CN112073480A - Method and device for monitoring consumption of muck vehicle through neural network algorithm self-organizing mapping - Google Patents

Method and device for monitoring consumption of muck vehicle through neural network algorithm self-organizing mapping Download PDF

Info

Publication number
CN112073480A
CN112073480A CN202010873307.8A CN202010873307A CN112073480A CN 112073480 A CN112073480 A CN 112073480A CN 202010873307 A CN202010873307 A CN 202010873307A CN 112073480 A CN112073480 A CN 112073480A
Authority
CN
China
Prior art keywords
data
monitoring
muck
neural network
vector
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.)
Granted
Application number
CN202010873307.8A
Other languages
Chinese (zh)
Other versions
CN112073480B (en
Inventor
王胜斌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hunan Jinrui Technology Co ltd
Original Assignee
Hunan Jinrui Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hunan Jinrui Technology Co ltd filed Critical Hunan Jinrui Technology Co ltd
Priority to CN202010873307.8A priority Critical patent/CN112073480B/en
Publication of CN112073480A publication Critical patent/CN112073480A/en
Application granted granted Critical
Publication of CN112073480B publication Critical patent/CN112073480B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
    • G01N15/06—Investigating concentration of particle suspensions
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/0004—Gaseous mixtures, e.g. polluted air
    • G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
    • G01N33/0027—General constructional details of gas analysers, e.g. portable test equipment concerning the detector
    • G01N33/0036—General constructional details of gas analysers, e.g. portable test equipment concerning the detector specially adapted to detect a particular component
    • G01N33/0037—NOx
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/0004—Gaseous mixtures, e.g. polluted air
    • G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
    • G01N33/0027—General constructional details of gas analysers, e.g. portable test equipment concerning the detector
    • G01N33/0036—General constructional details of gas analysers, e.g. portable test equipment concerning the detector specially adapted to detect a particular component
    • G01N33/0039—O3
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/0004—Gaseous mixtures, e.g. polluted air
    • G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
    • G01N33/0027—General constructional details of gas analysers, e.g. portable test equipment concerning the detector
    • G01N33/0036—General constructional details of gas analysers, e.g. portable test equipment concerning the detector specially adapted to detect a particular component
    • G01N33/004—CO or CO2
    • 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
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
    • G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • 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
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
    • G06V20/597—Recognising the driver's state or behaviour, e.g. attention or drowsiness
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00—Registering or indicating the working of vehicles
    • G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
    • G07C5/0841—Registering performance data
    • G07C5/085—Registering performance data using electronic data carriers
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00—Registering or indicating the working of vehicles
    • G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
    • G07C5/0841—Registering performance data
    • G07C5/085—Registering performance data using electronic data carriers
    • G07C5/0866—Registering performance data using electronic data carriers the electronic data carrier being a digital video recorder in combination with video camera
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
    • H04L67/125—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks involving control of end-device applications over a network
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/76—Television signal recording
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Pathology (AREA)
  • Signal Processing (AREA)
  • Immunology (AREA)
  • Multimedia (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Food Science & Technology (AREA)
  • Medicinal Chemistry (AREA)
  • Theoretical Computer Science (AREA)
  • Computing Systems (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Remote Sensing (AREA)
  • Combustion & Propulsion (AREA)
  • Medical Informatics (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Molecular Biology (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Electromagnetism (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Dispersion Chemistry (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention provides a method and a device for monitoring the consumption of a muck vehicle by self-organizing mapping of a neural network algorithm, wherein the method comprises the following steps: acquiring dead time data and current position data of the muck truck through a monitoring neural network model preset in the muck truck; taking the dead time data and the current position data as input, correspondingly converting the dead time data and the current position data into vector data, inputting the vector data into a hidden layer of a neural network algorithm to perform weight processing according to vectors, and outputting formed monitoring rule data to a monitoring neural network model; according to the monitoring rule data, if the waste soil truck has a violation condition, carrying out data synapse regulation to form a violation data packet; uploading the violation data packet to a cloud monitoring platform by adopting a 5G network, and acquiring a lock-back instruction of the cloud monitoring platform; lifting a container of the muck truck through the back-locking instruction to perform back-locking, so as to prevent muck in the container from being poured out; the effect of converting post-treatment and prevention into instant emergency treatment is realized.

Description

Method and device for monitoring consumption of muck vehicle through neural network algorithm self-organizing mapping
Technical Field
The invention relates to the technical field of large-scale transport vehicle monitoring platforms, in particular to a method and a device for monitoring the consumption of a muck vehicle through self-organizing mapping of a neural network algorithm.
Background
Because of construction site area is limited, general building materials all adopt large-scale transport vechicle to transport, and to the transportation of dregs, transport by the dregs car, and to dregs car transportation dregs to appointed place in-process of absorption, have following technical problem:
(1) the driver is not in appointed digestion place unloading, leads to the unordered of dregs transportation, influences the construction process.
(2) The vehicles of the muck truck are not tightly sealed, and then spilled objects are generated along the way, so that the spilled objects of the vehicles influence the appearance of the city, the environment is deteriorated, meanwhile, the wastes are easily checked and penalized by departments such as sanitation, city management and the like, and the profits of muck companies and drivers are reduced.
For the problems, an intelligent monitoring system is provided in the prior art, and the monitoring process of various problems is realized based on the dynamic monitoring of a construction site and a consumption site, the real-time dynamic monitoring of the transportation process and the intelligent identification of a black construction site and a black consumption site by computer equipment;
however, the monitoring is either manual monitoring or machine monitoring, and is a process for handling the violation of the muck vehicle, or restricts a driver to prevent the violation, and cannot perform related control reaction in the violation process, and the main reason is that the data acquisition and the output of the existing cloud platform monitoring depend on wireless 4G or base station PLC communication, so the reaction time is long, and the instant reaction cannot be realized.
Disclosure of Invention
The invention provides a method and a device for monitoring the consumption of a muck vehicle by self-organizing mapping of a neural network algorithm, which are used for restricting transmission data and adopting a 5G technology to achieve the aim of improving the response speed of machine supervision, so that a cloud platform carries out dynamic supervision on a construction site and a consumption site, real-time dynamic supervision on a transportation process and intelligent identification on a black construction site and a black consumption site based on computer equipment, and the effect of converting post-treatment and prevention into instant emergency treatment is realized.
The invention adopts the following technical means for solving the technical problems:
the application provides a method for monitoring the consumption of a muck vehicle by self-organizing mapping of a neural network algorithm, which comprises the following steps:
acquiring dead time data and current position data of the muck truck through a monitoring neural network model preset in the muck truck;
taking the dead time data and the current position data as input, correspondingly converting the dead time data and the current position data into vector data, inputting the vector data into a hidden layer of a neural network algorithm to perform weight processing according to vectors, and outputting formed monitoring rule data to a monitoring neural network model;
according to the monitoring rule data, if the waste soil truck has a violation condition, carrying out data synapse regulation to form a violation data packet;
uploading the violation data packet to a cloud monitoring platform by adopting a 5G network, and acquiring a lock-back instruction of the cloud monitoring platform;
and lifting the container of the muck truck through the back-locking instruction to carry out back-locking, so as to prevent muck in the container from being poured out.
Further, the step of obtaining the dead time data and the current position data of the slag car through a monitoring neural network model preset in the slag car includes:
the monitoring neural network model judges whether the slag car is stopped or not through monitoring equipment arranged on the slag car;
if so, the monitoring neural network model acquires dead time data and current position data.
Further, the step of correspondingly converting dead time data and current position data into vector data by using the dead time data and the current position data as input includes:
quantifying the time length in the dead time data in real time to obtain a gradually increasing first vector;
and determining a transportation route, marking the position information in the current position data on the transportation route, and quantifying to obtain a second vector.
Further, inputting vector data to a hidden layer of a neural network algorithm to perform weight processing according to the vector, and outputting the formed monitoring rule data to a monitoring neural network model, including:
the hidden layer adopts a source node layer to access a first vector and a second vector;
and a plurality of first neurons are connected to the hidden layer, the first neurons are activated step by step according to the real-time increment of the first vector, the weight value of the first vector is increased step by step, and the weight value of the first vector is fixed when the increment of the first vector is stopped, wherein the activation number of the first neurons has an upper limit value.
A number of second neurons are connected to the hidden layer, assigning a fixed weight to the second vector.
And when the weight values of the first vector and the second vector are defined, forming monitoring rule data, and outputting the monitoring rule data to the monitoring neural network model from a hidden layer of the Microsoft neural network.
Further, according to the monitoring rule data, if the muck vehicle has a violation condition, performing data synapse adjustment to form a violation data packet includes:
the absorption violation condition is that the muck vehicle is stopped in a non-specified absorption site, so that the stopping time and the current position are obtained;
outputting the dead time and the current position to a monitoring neural network model;
determining the neurons forming the weight data by adopting a post-synaptic neuron two-bit array of a Kohoncn model according to the weight data determined by the dead time and the current position;
after determining the neurons in the synaptic neuron two-bit array, neuron synaptic bundles are performed to self-organize mapping and compress into violation data packets.
The application also provides a device for monitoring the consumption of the muck vehicle through self-organizing mapping of a neural network algorithm, which comprises the following steps:
the model acquisition unit is used for acquiring the dead time data and the current position data of the muck truck through a monitoring neural network model preset in the muck truck;
the model processing unit is used for taking the dead time data and the current position data as input, correspondingly converting the dead time data and the current position data into vector data, inputting the vector data into a hidden layer of a neural network algorithm to perform weight processing according to vectors, and outputting formed monitoring rule data to a monitoring neural network model;
the compression unit is used for carrying out data synapse regulation to form an illegal data packet if the muck vehicle has a consumption violation condition according to the monitoring rule data;
the data transmission unit is used for uploading the violation data packet to a cloud monitoring platform by adopting a 5G network and acquiring a lock return instruction of the cloud monitoring platform;
and the execution unit is used for lifting the container of the muck truck through the back-locking instruction to carry out back-locking, so that muck in the container is prevented from being poured out.
The application also provides an intelligent muck vehicle monitoring system, which is composed of muck vehicles arranged on the vehicles through various hardware equipment layouts and a cloud monitoring platform used for monitoring the muck vehicles, wherein the monitoring system runs the method for monitoring the consumption of the muck vehicles through the neural network algorithm self-organizing mapping, and comprises the following steps:
the layout of hardware equipment on the muck truck comprises left and right blind area cameras, a container state analyzer, a driver state camera, a driver interactive intercom screen, a tail camera, an active safety video recorder and main control equipment;
the left and right blind area cameras are two blind area cameras which are respectively arranged on the vehicle side positions of the left and right visual blind areas of the muck vehicle, the container state analyzer is arranged on the container position of the muck vehicle, the driver state camera is arranged in the cab, the visual angle of the driver state camera faces the position of a driver, the driver interaction intercommunication screen is arranged in the cab, the tail camera is arranged at the tail part of the muck vehicle, the visual angle of the tail camera faces the tail baffle and/or the tail tire, and the active safety video recorder is arranged in the muck vehicle;
the main control equipment is arranged in the muck truck and is respectively connected with the left and right blind area cameras, the container state analyzer, the driver state camera, the driver interactive talkback screen, the tail camera and the active safety video recorder;
the cloud monitoring platform is loaded in the computer equipment and comprises a data processing module, a display module, an intercom module and a data storage module, wherein all the modules are mutually connected;
the data processing module comprises a driving violation processing unit, a muck dumping processing unit, a tail gas emission monitoring unit and a container muck processing unit, and all the units are connected with one another.
Furthermore, a deflection angle calculation assembly connected with a main control device is also arranged on the slag car, and the main control device is connected with a steering wheel of a cab;
the deflection angle calculation component calculates the maximum deflection angle of the muck truck according to the length of the muck truck, load bearing data of a container and weight data of the current truck, and enables the main control equipment to lock the maximum torque of the steering wheel through a conversion algorithm.
The invention provides a method and a device for monitoring the consumption of a muck vehicle by self-organizing mapping of a neural network algorithm, which have the following beneficial effects:
the method changes the traditional mode that the data are uploaded to the cloud monitoring platform by the muck truck, adopts the mode of Microsoft neural network and self-organizing mapping to compress the data stream most accurately, improves the response speed of the cloud monitoring platform, and realizes the effect of converting post-processing and prevention into instant emergency processing.
Drawings
FIG. 1 is a schematic flow chart of an embodiment of a method for monitoring the consumption of a muck vehicle by neural network algorithm self-organizing map according to the present invention;
FIG. 2 is a schematic diagram of hidden layer weight neurons of a Microsoft neural network in one embodiment of a method for monitoring dregs car consumption by neural network algorithm self-organizing map of the present invention;
FIG. 3 is a schematic diagram of a self-organizing map of a Microsoft neural network in an embodiment of a method for monitoring dregs car consumption by the neural network algorithm self-organizing map of the present invention;
FIG. 4 is a block diagram of the structure of an embodiment of the intelligent monitoring system for a muck truck according to the invention;
fig. 5 is a schematic flow chart of a monitoring method executed by the intelligent monitoring system for the muck vehicle provided by the invention.
The implementation, functional features and advantages of the present invention will be further described with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a schematic flow chart of a method for monitoring the consumption of the muck car by the neural network algorithm self-organizing map proposed by the present application is shown;
the method for monitoring the consumption of the muck vehicle by the neural network algorithm self-organizing mapping comprises the following steps:
s100, acquiring stagnation time data and current position data of the slag car through a monitoring neural network model preset in the slag car;
s200, taking the dead time data and the current position data as input, correspondingly converting the dead time data and the current position data into vector data, inputting the vector data into a hidden layer of a neural network algorithm to perform weight processing according to the vector, and outputting the formed monitoring rule data to a monitoring neural network model;
s300, according to the monitoring rule data, if the waste soil truck has a violation condition, carrying out data synapse regulation to form a violation data packet;
s400, uploading the violation data packet to a cloud monitoring platform by adopting a 5G network, and acquiring a lock-back instruction of the cloud monitoring platform;
s500, lifting the container of the muck truck through a back-locking instruction to perform back-locking, and preventing muck in the container from being poured out.
In particular, the method comprises the following steps of,
the neural network algorithm described above employs a Microsoft neural network algorithm.
In one embodiment, the step of obtaining the dead time data and the current position data of the slag car through a monitoring neural network model preset in the slag car comprises the following steps:
the monitoring neural network model judges whether the slag car is stopped or not through monitoring equipment arranged on the slag car;
and if so, the monitoring neural network model acquires dead time data and current position data.
In one embodiment, the step of converting dead-time data and current position data into vector data correspondingly comprises:
quantifying the time length in the dead time data in real time to obtain a first vector gradually increasing;
and determining a transportation route, marking the position information in the current position data on the transportation route, and quantifying to obtain a second vector.
Referring to fig. 2, a schematic diagram of a hidden layer of a neural network algorithm is shown;
inputting vector data to a hidden layer of a neural network algorithm to perform weight processing according to vectors, and outputting formed monitoring rule data to a monitoring neural network model, wherein the step comprises the following steps:
the hidden layer adopts a source node layer to access a first vector and a second vector;
and the first neurons are connected to the hidden layer, the first neurons are gradually activated according to the real-time increment of the first vector, the weight value of the first vector is gradually increased, and the weight value of the first vector is fixed when the increment of the first vector stops, wherein the activation number of the first neurons has an upper limit value.
Several second neurons are connected to the hidden layer, assigning a fixed weight to the second vector.
When the weight values of the first vector and the second vector are defined, monitoring rule data is formed and is output to the monitoring neural network model from the hidden layer of the Microsoft neural network.
As can be seen from the above, the first vector is a vector that gradually increases with time, and the more first neurons are activated according to the increase in time. The second vector is determined by the current position, and only two cases of 'being located in the consumption field' or 'not being in the consumption field' exist, and when the case is 'not in the consumption field', the corresponding second neuron is fixedly activated, namely, the second neuron is fixed weight.
Referring to fig. 3, a schematic diagram of neuron determination for a post-synaptic neuron two-bit array of the Kohoncn model.
According to the monitoring rule data, if the waste soil vehicle has a rule violation condition, carrying out data synapse regulation, and forming a rule violation data packet, wherein the step comprises the following steps:
the absorption violation condition is that the muck vehicle is stopped in a non-specified absorption site, so that the stopping time and the current position are obtained;
outputting the dead time and the current position to a monitoring neural network model;
determining the neurons forming the weight data by adopting a post-synaptic neuron two-bit array of a Kohoncn model according to the weight data determined by the dead time and the current position;
after determining the neurons in the synaptic neuron two-bit array, neuron synaptic bundles are performed to self-organize mapping and compress into violation data packets.
In particular, the method comprises the following steps of,
the larger the range of the neuron protrusion rule along with the increasing rule of the first vector is, and the data stream uploaded to the neuron monitoring platform is always data with a specific size after the rule is finished. Through the self-organizing map, the mode that the traditional muck truck uploads data to the cloud monitoring platform is changed, the mode of a Microsoft neural network algorithm and the self-organizing map is adopted, the data stream is compressed most accurately, the reaction speed of the cloud monitoring platform is improved, and the effect of converting post-processing and prevention into instant emergency processing is achieved.
The application also provides a device for monitoring the consumption of the muck vehicle through self-organizing mapping of a neural network algorithm, which comprises the following steps:
the model acquisition unit is used for acquiring the dead time data and the current position data of the muck truck through a monitoring neural network model preset in the muck truck;
the model processing unit is used for taking the dead time data and the current position data as input, correspondingly converting the dead time data and the current position data into vector data, inputting the vector data into a hidden layer of a neural network algorithm to carry out weight processing according to the vector, and outputting the formed monitoring rule data to the monitoring neural network model;
the compression unit is used for carrying out data synapse regulation to form an illegal data packet if the waste soil truck has a consumption illegal condition according to monitoring rule data;
the data transmission unit is used for uploading the violation data packet to the cloud monitoring platform by adopting a 5G network and acquiring a lock-back instruction of the cloud monitoring platform;
and the execution unit is used for lifting the container of the muck truck through a back-locking instruction to carry out back-locking, so that muck in the container is prevented from being poured out.
Referring to fig. 4, a block diagram of an intelligent monitoring system for a muck truck according to an embodiment of the present invention is shown;
the invention provides an intelligent monitoring system of a muck truck, which is composed of muck trucks and cloud monitoring platforms, wherein all hardware devices are distributed on the vehicles, and the cloud monitoring platforms are used for monitoring the muck trucks, and the intelligent monitoring system comprises:
the layout of hardware equipment on the muck truck comprises left and right blind area cameras, a container state analyzer, a driver state camera, a driver interactive intercom screen, a tail camera, an active safety video recorder and main control equipment;
the left and right blind area cameras are two blind area cameras which are respectively arranged on the vehicle side positions of the left and right visual blind areas of the muck vehicle, the container state analyzer is arranged on the container position of the muck vehicle, the driver state camera is arranged in the cab, the visual angle of the driver state camera faces the position of a driver, the driver interaction intercommunication screen is arranged in the cab, the tail camera is arranged at the tail part of the muck vehicle, the visual angle of the tail camera faces the tail baffle and/or the tail tire, and the active safety video recorder is arranged in the muck vehicle;
the main control equipment is arranged in the muck truck and is respectively connected with the left and right blind area cameras, the container state analyzer, the driver state camera, the driver interactive talkback screen, the tail camera and the active safety video recorder;
the cloud monitoring platform is loaded in the computer equipment and comprises a data processing module, a display module, an intercom module and a data storage module, wherein all the modules are mutually connected;
the data processing module comprises a driving violation processing unit, a muck dumping processing unit, a tail gas emission monitoring unit and a container muck processing unit, and all the units are connected with one another.
In particular, the method comprises the following steps of,
the left and right blind area cameras collect the visual field blind areas on two sides of the muck truck, and the vehicle-mounted display installed in the cab is used for displaying the visual field blind area images, because the technology is common, the technology is not explained in detail, but the technology mainly utilizes the left and right blind area cameras to measure the speed, obtains the moving fuzzy images through the left and right blind area cameras, processes the moving fuzzy images and determines the current driving speed of the vehicle, so that the effect of simultaneously performing blind area compensation and speed measurement is realized.
The container state analyzer is used for determining data such as the weight and the height of muck on a container of a muck vehicle, preventing the muck vehicle from having the defects of overload, easiness in throwing missing objects along the way and the like, and uploading the muck data such as the weight and the height of muck to a main control device or a data processing module of a cloud monitoring platform, wherein the main control device can limit the maximum steering wheel torque through the muck data and prevent the muck vehicle from inclining and turning over; the data processing module can automatically set an overload threshold and an overspeed threshold through the muck data, so that the illegal conditions such as overload, overspeed and the like are prevented.
The driver state camera is used for collecting a facial image of a driver, can determine the identity of the driver, determines a transportation task and the like of the driver according to the facial image from the data storage module, collects the facial image of the driver and uploads the facial image to the data processing module of the cloud monitoring platform so as to monitor whether the driver is tired of driving through an image and a video screen.
Carry out data transmission through talkback module and driver interactive talkback screen from the cloud monitoring platform of computer equipment, supervisory personnel can communicate with the driver through driver interactive talkback screen, or the appointed sentence of cloud monitoring platform output is exported by driver interactive talkback screen, realize suggestion driver's process, it is concrete, when supervisory personnel sees driver's violation operation through the data that display module shows, can communicate with the driver through driver interactive talkback screen, or, when the data processing module of cloud monitoring platform judges that driver appears violation operation, search predetermined speech information from the voice storehouse, and export this speech information through driver interactive talkback screen, in order to indicate the driver.
Above-mentioned afterbody camera sets up in the rear of a vehicle of dregs car, be used for gathering and shoot the rear of a vehicle image, through its combination work with cloud monitoring platform's data processing module, prevent that the carriage sideboard residue of dregs car is shed, roll up road surface dust through the tire, produce the raise dust pollution, the raise dust increases air solid particle concentration, lead to forming the haze, cause the vehicle restriction operation, reduce the rate of attendance, reduce the problem of income, and the vehicle tail gas emission volume control of the current dregs car of prevention is not enough, general emission standard is low, fuel burning is insufficient, the more problem of particulate matter in the tail gas.
The active safety video recorder is used for recording all processes in the driving process of the muck truck.
The main control equipment is a data processing module which collects data corresponding to the left and right blind area cameras, the container state analyzer, the driver state camera, the driver interactive talkback screen, the tail camera and the active safety video recorder and uploads the data to the cloud monitoring platform.
The cloud monitoring platform monitors the driving of the slag car by drivers of various companies according to regions and regional companies.
Referring to fig. 5, a schematic flow chart of a monitoring method executed by the intelligent monitoring system for the muck vehicle provided by the invention is shown, wherein the monitoring method comprises the following steps:
s1, the driver state camera collects the driver face information, uploads the face information to the data processing module, and the driver data corresponding to the face information is called from the data storage module after image processing, wherein the driver data comprises a name, a work number, a working vehicle number and a working vehicle driving route;
specifically, when a driver takes a driving position, the driver state camera is activated to shoot the driver, so that driver data are obtained, the cloud monitoring platform judges that the corresponding driver drives the corresponding muck vehicle, and if the fact that the driver work number is not related to the work vehicle number is determined from the data storage module, the cloud monitoring platform instructs the main control equipment to lock the steering wheel through the data processing module, so that errors in transportation of the muck vehicle are prevented.
In another embodiment, a driver state camera is used for collecting driver images and videos, the accumulated time for uploading the videos is monitored, and if the accumulated time reaches a threshold value, a driver is prompted to prevent fatigue driving; or adopting image recognition processing, comparing the collected driver image with a prestored image to judge whether the driver is tired, wherein the comparison value comprises whether the face of the driver faces to the driving front or not and whether the eyes of the driver are kept closed or not (collecting multiple images for determination).
S2, the data processing module judges whether the driver drives the corresponding muck vehicle or not according to the work number and the working vehicle number;
s3, if yes, obtaining driving safety data of the muck truck through the left and right blind area cameras, the container state analyzer, the driver state camera and the tail camera, wherein the driving safety data comprises overload information, overspeed information, light running information, fatigue driving information, container muck state information and tail baffle/tire dust raising information;
it should be noted that overload information, overspeed information, light running information and fatigue driving information belong to illegal driving operations of drivers, and container residue soil state information and vehicle tail baffle/tire dust raising information belong to real-time monitoring information.
S4, the data processing module displays the driving safety data according to a preset UI frame, displays the driving safety data through the display module, and judges each information in the driving safety data;
the various information is displayed through the display module, so that monitoring personnel can conveniently monitor and monitor the information, if the monitoring personnel find abnormal conditions, the voice information can be output through the talkback module, and then the voice information is output through the interactive talkback screen of the driver of the muck truck.
S5, if one or more pieces of information in the driving safety data are judged not to accord with the preset conditions, the talkback module carries out voice communication with the driver through the driver interactive talkback screen, prompts violation, and carries out recording and reporting;
when the supervision personnel are not at the post, the cloud monitoring platform can automatically prompt the driver, namely the data processing module judges whether the driving violation operation of the driver occurs or not according to the driving safety data, and the data processing module judges whether the residue soil state information of the residue soil vehicle is abnormal or not according to the driving safety data.
If any one or more problems exist, the voice information is called from the voice library of the data storage module and is automatically uploaded to output prompts through the driver interactive talkback screen.
And S6, after the driving is finished, the active safety video recorder uploads the driving process data to the data storage unit.
So as to ensure that the driver accurately pours the muck into an accurate digestion site and records the muck.
In one embodiment, the step of executing the monitoring method by the intelligent muck vehicle monitoring system comprises the following steps before a driver starts the muck vehicle to run:
the data processing module calls the record information of the muck vehicle to be started from the data storage module, wherein the record information comprises a construction site application part, a route application part, a clearing and transportation certificate application part and an approval result;
judging whether the filing information meets preset conditions or not;
if yes, allowing the driver to enter the muck truck so that the driver state camera can acquire the facial information of the driver.
In particular, the method comprises the following steps of,
after the muck vehicle authorizes work, the muck vehicle can be started by a driver.
In one embodiment, the monitoring system performs a filing process, and stores filing information and a data storage module, and the step of performing the filing process by the monitoring system through the cloud monitoring platform is as follows:
the data processing module sends the electronic parts of the construction site application part, the route application part and the clearance certificate application part to a third party supervision platform;
and after the approval result of the third-party supervision platform is obtained, the filing information is formed and stored in the data storage module.
The purpose is that help the transport company carry out the transportation application of national department and record through the cloud monitoring platform, realizes that the people runs more less, the effect of data many transmission.
In one embodiment, before the step S5 of the monitoring method is executed by the intelligent monitoring system for the muck truck, the method includes:
the data processing module acquires container bearing data of the current muck truck through the container state analyzer, and the data processing module acquires weight data of the current muck truck from the data storage module;
and automatically setting preset conditions through the load bearing data and the weight data of the cargo box to form an overload threshold value, an overspeed threshold value and a cargo box load bearing threshold value.
Because each hardware arranged on the muck truck can collect driving safety data and upload the driving safety data to the cloud monitoring platform, monitoring personnel are required to check the driving safety data, the monitoring personnel are difficult to take care of all the muck trucks, and the monitoring is not accurate; in the technology, a supervision department inputs a threshold value to a cloud monitoring platform, so that the cloud monitoring platform can determine illegal operation of the muck truck in real time; however, the supervision department inputs the threshold value according to the road rule, for example, the speed limit is 80km/h at high speed, the load of the muck truck in the actual situation is ignored, and the threshold value is set inaccurately.
Therefore, the invention provides that the container data are collected by each hardware device distributed on the muck truck body, and each preset condition is set independently, so that the violation numerical value of the muck truck is determined accurately and the road safety is guaranteed.
In one embodiment, in step S3 of the monitoring method executed by the intelligent monitoring system for a muck truck, the step of obtaining the car tailboard/tire flying dust information of the muck truck by the tail camera includes:
the dust raising information of the tail baffle/the tire is a dust fog picture, and the dust fog picture is acquired by the data processing unit in real time so as to monitor whether the dust is raised when the muck truck runs.
The carriage sideboard residue with prevention dregs car is shed, through the road surface dust of tire jack-up, produces the raise dust pollution, and the raise dust increases air solid particle concentration, leads to forming the haze, causes the vehicle restriction operation, reduces the rate of attendance, reduces the problem of income to and the vehicle exhaust emission control of the current dregs car of prevention is not enough, and general emission standard is low, and the fuel burning is insufficient, the more problem of particulate matter in the tail gas.
In one embodiment, a tail gas rocker monitoring assembly is arranged at the tail part of the muck truck, so that the quality of roadside ambient air can be monitored in real time, and CO and O can be detected3、SO2、NO2、PM2.5、PM10The environmental air quality monitoring parameters are combined with the images shot by the tail camera to form tail gas data and the tail gas data are uploaded to the data processing module.
The vehicle exhaust emission of the current dregs car of prevention control is not enough, and general emission standard is low, and the fuel burning is not abundant, the more problem of particulate matter in the tail gas.
In one embodiment, a pedestrian acousto-optic prompter is arranged on a side position of the muck truck, an on-board display is arranged in a cab of the muck truck, the pedestrian acousto-optic prompter comprises an acousto-optic alarm and an anti-collision radar, and the acousto-optic alarm and the anti-collision radar are both connected with the main control equipment.
So as to prevent the driving from colliding with the muck truck and causing the harm to the masses in the blind area.
In one embodiment, the slag car is also provided with a deflection angle calculation component connected with a main control device, and the main control device is connected with a steering wheel of a cab;
the deflection angle calculation component calculates the maximum deflection angle of the muck truck according to the length of the muck truck, load bearing data of a container and weight data of the current truck, and enables the main control equipment to lock the maximum torque of the steering wheel through a conversion algorithm.
In particular, the method comprises the following steps of,
the maximum torque calculation algorithm is as follows:
β＝α+arcsin{*sin[α+arctan(a/b)]/c}
the values of alpha and b are respectively the values of parallel line of vehicle tails of the left and right rearview mirrors seen from the driving position, and the width of the left and right rearview mirrors is taken as an X axis to obtain the positions of a and b falling into the X axis on the corresponding rearview mirrors so as to determine the values of the parallel line of vehicle tails a and b;
and C is an objective factor constant and consists of the length of the muck truck and the weight data (original truck weight + truck bearing data) of the current truck.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.

Claims (8)

1. A method for monitoring the consumption of a muck vehicle by a neural network algorithm self-organizing map, which is characterized by comprising the following steps:
acquiring dead time data and current position data of the muck truck through a monitoring neural network model preset in the muck truck;
taking the dead time data and the current position data as input, correspondingly converting the dead time data and the current position data into vector data, inputting the vector data into a hidden layer of a neural network algorithm to perform weight processing according to vectors, and outputting formed monitoring rule data to a monitoring neural network model;
according to the monitoring rule data, if the waste soil truck has a violation condition, carrying out data synapse regulation to form a violation data packet;
uploading the violation data packet to a cloud monitoring platform by adopting a 5G network, and acquiring a lock-back instruction of the cloud monitoring platform;
and lifting the container of the muck truck through the back-locking instruction to carry out back-locking, so as to prevent muck in the container from being poured out.
2. The method for monitoring the consumption of the slag car by the neural network algorithm self-organizing map as claimed in claim 1, wherein the step of obtaining the dead time data and the current position data of the slag car through the monitoring neural network model preset in the slag car comprises:
the monitoring neural network model judges whether the slag car is stopped or not through monitoring equipment arranged on the slag car;
if so, the monitoring neural network model acquires dead time data and current position data.
3. The method for monitoring the consumption of the muck vehicle by the neural network algorithm self-organizing map according to claim 1, wherein the step of correspondingly converting dead time data and current position data into vector data by taking the dead time data and the current position data as input comprises the following steps of:
quantifying the time length in the dead time data in real time to obtain a gradually increasing first vector;
and determining a transportation route, marking the position information in the current position data on the transportation route, and quantifying to obtain a second vector.
4. The method for monitoring the consumption of the dump truck by the self-organizing map of the neural network algorithm as claimed in claim 3, wherein the step of inputting vector data to a hidden layer of the neural network algorithm for weight processing according to the vector and outputting the formed monitoring rule data to the monitoring neural network model comprises:
the hidden layer adopts a source node layer to access a first vector and a second vector;
and a plurality of first neurons are connected to the hidden layer, the first neurons are activated step by step according to the real-time increment of the first vector, the weight value of the first vector is increased step by step, and the weight value of the first vector is fixed when the increment of the first vector is stopped, wherein the activation number of the first neurons has an upper limit value.
A number of second neurons are connected to the hidden layer, assigning a fixed weight to the second vector.
And when the weight values of the first vector and the second vector are defined, forming monitoring rule data, and outputting the monitoring rule data to the monitoring neural network model from a hidden layer of the Microsoft neural network.
5. The method for monitoring the consumption of the muck vehicle by the neural network algorithm self-organizing map according to claim 1, wherein the step of performing data synapse adjustment to form violation data packets if the muck vehicle has a consumption violation according to the monitoring rule data comprises:
the absorption violation condition is that the muck vehicle is stopped in a non-specified absorption site, so that the stopping time and the current position are obtained;
outputting the dead time and the current position to a monitoring neural network model;
determining the neurons forming the weight data by adopting a post-synaptic neuron two-bit array of a Kohoncn model according to the weight data determined by the dead time and the current position;
after determining the neurons in the synaptic neuron two-bit array, neuron synaptic bundles are performed to self-organize mapping and compress into violation data packets.
6. An apparatus for monitoring dregs car consumption by neural network algorithm self-organizing map, comprising:
the model acquisition unit is used for acquiring the dead time data and the current position data of the muck truck through a monitoring neural network model preset in the muck truck;
the model processing unit is used for taking the dead time data and the current position data as input, correspondingly converting the dead time data and the current position data into vector data, inputting the vector data into a hidden layer of a neural network algorithm to perform weight processing according to vectors, and outputting formed monitoring rule data to a monitoring neural network model;
the compression unit is used for carrying out data synapse regulation to form an illegal data packet if the muck vehicle has a consumption violation condition according to the monitoring rule data;
the data transmission unit is used for uploading the violation data packet to a cloud monitoring platform by adopting a 5G network and acquiring a lock return instruction of the cloud monitoring platform;
and the execution unit is used for lifting the container of the muck truck through the back-locking instruction to carry out back-locking, so that muck in the container is prevented from being poured out.
7. An intelligent muck vehicle monitoring system is composed of muck vehicles and cloud monitoring platforms, wherein the muck vehicles are arranged on the vehicles in a hardware device layout mode, the cloud monitoring platforms are used for monitoring the muck vehicles, the monitoring system runs the method for monitoring the consumption of the muck vehicles through the neural network algorithm self-organizing mapping according to any one of claims 1 to 5, and the monitoring system comprises:
the layout of hardware equipment on the muck truck comprises left and right blind area cameras, a container state analyzer, a driver state camera, a driver interactive intercom screen, a tail camera, an active safety video recorder and main control equipment;
the left and right blind area cameras are two blind area cameras which are respectively arranged on the vehicle side positions of the left and right visual blind areas of the muck vehicle, the container state analyzer is arranged on the container position of the muck vehicle, the driver state camera is arranged in the cab, the visual angle of the driver state camera faces the position of a driver, the driver interaction intercommunication screen is arranged in the cab, the tail camera is arranged at the tail part of the muck vehicle, the visual angle of the tail camera faces the tail baffle and/or the tail tire, and the active safety video recorder is arranged in the muck vehicle;
the main control equipment is arranged in the muck truck and is respectively connected with the left and right blind area cameras, the container state analyzer, the driver state camera, the driver interactive talkback screen, the tail camera and the active safety video recorder;
the cloud monitoring platform is loaded in the computer equipment and comprises a data processing module, a display module, an intercom module and a data storage module, wherein all the modules are mutually connected;
the data processing module comprises a driving violation processing unit, a muck dumping processing unit, a tail gas emission monitoring unit and a container muck processing unit, and all the units are connected with one another.
8. The intelligent muck car monitoring system according to claim 7, wherein the muck car is further provided with a deflection angle calculation component connected with a main control device, and the main control device is connected with a steering wheel of a cab;
the deflection angle calculation component calculates the maximum deflection angle of the muck truck according to the length of the muck truck, load bearing data of a container and weight data of the current truck, and enables the main control equipment to lock the maximum torque of the steering wheel through a conversion algorithm.
CN202010873307.8A 2020-08-26 2020-08-26 Method and device for monitoring consumption of muck vehicle through neural network algorithm self-organizing mapping Active CN112073480B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010873307.8A CN112073480B (en) 2020-08-26 2020-08-26 Method and device for monitoring consumption of muck vehicle through neural network algorithm self-organizing mapping

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010873307.8A CN112073480B (en) 2020-08-26 2020-08-26 Method and device for monitoring consumption of muck vehicle through neural network algorithm self-organizing mapping

Publications (2)

Publication Number Publication Date
CN112073480A true CN112073480A (en) 2020-12-11
CN112073480B CN112073480B (en) 2022-06-14

Family

ID=73658982

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010873307.8A Active CN112073480B (en) 2020-08-26 2020-08-26 Method and device for monitoring consumption of muck vehicle through neural network algorithm self-organizing mapping

Country Status (1)

Country Link
CN (1) CN112073480B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112905724A (en) * 2021-01-22 2021-06-04 武汉依迅北斗时空技术股份有限公司 Method and system for searching suspicious digestion site of muck truck
CN113469154A (en) * 2021-09-03 2021-10-01 海门市重型矿山机械厂 Method and system for monitoring unloading progress of muck truck based on artificial intelligence
CN113609915A (en) * 2021-07-09 2021-11-05 南京泰晟科技实业有限公司 Intelligent monitoring system and method for muck truck
CN113905215A (en) * 2021-12-07 2022-01-07 江西佳铭特实业有限公司 Bus safe driving monitoring system
CN114613141A (en) * 2022-03-21 2022-06-10 美境数字科技(杭州)有限公司 Monitoring system and method for raised dust of muck truck

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0468500A (en) * 1990-07-09 1992-03-04 Toyota Motor Corp Vehicle driver monitoring device
CN104463513A (en) * 2015-01-19 2015-03-25 长沙致天信息科技有限责任公司 Transportation vehicle management system and management method thereof
CN105068473A (en) * 2015-07-30 2015-11-18 苏州宏展信息科技有限公司 RF matched muck dumping system based on fully closed dump trucks
CN105467918A (en) * 2016-01-15 2016-04-06 贵港市嘉特电子科技有限公司 Residue soil vehicle transportation process monitoring system and method
CN106303960A (en) * 2016-08-11 2017-01-04 北汽福田汽车股份有限公司 The methods, devices and systems of management and control slag-soil truck illegal dumping operation
CN106327859A (en) * 2016-08-31 2017-01-11 河海大学 Engineering vehicle intelligent control system based on Internet of Things
CN109299890A (en) * 2018-07-28 2019-02-01 鸿翔环境产业有限公司 A kind of building castoff management cloud platform system
US20190102668A1 (en) * 2017-10-04 2019-04-04 Hengshuai Yao Method of prediction of a state of an object in the environment using an action model of a neural network

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0468500A (en) * 1990-07-09 1992-03-04 Toyota Motor Corp Vehicle driver monitoring device
CN104463513A (en) * 2015-01-19 2015-03-25 长沙致天信息科技有限责任公司 Transportation vehicle management system and management method thereof
CN105068473A (en) * 2015-07-30 2015-11-18 苏州宏展信息科技有限公司 RF matched muck dumping system based on fully closed dump trucks
CN105467918A (en) * 2016-01-15 2016-04-06 贵港市嘉特电子科技有限公司 Residue soil vehicle transportation process monitoring system and method
CN106303960A (en) * 2016-08-11 2017-01-04 北汽福田汽车股份有限公司 The methods, devices and systems of management and control slag-soil truck illegal dumping operation
CN106327859A (en) * 2016-08-31 2017-01-11 河海大学 Engineering vehicle intelligent control system based on Internet of Things
US20190102668A1 (en) * 2017-10-04 2019-04-04 Hengshuai Yao Method of prediction of a state of an object in the environment using an action model of a neural network
CN109299890A (en) * 2018-07-28 2019-02-01 鸿翔环境产业有限公司 A kind of building castoff management cloud platform system

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112905724A (en) * 2021-01-22 2021-06-04 武汉依迅北斗时空技术股份有限公司 Method and system for searching suspicious digestion site of muck truck
CN112905724B (en) * 2021-01-22 2022-06-24 武汉依迅北斗时空技术股份有限公司 Method and system for searching suspicious digestion site of muck truck
CN113609915A (en) * 2021-07-09 2021-11-05 南京泰晟科技实业有限公司 Intelligent monitoring system and method for muck truck
CN113469154A (en) * 2021-09-03 2021-10-01 海门市重型矿山机械厂 Method and system for monitoring unloading progress of muck truck based on artificial intelligence
CN113905215A (en) * 2021-12-07 2022-01-07 江西佳铭特实业有限公司 Bus safe driving monitoring system
CN114613141A (en) * 2022-03-21 2022-06-10 美境数字科技(杭州)有限公司 Monitoring system and method for raised dust of muck truck

Also Published As

Publication number Publication date
CN112073480B (en) 2022-06-14

Similar Documents

Publication Publication Date Title
CN112073480B (en) Method and device for monitoring consumption of muck vehicle through neural network algorithm self-organizing mapping
CN111325872B (en) Driver driving abnormity detection method based on computer vision
CN105675101B (en) Vehicle mass dynamic measurement device based on OBD and measurement method
DE102018129048A1 (en) SYSTEMS AND METHOD FOR DETERMINING SAFETY EVENTS FOR AN AUTONOMOUS VEHICLE
CN104754011A (en) Internet of Vehicles multi-party coordination control method and Internet of Vehicles coordination platform
CN113515985B (en) Self-service weighing system, weighing detection method, weighing detection equipment and storage medium
CN108423003A (en) A kind of driving safety monitoring method and system
CN110470570B (en) Method and system for checking loading compliance of fresh agricultural product transport vehicle
CN115311633B (en) Method and device for detecting illegal boarding and alighting of vehicle, electronic equipment and storage medium
CN104794893A (en) Heavy vehicle bridge-passing monitoring device
CN115802119A (en) Safety monitoring system based on block chain
CN107507420A (en) Overload of vehicle monitoring method, system and vehicle
TWM626569U (en) car accident severity prediction device
US11263837B2 (en) Automatic real-time detection of vehicular incidents
CN109747535B (en) Video networking information management system based on big data
CN116416796A (en) Unmanned vehicle traffic accident responsibility identification method, device, medium and equipment
CN116026441A (en) Method, device, equipment and storage medium for detecting abnormal load capacity of vehicle
CN115511879A (en) Detection system and detection method for detecting whether muck truck is covered with no cover based on computer vision
JP2019185410A (en) Vehicle estimation system, learning equipment, and vehicle estimation method
CN115049992A (en) Logistics monitoring system and method based on big data
CN115373305A (en) Method for monitoring state of concrete transport vehicle
CN106960407A (en) Parking lot remote supervisory method and device
CN114613141A (en) Monitoring system and method for raised dust of muck truck
CN113990077A (en) Vehicle load and characteristic monitoring system and method
JP2021192181A (en) Abnormality notification system and abnormality notification method

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