CN114757625B - LNG (liquefied Natural gas) canning safety management method based on position matching and Internet of things system - Google Patents
LNG (liquefied Natural gas) canning safety management method based on position matching and Internet of things system Download PDFInfo
- Publication number
- CN114757625B CN114757625B CN202210669238.8A CN202210669238A CN114757625B CN 114757625 B CN114757625 B CN 114757625B CN 202210669238 A CN202210669238 A CN 202210669238A CN 114757625 B CN114757625 B CN 114757625B
- Authority
- CN
- China
- Prior art keywords
- lng
- distributed energy
- canning
- transport vehicle
- matching
- 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
- 239000003949 liquefied natural gas Substances 0.000 title claims abstract description 465
- 238000009924 canning Methods 0.000 title claims abstract description 167
- 238000007726 management method Methods 0.000 title claims abstract description 131
- 238000000034 method Methods 0.000 claims abstract description 63
- 238000012544 monitoring process Methods 0.000 claims abstract description 16
- 230000002457 bidirectional effect Effects 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims description 55
- 239000013598 vector Substances 0.000 claims description 40
- 238000012795 verification Methods 0.000 claims description 30
- 238000012360 testing method Methods 0.000 claims description 25
- 230000001133 acceleration Effects 0.000 claims description 18
- 238000003058 natural language processing Methods 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 7
- 238000006073 displacement reaction Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 230000005484 gravity Effects 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 6
- 238000000638 solvent extraction Methods 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 abstract description 4
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 14
- 239000007789 gas Substances 0.000 description 10
- 239000003345 natural gas Substances 0.000 description 7
- 238000010276 construction Methods 0.000 description 4
- 238000002309 gasification Methods 0.000 description 3
- MWUXSHHQAYIFBG-UHFFFAOYSA-N nitrogen oxide Inorganic materials O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 239000003245 coal Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 230000008016 vaporization Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000005429 filling process Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000003915 liquefied petroleum gas Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0833—Tracking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y10/00—Economic sectors
- G16Y10/35—Utilities, e.g. electricity, gas or water
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/50—Safety; Security of things, users, data or systems
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Computer Security & Cryptography (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Public Health (AREA)
- Accounting & Taxation (AREA)
- Educational Administration (AREA)
- Water Supply & Treatment (AREA)
- Remote Sensing (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Filling Or Discharging Of Gas Storage Vessels (AREA)
Abstract
The invention discloses a LNG (liquefied natural gas) canning safety management method based on position matching and an Internet of things system.A smart terminal senses and acquires terminal operation information, generates a canning request and sends the canning request to a management platform, and the management platform acquires vehicle information of an LNG transport vehicle after receiving the canning request, generates a canning task plan and sends the canning task plan to the LNG transport vehicle and the smart terminal respectively; the LNG transport vehicle goes to the location of the terminal according to the canning task plan, and the management platform carries out real-time tracking monitoring on the running track of the LNG transport vehicle; after the LNG transport vehicle arrives at the location of the terminal, bidirectional position matching authentication is completed through the management platform and the intelligent terminal, and the LNG distributed energy intelligent terminal is canned. According to the method, the semantic features are extracted from the address text by using a deep learning algorithm, the influence of an address expression mode and a structure on the address matching degree is reduced, the driving direction is predicted by matching map information, and the whole-process monitoring of LNG transportation is realized.
Description
Technical Field
The invention relates to the technical field of liquefied natural gas management, in particular to a LNG canning safety management method based on position matching and an Internet of things system.
Background
In 8 months at 2021, department of national energy and gas department, etc. promulgated "Chinese Natural gas development report (2021)", which showed: the natural gas multi-supply system in China is continuously improved, and one net in China is basically formed. The long-distance pipeline is built up by accumulation for 4.6 ten thousand kilometers, and the total mileage of the natural gas pipelines in the country reaches about 11 ten thousand kilometers. However, in areas with underdeveloped economy such as suburban counties, mountainous areas, and rural areas and areas with insufficient pipeline radiation, natural gas with obvious advantages, safety, and cleanness cannot be used for life and work. According to statistics, nearly 6 hundred million people in China still cannot use natural gas at present.
However, the gas markets in suburban counties, mountain areas and rural areas are potential gas markets of town gas, the energy supply in the areas is an integral part of the whole national energy system, and the supply and consumption of the energy supply necessarily influence the supply and demand situation of Chinese energy. At present, the key points of city construction gradually shift from urban areas to suburban counties, mountainous areas and rural strategies, and an efficient, safe and economic energy supply system needs to be established. In 2021, 1 month, the central "document one" has formally issued a "gas-off-country" policy document, and proposed "strengthening the construction of rural public infrastructure, propelling gas off-country, and supporting the construction of safe and reliable rural gas storage stations and micro-pipe network gas supply systems".
Liquefied Natural Gas (LNG) is now attracting attention as a clean energy source, and the carbon dioxide and nitrogen oxides produced after combustion of natural gas are only 50% and 20% of coal, and are contaminated with 1/4, which is liquefied petroleum gas, and 1/800, which is coal. Due to the fact that the investment cost of pipeline laying is high, the LNG gasification station has better economy than pipeline gas, the LNG gasification station can be used as a gas source for residents in medium and small towns, and the LNG gasification station can also be used for life of businesses and public institutions and heating of users. The virtual pipe network system can be constructed to promote the gas to work in the countryside, and the current situation that nearly 6 hundred million people in China still cannot use natural gas is solved.
The supplement of the LNG vaporizing station usually adopts an LNG transportation tank car to carry out distribution and supplement, and the position of the vaporizing station and the position of the tank car need to be matched in the process of supplying and canning, so that the distribution accuracy is ensured. However, the traditional address matching method mainly focuses on the matching relationship between words in the address text, cannot accurately identify the same directional relationship of different addresses in different expression modes, and has a slow address matching speed. Therefore, under the background, the traditional address matching method is no longer applicable to matching multi-source heterogeneous mass address data.
In addition, in the distribution process of the LNG transportation tank car, the accurate positioning of the position of the transportation tank car and the supervision of transportation data are lacked, and the safety of LNG transportation needs to be improved.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a LNG canning safety management method and an Internet of things system based on position matching. Meanwhile, in the transportation process, the running direction is predicted by matching map information according to the relative position and the movement direction of the transportation tank car, and the whole-process monitoring of LNG transportation is realized.
The purpose of the invention is realized by the following technical scheme:
a LNG canning safety management method based on location matching comprises the following steps:
the method comprises the following steps: the LNG distributed energy intelligent terminal senses the operation information of the acquisition terminal, generates a canning request and sends the canning request to the LNG distributed energy management platform;
step two: after receiving the canning request, the LNG distributed energy management platform acquires vehicle information of the LNG transport vehicle, generates a canning task plan and respectively issues the canning task plan to the LNG transport vehicle and the LNG distributed energy intelligent terminal;
step three: the LNG transport vehicle goes to the location of the LNG distributed energy intelligent terminal according to the canning task plan, and the LNG distributed energy management platform carries out real-time tracking monitoring on the running track of the LNG transport vehicle;
step four: after the LNG transport vehicle arrives at the location of the LNG distributed energy intelligent terminal, a position matching request is initiated, bidirectional position matching authentication is completed through the LNG distributed energy management platform and the LNG distributed energy intelligent terminal, and the LNG distributed energy intelligent terminal is canned.
Specifically, the first step specifically comprises: the LNG distributed energy intelligent terminal utilizes the sensing acquisition device to sense and acquire the position information and the liquefied natural gas reserve information of the LNG distributed energy intelligent terminal, generates a canning request when the liquefied natural gas reserve is lower than a preset alarm threshold value, and sends the canning request and the position information to the LNG distributed energy management platform.
Specifically, the second step is specifically as follows: the method comprises the steps that after an LNG distributed energy management platform receives a canning request and position information of an LNG distributed energy intelligent terminal, vehicle information of an LNG transport vehicle which is in communication connection with the LNG distributed energy management platform at present is obtained, wherein the vehicle information comprises a tank car number, vehicle position information and vehicle speed information; according to the shortest matching principle, the tank car number and the vehicle position information of the LNG transport vehicle with the shortest transport time away from the LNG distributed energy intelligent terminal are obtained, a canning task plan is generated and is respectively issued to the LNG transport vehicle and the LNG distributed energy intelligent terminal.
Specifically, the process of monitoring the running track of the LNG carrier vehicle by the LNG distributed energy management platform in the third step by real-time tracking specifically includes:
the LNG distributed energy management platform plans a canning path of the LNG transport vehicle in advance according to the vehicle position information of the LNG transport vehicle and the location of the LNG distributed energy intelligent terminal;
selecting an inertial reference system as a reference, setting the center of a circle of the coordinate at the central position of the vehicle, and constructing the running coordinate of the LNG transport vehicle according to the vehicle position information and the speed information of the LNG transport vehicle;
determining the attitude angle and the direction information of the LNG transport vehicle based on the running coordinate of the LNG transport vehicle, dividing the total gravity acceleration of the LNG transport vehicle into a plurality of components, obtaining the displacement interval of the LNG transport vehicle by adopting a mode of accumulating linear acceleration, calculating the direction angle value of the LNG transport vehicle, substituting the measured acceleration component into the running coordinate, and estimating the running direction of the LNG transport vehicle;
and analyzing and obtaining the running path of the LNG transport vehicle according to the running direction and the vehicle position information of the LNG transport vehicle, matching the canning path and the running path of the pre-planned LNG transport vehicle, and issuing a route deviation alarm to the LNG transport vehicle if the paths are not matched.
Specifically, the two-way location matching authentication process in the fourth step is as follows:
when LNG is canned, the LNG transport vehicle sends canning request information and tank car position information corresponding to the LNG distributed energy intelligent terminal to the LNG distributed energy management platform;
the LNG distributed energy intelligent terminal sends canning request information corresponding to the tank car number and position information of the LNG distributed energy intelligent terminal to the management platform;
the LNG distributed energy management platform is matched with sensing information sent by the LNG transport vehicle and the LNG distributed energy intelligent terminal and a canning task plan in a database, and if the matching is successful, a canning instruction is issued to the LNG transport vehicle and the LNG distributed energy intelligent terminal respectively; if the matching fails, an alarm prompt is sent to the platform manager;
after the LNG transport vehicle and the LNG distributed energy intelligent terminal obtain the canning instruction, the valves of the LNG transport vehicle and the LNG distributed energy intelligent terminal are respectively opened for canning.
Specifically, the information matching process of the LNG distributed energy management platform according to the canning task plan specifically includes: the LNG distributed energy management platform builds an address matching model, and semantic feature extraction is respectively carried out on tank car position information and position information of the LNG distributed energy intelligent terminal; the LNG distributed energy management platform queries a canning task plan stored in a database according to the canning request information, and acquires position information of the LNG distributed energy intelligent terminal and tank car position information in the canning task plan; and carrying out address text semantic matching on the extracted semantic features and addresses of canned task plans in the database, and outputting matching results.
Specifically, the process of constructing the address matching model by the LNG distributed energy management platform specifically includes:
address data set partitioning: acquiring address data in a historical canning task plan of an LNG distributed energy management platform to form an address database, constructing an address data set containing manual marks, and dividing the address data set into a training set, a verification set and a test set;
word vector training of address elements: performing Word vector training on a training set in an address database by adopting a Word2vec model in a genim natural language processing library so as to obtain Word vectors of a Word list under the current application context;
address text semantic matching: adopting an ESIM model as a basic model for address text semantic matching, and carrying out local modeling according to the context dependency of address elements to obtain an address matching model;
address matching verification and test: and performing address matching verification on the address matching model according to the verification set, adjusting the number of hidden nodes, the learning rate and the mini batch size of the model according to the verification result, and finally performing address matching test by using the test set.
Specifically, the word vector training process of the address element specifically includes: word2vec belongs to an unsupervised neural network language model, Word vector training is carried out on a training set in an address database by adopting a Word2vec model in a genim natural language processing library, and modeling is carried out according to the current Word and the distribution of the local context of the current Word so as to obtain the Word vector of the current Word; the model adopted in the training process is a CBOW model, and the training method is Negative Sampling; and finally, generating an address element word list of the corpus and a corresponding 256-dimensional word vector.
An LNG canning safety management Internet of things system based on position matching is realized by adopting the LNG canning safety management method based on position matching, and the system comprises an object platform, a sensing network platform, an LNG distributed energy management platform, a service platform and a user platform; wherein the content of the first and second substances,
the object platform is used for sensing and acquiring vehicle information of the LNG transport vehicle and terminal operation information of the LNG distributed energy intelligent terminal, generating a canning request according to the terminal operation information and transmitting the canning request to the LNG distributed energy management platform through the sensing network platform;
the object platform comprises an LNG distributed energy intelligent terminal and an LNG transport vehicle; the LNG distributed energy intelligent terminal senses and collects the position information and the liquefied natural gas storage amount information of the LNG distributed energy intelligent terminal by using the sensing and collecting device, generates a canning request when the liquefied natural gas storage amount is lower than a preset alarm threshold value, and sends the canning request and the position information to the LNG distributed energy management platform;
the sensing network platform is used for realizing the communication connection between the management platform and the object platform for sensing and controlling;
the LNG distributed energy management platform is used for generating a canning task plan according to the acquired vehicle information of the LNG transport vehicle and the terminal operation information of the LNG distributed energy intelligent terminal, respectively issuing the canning task plan to the LNG transport vehicle and the LNG distributed energy intelligent terminal, and carrying out real-time tracking monitoring on the running track of the LNG transport vehicle; the method comprises the steps that after an LNG distributed energy management platform receives a canning request and position information of an LNG distributed energy intelligent terminal, vehicle information of an LNG transport vehicle which is in communication connection with the LNG distributed energy management platform at present is obtained, wherein the vehicle information comprises a tank car number, vehicle position information and vehicle speed information; according to the shortest matching principle, acquiring a tank car number and vehicle position information of an LNG transport vehicle with the shortest transport time away from the LNG distributed energy intelligent terminal, generating a canning task plan and respectively issuing the canning task plan to the LNG transport vehicle and the LNG distributed energy intelligent terminal;
the real-time tracking and monitoring process of the LNG transport vehicle on the running track by the LNG distributed energy management platform specifically comprises the following steps:
the LNG distributed energy management platform plans a canning path of the LNG transport vehicle in advance according to the vehicle position information of the LNG transport vehicle and the location of the LNG distributed energy intelligent terminal;
selecting an inertial reference system as a reference, setting the center of a circle of the coordinate at the central position of the vehicle, and constructing the running coordinate of the LNG transport vehicle according to the vehicle position information and the speed information of the LNG transport vehicle;
determining the attitude angle and the direction information of the LNG transport vehicle based on the running coordinate of the LNG transport vehicle, dividing the total gravity acceleration of the LNG transport vehicle into a plurality of components, obtaining the displacement interval of the LNG transport vehicle by adopting a mode of accumulating linear acceleration, calculating the direction angle value of the LNG transport vehicle, bringing the measured acceleration component into the running coordinate, and inferring the running direction of the LNG transport vehicle;
analyzing and obtaining a running path of the LNG transport vehicle according to the running direction and the vehicle position information of the LNG transport vehicle, matching a canning path of the LNG transport vehicle planned in advance with the running path, and issuing a route deviation alarm to the LNG transport vehicle if the paths are not matched;
the service platform is used for acquiring vehicle information of an LNG transport vehicle and terminal operation information of an LNG distributed energy intelligent terminal in an LNG canning process required by a user from the LNG distributed energy management platform;
the user platform is used for various users to obtain vehicle information of the LNG transport vehicle and terminal operation information of the LNG distributed energy intelligent terminal from the service platform.
Specifically, after the LNG transport vehicle arrives at the location of the LNG distributed energy intelligent terminal, a position matching request is initiated, bidirectional position matching authentication is completed through the LNG distributed energy management platform and the LNG distributed energy intelligent terminal, and the LNG distributed energy intelligent terminal is canned; the two-way position matching authentication process comprises the following steps:
when LNG is canned, the LNG transport vehicle sends canning request information and tank car position information corresponding to the LNG distributed energy intelligent terminal to the LNG distributed energy management platform;
the LNG distributed energy intelligent terminal sends canning request information corresponding to a tank car number and position information of the LNG distributed energy intelligent terminal to the LNG distributed energy management platform;
the LNG distributed energy management platform carries out information matching according to the canning task plan, and if the matching is successful, a canning instruction is issued to the LNG transport vehicle and the LNG distributed energy intelligent terminal respectively; if the matching fails, an alarm prompt is sent to the platform manager;
after the LNG transport vehicle and the LNG distributed energy intelligent terminal obtain the canning instruction, respective valves are respectively opened for canning.
The information matching process of the LNG distributed energy management platform according to the canning task plan specifically comprises the following steps: the LNG distributed energy management platform builds an address matching model, and semantic feature extraction is respectively carried out on tank car position information and position information of the LNG distributed energy intelligent terminal; the LNG distributed energy management platform queries a canning task plan stored in a database according to the canning request information, and acquires position information of an LNG distributed energy intelligent terminal and tank car position information in the canning task plan; and carrying out address text semantic matching on the extracted semantic features and addresses of canned task plans in the database, and outputting matching results.
The process of constructing the address matching model by the LNG distributed energy management platform specifically comprises the following steps:
address data set partitioning: acquiring address data in a historical canning task plan of an LNG (liquefied natural gas) distributed energy management platform to form an address database, constructing an address data set containing artificial marks, and dividing the address data set into a training set, a verification set and a test set;
word vector training of address elements: performing Word vector training on a training set in an address database by adopting a Word2vec model in a genim natural language processing library so as to obtain Word vectors of a Word list under the current application context;
address text semantic matching: and (3) adopting an ESIM model as a basic model for address text semantic matching, and carrying out local modeling according to the context dependency of the address elements to obtain an address matching model.
And (3) address matching verification and test, namely performing address matching verification on the address matching model according to a verification set, adjusting the number of hidden nodes, the learning rate and the mini batch size of the model according to a verification result, and finally performing address matching test by using the test set.
The word vector training process of the address elements specifically comprises the following steps: word2vec belongs to an unsupervised neural network language model, Word vector training is carried out on a training set in an address database by adopting a Word2vec model in a genim natural language processing library, and modeling is carried out according to the current Word and the distribution of the local context of the current Word so as to obtain the Word vector of the current Word; the model adopted in the training process is a CBOW model, and the training method is Negative Sampling; and finally, generating an address element word list of the corpus and a corresponding 256-dimensional word vector.
The invention has the beneficial effects that:
1. according to the method, the semantic features are extracted from the address text by using a deep learning algorithm, the deep learning is applied to address matching, the influence of an address expression mode and a structure on the address matching degree is reduced to a great extent, the position matching time in the LNG filling process is reduced, and the LNG filling efficiency is improved.
2. The invention senses and acquires the relevant information of the vehicle in real time to monitor in the transportation process, and predicts the driving direction by matching with the map information according to the relative position and the movement direction of the transportation tank car, thereby realizing the whole-process monitoring of the LNG transportation and improving the safety of the LNG transportation and canning.
Drawings
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a model building flow diagram;
fig. 3 is a system architecture diagram of the present invention.
Detailed Description
The following detailed description will be selected to more clearly understand the technical features, objects and advantages of the present invention. It should be understood that the embodiments described are illustrative of some, but not all embodiments of the invention, and are not to be construed as limiting the scope of the invention. All other embodiments that can be obtained by a person skilled in the art based on the embodiments of the present invention without any inventive step are within the scope of the present invention.
The first embodiment is as follows:
in this embodiment, as shown in fig. 1, a method for managing LNG canning safety based on location matching includes the following steps:
the method comprises the following steps: the LNG distributed energy intelligent terminal senses the operation information of the acquisition terminal, generates a canning request and sends the canning request to the LNG distributed energy management platform;
step two: after receiving the canning request, the LNG distributed energy management platform acquires vehicle information of the LNG transport vehicle, generates a canning task plan and respectively issues the canning task plan to the LNG transport vehicle and the LNG distributed energy intelligent terminal;
step three: the LNG transport vehicle goes to the location of the LNG distributed energy intelligent terminal according to the canning task plan, and the LNG distributed energy management platform carries out real-time tracking monitoring on the running track of the LNG transport vehicle;
step four: after the LNG transport vehicle arrives at the location of the LNG distributed energy intelligent terminal, a position matching request is initiated, bidirectional position matching authentication is completed through the LNG distributed energy management platform and the LNG distributed energy intelligent terminal, and the LNG distributed energy intelligent terminal is canned.
In this embodiment, the first step specifically includes: the LNG distributed energy intelligent terminal utilizes the sensing acquisition device to sense and acquire the position information and the liquefied natural gas reserve information of the LNG distributed energy intelligent terminal, generates a canning request when the liquefied natural gas reserve is lower than a preset alarm threshold value, and sends the canning request and the position information to the LNG distributed energy management platform.
In this embodiment, the second step specifically includes: the method comprises the steps that after an LNG distributed energy management platform receives a canning request and position information of an LNG distributed energy intelligent terminal, vehicle information of an LNG transport vehicle which is in communication connection with the LNG distributed energy management platform at present is obtained, wherein the vehicle information comprises a tank car number, vehicle position information and vehicle speed information; and according to the shortest time matching principle, calculating and evaluating the time required by each transport vehicle according to the position information and the speed information, acquiring the tank car number and the vehicle position information of the LNG transport vehicle with the shortest transport time away from the LNG distributed energy intelligent terminal, generating a canning task plan, and respectively issuing the canning task plan to the LNG transport vehicle and the LNG distributed energy intelligent terminal.
In this embodiment, the process of real-time tracking and monitoring the driving track of the LNG carrier by the LNG distributed energy management platform specifically includes:
the LNG distributed energy management platform plans a canning path of the LNG transport vehicle in advance according to the vehicle position information of the LNG transport vehicle and the location of the LNG distributed energy intelligent terminal;
selecting an inertial reference system as a reference, setting the center of a circle of the coordinate at the central position of the vehicle, and constructing the running coordinate of the LNG transport vehicle according to the vehicle position information and the speed information of the LNG transport vehicle;
determining the attitude angle and the direction information of the LNG transport vehicle based on the running coordinate of the LNG transport vehicle, dividing the total gravity acceleration of the LNG transport vehicle into a plurality of components, obtaining the displacement interval of the LNG transport vehicle by adopting a mode of accumulating linear acceleration, calculating the direction angle value of the LNG transport vehicle, bringing the measured acceleration component into the running coordinate, and inferring the running direction of the LNG transport vehicle;
and analyzing and obtaining the running path of the LNG transport vehicle according to the running direction and the vehicle position information of the LNG transport vehicle, matching the canning path and the running path of the pre-planned LNG transport vehicle, and issuing a route deviation alarm to the LNG transport vehicle if the paths are not matched.
In this embodiment, the bidirectional location matching authentication process is as follows:
when LNG is canned, the LNG transport vehicle sends canning request information and tank car position information corresponding to the LNG distributed energy intelligent terminal to the LNG distributed energy management platform;
the LNG distributed energy intelligent terminal sends canning request information corresponding to the tank car number and position information of the LNG distributed energy intelligent terminal to the management platform;
the LNG distributed energy management platform is matched with sensing information sent by the LNG transport vehicle and the LNG distributed energy intelligent terminal and a canning task plan in a database, and if the matching is successful, a canning instruction is issued to the LNG transport vehicle and the LNG distributed energy intelligent terminal respectively; if the matching fails, an alarm prompt is sent to the platform manager;
after the LNG transport vehicle and the LNG distributed energy intelligent terminal obtain the canning instruction, respective valves are respectively opened for canning.
In this embodiment, the information matching process performed by the LNG distributed energy management platform according to the canning task plan specifically includes: the LNG distributed energy management platform builds an address matching model, and semantic feature extraction is respectively carried out on tank car position information and position information of the LNG distributed energy intelligent terminal; the LNG distributed energy management platform queries a canning task plan stored in a database according to the canning request information, and acquires position information of an LNG distributed energy intelligent terminal and tank car position information in the canning task plan; and carrying out address text semantic matching on the extracted semantic features and addresses of canned task plans in the database, and outputting matching results.
In this embodiment, as shown in fig. 2, the process of constructing the address matching model by the LNG distributed energy management platform is specifically as follows:
address data set partitioning: the method comprises the steps of obtaining address data in a historical canning task plan of the LNG distributed energy management platform to form an address database, constructing an address data set containing manual marks, and dividing the address data set into a training set, a verification set and a test set. The training set is used for training parameters of the model, the verification set is used for adjusting and optimizing hyper-parameters of the model, and the test set is used for final evaluation of model precision.
Word vector training of address elements: and performing Word vector training on a training set in an address database by adopting a Word2vec model in a genesis natural language processing library so as to obtain vector representation of a Word list under the current application context and construct input of an address semantic matching model. Word2vec belongs to an unsupervised Neural Network Language Model (NNLM), is essentially a fully connected Neural network, and can be modeled according to the distribution of the current Word and its local context, thereby obtaining the Word vector of the current Word. The model adopted in the training process is a CBOW model, and the training method is Negative Sampling. And finally, generating an address element word list of the corpus and a corresponding 256-dimensional word vector.
Address text semantic matching: the ESIM model is used as a basic model for address text semantic matching, belongs to one of deep text matching models based on interaction, and comprehensively utilizes some characteristics of a convolutional neural network and a cyclic neural network in natural language processing in model construction, so that local modeling can be performed according to the context dependency of address elements, and an address matching task is finally completed.
Address matching verification and test: the invention adjusts the hidden node number, the learning rate and the mini batch size of the model and selects a group of better parameter combinations according to the optimal precision of the model on the verification set, the training time length of the model, the convergence rate of the model training loss and the stability of the prediction precision of the model on the verification set. And finally, carrying out address matching test by using the test set.
The traditional address matching algorithm mainly focuses on utilizing the literal overlapping of the matched addresses to directly carry out similarity calculation and text matching, and the method is difficult to be applied to the matching task of the current massive multi-source heterogeneous address data. Therefore, the invention designs and realizes the address matching algorithm based on deep learning, which is different from the traditional address matching algorithm and focuses on researching the semantic similarity of the address text and completes the matching task on the basis of the semantic similarity.
Example two:
as shown in fig. 3, the present embodiment further provides an LNG canning safety management internet of things system based on location matching, which is implemented by using the LNG canning safety management method based on location matching in the first embodiment, and the system includes an object platform, a sensing network platform, an LNG distributed energy management platform, a service platform, and a user platform; wherein the content of the first and second substances,
the object platform is used for sensing and acquiring vehicle information of the LNG transport vehicle and terminal operation information of the LNG distributed energy intelligent terminal, generating a canning request according to the terminal operation information and transmitting the canning request to the LNG distributed energy management platform through the sensing network platform;
the object platform comprises an LNG distributed energy intelligent terminal and an LNG transport vehicle; the LNG distributed energy intelligent terminal senses and collects the position information and the liquefied natural gas storage amount information of the LNG distributed energy intelligent terminal by using the sensing and collecting device, generates a canning request when the liquefied natural gas storage amount is lower than a preset alarm threshold value, and sends the canning request and the position information to the LNG distributed energy management platform;
the sensing network platform is used for realizing the communication connection between the management platform and the object platform for sensing and controlling;
the LNG distributed energy management platform is used for generating a canning task plan according to the acquired vehicle information of the LNG transport vehicle and the terminal operation information of the LNG distributed energy intelligent terminal, respectively issuing the canning task plan to the LNG transport vehicle and the LNG distributed energy intelligent terminal, and carrying out real-time tracking monitoring on the running track of the LNG transport vehicle; after receiving a canning request and the position information of an LNG distributed energy intelligent terminal, the LNG distributed energy management platform acquires vehicle information of an LNG transport vehicle which is in communication connection with the LNG distributed energy management platform at present, wherein the vehicle information comprises a tank car number, vehicle position information and vehicle speed information; according to the shortest matching principle, acquiring a tank car number and vehicle position information of an LNG transport vehicle with the shortest transport time away from the LNG distributed energy intelligent terminal, generating a canning task plan and respectively issuing the canning task plan to the LNG transport vehicle and the LNG distributed energy intelligent terminal;
the real-time tracking and monitoring process of the LNG transport vehicle on the running track by the LNG distributed energy management platform specifically comprises the following steps:
the LNG distributed energy management platform plans a canning path of the LNG transport vehicle in advance according to the vehicle position information of the LNG transport vehicle and the location of the LNG distributed energy intelligent terminal;
selecting an inertial reference system as a reference, setting the center of a circle of the coordinate at the central position of the vehicle, and constructing the running coordinate of the LNG transport vehicle according to the vehicle position information and the speed information of the LNG transport vehicle;
determining the attitude angle and the direction information of the LNG transport vehicle based on the running coordinate of the LNG transport vehicle, dividing the total gravity acceleration of the LNG transport vehicle into a plurality of components, obtaining the displacement interval of the LNG transport vehicle by adopting a mode of accumulating linear acceleration, calculating the direction angle value of the LNG transport vehicle, bringing the measured acceleration component into the running coordinate, and inferring the running direction of the LNG transport vehicle;
analyzing and obtaining a running path of the LNG transport vehicle according to the running direction and the vehicle position information of the LNG transport vehicle, matching a canning path of the LNG transport vehicle planned in advance with the running path, and issuing a route deviation alarm to the LNG transport vehicle if the paths are not matched;
the service platform is used for acquiring vehicle information of an LNG transport vehicle and terminal operation information of an LNG distributed energy intelligent terminal in an LNG canning process required by a user from the LNG distributed energy management platform;
the user platform is used for various users to obtain vehicle information of the LNG transport vehicle and terminal operation information of the LNG distributed energy intelligent terminal from the service platform.
Specifically, after the LNG transport vehicle arrives at the location of the LNG distributed energy intelligent terminal, a position matching request is initiated, bidirectional position matching authentication is completed through the LNG distributed energy management platform and the LNG distributed energy intelligent terminal, and the LNG distributed energy intelligent terminal is canned; the two-way position matching authentication process comprises the following steps:
when LNG is canned, the LNG transport vehicle sends canning request information and tank car position information corresponding to the LNG distributed energy intelligent terminal to the LNG distributed energy management platform;
the LNG distributed energy intelligent terminal sends canning request information corresponding to a tank car number and position information of the LNG distributed energy intelligent terminal to the LNG distributed energy management platform;
the LNG distributed energy management platform carries out information matching according to the canning task plan, and if the matching is successful, a canning instruction is issued to the LNG transport vehicle and the LNG distributed energy intelligent terminal respectively; if the matching fails, an alarm prompt is sent to the platform manager;
after the LNG transport vehicle and the LNG distributed energy intelligent terminal obtain the canning instruction, respective valves are respectively opened for canning.
The information matching process of the LNG distributed energy management platform according to the canning task plan specifically comprises the following steps: the LNG distributed energy management platform builds an address matching model, and semantic feature extraction is respectively carried out on tank car position information and position information of the LNG distributed energy intelligent terminal; the LNG distributed energy management platform queries a canning task plan stored in a database according to the canning request information, and acquires position information of the LNG distributed energy intelligent terminal and tank car position information in the canning task plan; and performing address text semantic matching on the extracted semantic features and addresses of canned task plans in the database, and outputting a matching result.
The process of constructing the address matching model by the LNG distributed energy management platform specifically comprises the following steps:
address data set partitioning: acquiring address data in a historical canning task plan of an LNG (liquefied natural gas) distributed energy management platform to form an address database, constructing an address data set containing artificial marks, and dividing the address data set into a training set, a verification set and a test set;
word vector training of address elements: performing Word vector training on a training set in an address database by adopting a Word2vec model in a genim natural language processing library so as to obtain Word vectors of a Word list under the current application context;
address text semantic matching: and (3) adopting an ESIM model as a basic model for address text semantic matching, and carrying out local modeling according to the context dependency of the address elements to obtain an address matching model.
And (3) address matching verification and test, namely performing address matching verification on the address matching model according to a verification set, adjusting the number of hidden nodes, the learning rate and the mini batch size of the model according to a verification result, and finally performing address matching test by using the test set.
The word vector training process of the address elements specifically comprises the following steps: word2vec belongs to an unsupervised neural network language model, Word vector training is carried out on a training set in an address database by adopting a Word2vec model in a genim natural language processing library, and modeling is carried out according to the current Word and the distribution of the local context of the current Word so as to obtain the Word vector of the current Word; the model adopted in the training process is a CBOW model, and the training method is Negative Sampling; and finally, generating an address element word list of the corpus and a corresponding 256-dimensional word vector.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (7)
1. A LNG canning safety management method based on position matching is characterized by comprising the following steps:
the method comprises the following steps: the LNG distributed energy intelligent terminal senses the operation information of the acquisition terminal, generates a canning request and sends the canning request to the LNG distributed energy management platform;
step two: after receiving the canning request, the LNG distributed energy management platform acquires vehicle information of the LNG transport vehicle, generates a canning task plan and respectively issues the canning task plan to the LNG transport vehicle and the LNG distributed energy intelligent terminal; the second step is specifically as follows: the method comprises the steps that after an LNG distributed energy management platform receives a canning request and position information of an LNG distributed energy intelligent terminal, vehicle information of an LNG transport vehicle which is in communication connection with the LNG distributed energy management platform at present is obtained, wherein the vehicle information comprises a tank car number, vehicle position information and vehicle speed information; according to the shortest matching principle, acquiring a tank car number and vehicle position information of an LNG transport vehicle with the shortest transport time away from the LNG distributed energy intelligent terminal, generating a canning task plan and respectively issuing the canning task plan to the LNG transport vehicle and the LNG distributed energy intelligent terminal;
step three: the LNG transport vehicle goes to the location of the LNG distributed energy intelligent terminal according to the canning task plan, and the LNG distributed energy management platform carries out real-time tracking monitoring on the running track of the LNG transport vehicle; the real-time tracking and monitoring process of the LNG distributed energy management platform on the running track of the LNG transport vehicle specifically comprises the following steps: the LNG distributed energy management platform plans a canning path of the LNG transport vehicle in advance according to the vehicle position information of the LNG transport vehicle and the location of the LNG distributed energy intelligent terminal;
selecting an inertial reference system as a reference, setting the center of a circle of the coordinate at the central position of the vehicle, and constructing the running coordinate of the LNG transport vehicle according to the vehicle position information and the speed information of the LNG transport vehicle;
determining the attitude angle and the direction information of the LNG transport vehicle based on the running coordinate of the LNG transport vehicle, dividing the total gravity acceleration of the LNG transport vehicle into a plurality of components, obtaining the displacement interval of the LNG transport vehicle by adopting a mode of accumulating linear acceleration, calculating the direction angle value of the LNG transport vehicle, bringing the measured acceleration component into the running coordinate, and inferring the running direction of the LNG transport vehicle;
analyzing and obtaining a running path of the LNG transport vehicle according to the running direction and the vehicle position information of the LNG transport vehicle, matching a canning path of the pre-planned LNG transport vehicle with the running path, and issuing a route deviation alarm to the LNG transport vehicle if the paths are not matched;
step four: after the LNG transport vehicle arrives at the location of the LNG distributed energy intelligent terminal, a position matching request is initiated, bidirectional position matching authentication is completed through the LNG distributed energy management platform and the LNG distributed energy intelligent terminal, and the LNG distributed energy intelligent terminal is canned; the bidirectional position matching authentication process comprises the following steps:
when LNG is canned, the LNG transport vehicle sends canning request information and tank car position information corresponding to the LNG distributed energy intelligent terminal to the LNG distributed energy management platform;
the LNG distributed energy intelligent terminal sends canning request information corresponding to a tank car number and position information of the LNG distributed energy intelligent terminal to the LNG distributed energy management platform;
the LNG distributed energy management platform performs information matching according to the canning task plan, and if the matching is successful, a canning instruction is issued to the LNG transport vehicle and the LNG distributed energy intelligent terminal respectively; if the matching fails, an alarm prompt is sent to the platform manager;
after the LNG transport vehicle and the LNG distributed energy intelligent terminal obtain the canning instruction, respective valves are respectively opened for canning.
2. The LNG canning safety management method based on location matching as claimed in claim 1, wherein the first step is specifically as follows: the LNG distributed energy intelligent terminal utilizes the sensing acquisition device to sense and acquire the position information and the liquefied natural gas reserve information of the LNG distributed energy intelligent terminal, generates a canning request when the liquefied natural gas reserve is lower than a preset alarm threshold value, and sends the canning request and the position information to the LNG distributed energy management platform.
3. The LNG canning safety management method based on position matching as claimed in claim 1, wherein the information matching process of the LNG distributed energy management platform according to the canning mission plan specifically comprises: the LNG distributed energy management platform builds an address matching model, and semantic feature extraction is respectively carried out on tank car position information and position information of the LNG distributed energy intelligent terminal; the LNG distributed energy management platform queries a canning task plan stored in a database according to the canning request information, and acquires position information of the LNG distributed energy intelligent terminal and tank car position information in the canning task plan; and carrying out address text semantic matching on the extracted semantic features and addresses of canned task plans in the database, and outputting matching results.
4. The LNG canning safety management method based on location matching as claimed in claim 3, wherein the LNG distributed energy management platform address matching model building process specifically comprises:
address data set partitioning: acquiring address data in a historical canning task plan of an LNG (liquefied natural gas) distributed energy management platform to form an address database, constructing an address data set containing artificial marks, and dividing the address data set into a training set, a verification set and a test set;
word vector training of address elements: performing Word vector training on a training set in an address database by adopting a Word2vec model in a genim natural language processing library so as to obtain Word vectors of a Word list under the current application context;
address text semantic matching: adopting an ESIM model as a basic model for address text semantic matching, and carrying out local modeling according to the context dependency of address elements to obtain an address matching model;
and (3) address matching verification and test, namely performing address matching verification on the address matching model according to a verification set, adjusting the number of hidden nodes, the learning rate and the size of the mini batch of the model according to a verification result, and finally performing address matching test by using a test set.
5. The LNG canning safety management method based on location matching as claimed in claim 4, wherein the word vector training process of the address elements specifically comprises: word2vec belongs to an unsupervised neural network language model, Word vector training is carried out on a training set in an address database by adopting a Word2vec model in a genim natural language processing library, and modeling is carried out according to the current Word and the distribution of the local context of the current Word so as to obtain the Word vector of the current Word; the model adopted in the training process is a CBOW model, and the training method is Negative Sampling; and finally, generating an address element word list of the corpus and a corresponding 256-dimensional word vector.
6. An LNG canning safety management Internet of things system based on position matching is realized by adopting the LNG canning safety management method based on the position matching as claimed in any one of claims 1 to 5, and the system comprises an object platform, a sensing network platform, an LNG distributed energy management platform, a service platform and a user platform; wherein the content of the first and second substances,
the object platform is used for sensing and acquiring vehicle information of the LNG transport vehicle and terminal operation information of the LNG distributed energy intelligent terminal, generating a canning request according to the terminal operation information and transmitting the canning request to the LNG distributed energy management platform through the sensing network platform;
the object platform comprises an LNG distributed energy intelligent terminal and an LNG transport vehicle; the LNG distributed energy intelligent terminal senses and collects the position information and the liquefied natural gas storage amount information of the LNG distributed energy intelligent terminal by using the sensing and collecting device, generates a canning request when the liquefied natural gas storage amount is lower than a preset alarm threshold value, and sends the canning request and the position information to the LNG distributed energy management platform;
the sensing network platform is used for realizing the communication connection between the management platform and the object platform for sensing and controlling;
the LNG distributed energy management platform is used for generating a canning task plan according to the acquired vehicle information of the LNG transport vehicle and the terminal operation information of the LNG distributed energy intelligent terminal, respectively issuing the canning task plan to the LNG transport vehicle and the LNG distributed energy intelligent terminal, and carrying out real-time tracking monitoring on the running track of the LNG transport vehicle; the method comprises the steps that after an LNG distributed energy management platform receives a canning request and position information of an LNG distributed energy intelligent terminal, vehicle information of an LNG transport vehicle which is in communication connection with the LNG distributed energy management platform at present is obtained, wherein the vehicle information comprises a tank car number, vehicle position information and vehicle speed information; according to the shortest matching principle, acquiring a tank car number and vehicle position information of an LNG transport vehicle with the shortest transport time away from the LNG distributed energy intelligent terminal, generating a canning task plan and respectively issuing the canning task plan to the LNG transport vehicle and the LNG distributed energy intelligent terminal;
the real-time tracking and monitoring process of the LNG transport vehicle on the running track by the LNG distributed energy management platform specifically comprises the following steps: the LNG distributed energy management platform plans a canning path of the LNG transport vehicle in advance according to the vehicle position information of the LNG transport vehicle and the location of the LNG distributed energy intelligent terminal;
selecting an inertial reference system as a reference, setting the center of a circle of the coordinate at the central position of the vehicle, and constructing the running coordinate of the LNG transport vehicle according to the vehicle position information and the speed information of the LNG transport vehicle;
determining the attitude angle and the direction information of the LNG transport vehicle based on the running coordinate of the LNG transport vehicle, dividing the total gravity acceleration of the LNG transport vehicle into a plurality of components, obtaining the displacement interval of the LNG transport vehicle by adopting a mode of accumulating linear acceleration, calculating the direction angle value of the LNG transport vehicle, bringing the measured acceleration component into the running coordinate, and inferring the running direction of the LNG transport vehicle;
analyzing and obtaining a running path of the LNG transport vehicle according to the running direction and the vehicle position information of the LNG transport vehicle, matching a canning path of the LNG transport vehicle planned in advance with the running path, and issuing a route deviation alarm to the LNG transport vehicle if the paths are not matched;
the service platform is used for acquiring vehicle information of an LNG transport vehicle and terminal operation information of an LNG distributed energy intelligent terminal in an LNG canning process required by a user from the LNG distributed energy management platform;
the user platform is used for various users to obtain vehicle information of the LNG transport vehicle and terminal operation information of the LNG distributed energy intelligent terminal from the service platform.
7. The LNG canning safety management Internet of things system based on position matching according to claim 6, wherein after the LNG carrier arrives at the LNG distributed energy intelligent terminal, a position matching request is initiated, bidirectional position matching authentication is completed through the LNG distributed energy management platform and the LNG distributed energy intelligent terminal, and the LNG distributed energy intelligent terminal is canned; the two-way position matching authentication process comprises the following steps:
when LNG is canned, the LNG transport vehicle sends canning request information and tank car position information corresponding to the LNG distributed energy intelligent terminal to the LNG distributed energy management platform;
the LNG distributed energy intelligent terminal sends canning request information corresponding to a tank car number and position information of the LNG distributed energy intelligent terminal to the LNG distributed energy management platform;
the LNG distributed energy management platform performs information matching according to the canning task plan, and if the matching is successful, a canning instruction is issued to the LNG transport vehicle and the LNG distributed energy intelligent terminal respectively; if the matching fails, an alarm prompt is sent to the platform manager;
after the LNG transport vehicle and the LNG distributed energy intelligent terminal obtain a canning instruction, respectively opening respective valves to carry out canning;
the information matching process of the LNG distributed energy management platform according to the canning task plan specifically comprises the following steps: the LNG distributed energy management platform builds an address matching model, and semantic feature extraction is respectively carried out on tank car position information and position information of the LNG distributed energy intelligent terminal; the LNG distributed energy management platform queries a canning task plan stored in a database according to the canning request information, and acquires position information of an LNG distributed energy intelligent terminal and tank car position information in the canning task plan; performing address text semantic matching on the extracted semantic features and addresses of canned task plans in a database, and outputting matching results;
the process of constructing the address matching model by the LNG distributed energy management platform specifically comprises the following steps:
address data set partitioning: acquiring address data in a historical canning task plan of an LNG distributed energy management platform to form an address database, constructing an address data set containing manual marks, and dividing the address data set into a training set, a verification set and a test set;
word vector training of address elements: performing Word vector training on a training set in an address database by adopting a Word2vec model in a genim natural language processing library so as to obtain Word vectors of a Word list under the current application context;
address text semantic matching: adopting an ESIM model as a basic model for address text semantic matching, and carrying out local modeling according to the context dependency of address elements to obtain an address matching model;
performing address matching verification and test, namely performing address matching verification on an address matching model according to a verification set, adjusting the number of hidden nodes, the learning rate and the mini batch size of the model according to a verification result, and finally performing address matching test by using a test set;
the word vector training process of the address elements specifically comprises the following steps: word2vec belongs to an unsupervised neural network language model, Word vector training is carried out on a training set in an address database by adopting a Word2vec model in a genim natural language processing library, and modeling is carried out according to the current Word and the distribution of the local context of the current Word so as to obtain the Word vector of the current Word; the model adopted in the training process is a CBOW model, and the training method is Negative Sampling; and finally, generating an address element word list of the corpus and a corresponding 256-dimensional word vector.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210669238.8A CN114757625B (en) | 2022-06-14 | 2022-06-14 | LNG (liquefied Natural gas) canning safety management method based on position matching and Internet of things system |
| US18/335,119 US11861552B1 (en) | 2022-06-14 | 2023-06-14 | Methods for managing liquefied natural gas (LNG) tanking safety based on location matching and internet of things systems thereof |
| US18/497,997 US20240062144A1 (en) | 2022-06-14 | 2023-10-30 | Method for liquefied natural gas (lng) station management and internet of things system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210669238.8A CN114757625B (en) | 2022-06-14 | 2022-06-14 | LNG (liquefied Natural gas) canning safety management method based on position matching and Internet of things system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114757625A CN114757625A (en) | 2022-07-15 |
| CN114757625B true CN114757625B (en) | 2022-09-16 |
Family
ID=82336127
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210669238.8A Active CN114757625B (en) | 2022-06-14 | 2022-06-14 | LNG (liquefied Natural gas) canning safety management method based on position matching and Internet of things system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114757625B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106707928A (en) * | 2016-11-30 | 2017-05-24 | 上海雷尼威尔技术有限公司 | Internet of things based LNG (Liquefied Natural Gas) system management method |
| JP2019189157A (en) * | 2018-04-27 | 2019-10-31 | 株式会社東芝 | Railway traveling position detection device and method |
| CN111275969A (en) * | 2020-02-15 | 2020-06-12 | 湖南大学 | Vehicle track filling method based on intelligent identification of road environment |
| CN112428911A (en) * | 2020-10-15 | 2021-03-02 | 甘肃蓝科石化高新装备股份有限公司 | Monitoring method and system for tank truck with pump |
| CN114037384A (en) * | 2021-11-15 | 2022-02-11 | 上海东普信息科技有限公司 | Logistics vehicle monitoring method, device, equipment and storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109270870A (en) * | 2018-10-29 | 2019-01-25 | 山东路科公路信息咨询有限公司 | Transport monitoring method and system |
| CN111861337B (en) * | 2020-07-24 | 2024-04-23 | 江苏天长环保科技有限公司 | Method, device, storage medium and system for monitoring dangerous waste transportation |
| CN111881677A (en) * | 2020-07-28 | 2020-11-03 | 武汉大学 | Address matching algorithm based on deep learning model |
-
2022
- 2022-06-14 CN CN202210669238.8A patent/CN114757625B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106707928A (en) * | 2016-11-30 | 2017-05-24 | 上海雷尼威尔技术有限公司 | Internet of things based LNG (Liquefied Natural Gas) system management method |
| JP2019189157A (en) * | 2018-04-27 | 2019-10-31 | 株式会社東芝 | Railway traveling position detection device and method |
| CN111275969A (en) * | 2020-02-15 | 2020-06-12 | 湖南大学 | Vehicle track filling method based on intelligent identification of road environment |
| CN112428911A (en) * | 2020-10-15 | 2021-03-02 | 甘肃蓝科石化高新装备股份有限公司 | Monitoring method and system for tank truck with pump |
| CN114037384A (en) * | 2021-11-15 | 2022-02-11 | 上海东普信息科技有限公司 | Logistics vehicle monitoring method, device, equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| A deep learning architecture for semantic address matching;Yue Lin等;《International Journal of Geographical Information Science》;20191024;第34卷(第3期);第559-576页 * |
| 物联网分布式LNG智慧生产供应系统软件开发;王子禛等;《电子世界》;20210830(第16期);第21-22页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114757625A (en) | 2022-07-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shukla et al. | An optimization framework for cost effective design of refueling station infrastructure for alternative fuel vehicles | |
| CN106297357B (en) | Real-time route planning and POI information searching system and method based on car networking | |
| Omidvar et al. | Sustainable vehicle routing: Strategies for congestion management and refueling scheduling | |
| CN110836675B (en) | Decision tree-based automatic driving search decision method | |
| CN112734176B (en) | Charging station building method and device, terminal equipment and readable storage medium | |
| Mahmoudi et al. | Accessibility with time and resource constraints: Computing hyper-prisms for sustainable transportation planning | |
| Trofimenko et al. | Model for the assessment greenhouse gas emissions from road transport | |
| CN102903038B (en) | Based on smallclothes Logistics Distribution Method and the system of user trajectory | |
| Zhou et al. | Intelligent tourism recommendation algorithm based on text mining and MP nerve cell model of multivariate transportation modes | |
| Jia et al. | A Microscopic Model of Vehicle CO₂ Emissions Based on Deep Learning—A Spatiotemporal Analysis of Taxicabs in Wuhan, China | |
| CN114757625B (en) | LNG (liquefied Natural gas) canning safety management method based on position matching and Internet of things system | |
| Amrani et al. | Train speed profiles optimization using a genetic algorithm based on a random-forest model to estimate energy consumption | |
| Chen et al. | Electric vehicle charging navigation strategy based on data driven and deep reinforcement learning | |
| CN116629425A (en) | Method and device for calculating vehicle energy consumption, computer readable medium and electronic equipment | |
| Wang | Application of Cloud Computing and GIS Based on Internet of Things in Oil and Gas Storage and Transportation Production Management and Safety Monitoring and Early Warning System | |
| CN115392569A (en) | Electric vehicle charging station site selection and volume fixing method and system | |
| Díaz-Parra et al. | Editorial for Volume 11 Number 2: Electric School Bus Routing Problem for Smart Cities | |
| Jwad et al. | An optimization approach for waste collection routes based on GIS in Hillah-Iraq | |
| Chen et al. | Logistics distribution path planning based on fireworks differential algorithm | |
| Xu et al. | Location Selection of Electric Vehicle Charging Station Based on Improved Immune Algorithm | |
| CN112085315A (en) | Gas station carbon emission intensity calculation method based on motor vehicle commuting trip | |
| US11861552B1 (en) | Methods for managing liquefied natural gas (LNG) tanking safety based on location matching and internet of things systems thereof | |
| Guo et al. | An urban metro network-based method to evaluate carbon emission and distribution cost of express delivery | |
| Argenzio et al. | The use of automatic vehicle location (AVL) data for improving public transport service regularity | |
| CN117113037B (en) | Traffic data determining method and device, electronic equipment and storage medium |
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 |