solutions are interconnected with the CORS module through a network RTK form, and a floating point solution of RTK positioning is obtained based on Kalman filtering;
the neural network model building module is used for building an LSTM neural network model;
the neural network model training module is used for taking output signal characteristics of the environmental sensor and floating point characteristics obtained based on extended Kalman filtering as inputs of the LSTM neural network model, taking the Beidou terminal coordinates as expected outputs of the LSTM neural network model, and training the constructed LSTM neural network model;
training the LSTM neural network model by utilizing the output signal characteristics of the environment sensor, floating point characteristics obtained based on the extended Kalman filtering and Beidou terminal coordinate characteristics;
the resolving module is used for inputting the feature data to be detected into the trained LSTM neural network model to obtain the coordinate information of the corresponding Beidou terminal, and further deducing the tower deflection condition through the accidental threshold judgment to realize the monitoring of the tower deflection.
As a preferable technical scheme, the central control module is configured to initiate a polling request to each beidou terminal in sequence, and the polling protocol to be followed is as follows:
when each Beidou terminal respectively accesses the network, a polling list is formed successively according to the time of address allocation, and the terminal which is allocated with the address at last is positioned at the head of the polling list, and the Beidou terminal which is allocated with the address at first is positioned at the tail of the polling list;
if the polling list does not detect the existence of the mark, the polling is ended, and the next polling is re-entered;
the polling list is expressed as:
pol＝{y 1 :l 1 ,y 2 :l 2 ,…,y n :l n }
wherein n represents the number of the Beidou polling terminals and y n Beidou terminal address representing polling, l n Representing the mark corresponding to the Beidou terminal address.
As an preferable technical solution, the resolving module is configured to perform a single-point positioning resolving on received data to obtain a resolved single-point solution, and specifically includes:
and carrying out single-point positioning through a pseudo-range error equation constructed by the reference satellite and each observation satellite, wherein the formula is as follows:
wherein ,as pseudorange residuals δx k 、δy k 、δz k Offset of single point positioning result relative to last epoch, < >>Respectively obtaining the first three coefficients obtained by Taylor series expansion of the geometric distance of the star and the ground at the approximate coordinates of the measuring station, wherein c is the light speed and δt k To monitor the node receiving module clock difference, δt p For satellite clock error>Single point location estimate representing last epoch, < >>Is ionospheric error, +.>Is a tropospheric error, if the receiver module is a single frequency module, then +.>Is built by a global Broadcast ionosphere model Broadcast model, if the receiving module is a dual-frequency module, the receiving module is +.>Obtained by ionosphere-Free linear combination Iono Free LC algorithm.
As a preferable technical solution, the kalman filter adopts extended kalman filter, which is specifically expressed as follows:
wherein , and Pk Is the current epoch t k To-be-estimated state vector of (c) and its variance-covariance matrix, (-) and (+) represent the before and after extended kalman filter measurement update, H (x) and R k The transformation vector of the metrology model, the corresponding partial derivative matrix, and the variance-covariance matrix of the corresponding error, respectively.
As the preferable technical scheme, through preventing sporadic threshold value judgement and then push away the pole tower skew condition, realize the monitoring to pole tower skew, specifically include:
and judging the threshold value and the duration time of the environmental feature, if the duration time and the variation of the environmental feature under different epochs are within the set threshold value range, differentiating the output result of the epoch neural network from the previous result to form a tower offset, and if the output result is not within the range, recording that the epoch result is not used.
Compared with the prior art, the invention has the following advantages and beneficial effects:
(1) According to the invention, polling requests are sequentially initiated for each Beidou terminal, single-point positioning calculation is carried out on received data, a floating point solution of RTK positioning is obtained based on Kalman filtering, an LSTM neural network is trained by utilizing the output signal characteristics of an environment sensor, the floating point characteristics obtained based on extended Kalman filtering and the Beidou terminal coordinate characteristics, coordinate information of the corresponding Beidou terminal is obtained, the condition of pole tower deflection is further calculated through accidental threshold judgment, and calculation logic is applied to pole tower use scenes through a neural network model, so that calculation errors caused by a low-cost receiver are reduced, and low-cost and high-efficiency monitoring of pole tower deflection is realized.
(2) According to the invention, the data receiving and resolving of the receiver are respectively and independently used as the Beidou terminal and the resolving module, the polling mode is used for reducing the pressure of the communication module, the manufacturing cost and the power consumption of the Beidou terminal are greatly reduced, the LSTM is used for carrying out auxiliary resolving to obtain a fixed solution, the resolving logic is suitable for a tower use scene through a neural network model, the resolving error caused by a low-cost receiver is reduced, and finally, the low-cost and high-efficiency monitoring of the tower deflection is realized through threshold judgment and data processing.
Drawings
FIG. 1 is a schematic diagram of a tower offset monitoring system based on polling Beidou RTK positioning and LSTM auxiliary calculation;
FIG. 2 is a schematic diagram of an implementation process of the tower offset monitoring system based on the polling Beidou RTK positioning and LSTM auxiliary calculation;
fig. 3 is a flow chart of the polling protocol according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Example 1
As shown in fig. 1 and fig. 2, this embodiment provides a tower offset monitoring system based on polling beidou RTK positioning and LSTM auxiliary calculation, including: big dipper terminal (big dipper module in the mapping), communication module, well accuse module, CORS module, resolving module, neural network model build module, neural network model training module specifically include:
step 1: the Beidou terminal receives the Beidou satellite message, and converts the Beidou satellite message into an original observation data format through de-mediation and expansion, and transmits the original observation data format to the communication module for further processing;
in this embodiment, in step 1, the beidou terminal only receives the satellite signal, demodulates and despreads the satellite signal, converts the satellite signal into the original observation data to be processed in RTCM3.3 format protocol, and does not perform edge resolving on the beidou terminal, so as to reduce the manufacturing cost and power consumption required by the beidou terminal.
In this embodiment, in order to reduce the size of the data packet of the communication module and slow down the communication pressure, most of the information in NMEA protocol format attached to the receiving module is not reserved, and only the data with information numbers 1042 and 1121 to 1127 in RTCM3.3 protocol format is transmitted.
Step 2: after receiving the polling confirmation request, the communication module carries out communication protocol packaging on the identity information of the Beidou terminal, the environmental sensor information and the original observation data which flow in real time and carries out data transmission;
in the step 2, the identity information of the Beidou terminal is an address automatically allocated by a program when the Beidou terminal is placed, the environment sensor comprises a temperature sensor, a humidity sensor and an air pressure sensor, the identity information of the Beidou terminal and the environment information are jointly inserted in front of an RTCM frame structure, and finally, a complete communication frame is formed by adding the frame head and the frame tail of a communication protocol before and after the whole data.
The communication means adopted in the step 2 should expand the packet capacity and rate of the single transmission packet as much as possible so as to ensure that one piece of Beidou original observation data is transmitted in one packet.
Step 3: the central control module sequentially initiates a polling request to each Beidou terminal according to an agreed protocol, and transmits data sent by the Beidou terminal responding to the request to the resolving module;
and 3, when the central control module in the step manages polling, a polling request is required to be initiated to the corresponding Beidou terminal, a polling confirmation request is initiated to the corresponding Beidou terminal again after a polling response of the Beidou terminal is received, and a data receiving channel is opened.
As shown in fig. 3, the polling protocol followed in step 3 is:
the central control module is powered on for the first time, when each Beidou terminal is respectively connected to the network, a polling list is formed according to the time of address allocation, and finally the Beidou terminal with the address allocation is positioned at the head of the polling list, and the Beidou terminal with the address allocation first is positioned at the tail of the polling list, so that the Beidou terminal can be checked and debugged quickly when being powered on again. Each polling unit in the polling list consists of a corresponding Beidou terminal address and a mark, if the central control module receives a training ending mark sent by the communication module in the polling thread, the central control module sends polling confirmation ending information to the communication module and deletes the mark of the Beidou terminal address in the polling list, if the existence of the mark is not detected in the polling list, the polling is ended, and all the polling units are re-marked to enter the next polling. The polling list is as follows:
pol＝{y 1 :l 1 ,y 2 :l 2 ,…,y n :l n }
wherein n represents the number of the Beidou polling terminals and y n Beidou terminal address representing polling, l n Representing the mark corresponding to the Beidou terminal address.
Step 4: the resolving module carries out single-point positioning resolving on the received data, the resolved single-point resolving is interconnected with the CORS module through a network RTK form to obtain differential information issued by a base station, and a floating point resolving of RTK positioning is obtained based on Kalman filtering;
in this embodiment, in step 4, the network RTK adopts a virtual reference station mode, and a virtual reference station is established near the single-point positioning coordinate of the beidou terminal, so as to form a short base line with a length within 1km, so as to reduce errors caused by the low-cost receiver.
And 4, performing single-point positioning through a pseudo-range error equation constructed by the reference satellite and each observation satellite, wherein the formula is as follows:
wherein As pseudorange residuals δx k 、δy k 、δz k Respectively the offset of the single point positioning result relative to the last epoch,respectively obtaining the first three coefficients obtained by Taylor series expansion of the geometric distance of the star and the ground at the approximate coordinates of the measuring station, wherein c is the light speed and δt k To monitor the node receiving module clock difference, δt p Is satellite clock error. />Single point location estimate representing last epoch, < >>Is ionospheric error, +.>Is the tropospheric error. If the receiver module is a single frequency module, then +.>Is built by a global Broadcast ionosphere model Broadcast model, if the receiving module is a dual-frequency module, the receiving module is +.>Obtained by ionosphere-Free linear combination Iono Free LC algorithm.
In this embodiment, the kalman filter adopted in step 4 is an extended kalman filter, and the formula is:
wherein , and Pk Is the current epoch t k And a variance-covariance matrix thereof. (-) and (+) represent the before and after extended Kalman filter measurement updates, H (x), H (x) and R k The non-linearities of the Kalman filtering are represented by the fact that h (x) is non-linear, y k Representing the observable measurement, +.>And the residual error obtained by converting the observable measured value and the measurement model before updating the extended Kalman filtering measurement is represented, and I is an identity matrix.
Under the conditions that the state of the observed satellites is good and the geometric relationship of the satellite space distribution is reasonable, the receiver autonomous straightness detection mode can be adopted to judge and screen all the observed satellites one by one, pseudo-range residual errors are calculated through single-point positioning again, and the result with the minimum residual error value is selected as the input of the next step.
Step 5: the neural network model building module builds an LSTM neural network model, and the neural network model training module trains the LSTM neural network by utilizing the output signal characteristics of the environment sensor, floating point characteristics obtained based on extended Kalman filtering and accurate coordinate characteristics of the Beidou terminal in a period of time when the environmental conditions of different Beidou terminals are kept longer and stable;
in a time period when the observation state of the Beidou satellite is good and the environmental conditions of different Beidou terminals are kept in a longer stable state, taking output signal characteristics of an environmental sensor and floating point characteristics obtained based on extended Kalman filtering as inputs of an LSTM neural network, taking accurate coordinates of the Beidou terminal as expected outputs of LSTM training, and training a constructed LSTM neural network model.
And repeating the training steps until the value of the loss function is smaller than a preset threshold value in a time period when the observation state of the Beidou satellite is good and the environmental conditions of different Beidou terminals are kept in a longer stable state, so as to obtain a trained LSTM neural network model.
Step 6: the resolving module inputs the characteristic data into the trained LSTM neural network model to obtain coordinate information of the corresponding Beidou terminal, and the condition of the tower deflection is further deduced through judgment of the anti-sporadic threshold value, so that the monitoring of the tower deflection is realized.
In this embodiment, in step 6, the anti-sporadic threshold value is determined by combining the information of the environmental feature and the time node, and the threshold value and the duration are determined for the environmental feature, if the duration and the variation of the environmental feature under different epochs are within the set threshold value range, the output result of the epoch neural network is differed from the previous result to form the tower offset, and if the output result is not within the range, the epoch result is recorded and not used. The reason for adopting the threshold value to judge is that the tower offset is gradually formed under the condition of accumulation of the sun and the moon under most conditions, the environment characteristic threshold value has slowness and stability, the deviation caused by unstable calculation due to the environment mutation can be effectively prevented, and the duration can help judge whether the abnormal solution is temporarily caused by poor quality of a communication channel or poor satellite signal. And for the extreme tower overturning condition, whether the geometric distance between the output result of the neural network and the threshold value is too large or not can be judged.
The above examples are preferred embodiments of the present invention, but the embodiments of the present invention are not limited to the above examples, and any other changes, modifications, substitutions, combinations, and simplifications that do not depart from the spirit and principle of the present invention should be made in the equivalent manner, and the embodiments are included in the protection scope of the present invention.
Claims (10)
1. A tower offset monitoring method based on polling Beidou RTK positioning and LSTM auxiliary calculation is characterized by comprising the following steps:
receiving Beidou satellite message, and converting the Beidou satellite message into an original observation data format through de-mediation and expansion;
after receiving the polling confirmation request, carrying out communication protocol packaging on the identity information of the current Beidou terminal, the environmental sensor information and the original observation data which flow in, and carrying out data transmission;
sequentially initiating a polling request to each Beidou terminal, initiating a polling confirmation request to the corresponding terminal again after receiving a polling response of the Beidou terminal, and opening a data receiving channel;
carrying out single-point positioning calculation on the received data to obtain a single-point solution after calculation, and obtaining a floating point solution of RTK positioning based on Kalman filtering;
constructing an LSTM neural network model, taking output signal characteristics of an environmental sensor and floating point characteristics obtained based on extended Kalman filtering as inputs of the LSTM neural network model, taking the Beidou terminal coordinates as expected outputs of the LSTM neural network model, and training the constructed LSTM neural network model;
inputting the feature data to be detected into the trained LSTM neural network model to obtain coordinate information of the corresponding Beidou terminal, judging through the anti-sporadic threshold value, further calculating the tower deflection condition, and monitoring the tower deflection.
2. The tower offset monitoring method based on polling Beidou RTK positioning and LSTM auxiliary calculation according to claim 1, wherein polling requests are initiated to each Beidou terminal in sequence, and a polling protocol is followed:
when each Beidou terminal respectively accesses the network, a polling list is formed successively according to the time of address allocation, and the Beidou terminal which is allocated with the address at last is positioned at the head of the polling list, and the Beidou terminal which is allocated with the address at first is positioned at the tail of the polling list;
if the polling list does not detect the existence of the mark, the polling is ended, and the next polling is re-entered;
the polling list is expressed as:
pol＝{y 1 : 1 ,y 2 : 2 ,…,y n : n }
wherein n represents the number of the Beidou polling terminals and y n Beidou terminal address representing polling, l n Representing the mark corresponding to the Beidou terminal address.
3. The tower offset monitoring method based on polling Beidou RTK positioning and LSTM auxiliary calculation of claim 1, wherein the method is characterized by performing single-point positioning calculation on received data to obtain a single-point solution after calculation, and specifically comprises the following steps:
and carrying out single-point positioning through a pseudo-range error equation constructed by the reference satellite and each observation satellite, wherein the formula is as follows:
wherein ,as pseudorange residuals δx k 、δy k 、δz k Respectively the offset of the single point positioning result relative to the last epoch,respectively obtaining the first three coefficients obtained by Taylor series expansion of the geometric distance of the star and the ground at the approximate coordinates of the measuring station, wherein c is the light speed and δt k To monitor the node receiving module clock difference, δt p For satellite clock error>Single point location estimate representing last epoch, < >>Is ionospheric error, +.>Is a tropospheric error, if the receiver module is a single frequency module, then +.>Is built by a global Broadcast ionosphere model Broadcast model, if the receiving module is a dual-frequency module, the receiving module is +.>Obtained by ionosphere-Free linear combination Iono Free LC algorithm.
4. The tower offset monitoring method based on polling Beidou RTK positioning and LSTM auxiliary calculation of claim 1, wherein the Kalman filtering adopts extended Kalman filtering, and is specifically expressed as:
wherein , and Pk Is the current epoch t k To-be-estimated state vector of (c) and its variance-covariance matrix, (-) and (+) represent the before and after extended kalman filter measurement update, H (x) and R k Conversion vector, corresponding partial derivative matrix and corresponding error of measurement modelVariance-covariance matrix of (2), y k Representing the observable measurement, +.>And the residual error obtained by converting the observable measured value and the measurement model before updating the extended Kalman filtering measurement is represented, and I is an identity matrix.
5. The tower offset monitoring method based on polling Beidou RTK positioning and LSTM auxiliary calculation of claim 1 is characterized in that the tower offset condition is further deduced through anti-sporadic threshold judgment, and the tower offset monitoring is realized, and specifically comprises the following steps:
and judging the threshold value and the duration time of the environmental feature, if the duration time and the variation of the environmental feature under different epochs are within the set threshold value range, differentiating the output result of the epoch neural network from the previous result to form a tower offset, and if the output result is not within the range, recording that the epoch result is not used.
6. Pole tower offset monitoring system based on polling big dipper RTK location and LSTM auxiliary solution, characterized in that includes: the system comprises a Beidou terminal, a communication module, a central control module, a CORS module, a resolving module, a neural network model building module and a neural network model training module;
the Beidou terminal is used for receiving Beidou satellite telegrams, converting the Beidou satellite telegrams into an original observation data format through de-mediation and expansion, and transmitting the Beidou satellite telegrams to the communication module;
the communication module is used for packaging the identity information of the Beidou terminal, the environmental sensor information and the original observation data which flow in through a communication protocol after receiving the polling confirmation request and transmitting the data;
the central control module is used for sequentially initiating a polling request to each Beidou terminal, initiating a polling confirmation request to the corresponding Beidou terminal again after receiving a Beidou terminal polling response, and opening a data receiving channel;
the resolving module is used for carrying out single-point positioning resolving on received data to obtain resolved single-point solutions, the resolved single-point solutions are interconnected with the CORS module through a network RTK form, and a floating point solution of RTK positioning is obtained based on Kalman filtering;
the neural network model building module is used for building an LSTM neural network model;
the neural network model training module is used for taking output signal characteristics of the environmental sensor and floating point characteristics obtained based on extended Kalman filtering as inputs of the LSTM neural network model, taking the Beidou terminal coordinates as expected outputs of the LSTM neural network model, and training the constructed LSTM neural network model;
training the LSTM neural network model by utilizing the output signal characteristics of the environment sensor, floating point characteristics obtained based on the extended Kalman filtering and Beidou terminal coordinate characteristics;
the resolving module is used for inputting the feature data to be detected into the trained LSTM neural network model to obtain the coordinate information of the corresponding Beidou terminal, and further deducing the tower deflection condition through the accidental threshold judgment to realize the monitoring of the tower deflection.
7. The tower offset monitoring system based on polling Beidou RTK positioning and LSTM auxiliary calculation according to claim 1, wherein the central control module is used for sequentially initiating polling requests to all Beidou terminals, and the following polling protocol is adopted:
when each Beidou terminal respectively accesses the network, a polling list is formed successively according to the time of address allocation, and the terminal which is allocated with the address at last is positioned at the head of the polling list, and the Beidou terminal which is allocated with the address at first is positioned at the tail of the polling list;
if the polling list does not detect the existence of the mark, the polling is ended, and the next polling is re-entered;
the polling list is expressed as:
pol＝{y 1 : 1 ,y 2 : 2 ,…,y n : n }
wherein n represents north pollingThe number of bucket terminals, y n Beidou terminal address representing polling, l n Representing the mark corresponding to the Beidou terminal address.
8. The tower offset monitoring system based on polling beidou RTK positioning and LSTM auxiliary calculation of claim 1, wherein the calculation module is configured to perform single-point positioning calculation on received data to obtain a single-point solution after calculation, and specifically includes:
and carrying out single-point positioning through a pseudo-range error equation constructed by the reference satellite and each observation satellite, wherein the formula is as follows:
wherein ,as pseudorange residuals δx k 、δy k 、δz k Respectively the offset of the single point positioning result relative to the last epoch,respectively obtaining the first three coefficients obtained by Taylor series expansion of the geometric distance of the star and the ground at the approximate coordinates of the measuring station, wherein c is the light speed and δt k To monitor the node receiving module clock difference, δt p For satellite clock error>Single point location estimate representing last epoch, < >>Is ionospheric error, +.>Is a tropospheric error, if the receiver module is a single frequency module, then +.>Is built by a global Broadcast ionosphere model Broadcast model, if the receiving module is a dual-frequency module, the receiving module is +.>Obtained by ionosphere-Free linear combination Iono Free LC algorithm.
9. The tower offset monitoring system based on polling Beidou RTK positioning and LSTM auxiliary calculation according to claim 1, wherein the Kalman filtering adopts extended Kalman filtering, and is specifically expressed as:
wherein , and Pk Is the current epoch t k To-be-estimated state vector of (c) and its variance-covariance matrix, (-) and (+) represent the before and after extended kalman filter measurement update, H (x) and R k The transformation vector of the metrology model, the corresponding partial derivative matrix, and the variance-covariance matrix of the corresponding error, respectively.
10. The tower offset monitoring system based on polling Beidou RTK positioning and LSTM auxiliary calculation of claim 1, wherein the tower offset condition is deduced through anti-sporadic threshold judgment, so as to realize the monitoring of the tower offset, and the system specifically comprises:
and judging the threshold value and the duration time of the environmental feature, if the duration time and the variation of the environmental feature under different epochs are within the set threshold value range, differentiating the output result of the epoch neural network from the previous result to form a tower offset, and if the output result is not within the range, recording that the epoch result is not used.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310461912.8A CN116679331A (en) | 2023-04-26 | 2023-04-26 | Pole tower offset monitoring method and system based on polling Beidou RTK positioning and LSTM auxiliary calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310461912.8A CN116679331A (en) | 2023-04-26 | 2023-04-26 | Pole tower offset monitoring method and system based on polling Beidou RTK positioning and LSTM auxiliary calculation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116679331A true CN116679331A (en) | 2023-09-01 |
Family
ID=87779873
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310461912.8A Pending CN116679331A (en) | 2023-04-26 | 2023-04-26 | Pole tower offset monitoring method and system based on polling Beidou RTK positioning and LSTM auxiliary calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116679331A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117092679A (en) * | 2023-10-19 | 2023-11-21 | 北京凯芯微科技有限公司 | Training method of artificial neural network for RTK ambiguity fixing judgment |
-
2023
- 2023-04-26 CN CN202310461912.8A patent/CN116679331A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117092679A (en) * | 2023-10-19 | 2023-11-21 | 北京凯芯微科技有限公司 | Training method of artificial neural network for RTK ambiguity fixing judgment |
| CN117092679B (en) * | 2023-10-19 | 2024-01-30 | 北京凯芯微科技有限公司 | Training method of artificial neural network for RTK ambiguity fixing judgment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108490473B (en) | GNSS and UWB integrated unmanned aerial vehicle enhanced positioning method and system | |
| CN112099069B (en) | RTK algorithm for correcting troposphere experience model by actually measured meteorological parameters and application | |
| CN107457784B (en) | GPS (Global positioning System) Beidou differential positioning and navigation method for substation inspection robot | |
| CN108387169B (en) | GNSS deformation monitoring system based on real-time atmospheric product | |
| CN110579787A (en) | high-precision inclination monitoring method for electric power iron tower based on Beidou multi-antenna attitude measurement | |
| CN114019584B (en) | VRS (virtual reference Signal System) resolving method for high-precision CORS (continuous reference Signal System) network in large-height-difference region | |
| CN109883313B (en) | Method for monitoring dynamic deflection of high-speed rail bridge based on single-frequency GNSS positioning technology | |
| CN215953863U (en) | Beidou/GNSS water vapor real-time inversion device | |
| CN116679331A (en) | Pole tower offset monitoring method and system based on polling Beidou RTK positioning and LSTM auxiliary calculation | |
| CN114910939B (en) | Troposphere delay actual measurement meteorological correction method in short-distance large-altitude-difference RTK | |
| CN110907971B (en) | Satellite positioning method and device for high-altitude equipment, computer equipment and storage medium | |
| TWI698656B (en) | Buoy position monitoring method and buoy position monitoring system | |
| CN108562279A (en) | A kind of unmanned plane mapping method | |
| CN113358017B (en) | Multi-station cooperative processing GNSS high-precision deformation monitoring method | |
| CN109459774A (en) | A kind of transmission tower deformation monitoring system and method based on judgement of transfiniting | |
| CN109459775A (en) | A kind of transmission tower deformation monitoring system that low rate is transmitted at a distance and method | |
| CN111856531A (en) | Agricultural Internet of things method based on satellite positioning | |
| CN116182795B (en) | Precision measurement method for vertical section of common speed railway | |
| CN117890936B (en) | Low-orbit satellite in-orbit real-time inter-satellite time transfer method and system | |
| CN115061170A (en) | Short-distance large-altitude-difference environment network RTK method | |
| CN115902968A (en) | PPP terminal positioning method based on Beidou third GEO broadcast enhancement information | |
| CN210862666U (en) | Device for three-dimensional modeling and mapping of image-control-point-free fixed-wing unmanned aerial vehicle | |
| CN111965674A (en) | Beidou positioning and resolving method and system based on self-adaptive cuckoo algorithm | |
| CN117111112A (en) | GNSS and LNSS data fusion processing method and system | |
| CN114488247A (en) | Method for analyzing mobility of equipment based on high-precision Beidou differential positioning |
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 |