CN112866337A - High-speed carrying system decision method and device based on intelligent sensing - Google Patents
High-speed carrying system decision method and device based on intelligent sensing Download PDFInfo
- Publication number
- CN112866337A CN112866337A CN202011617320.3A CN202011617320A CN112866337A CN 112866337 A CN112866337 A CN 112866337A CN 202011617320 A CN202011617320 A CN 202011617320A CN 112866337 A CN112866337 A CN 112866337A
- Authority
- CN
- China
- Prior art keywords
- data
- decision
- sensor
- virtual
- network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/12—Avoiding congestion; Recovering from congestion
- H04L47/125—Avoiding congestion; Recovering from congestion by balancing the load, e.g. traffic engineering
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/24—Traffic characterised by specific attributes, e.g. priority or QoS
- H04L47/2425—Traffic characterised by specific attributes, e.g. priority or QoS for supporting services specification, e.g. SLA
- H04L47/2433—Allocation of priorities to traffic types
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention belongs to the technical field of computers, and particularly relates to a high-speed handling system decision method and a device based on intelligent sensing, wherein the method comprises the following steps: step 1: arranging a plurality of sensors which are randomly distributed in a space with a fixed size, and mutually connecting the sensors to form a sensor network; meanwhile, a transport track is built by taking a connection route of sensors in the sensor network as a bluebook, and a carrying system is built; each connecting node of the transportation track is a sensor; step 2: the sensor nodes sense and acquire the operation data of the carrying system in real time; the operational data includes: the speed of travel of the load and the number of loads. The method and the system perform decision optimization for the handling system by abstracting the mapping of the handling system into a virtual decision network, so that the handling system can work with the maximum efficiency, and have the advantages of high intelligent degree, high decision efficiency and high decision making accuracy.
Description
Technical Field
The invention belongs to the technical field of computers, and particularly relates to a high-speed carrying system decision method and device based on intelligent sensing.
Background
In general, an effective artificial intelligence system is based on its ability to perceive, remember, and think, as well as its ability to learn, adapt, and self-act. The dynamic intelligent perception capability in a complex scene is realized, and the purposes of recognizing the environment and the object type and attribute can be achieved through memory, learning, judgment and reasoning by collecting and fusing the similar and heterogeneous sensing information across time and space by using a multi-source information fusion technology. On the basis of which decisions based on empirical judgment and intelligent processing are made possible.
As one of the greatest inventions of the human 20 th century, the robot has changed from day to day in as little as 40 years. Robots have not only become indispensable automation equipment for advanced manufacturing, but are also penetrating at alarming speeds into various fields of oceans, aviation, aerospace, military, agriculture, services, entertainment, and the like. The intelligent perception based on multi-source information fusion is one of modern support technologies of robots, and can comprehensively recognize the categories and attributes of environments and objects through intelligent information processing according to multi-source isomorphic or heterogeneous information provided by multiple sensors so as to achieve the purpose of intelligent perception, thereby realizing due behavior decision according to behavior criteria.
Modern intelligent perception systems need to imitate cognitive mechanisms of human and animals to complete processes of feature extraction, intelligent reasoning and the like of objects. The multi-sensing information fusion mechanism of human and animal understanding of objective objects in nature is not disclosed, but the artificial intelligence can simulate the cognitive process of human and animal by using the whole process of machine vision-machine hearing-machine touch and perception information fusion, which also needs to establish a new theoretical framework to describe the nature of cognition. There are many methods for establishing judgment and reasoning, such as probabilistic reasoning, fuzzy decision, evidence theory, etc.
Disclosure of Invention
The invention mainly aims to provide a high-speed carrying system decision method and a high-speed carrying system decision device based on intelligent sensing, which map and abstract a carrying system into a virtual decision network, sense data in the carrying system in real time through a sensor in the carrying system, combine factors such as set carrying conditions, carrying priority and the like to carry out decision optimization on the carrying system, enable the carrying system to work with the maximum efficiency, and have the advantages of high intelligent degree, high decision efficiency and high decision making accuracy.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
the high-speed handling system decision method based on intelligent perception comprises the following steps:
step 1: arranging a plurality of sensors which are randomly distributed in a space with a fixed size, and mutually connecting the sensors to form a sensor network; meanwhile, a transport track is built by taking a connection route of sensors in the sensor network as a bluebook, and a carrying system is built; each connecting node of the transportation track is a sensor;
step 2: the sensor nodes sense and acquire the operation data of the carrying system in real time; the operational data includes: the running speed of the conveyed objects and the number of the conveyed objects;
and step 3: constructing a virtual decision network by taking a transportation track and a sensor of a carrying system as blueprints and using a one-to-one mapping relation; the transportation track is mapped to be a connecting line of the virtual decision network, and the sensor is mapped to be a shunting point of the virtual decision network; setting a preset value, and grouping one or more adjacent shunting points with the number equal to the preset value to obtain a shunting point group, wherein the shunting point group is used as a flow node of a virtual decision network; the data acquired by the sensor in real time is also transmitted to the virtual decision network in real time;
and 4, step 4: setting a plurality of transport conditions, a plurality of transport priority classes and a plurality of effective flow upper limits in a virtual decision network; the conveying condition is defined as conveying time and conveying speed, and the values of the conveying time and the conveying speed are determined by presetting; the transport priority is defined as the priority level of transport, which includes three priority levels, respectively: the priority level of the third level is highest, and the priority level of the first level is lowest; each priority level corresponds to an effective flow upper limit;
and 5: the virtual decision network acts on the shunting point through a load balancing decision based on the carrying condition, the carrying priority category and the effective flow upper limit, so that each flow node keeps a stable state; the steady state is defined as the incoming flow being equal to the outgoing flow at the same time.
Further, the load balancing decision is constructed based on a load balancing module according to a plurality of carrying conditions and an effective flow upper limit of each carrying priority class based on the corresponding service class; wherein the virtual decision network comprises a plurality of virtual area networks, each corresponding to a different one of the virtual area network tags, and the load balancing decision considers the virtual area networks based on each of the virtual area network tags, wherein each of the virtual area networks is defined by a corresponding transport priority class, wherein each of the plurality of shunting points corresponds to one of the virtual area network tags.
Further, the load balancing module is a centralized module, and the load balancing decision is formed by the centralized module.
Further, when the corresponding transport priority class of one of the vlan tags is mapped to a fixed bitrate transport type, the load balancing module of one of the traffic nodes forms the load balancing decision, which includes: reserving and partitioning the traffic cap for each of the traffic nodes based on the bit rate to obtain a plurality of simultaneous connections suitable for reservation; and allowing a new fixed bitrate requirement only if a portion of the upper limit of traffic equal to the bitrate is valid and assigning the portion of the upper limit of traffic to a desired object.
Furthermore, after the sensor acquires data in real time, the data is preprocessed, and then the processed data is sent to the virtual decision network.
Further, the method for preprocessing data by the sensor comprises the following steps: converting the acquired data into a phase space, and then carrying out differential filtering on the data in the phase space, wherein the differential filtering refers to directly acting a differential filtering signal as a filter on the data to filter noise data; then, data preprocessing is carried out on the data with the noise data filtered; the differential filtered signal is generated by a differential sequence.
Further, the data of the converted phase space is represented as: data (T) ═ Asines (cos ω 0T + cosB ^ c (T) dt), 0 ≦ T ≦ T; wherein the modulation signal c (t) is: acos (ω 0t + B |) dt; wherein T is the time length of s (T), ω 0 is the center frequency, B is the modulation index, a is the amplitude, and c (T) is the data acquired by the sensor.
Further, the differential sequence is: sn+1＝cos(tanωarccos(Sn))，-1＜SnLess than 1, when the parameter value S is takennTo 0.65, a first seed S is given0Generating a difference sequence as 5; on the basis, according to the formula: s (t) ═ Acos (sin ω 0t + cosB ═ Sn+1dt) to generate a differential filter signal, wherein T is greater than or equal to 0 and less than or equal to T; wherein the parameters T, omega 0 and B can be adjusted according to the actual conversion rate, the error rate and the conversion distance; the time length T is between 2.0s and 10.0s, the central frequency omega 0 is less than 1000Hz, and the signal bandwidth B is between 60Hz and 290 Hz.
Further, the data preprocessing of the data after the noise data filtering includes: removing the unique attribute, processing missing values and abnormal value detection and processing; and carrying out data specification processing, including: removing an average value, calculating a covariance matrix, calculating an eigenvalue and an eigenvector of the covariance matrix, sorting the eigenvalues from large to small, reserving the largest eigenvector, and converting data into a new space constructed by the eigenvector; finally, new processed data are obtained, and the data are irrelevant pairwise, but the original information is kept.
A high-speed carrying system decision-making device based on intelligent sensing.
The intelligent sensing-based high-speed carrying system decision method and device have the following beneficial effects: the carrying system is mapped and abstracted into a virtual decision network, data in the carrying system is sensed in real time through a sensor in the carrying system, and factors such as set carrying conditions, carrying priority and the like are combined to perform decision optimization for the carrying system, so that the carrying system can work with the maximum efficiency, and the method has the advantages of high intelligent degree, high decision making efficiency and high decision making accuracy. The method is mainly realized by the following steps: 1. and (3) mapping construction of a virtual decision network: the method takes a transportation track and a sensor of a handling system as a bluebook, and constructs a virtual decision network in a one-to-one mapping relationship; the transportation track is mapped to be a connecting line of the virtual decision network, and the sensor is mapped to be a shunting point of the virtual decision network; setting a preset value, and grouping one or more adjacent shunting points with the number equal to the preset value to obtain a shunting point group, wherein the shunting point group is used as a flow node of a virtual decision network; the data acquired by the sensor in real time is also transmitted to the virtual decision network in real time; the transport system can be accurately simulated through the constructed virtual decision network, and then decision is made on the transport system through the virtual decision network, so that the decision efficiency is higher; 2. the decision method of the virtual decision network comprises the following steps: the invention carries out a carrying decision through a load balancing decision, wherein the load balancing decision is constructed based on a load balancing module according to a plurality of carrying conditions and the upper limit of effective flow of each carrying priority class based on the corresponding service class; wherein the virtual decision network comprises a plurality of virtual area networks, each corresponding to a different one of the virtual area network tags, and the load balancing decision considers the virtual area networks based on each of the virtual area network tags, wherein each of the virtual area networks is defined by a corresponding transport priority class, wherein each of the plurality of shunting points corresponds to one of the virtual area network tags; therefore, the carrying system can operate at the maximum efficiency, and the system congestion cannot be caused; 3. the data denoising method comprises the steps of performing data denoising through data filtering, converting acquired data into a phase space in the denoising process, and then performing differential filtering on the data in the phase space, wherein the differential filtering refers to directly acting a differential filtering signal as a filter on the data to filter noise data; then, data preprocessing is carried out on the data with the noise data filtered; the differential filtering signal is generated through a differential sequence, so that the result obtained by subsequent decision and processing can be more accurate.
Drawings
Fig. 1 is a schematic flow chart of a method for a high-speed handling system decision method based on intelligent sensing according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of data processing of a high-speed handling system decision method and apparatus based on intelligent sensing according to an embodiment of the present invention;
fig. 3 is a schematic diagram illustrating a principle of decision making in a virtual decision network of a decision making method of a high-speed handling system based on intelligent sensing according to an embodiment of the present invention;
fig. 4 is a schematic diagram illustrating a principle of decision making in a virtual decision network of a decision making method of a high-speed handling system based on intelligent sensing according to an embodiment of the present invention;
fig. 5 is a schematic diagram of an experimental effect of the method and device for deciding a high-speed handling system based on intelligent sensing, according to which the decision efficiency varies with the number of experiments, and a schematic diagram of a comparative experimental effect in the prior art.
Detailed Description
The technical solution of the present invention is further described in detail below with reference to the following detailed description and the accompanying drawings:
example 1
As shown in fig. 1, a high-speed handling system decision method based on intelligent sensing performs the following steps:
step 1: arranging a plurality of sensors which are randomly distributed in a space with a fixed size, and mutually connecting the sensors to form a sensor network; meanwhile, a transport track is built by taking a connection route of sensors in the sensor network as a bluebook, and a carrying system is built; each connecting node of the transportation track is a sensor;
step 2: the sensor nodes sense and acquire the operation data of the carrying system in real time; the operational data includes: the running speed of the conveyed objects and the number of the conveyed objects;
and step 3: constructing a virtual decision network by taking a transportation track and a sensor of a carrying system as blueprints and using a one-to-one mapping relation; the transportation track is mapped to be a connecting line of the virtual decision network, and the sensor is mapped to be a shunting point of the virtual decision network; setting a preset value, and grouping one or more adjacent shunting points with the number equal to the preset value to obtain a shunting point group, wherein the shunting point group is used as a flow node of a virtual decision network; the data acquired by the sensor in real time is also transmitted to the virtual decision network in real time;
and 4, step 4: setting a plurality of transport conditions, a plurality of transport priority classes and a plurality of effective flow upper limits in a virtual decision network; the conveying condition is defined as conveying time and conveying speed, and the values of the conveying time and the conveying speed are determined by presetting; the transport priority is defined as the priority level of transport, which includes three priority levels, respectively: the priority level of the third level is highest, and the priority level of the first level is lowest; each priority level corresponds to an upper limit on the available traffic,
and 5: the virtual decision network acts on the shunting point through a load balancing decision based on the carrying condition, the carrying priority category and the effective flow upper limit, so that each flow node keeps a stable state; the steady state is defined as the incoming flow being equal to the outgoing flow at the same time.
As shown in fig. 3, when making a decision in the virtual decision network, first, the transport conditions are considered, and there are cases where the transport conditions are satisfied and are not satisfied. Wherein the transport condition is y in the figure1If the transport condition is satisfied, the transport priority type, i.e., y in the figure, is determined2. Then, the upper limit of the effective flow is found according to the transport priority, namely y in the figure3。
Meanwhile, as shown in fig. 4, when making a decision, the virtual decision network may have two decisions at the same time, each of which corresponds to one pair mirror, in the case of meeting the transportation condition and the transportation priority, and in the case of the same effective flow upper limit, the decision is determined according to the load balancing mode.
There are generally two load balancing modes, i.e., a 0 mode and a 1 mode. The route of the virtual decision network to make decisions will also be different for different modes.
Example 2
Based on the above embodiment, the load balancing decision is constructed based on a load balancing module according to a plurality of carrying conditions and an upper limit of effective traffic of each carrying priority class based on the corresponding service class; wherein the virtual decision network comprises a plurality of virtual area networks, each corresponding to a different one of the virtual area network tags, and the load balancing decision considers the virtual area networks based on each of the virtual area network tags, wherein each of the virtual area networks is defined by a corresponding transport priority class, wherein each of the plurality of shunting points corresponds to one of the virtual area network tags.
In particular, load balancing builds on existing network architectures, which provides an inexpensive, efficient, transparent way to extend the bandwidth of network devices and servers, increase throughput, enhance network data processing capabilities, and increase network flexibility and availability.
Load Balance means that the Load Balance is shared by a plurality of operation units to be executed, such as a Web server, an FTP server, an enterprise key application server and other key task servers, so as to jointly complete work tasks.
The present invention lends the concept of load balancing to a virtual decision network. Load balancing in a virtual decision network has the same characteristics as load balancing in other networks. However, the virtual decision network of the present invention is a non-existent network and is only used for decision simulation.
Example 3
Based on the above embodiment, the load balancing module is a centralized module, and the load balancing decision is formed by the centralized module.
Example 4
Based on the above embodiment, when the corresponding transport priority class of one of the vlan tags is mapped to a fixed bitrate transport type, the load balancing decision is composed by the load balancing module of one of the traffic nodes, which includes: reserving and partitioning the traffic cap for each of the traffic nodes based on the bit rate to obtain a plurality of simultaneous connections suitable for reservation; and allowing a new fixed bitrate requirement only if a portion of the upper limit of traffic equal to the bitrate is valid and assigning the portion of the upper limit of traffic to a desired object.
Specifically, the amount of fluid flowing through an effective cross section of a closed pipeline or an open channel per unit time is referred to as instantaneous flow. When the amount of fluid is expressed in volume, it is called the volumetric flow; when fluid volume is expressed as mass, it is referred to as mass flow. The volume of fluid flowing through a section of pipe per unit time is referred to as the volumetric flow rate of that cross section.
Example 5
On the basis of the previous embodiment, after the sensor acquires the data in real time, the data is preprocessed, and then the processed data is sent to the virtual decision network.
Example 6
As shown in fig. 2, on the basis of the previous embodiment, the method for preprocessing data by the sensor includes: converting the acquired data into a phase space, and then carrying out differential filtering on the data in the phase space, wherein the differential filtering refers to directly acting a differential filtering signal as a filter on the data to filter noise data; then, data preprocessing is carried out on the data with the noise data filtered; the differential filtered signal is generated by a differential sequence.
Specifically, a sensor (known by the english name: transducer/sensor) is a detection device, which can sense measured information and convert the sensed information into an electrical signal or other information in a required form according to a certain rule for output, so as to meet the requirements of information transmission, processing, storage, display, recording, control and the like.
The sensor features include: miniaturization, digitalization, intellectualization, multifunction, systematization and networking. The method is the first link for realizing automatic detection and automatic control. The existence and development of the sensor enable the object to have the senses of touch, taste, smell and the like, and the object slowly becomes alive. Generally, the sensor is classified into ten categories, i.e., a thermosensitive element, a photosensitive element, a gas-sensitive element, a force-sensitive element, a magnetic-sensitive element, a humidity-sensitive element, a sound-sensitive element, a radiation-sensitive element, a color-sensitive element, and a taste-sensitive element, according to their basic sensing functions.
Example 7
On the basis of the above embodiment, the data of the converted phase space is represented as: data (T) ═ Asincos (cos ω 0T + cosB ═ c (T) dt), 0 ≦ T; wherein the modulation signal c (t) is: acos (ω 0t + B |) dt; wherein T is the time length of s (T), ω 0 is the center frequency, B is the modulation index, a is the amplitude, and c (T) is the data acquired by the sensor.
Specifically, the displacement sensor is also called a linear sensor, and is a sensor for converting displacement into electric quantity. The displacement sensor is a linear device belonging to metal induction, and is divided into an inductive displacement sensor, a capacitive displacement sensor, a photoelectric displacement sensor, an ultrasonic displacement sensor and a Hall displacement sensor, wherein the sensor is used for converting various measured physical quantities into electric quantities.
In such a conversion process, many physical quantities (such as pressure, flow, acceleration, etc.) are often required to be converted into displacement, and then the displacement is converted into an electrical quantity. Displacement sensors are therefore an important basic class of sensors. In the production process, the measurement of displacement is generally divided into measurement of physical size and mechanical displacement. Mechanical displacements include linear and angular displacements. The displacement sensor can be divided into an analog type and a digital type according to the conversion form of the measured variable. The analog type can be classified into a physical type (e.g., self-power generation type) and a structural type. The common displacement sensors are mostly of analog structure type, and include potentiometer type displacement sensors, inductive type displacement sensors, synchro machines, capacitive type displacement sensors, eddy current type displacement sensors, hall type displacement sensors, and the like. An important advantage of digital displacement sensors is the ease of directly feeding the signals into the computer system. The sensor is developed rapidly and is increasingly widely applied.
Example 8
On the basis of the above embodiment, the differential sequence is: sn+1＝cos(tanωarccos(Sn))，-1＜SnLess than 1, when the parameter value S is takennTo 0.65, a first seed S is given0Generating a difference sequence as 5; on the basis, according to the formula: s (t) ═ Acos (sin ω 0t + cosB ═ Sn+1dt) to generate a differential filter signal, wherein T is greater than or equal to 0 and less than or equal to T; wherein the parameters T, omega 0 and B can be adjusted according to the actual conversion rate, the error rate and the conversion distance; time of dayThe length T is between 2.0s and 10.0s, the central frequency omega 0 is less than 1000Hz, and the signal bandwidth B is between 60Hz and 290 Hz.
Example 9
On the basis of the above embodiment, the data preprocessing on the data after the noise data is filtered includes: removing the unique attribute, processing missing values and abnormal value detection and processing; and carrying out data specification processing, including: removing an average value, calculating a covariance matrix, calculating an eigenvalue and an eigenvector of the covariance matrix, sorting the eigenvalues from large to small, reserving the largest eigenvector, and converting data into a new space constructed by the eigenvector; finally, new processed data are obtained, and the data are irrelevant pairwise, but the original information is kept.
Example 10
A high-speed carrying system decision-making device based on intelligent sensing.
Specifically, in the prior art, when making an intelligent decision, the decision is often made by pre-programming software. And parameters for decision making are set in the pre-programmed software. Compared with manual decision scheduling, the method has the advantages that the efficiency can be remarkably improved, but in actual situations, due to the change of environment and running state, a single parameter is difficult to adapt to decisions of various situations, so that the accuracy and efficiency of decisions are difficult to achieve higher levels.
The method abstracts the mapping of the carrying system into the virtual decision network, senses the data in the carrying system in real time through the sensor in the carrying system, and performs decision optimization on the carrying system by combining the set carrying conditions, carrying priority and other factors, so that the carrying system can work with the maximum efficiency, and the method has the advantages of high intelligent degree, high decision efficiency and high decision making accuracy.
Specifically, the method abstracts the mapping of the carrying system into a virtual decision network, senses data in the carrying system in real time through a sensor in the carrying system, combines set carrying conditions, carrying priority and other factors to carry out decision optimization on the carrying system, enables the carrying system to work with the maximum efficiency, and has the advantages of high intelligent degree, high decision efficiency and high decision making accuracy. The method is mainly realized by the following steps: 1. and (3) mapping construction of a virtual decision network: the method takes a transportation track and a sensor of a handling system as a bluebook, and constructs a virtual decision network in a one-to-one mapping relationship; the transportation track is mapped to be a connecting line of the virtual decision network, and the sensor is mapped to be a shunting point of the virtual decision network; setting a preset value, and grouping one or more adjacent shunting points with the number equal to the preset value to obtain a shunting point group, wherein the shunting point group is used as a flow node of a virtual decision network; the data acquired by the sensor in real time is also transmitted to the virtual decision network in real time; the transport system can be accurately simulated through the constructed virtual decision network, and then decision is made on the transport system through the virtual decision network, so that the decision efficiency is higher; 2. the decision method of the virtual decision network comprises the following steps: the invention carries out a carrying decision through a load balancing decision, wherein the load balancing decision is constructed based on a load balancing module according to a plurality of carrying conditions and the upper limit of effective flow of each carrying priority class based on the corresponding service class; wherein the virtual decision network comprises a plurality of virtual area networks, each corresponding to a different one of the virtual area network tags, and the load balancing decision considers the virtual area networks based on each of the virtual area network tags, wherein each of the virtual area networks is defined by a corresponding transport priority class, wherein each of the plurality of shunting points corresponds to one of the virtual area network tags; therefore, the carrying system can operate at the maximum efficiency, and the system congestion cannot be caused; 3. the data denoising method comprises the steps of performing data denoising through data filtering, converting acquired data into a phase space in the denoising process, and then performing differential filtering on the data in the phase space, wherein the differential filtering refers to directly acting a differential filtering signal as a filter on the data to filter noise data; then, data preprocessing is carried out on the data with the noise data filtered; the differential filtering signal is generated through a differential sequence, so that the result obtained by subsequent decision and processing can be more accurate
The above description is only an embodiment of the present invention, but not intended to limit the scope of the present invention, and any structural changes made according to the present invention should be considered as being limited within the scope of the present invention without departing from the spirit of the present invention.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process and related description of the system described above may refer to the corresponding process in the foregoing method embodiments, and will not be described herein again.
It should be noted that, the system provided in the foregoing embodiment is only illustrated by dividing the functional modules, and in practical applications, the functions may be distributed by different functional modules according to needs, that is, the modules or steps in the embodiment of the present invention are further decomposed or combined, for example, the modules in the foregoing embodiment may be combined into one module, or may be further split into multiple sub-modules, so as to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the modules or steps, and are not to be construed as unduly limiting the present invention.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes and related descriptions of the storage device and the processing device described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
Those of skill in the art would appreciate that the various illustrative modules, method steps, and modules described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that programs corresponding to the software modules, method steps may be located in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. To clearly illustrate this interchangeability of electronic hardware and software, various illustrative components and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as electronic hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The terms "first," "second," and the like are used for distinguishing between similar elements and not necessarily for describing or implying a particular order or sequence.
The terms "comprises," "comprising," or any other similar term are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
So far, the technical solutions of the present invention have been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of the present invention is obviously not limited to these specific embodiments. Equivalent changes or substitutions of related technical features can be made by those skilled in the art without departing from the principle of the invention, and the technical scheme after the changes or substitutions can fall into the protection scope of the invention.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention.
Claims (10)
1. The decision method of the high-speed handling system based on intelligent perception is characterized by comprising the following steps:
step 1: arranging a plurality of sensors which are randomly distributed in a space with a fixed size, and mutually connecting the sensors to form a sensor network; meanwhile, a transport track is built by taking a connection route of sensors in the sensor network as a bluebook, and a carrying system is built; each connecting node of the transportation track is a sensor;
step 2: the sensor nodes sense and acquire the operation data of the carrying system in real time; the operational data includes: the running speed of the conveyed objects and the number of the conveyed objects;
and step 3: constructing a virtual decision network by taking a transportation track and a sensor of a carrying system as blueprints and using a one-to-one mapping relation; the transportation track is mapped to be a connecting line of the virtual decision network, and the sensor is mapped to be a shunting point of the virtual decision network; setting a preset value, and grouping one or more adjacent shunting points with the number equal to the preset value to obtain a shunting point group, wherein the shunting point group is used as a flow node of a virtual decision network; the data acquired by the sensor in real time is also transmitted to the virtual decision network in real time;
and 4, step 4: setting a plurality of transport conditions, a plurality of transport priority classes and a plurality of effective flow upper limits in a virtual decision network; the conveying condition is defined as conveying time and conveying speed, and the values of the conveying time and the conveying speed are determined by presetting; the transport priority is defined as the priority level of transport, which includes three priority levels, respectively: the priority level of the third level is highest, and the priority level of the first level is lowest; each priority level corresponds to an effective flow upper limit;
and 5: the virtual decision network acts on the shunting point through a load balancing decision based on the carrying condition, the carrying priority category and the effective flow upper limit, so that each flow node keeps a stable state; the steady state is defined as the incoming flow being equal to the outgoing flow at the same time.
2. The method of claim 1, wherein the load balancing decision is constructed based on load balancing modules based on a plurality of handling conditions and an upper limit of effective traffic for each handling priority class based on a corresponding class of service; wherein the virtual decision network comprises a plurality of virtual area networks, each corresponding to a different one of the virtual area network tags, and the load balancing decision considers the virtual area networks based on each of the virtual area network tags, wherein each of the virtual area networks is defined by a corresponding transport priority class, wherein each of the plurality of shunting points corresponds to one of the virtual area network tags.
3. The method of claim 2, wherein the load balancing module is a centralized module through which the load balancing decision is made.
4. The method of claim 3 wherein the load balancing decision is made up of the load balancing module of one of the traffic nodes when the corresponding transport priority class of one of the VLAN tags maps to a fixed bitrate transport type, comprising: reserving and partitioning the traffic cap for each of the traffic nodes based on the bit rate to obtain a plurality of simultaneous connections suitable for reservation; and allowing a new fixed bitrate requirement only if a portion of the upper limit of traffic equal to the bitrate is valid and assigning the portion of the upper limit of traffic to a desired object.
5. The system of claim 4, wherein after the sensor acquires the data in real time, the sensor performs data preprocessing on the data and then sends the processed data to the virtual decision network.
6. The method of claim 5, wherein the method of data pre-processing by the sensor comprises: converting the acquired data into a phase space, and then carrying out differential filtering on the data in the phase space, wherein the differential filtering refers to directly acting a differential filtering signal as a filter on the data to filter noise data; then, data preprocessing is carried out on the data with the noise data filtered; the differential filtered signal is generated by a differential sequence.
7. The method of claim 6, wherein the data of the converted phase space is represented as: data (T) ═ Asincos (cos ω 0T + cosB ═ c (T) dt), 0 ≦ T; wherein the modulation signal c (t) is: acos (ω 0t + B |) dt; wherein T is the time length of s (T), ω 0 is the center frequency, B is the modulation index, a is the amplitude, and c (T) is the data acquired by the sensor.
8. The method of claim 7, wherein the differential sequence is: sn+1＝cos(tanωarccos(Sn))，-1＜SnLess than 1, when the parameter value S is takennTo 0.65, a first seed S is given0Generating a difference sequence as 5; on the basis, according to the formula: s (t) ═ Acos (sin ω 0t + cosB ═ Sn+1dt) to generate a differential filter signal, wherein T is greater than or equal to 0 and less than or equal to T; wherein the parameters T, omega 0 and B can be adjusted according to the actual conversion rate, the error rate and the conversion distance; the time length T is between 2.0s and 10.0s, the central frequency omega 0 is less than 1000Hz, and the signal bandwidth B is between 60Hz and 290 Hz.
9. The method of claim 8, wherein the pre-processing the data after filtering the noise data comprises: removing the unique attribute, processing missing values and abnormal value detection and processing; and carrying out data specification processing, including: removing an average value, calculating a covariance matrix, calculating an eigenvalue and an eigenvector of the covariance matrix, sorting the eigenvalues from large to small, reserving the largest eigenvector, and converting data into a new space constructed by the eigenvector; finally, new processed data are obtained, and the data are irrelevant pairwise, but the original information is kept.
10. A high speed handling system decision making device based on intelligent sensing for implementing the method of any one of claims 1 to 9.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011617320.3A CN112866337A (en) | 2020-12-30 | 2020-12-30 | High-speed carrying system decision method and device based on intelligent sensing |
| CN202111538525.7A CN113938507B (en) | 2020-12-30 | 2021-12-16 | High-speed carrying system decision method and device based on intelligent sensing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011617320.3A CN112866337A (en) | 2020-12-30 | 2020-12-30 | High-speed carrying system decision method and device based on intelligent sensing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112866337A true CN112866337A (en) | 2021-05-28 |
Family
ID=75998810
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011617320.3A Pending CN112866337A (en) | 2020-12-30 | 2020-12-30 | High-speed carrying system decision method and device based on intelligent sensing |
| CN202111538525.7A Active CN113938507B (en) | 2020-12-30 | 2021-12-16 | High-speed carrying system decision method and device based on intelligent sensing |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111538525.7A Active CN113938507B (en) | 2020-12-30 | 2021-12-16 | High-speed carrying system decision method and device based on intelligent sensing |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN112866337A (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1604551B (en) * | 2003-09-10 | 2012-04-25 | 达创科技股份有限公司 | Qos based load-balance policy for WLAN |
| CN106572513A (en) * | 2016-10-17 | 2017-04-19 | 宁波深路信息科技有限公司 | Wireless sensor routing algorithm based on fuzzy multi-attribute decision |
| CN106843890B (en) * | 2017-02-04 | 2020-04-28 | 北京信息科技大学 | Sensor network, node and operation method thereof based on intelligent decision |
| CN107820276B (en) * | 2017-10-27 | 2019-09-20 | 北京邮电大学 | A kind of wireless sensor method for allocating tasks |
| CN111698703B (en) * | 2020-05-25 | 2024-02-20 | 国网河北省电力有限公司石家庄供电分公司 | Network reliability optimization method based on service priority and load balancing |
-
2020
- 2020-12-30 CN CN202011617320.3A patent/CN112866337A/en active Pending
-
2021
- 2021-12-16 CN CN202111538525.7A patent/CN113938507B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113938507A (en) | 2022-01-14 |
| CN113938507B (en) | 2022-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106326585B (en) | Prediction analysis method and device based on Bayesian Network Inference | |
| Ge et al. | Distributed fault detection over sensor networks with Markovian switching topologies | |
| CN110390246A (en) | A kind of video analysis method in side cloud environment | |
| Ahmed et al. | Distributed fog computing for Internet of Things (IOT) based ambient data processing and analysis | |
| EP3349152A1 (en) | Classifying data | |
| CN113225359A (en) | Safety flow analysis system based on brain-like calculation | |
| Rúbio et al. | Industrial IoT devices and cyber-physical production systems: Review and use case | |
| CN115686868B (en) | Cross-node-oriented multi-mode retrieval method based on federated hash learning | |
| Shoukat et al. | Smart home for enhanced healthcare: exploring human machine interface oriented digital twin model | |
| Kim et al. | Deep RNN-based network traffic classification scheme in edge computing system | |
| CN116011507A (en) | Rare fault diagnosis method for fusion element learning and graph neural network | |
| Wang et al. | Ensemble clustering-based fault diagnosis method incorporating traditional and deep representation features | |
| CN113938507B (en) | High-speed carrying system decision method and device based on intelligent sensing | |
| CN114611636B (en) | Method for realizing measured value analysis by fusing information of various sensors | |
| CN115001935A (en) | Hierarchical layout method of large-scale network | |
| Chakraborty et al. | Application of soft computing techniques over hard computing techniques: A survey | |
| Peniak et al. | The redundant virtual sensors via edge computing | |
| Badidi | A fog node architecture for real-time processing of urban IoT data streams | |
| Malinowski et al. | Analysis of district heating network monitoring by neural networks classification | |
| Ahmed et al. | Feedback learning in software-defined mobile network for resource aware load balancing under fault tolerance conditions | |
| Alexandrov et al. | Method for modeling and simulation of parallel data integration processes in Wireless Sensor Networks | |
| Sungur et al. | Labview and embedded system based new iot solution for industrial applications | |
| CN117094381B (en) | Multi-mode federal collaboration method taking high-efficiency communication and individuation into consideration | |
| Han | Framework for real-time traffic management with case studies | |
| Saini et al. | Enhancing qos of network traffic based on 5g wireless networking using machine learning approaches |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210528 |