CN114912852A - Abnormity monitoring and early warning system for storage tank of refrigeration bin - Google Patents

Abnormity monitoring and early warning system for storage tank of refrigeration bin Download PDF

Info

Publication number
CN114912852A
CN114912852A CN202210838504.5A CN202210838504A CN114912852A CN 114912852 A CN114912852 A CN 114912852A CN 202210838504 A CN202210838504 A CN 202210838504A CN 114912852 A CN114912852 A CN 114912852A
Authority
CN
China
Prior art keywords
data
point
column
detection matrix
element data
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
CN202210838504.5A
Other languages
Chinese (zh)
Other versions
CN114912852B (en
Inventor
苏广荣
赵阳
赵肖恺
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.)
Shandong Xinya Equipment Manufacturing Co ltd
Original Assignee
Shandong Xinya Equipment Manufacturing 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 Shandong Xinya Equipment Manufacturing Co ltd filed Critical Shandong Xinya Equipment Manufacturing Co ltd
Priority to CN202210838504.5A priority Critical patent/CN114912852B/en
Publication of CN114912852A publication Critical patent/CN114912852A/en
Application granted granted Critical
Publication of CN114912852B publication Critical patent/CN114912852B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
    • G01K1/00—Details of thermometers not specially adapted for particular types of thermometer
    • G01K1/02—Means for indicating or recording specially adapted for thermometers
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
    • G01K13/00—Thermometers specially adapted for specific purposes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083—Shipping
    • G06Q10/0832—Special goods or special handling procedures, e.g. handling of hazardous or fragile goods
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/18—Status alarms
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Operations Research (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Theoretical Computer Science (AREA)
  • Educational Administration (AREA)
  • Emergency Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Devices That Are Associated With Refrigeration Equipment (AREA)

Abstract

The invention relates to the technical field of data identification, in particular to an abnormity monitoring and early warning system for a refrigerated storage tank, which comprises a data acquisition module and a data processing module, wherein the data acquisition module is used for acquiring temperature time sequence data of the refrigerated storage tank to be monitored in a specified time period and sending the temperature time sequence data to the data processing module, and the data processing module is used for receiving the temperature time sequence data and realizing the following steps: according to the temperature time sequence data, determining a detection matrix corresponding to the temperature time sequence data, further obtaining each suspicious noise point of the detection matrix, further determining the possibility that each suspicious noise point is a real noise point, and further determining each suspected abnormal point of the detection matrix, thereby judging whether each suspected abnormal point of the detection matrix is a real abnormal point, and realizing the abnormal monitoring of the refrigerated storage box. The invention utilizes the data identification technology to detect the real abnormal points in the temperature time sequence data, thereby improving the accuracy of monitoring the abnormality of the storage tank of the refrigeration bin.

Description

Abnormity monitoring and early warning system for storage tank of refrigeration bin
Technical Field
The invention relates to the technical field of data identification, in particular to an abnormity monitoring and early warning system for a refrigerating storage tank.
Background
Refrigerated storage bins are commonly used to store and utilize cargo for transportation. Along with the development of society, storage box uses more and more extensively in the storage commodity circulation, because people's cold storage requirement and the time requirement to goods such as lettuce are more and more strict, correspondingly, also more and more high to the cold storage effect requirement of equipment such as storage box of its transportation usefulness. When the storage box of the refrigeration bin has abnormal conditions, the refrigeration time is reduced, and the quality of refrigerated goods is influenced. The mode that traditional fridge transportation management mode adopted the manual work to patrol and examine regularly and copy data not only consumes a large amount of manpowers, material resources, is difficult to in time know fridge real-time condition moreover, has increased the possibility of goods harm, and it is big to patrol and examine the work load simultaneously, and man-machine cross operation risk and goods damage risk are higher, lead to the abnormal monitoring of cold-stored storage tank and inaccurate.
Disclosure of Invention
In order to solve the problem of inaccurate abnormality monitoring of the conventional refrigerating storage tank, the invention aims to provide an abnormality monitoring and early warning system for the refrigerating storage tank.
The invention provides an abnormity monitoring and early warning system for a refrigerated storage tank, which comprises a data acquisition module and a data processing module, wherein the data acquisition module is used for acquiring temperature time sequence data of the refrigerated storage tank to be monitored in a specified time period and sending the acquired temperature time sequence data of the refrigerated storage tank to be monitored in the specified time period to the data processing module, the data processing module is used for receiving the temperature time sequence data of the refrigerated storage tank to be monitored in the specified time period sent by the data acquisition module, and the following steps are realized:
determining a detection matrix corresponding to the temperature time sequence data in the specified time period according to the temperature time sequence data of the storage tank of the refrigeration bin to be monitored in the specified time period;
determining a stability index corresponding to each row element data in each row vector according to each row element data in each row vector of the detection matrix, and further obtaining each suspicious noise point of the detection matrix;
determining an overall relevance index corresponding to each column element data in each column vector of the detection matrix according to each column element data in each column vector of the detection matrix, and further determining an overall relevance index corresponding to each suspicious noise point of the detection matrix;
acquiring the number of suspicious noise points in a column vector of each suspicious noise point, determining the possibility that each suspicious noise point is a real noise point according to the number of suspicious noise points in the column vector of each suspicious noise point and an overall correlation index corresponding to each suspicious noise point, and further determining each suspected abnormal point of the detection matrix;
and judging whether each suspected abnormal point of the detection matrix is a real abnormal point or not according to each suspected abnormal point of the detection matrix and preset normal temperature data, and if a certain suspected abnormal point is a real abnormal point, early warning is carried out.
Further, the step of determining an overall relevance indicator corresponding to each column element data in each column vector comprises:
determining a data point set corresponding to each column element data according to each column element data in each column vector of the detection matrix;
determining a Gaussian mixture model of the data point set according to the data point set corresponding to each column element data, and further determining three model parameters of the Gaussian mixture model, wherein the three model parameters are respectively as follows: the number of single Gaussian functions, the mean parameter and the variance parameter;
determining element characterization vectors corresponding to each column element data according to three model parameters of a Gaussian mixture model of the data point set;
and determining an overall relevance index corresponding to each column element data in each column vector according to each column element data and the corresponding element characterization vector.
Further, the step of determining the data point set corresponding to each column element data includes:
and taking each column element data in each column vector of the detection matrix as a center, selecting a plurality of data points in the vertical direction of the center, and forming a data point set by the center and a plurality of data points corresponding to the center to obtain a data point set corresponding to each column element data.
Further, the calculation formula for determining the overall correlation index corresponding to each column element data in each column vector is as follows:
Figure 100002_DEST_PATH_IMAGE001
wherein the content of the first and second substances,
Figure 201716DEST_PATH_IMAGE002
for the second in each column vectorjThe overall relevance indicators corresponding to the individual column element data,
Figure 208462DEST_PATH_IMAGE003
for the second in each column vectorjThe element characterization vector corresponding to each column element data and the second element in each column vectoriThe cosine similarity between the element characterization vectors corresponding to the column element data,
Figure 854469DEST_PATH_IMAGE004
for the second in each column vectorjColumn element data andithe spatial distance between the individual column element data,Qthe number of column element data in each column vector.
Further, the step of determining the detection matrix corresponding to the temperature time sequence data in the specified time period comprises:
determining the data cutting length of the temperature time sequence data in the specified time period according to the data quantity of the temperature time sequence data of the refrigerating storage box to be monitored in the specified time period;
and determining each sub-temperature time sequence data according to the temperature time sequence data and the data cutting length of the refrigerating storage box to be monitored in the specified time period, and constructing a detection matrix corresponding to the temperature time sequence data in the specified time period by taking the sub-temperature time sequence data as a column vector.
Further, a calculation formula for determining the stability index corresponding to each row element data in each row vector is as follows:
Figure 247273DEST_PATH_IMAGE005
wherein the content of the first and second substances,
Figure 190565DEST_PATH_IMAGE006
for the second in each row vectorjThe stability index corresponding to the element data of each line,
Figure 26934DEST_PATH_IMAGE007
for the first in each row vectorjThe data of the elements of one line is,
Figure 393193DEST_PATH_IMAGE008
for the first in each row vector
Figure 887891DEST_PATH_IMAGE009
-1 line element data of the image data,
Figure 672307DEST_PATH_IMAGE010
for the second in each row vector
Figure 460003DEST_PATH_IMAGE009
The number of +1 row element data,
Figure 77673DEST_PATH_IMAGE011
in order to be a hyper-parameter,hfor the number of row element data in each row vector,
Figure 828592DEST_PATH_IMAGE012
to find the minimum function.
Further, the step of obtaining each suspected noise point of the detection matrix further includes:
and if the stability index corresponding to any row element data of the detection matrix is smaller than the stability threshold value, judging the row element data to be suspicious noise points, and otherwise, judging the row element data to be normal temperature data.
Further, the calculation formula for determining the possibility that each suspected noise point is a true noise point is as follows:
Figure 982361DEST_PATH_IMAGE013
wherein the content of the first and second substances,wfor the likelihood that each suspect noise point is a true noise point,rfor the overall correlation index corresponding to each suspect noise point,Mthe number of suspect noise points in the column element data set corresponding to each suspect noise point.
Further, the step of determining each suspected outlier of the detection matrix further comprises:
if the probability that any suspicious noise point of the detection matrix is a real noise point is larger than a preset probability threshold, the suspicious noise point is judged not to be a suspected abnormal point, otherwise, the suspicious noise point is judged to be a suspected abnormal point.
Further, the step of determining whether each suspected abnormal point of the detection matrix is a real abnormal point includes:
calculating the difference value of each suspected abnormal point and preset normal temperature data according to each suspected abnormal point and preset normal temperature data of the detection matrix;
and judging whether each suspected abnormal point of the detection matrix is a real abnormal point or not according to the difference value of each suspected abnormal point and preset normal temperature data, when the difference value of any one suspected abnormal point and the preset normal temperature data is larger than a temperature difference threshold value, judging that the suspected abnormal point is the real abnormal point, and otherwise, judging that the suspected abnormal point is not the real abnormal point.
The invention has the following beneficial effects:
according to the method, the temperature time sequence data of the storage tank of the refrigeration bin to be monitored in the specified time period are obtained, and the detection matrix corresponding to the temperature time sequence data in the specified time period is determined by using a data identification technology. Each column vector of the detection matrix can reflect local information of the temperature data of the refrigerating storage box, local characteristic information corresponding to each column vector is extracted, the change characteristics of the temperature data corresponding to continuous time sequences can be analyzed conveniently, each row vector of the detection matrix can represent the temperature data obtained by sampling at equal intervals, the local characteristic information corresponding to each row vector is extracted, the whole temperature change development trend of the refrigerating storage box can be analyzed conveniently, and the detection matrix can be determined to accurately monitor the abnormal condition of the refrigerating storage box; and determining a stability index corresponding to each row element data in each row vector according to each row element data in each row vector of the detection matrix, and obtaining each suspicious noise data in the detection matrix according to the stability index corresponding to each row element data, the abnormal data of the refrigerating storage tank and the characteristics of the noise data. The temperature time sequence data in a specified time period are analyzed through the stability index, so that normal temperature data and suspicious noise data in the temperature time sequence data are distinguished, and the monitoring accuracy of the storage tank of the refrigeration bin can be effectively improved through primary screening; and determining the overall correlation index corresponding to each suspicious noise point according to each column element data in each column vector of the detection matrix and each suspicious noise point in the detection matrix, and further determining the suspected abnormal point in each suspicious noise point, thereby judging whether each suspected abnormal point of the detection matrix is a real abnormal point. Through the analysis, discern the true abnormal point in the temperature time sequence data in the regulation period, the early warning will in time be made to the system, and the cold-stored abnormal situation appears in the cold-stored storage tank of suggestion relevant detection personnel, in time carries out corresponding maintenance to this cold-stored storage tank, avoids appearing the quality problem because of abnormal situation too seriously leads to cold-stored article.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic diagram of an anomaly monitoring and warning system for a refrigerated storage tank according to the present invention;
fig. 2 is a flowchart of implementation steps of a data processing module in the anomaly monitoring and early warning system in the embodiment of the present invention.
Detailed Description
To further explain the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description of the embodiments, structures, features and effects of the technical solutions according to the present invention will be given with reference to the accompanying drawings and preferred embodiments. In the following description, different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The embodiment provides an abnormity monitoring and early warning system for a refrigerated storage tank, the structural schematic diagram of the system is shown in fig. 1, and the system comprises a data acquisition module and a data processing module, wherein the data acquisition module is used for acquiring temperature time sequence data of the refrigerated storage tank to be monitored in a specified time period in real time and sending the acquired temperature time sequence data of the refrigerated storage tank to be monitored in the specified time period to the data processing module.
In this embodiment, the condition of the storage tank to be monitored is monitored and analyzed based on the temperature time sequence data of the storage tank to be monitored. The temperature time sequence data of the refrigerating storage box to be monitored in a specified time period is collected in real time through a temperature sensor, and the temperature time sequence data is recorded asTTemperature time series dataTFor the temperature data of the storage tank to be monitored at different times, the specified time interval is set to 1 minute and the collection frequency is 1msThe temperature time sequence data is collected once every 1 millisecond, and the specified time period and the collection frequency in the temperature time sequence data collection process can be set by an implementer according to the actual situation. The types of the temperature sensors are various, an implementer can select the temperature sensors according to actual conditions, and common temperature sensors comprise a bimetallic thermometer, a glass liquid thermometer, a thermocouple and the like.
It should be noted that, with the wide application and research of low temperature technology in national defense engineering, space technology, metallurgy, electronics, food, medicine and petrochemical sectors, measurement 120KLow temperature thermometers for measuring temperatures below 1.6-300 deg.C have been developed, such as low temperature gas thermometers, vapor pressure thermometers, acoustic thermometers, paramagnetic salt thermometers, quantum thermometers, low temperature thermal resistors, low temperature thermocouples, and the likeKA cryogenic temperature within the range.
The data processing module is used for receiving the temperature time sequence data of the refrigerated storage tank to be monitored in the specified time period, which is sent by the data acquisition module, and the flow chart of the implementation steps of the data processing module in the abnormity monitoring and early warning system is shown in fig. 2, and the following steps are implemented:
(1) and determining a detection matrix corresponding to the temperature time sequence data in the specified time period according to the temperature time sequence data of the refrigerating storage box to be monitored in the specified time period.
First, it should be noted that, in order to facilitate subsequent analysis of local changes and long-term development trends of temperature time series data, the present embodiment constructs a detection matrix corresponding to the temperature time series data within a specified time period, and includes the following steps:
(1-1) determining the data cutting length of the temperature time sequence data in the specified time period according to the data quantity of the temperature time sequence data of the refrigerated storage tank to be monitored in the specified time period.
In this embodiment, the data amount of the temperature time series data of the storage tank to be monitored in a specified time period is counted and recorded asLThe data cutting length of the temperature time sequence data in the specified time period is determined by the data volume of the temperature time sequence data in the specified time period, namely, the temperature time sequence data in the specified time period is divided into each sub-temperature time sequence data with the fixed data length on the basis that the data cutting length is not larger than the data volume of the temperature time sequence data, and of course, an implementer can set the data cutting length by himself. For example, the amount of data of temperature time series data collected in a prescribed time periodLIs a number of 12, and is,
Figure 645686DEST_PATH_IMAGE014
then the data cut length can be 1, 2, 3, 4, 6, 12, the data cut length is noted asQ。
And (1-2) determining each sub-temperature time sequence data according to the temperature time sequence data and the data cutting length of the refrigerating storage box to be monitored in the specified time period, taking the sub-temperature time sequence data as a column vector, and constructing a detection matrix corresponding to the temperature time sequence data in the specified time period.
In this embodiment, the respective sub-temperature time series data are determined by the temperature time series data of the refrigerated storage tank to be monitored in a prescribed period and the data cutting length, for example, when the data amount of the temperature time series data in the prescribed periodLIs a number of 12, and is,
Figure 252117DEST_PATH_IMAGE014
length of data cutQWhen the time is 4, determining each sub-temperature time sequence data, wherein each sub-temperature time sequence data is
Figure DEST_PATH_IMAGE015
、
Figure 226633DEST_PATH_IMAGE016
And
Figure 234909DEST_PATH_IMAGE017
. The sub-temperature time sequence data are used as column vectors of a detection matrix, and the detection matrix corresponding to the temperature time sequence data in a specified time period is constructed according to each column vector of the detection matrix, wherein the detection matrix specifically comprises the following components:
Figure 115140DEST_PATH_IMAGE018
wherein the content of the first and second substances,Xa detection matrix corresponding to the temperature time sequence data in a specified time period,Lthe data amount of the temperature time series data within the prescribed period, that is, the sequence length of the temperature time series data within the prescribed period,Qfor cutting the length of the data of the temperature time sequence data in a specified time period, and thenIn a length ofQThe local characteristics of the temperature data are analyzed in the sub-temperature time series data.
It should be noted that each column vector in the detection matrix can reflect local information of the temperature time sequence data of the storage tank of the refrigeration bin to be detected, and meanwhile, the change condition of the temperature data of a continuous time sequence is conveniently analyzed; each row vector in the detection matrix can represent equally spaced temperature time sequence data, the overall development trend of the temperature time sequence data of the refrigerated storage tank to be monitored can be analyzed, and the condition of the temperature time sequence data can be conveniently detected from the whole; through the analysis of the detection matrix corresponding to the temperature time sequence data in the specified time period, the abnormal condition of the storage box of the refrigeration bin to be detected can be accurately detected.
(2) And determining a stability index corresponding to each row element data in each row vector according to each row element data in each row vector of the detection matrix, and further obtaining each suspicious noise point of the detection matrix.
First, it should be noted that, in general, most of noise points in the data acquisition process are represented as isolated points, while more of abnormal points are accumulated in time relative to noise points, that is, abnormal points appearing in the temperature time series data have the characteristic of time series continuity, and each column vector of the detection matrix can represent the change condition of the temperature data in a continuous time series. Therefore, by analyzing the row element data in each row vector of the detection matrix, each suspected noise point of the detection matrix can be obtained, which includes the steps of:
and (2-1) determining the stability index corresponding to each row element data in each row vector according to each row element data in each row vector of the detection matrix.
In the present embodiment, each row vector of the detection matrix is
Figure 241490DEST_PATH_IMAGE019
,
Figure 865370DEST_PATH_IMAGE020
,
Figure DEST_PATH_IMAGE021
,
Figure 931415DEST_PATH_IMAGE022
，GTo detect the number of row vectors in the matrix,
Figure 668033DEST_PATH_IMAGE019
to detect the 1 st row vector of the matrix,
Figure 45794DEST_PATH_IMAGE023
，
Figure 411047DEST_PATH_IMAGE024
to detect the 1 st row element data of the 1 st row vector in the matrix. By analyzing each row element data in each row vector of the detection matrix, a stability index corresponding to each row element data can be obtained, and the calculation formula is as follows:
Figure 895380DEST_PATH_IMAGE005
wherein the content of the first and second substances,
Figure 632261DEST_PATH_IMAGE006
for the second in each row vectorjThe stability index corresponding to the element data of each line,
Figure 982471DEST_PATH_IMAGE007
for the second in each row vectorjThe number of the individual line elements is the data,
Figure 430376DEST_PATH_IMAGE008
for the first in each row vector
Figure 752904DEST_PATH_IMAGE009
-1 line element data of the image data,
Figure 660686DEST_PATH_IMAGE010
for the second in each row vector
Figure 498192DEST_PATH_IMAGE009
The number of +1 row element data,
Figure 752718DEST_PATH_IMAGE011
in order to be a hyper-parameter,hfor the number of row element data in each row vector, the number of row element data in each row vector is equal,
Figure 179021DEST_PATH_IMAGE012
to find the minimum function.
It should be noted that, for the stability indicator of the first row element data and the last row element data in each row vector, since there is no other row element data before the first row element data in each row vector, the stability indicator corresponding to the first row element data in each row vector can be calculated by the first row element data and the second row element data, that is, when the stability indicator is calculated by the first row element data and the second row element data in each row vector
Figure 742857DEST_PATH_IMAGE025
When the temperature of the water is higher than the set temperature,
Figure 81041DEST_PATH_IMAGE026
，
Figure 326209DEST_PATH_IMAGE027
(ii) a Since there is no other row element data after the last row element data in each row vector, the stability indicator corresponding to the last row element data in each row vector can be calculated from the last row element data and the previous row element data, i.e. the stability indicator is calculated from the last row element data and the previous row element data
Figure 669334DEST_PATH_IMAGE028
. Thus, in this embodiment, the stability index corresponding to each line element data in each line vector is obtained, and the stability index corresponding to each line element data is normalized to ensure that the stability index corresponding to each line element data is (0, 1).
And (2-2) obtaining each suspicious noise point of the detection matrix according to the stability index corresponding to each row element data in each row vector.
And if the stability index corresponding to any row element data of the detection matrix is smaller than the stability threshold value, judging the row element data to be suspicious noise points, and otherwise, judging the row element data to be normal temperature data.
In this embodiment, each element of the detection matrix is analyzed based on the stability index, and a stability threshold is set and recorded as
Figure 669651DEST_PATH_IMAGE029
When the stability index corresponding to any row element data of the detection matrix is lower than the stability threshold value
Figure 170165DEST_PATH_IMAGE029
When the row element data is judged to be noise point data or abnormal point data, the possibility that the row element data is noise point data or abnormal point data is high, the row element data is marked as a suspicious noise point, the suspicious noise point refers to that the temperature data at the position is abnormal temperature data, the suspicious noise point is different from the adjacent temperature data greatly, and the stability index of the suspicious noise point is poor; on the contrary, it is indicated that the possibility that the row element data is noise point data or abnormal point data is low, and the row element data is marked as normal temperature data.
(3) And determining an overall correlation index corresponding to each column element data in each column vector according to each column element data in each column vector of the detection matrix, and further determining an overall correlation index corresponding to each suspicious noise point of the detection matrix.
(3-1) determining an overall correlation index corresponding to each column element data in each column vector according to each column element data in each column vector of the detection matrix, wherein the overall correlation index comprises the following steps:
and (3-1-1) determining a data point set corresponding to each column element data according to each column element data in each column vector of the detection matrix.
And taking each column element data in each column vector of the detection matrix as a center, selecting a plurality of data points in the vertical direction of the center, and forming a data point set by the center and a plurality of data points corresponding to the center to obtain a data point set corresponding to each column element data.
In this embodiment, each column vector of the detection matrix is
Figure 530608DEST_PATH_IMAGE030
，
Figure 744552DEST_PATH_IMAGE031
，
Figure 421431DEST_PATH_IMAGE021
，
Figure 455246DEST_PATH_IMAGE032
，
Figure 291484DEST_PATH_IMAGE030
To detect the 1 st column vector of the matrix,Fto detect the number of column vectors in the matrix,
Figure 625513DEST_PATH_IMAGE033
，
Figure 656049DEST_PATH_IMAGE034
to detect the 1 st column element data in the 1 st column vector of the matrix. In this embodiment, each column element data in each column vector of the detection matrix is analyzed, and first, a data point set corresponding to each column element data is determined based on each column element data in each column vector of the detection matrix.
To determine the second in any column vectorjTaking the data point set corresponding to the individual column element data as an example, the first onejThe column element data is the central point and adopts the size of
Figure 426427DEST_PATH_IMAGE035
Window of (1) selectingjEach of the upper and lower sides of the column element datanData points, here data pointsRefers to the column element data in the column vector, from which
Figure 879405DEST_PATH_IMAGE036
A data point constitutesjA set of data points corresponding to the individual column element data, the set of data points being usable for subsequent analysisjLocal features of individual column element data.
It should be noted that if
Figure 550165DEST_PATH_IMAGE025
May choose only the firstjA number of data points below the column element data will be temporarily disregardedjData point condition above the column element data ifjFor the last column element data in the column vector, only the second column element data may be selectedjA number of data points above the column element data will be temporarily disregardedjThe data point condition below the element data of each row, the number of the selected data pointsnThe magnitude of the value of (A) can be set by an implementer according to actual conditions. Refer to the second in any column vectorjAnd determining a data point set corresponding to each column element data to obtain the data point set corresponding to each column element data.
(3-1-2) determining a Gaussian mixture model of the data point set according to the data point set corresponding to each column of element data, and further determining three model parameters of the Gaussian mixture model, wherein the three model parameters are respectively as follows: the number of single Gaussian functions, the mean parameter and the variance parameter.
In this embodiment, a gaussian mixture model corresponding to each column element data is constructed through a data point set corresponding to each column element data, and the data point set is used for the second timejThe Gaussian mixture model corresponding to the column element data is recorded as
Figure 797607DEST_PATH_IMAGE037
. According to the Gaussian mixture model corresponding to each column element data, three model parameters of the Gaussian mixture model corresponding to each column element data can be obtained, wherein the three model parameters are the number of single Gaussian functions in the Gaussian mixture model respectivelykMean parameter in Gaussian mixture model
Figure 55281DEST_PATH_IMAGE038
And variance parameter
Figure 46371DEST_PATH_IMAGE039
. It should be noted that the process of constructing the gaussian mixture model and the process of calculating the model parameters are all the prior art, and are not within the scope of the present invention, and will not be described in detail herein.
And (3-1-3) determining the element characterization vector corresponding to each column element data according to the three model parameters of the Gaussian mixture model of the data point set.
The embodiment constructs the element characterization vector corresponding to the column element data based on three model parameters of the gaussian mixture model of the data point set corresponding to the column element data,
Figure 777829DEST_PATH_IMAGE040
wherein
Figure 461751DEST_PATH_IMAGE041
Is as followsjThe elements corresponding to the column element data characterize the vector,
Figure 941143DEST_PATH_IMAGE042
is as followsjThe number of single Gaussian functions corresponding to the data of each column element,
Figure 952568DEST_PATH_IMAGE043
is as followsjThe mean parameter corresponding to the individual column element data,
Figure 505909DEST_PATH_IMAGE044
is as followsjThe variance parameter and the element characterization vector corresponding to the column element data can be used for detecting the local data change distribution condition of the analysis column element data.
And (3-1-4) determining an overall relevance index corresponding to each column element data in each column vector according to each column element data and the corresponding element characterization vector.
In the present embodiment, to determine the second in each column vectorjTaking the overall relevance index corresponding to the individual column element data as an example, the method is based onjThe corresponding element characterization vector of each column element data is calculatedjThe calculation formula of the overall relevance index corresponding to the individual column element data is as follows:
Figure 563995DEST_PATH_IMAGE001
wherein the content of the first and second substances,
Figure 32148DEST_PATH_IMAGE002
for the second in each column vectorjThe overall relevance indicator corresponding to the individual column element data,
Figure 551991DEST_PATH_IMAGE003
for the second in each column vectorjThe element characterization vector corresponding to each column element data and the second element in each column vectoriThe cosine similarity between the element characterization vectors corresponding to the column element data,
Figure 786270DEST_PATH_IMAGE004
for the second in each column vectorjColumn element data andithe spatial distance between the individual column element data,Qthe number of column element data in each column vector.
It should be noted that, in the present embodiment, the euclidean distance is used to calculate the spatial distance between each column element data, and the process of calculating the spatial distance between the column element data by using the euclidean distance is prior art and is not within the scope of the present invention, and will not be described in detail here. Refer to the second in each column vectorjAnd determining the overall relevance index corresponding to each column element data to obtain the overall relevance index corresponding to each column element data in each column vector. Thus, the present embodiment obtains the overall relevance index corresponding to each column element data in each column vector.
And (3-2) determining the overall correlation indexes corresponding to the suspicious noise points of the detection matrix according to the overall correlation indexes corresponding to the column element data in each column vector and the positions of the suspicious noise points of the detection matrix.
In this embodiment, the position of each suspected noise point of the detection matrix is obtained through step (2-2), each suspected noise point in each column element data is determined according to the position of each suspected noise point of the detection matrix, and the overall relevance index corresponding to each suspected noise point in each column element data is obtained according to the overall relevance index corresponding to each column element data in each column vector in step (3-1-4).
It should be noted that the overall correlation index is used to determine noise point data in the detection matrix, and the higher the overall correlation index corresponding to a suspected noise point is, the lower the possibility that the suspected noise point is a true noise point is.
(4) And determining the possibility that each suspicious noise point is a real noise point according to the number of the suspicious noise points in the column vector where each suspicious noise point is located and the overall correlation index corresponding to each suspicious noise point, and further determining each suspected abnormal point of the detection matrix.
First, it should be noted that, in order to improve the accuracy of monitoring the abnormality of the refrigeration storage tank, avoid the influence of real noise point data on the abnormal point data, accurately identify each suspected abnormal point data in the detection matrix, and accurately determine each suspected abnormal point data in the detection matrix, the method includes the following steps:
(4-1) acquiring the number of suspicious noise points in the column vector of each suspicious noise point, and determining the possibility that each suspicious noise point is a real noise point according to the number of suspicious noise points in the column vector of each suspicious noise point and the overall relevance index corresponding to each suspicious noise point.
In this embodiment, the number of suspected noise points in a column vector where each suspected noise point is located is counted, a suspected noise point fine determination model is constructed according to the number of suspected noise points in the column vector where each suspected noise point is located and an overall correlation index corresponding to each suspected noise point, and the suspected noise point fine determination model is used to determine the possibility that each suspected noise point is a true noise point, wherein the calculation formula is as follows:
Figure 202207DEST_PATH_IMAGE013
wherein the content of the first and second substances,wfor the likelihood that each suspect noise point is a true noise point,rfor the overall correlation index corresponding to each suspect noise point,Mthe number of suspicious noise points in the column vector of each suspicious noise point is shown.
Thus, the present embodiment obtains the possibility that each suspected noise point is a true noise point, and normalizes the possibility that each suspected noise point is a true noise point to ensure that the possibility value of the true noise point is [0,1 ]. The more the number of the suspicious noise points in the column vector of the suspicious noise points is, the larger the overall correlation index corresponding to the suspicious noise points is, the smaller the possibility that the suspicious noise points are real noise points is, and the more the suspicious noise points are likely to be suspected abnormal points.
And (4-2) determining each suspected abnormal point of the detection matrix according to the possibility that each suspected noise point is a real noise point.
In this embodiment, if the probability that any suspicious noise point in the detection matrix is a real noise point is greater than the preset probability threshold, and the preset probability threshold is set to 0.75, it is determined that the suspicious noise point is not a suspected abnormal point, otherwise, it is determined that the suspicious noise point is a suspected abnormal point, and the suspected abnormal point is a point where the temperature data abnormality is likely to be caused by the influence of the abnormal condition of the refrigeration storage tank. Therefore, the suspected abnormal points in the identification detection matrix can be accurately extracted, and the accuracy of monitoring the abnormal condition of the refrigerating storage box by the monitoring system is improved.
(5) Judging whether each suspected abnormal point of the detection matrix is a real abnormal point or not according to each suspected abnormal point of the detection matrix and preset normal temperature data, and if a certain suspected abnormal point is a real abnormal point, carrying out early warning, wherein the steps comprise:
and (5-1) calculating the difference value between each suspected abnormal point and the preset normal temperature data according to each suspected abnormal point and the preset normal temperature data of the detection matrix.
In this embodiment, the preset normal temperature data is subtracted from the temperature data corresponding to each suspected abnormal point, where the preset normal temperature data is temperature time sequence data of the refrigerated storage tank under the condition that no accident occurs, so as to obtain a difference value corresponding to the temperature data corresponding to each suspected abnormal point, and the difference value corresponding to each suspected abnormal point is obtained, and the second step is to calculate the difference value of the temperature data corresponding to each suspected abnormal pointiThe difference value corresponding to each suspected abnormal point is recorded as
Figure 406924DEST_PATH_IMAGE045
The preset normal temperature data is recorded as
Figure 231923DEST_PATH_IMAGE046
。
(5-2) judging whether each suspected abnormal point of the detection matrix is a real abnormal point or not according to the difference value of each suspected abnormal point and preset normal temperature data, when the difference value of any one suspected abnormal point and the preset normal temperature data is larger than a temperature difference threshold value, judging that the suspected abnormal point is the real abnormal point, and otherwise, judging that the suspected abnormal point is not the real abnormal point.
In this embodiment, when the difference between any suspected abnormal point and the preset normal temperature data is greater than the temperature difference threshold, the temperature difference threshold is set to 10,
Figure 759856DEST_PATH_IMAGE047
this embodiment considers this suspected anomaly point to be real anomaly point, that is to say explains that the cold-stored storage tank of waiting to monitor appears abnormal conditions, and anomaly monitoring early warning system will in time make the early warning, and the suggestion related detection personnel of waiting to monitor the cold-stored storage tank and appear cold-stored abnormal conditions, in time carries out corresponding inspection to this cold-stored storage tank of waiting to monitor and repairs to avoid abnormal conditions to seriously lead to the refrigerated goods to appear quality problems. This embodiment will gather data information in real time, and the abnormal condition can appear in the monitoring cold-stored storehouse storage tank, stops the work of cold-stored article until waiting to monitor cold-stored storehouse storage tank.
According to the invention, the abnormal condition of the refrigerating storage tank is monitored by the abnormal monitoring and early warning system for the refrigerating storage tank, and if the abnormal condition exists, the early warning prompt can be given in time, so that the accuracy of the abnormal monitoring of the refrigerating storage tank is effectively improved.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.

Claims (10)

1. The utility model provides an unusual monitoring early warning system for cold-stored storage tank, its characterized in that includes data acquisition module and data processing module, and the data acquisition module is used for acquireing the temperature time series data of waiting to monitor cold-stored storage tank in the regulation period to send the temperature time series data of waiting to monitor cold-stored storage tank in the regulation period who obtains to data processing module, and data processing module is used for receiving the temperature time series data of waiting to monitor cold-stored storage tank in the regulation period that data acquisition module sent, and realize following step:
determining a detection matrix corresponding to the temperature time sequence data in the specified time period according to the temperature time sequence data of the storage tank of the refrigeration bin to be monitored in the specified time period;
determining a stability index corresponding to each row element data in each row vector according to each row element data in each row vector of the detection matrix, and further obtaining each suspicious noise point of the detection matrix;
determining an overall relevance index corresponding to each column element data in each column vector of the detection matrix according to each column element data in each column vector of the detection matrix, and further determining an overall relevance index corresponding to each suspicious noise point of the detection matrix;
acquiring the number of suspicious noise points in a column vector of each suspicious noise point, determining the possibility that each suspicious noise point is a real noise point according to the number of suspicious noise points in the column vector of each suspicious noise point and an overall correlation index corresponding to each suspicious noise point, and further determining each suspected abnormal point of the detection matrix;
and judging whether each suspected abnormal point of the detection matrix is a real abnormal point or not according to each suspected abnormal point of the detection matrix and preset normal temperature data, and if a certain suspected abnormal point is a real abnormal point, early warning is carried out.
2. The anomaly monitoring and pre-warning system for a refrigerated storage tank of claim 1, wherein the step of determining the overall relevance indicator corresponding to each column element data in each column vector comprises:
determining a data point set corresponding to each column element data according to each column element data in each column vector of the detection matrix;
determining a Gaussian mixture model of the data point set according to the data point set corresponding to each column element data, and further determining three model parameters of the Gaussian mixture model, wherein the three model parameters are respectively as follows: the number of single Gaussian functions, the mean parameter and the variance parameter;
determining element characterization vectors corresponding to each column element data according to three model parameters of a Gaussian mixture model of the data point set;
and determining an overall relevance index corresponding to each column element data in each column vector according to each column element data and the corresponding element characterization vector.
3. The anomaly monitoring and warning system for a refrigerated storage tank as claimed in claim 2 wherein the step of determining the set of data points corresponding to each column of elemental data comprises:
and taking each column element data in each column vector of the detection matrix as a center, selecting a plurality of data points in the vertical direction of the center, and forming a data point set by the center and a plurality of data points corresponding to the center to obtain a data point set corresponding to each column element data.
4. The anomaly monitoring and early warning system for the refrigerated storage tank as claimed in claim 2, wherein the calculation formula for determining the overall correlation index corresponding to each column element data in each column vector is as follows:
Figure DEST_PATH_IMAGE001
wherein the content of the first and second substances,
Figure 267517DEST_PATH_IMAGE002
for the second in each column vectorjThe overall relevance indicator corresponding to the individual column element data,
Figure 693950DEST_PATH_IMAGE003
for the second in each column vectorjThe element characterization vector corresponding to each column element data and the second element in each column vectoriThe cosine similarity between the element characterization vectors corresponding to the column element data,
Figure 883492DEST_PATH_IMAGE004
for the second in each column vectorjColumn element data andithe spatial distance between the individual column element data,Qthe number of column element data in each column vector.
5. The abnormality monitoring and warning system for the refrigerated storage tank as set forth in claim 1 wherein the step of determining the detection matrix corresponding to the temperature time series data over the prescribed time period comprises:
determining the data cutting length of the temperature time sequence data in the specified time period according to the data quantity of the temperature time sequence data of the refrigerating storage box to be monitored in the specified time period;
and determining each sub-temperature time sequence data according to the temperature time sequence data and the data cutting length of the refrigerating storage box to be monitored in the specified time period, and constructing a detection matrix corresponding to the temperature time sequence data in the specified time period by taking the sub-temperature time sequence data as a column vector.
6. The anomaly monitoring and early warning system for the refrigerated storage tank as claimed in claim 1, wherein the calculation formula for determining the stability index corresponding to each row element data in each row vector is as follows:
Figure 141298DEST_PATH_IMAGE005
wherein the content of the first and second substances,
Figure 725470DEST_PATH_IMAGE006
for the second in each row vectorjThe stability index corresponding to the element data of each line,
Figure 904779DEST_PATH_IMAGE007
for the second in each row vectorjThe data of the elements of one line is,
Figure 179902DEST_PATH_IMAGE008
for the second in each row vector
Figure 744744DEST_PATH_IMAGE009
-1 line element data of a row element,
Figure 17594DEST_PATH_IMAGE010
for the second in each row vector
Figure 966090DEST_PATH_IMAGE009
The number of +1 row element data,
Figure 982587DEST_PATH_IMAGE011
in order to be a hyper-parameter,hfor the number of row element data in each row vector,
Figure 667515DEST_PATH_IMAGE012
to find the minimum function.
7. An anomaly monitoring and pre-warning system for a refrigerated storage tank as claimed in claim 1 wherein the step of obtaining each suspected noise point of the detection matrix further comprises:
and if the stability index corresponding to any row element data of the detection matrix is smaller than the stability threshold value, judging the row element data to be suspicious noise points, and otherwise, judging the row element data to be normal temperature data.
8. An anomaly monitoring and pre-warning system for a refrigerated storage tank as claimed in claim 1 wherein the calculation formula to determine the likelihood of each suspected noise point being a true noise point is:
Figure 111266DEST_PATH_IMAGE013
wherein the content of the first and second substances,wfor the likelihood that each suspect noise point is a true noise point,rfor the overall correlation index corresponding to each suspect noise point,Mthe number of suspect noise points in the column element data set corresponding to each suspect noise point.
9. An anomaly monitoring and warning system for a refrigerated storage tank as claimed in claim 1 wherein the step of determining each suspected anomaly point of the detection matrix further comprises:
if the probability that any suspicious noise point of the detection matrix is a real noise point is larger than a preset probability threshold, the suspicious noise point is judged not to be a suspected abnormal point, otherwise, the suspicious noise point is judged to be a suspected abnormal point.
10. The abnormality monitoring and warning system for the refrigerated storage tank as claimed in claim 1 wherein the step of determining whether each suspected abnormality of the detection matrix is a true abnormality comprises:
calculating the difference value of each suspected abnormal point and preset normal temperature data according to each suspected abnormal point and preset normal temperature data of the detection matrix;
and judging whether each suspected abnormal point of the detection matrix is a real abnormal point or not according to the difference value of each suspected abnormal point and preset normal temperature data, when the difference value of any one suspected abnormal point and the preset normal temperature data is larger than a temperature difference threshold value, judging that the suspected abnormal point is the real abnormal point, and otherwise, judging that the suspected abnormal point is not the real abnormal point.
CN202210838504.5A 2022-07-18 2022-07-18 Abnormity monitoring and early warning system for storage tank of refrigeration bin Active CN114912852B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210838504.5A CN114912852B (en) 2022-07-18 2022-07-18 Abnormity monitoring and early warning system for storage tank of refrigeration bin

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210838504.5A CN114912852B (en) 2022-07-18 2022-07-18 Abnormity monitoring and early warning system for storage tank of refrigeration bin

Publications (2)

Publication Number Publication Date
CN114912852A true CN114912852A (en) 2022-08-16
CN114912852B CN114912852B (en) 2022-09-23

Family

ID=82772083

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210838504.5A Active CN114912852B (en) 2022-07-18 2022-07-18 Abnormity monitoring and early warning system for storage tank of refrigeration bin

Country Status (1)

Country Link
CN (1) CN114912852B (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116295539A (en) * 2023-05-18 2023-06-23 山东省地质矿产勘查开发局八〇一水文地质工程地质大队(山东省地矿工程勘察院) Underground space monitoring method based on urban underground space exploration data
CN116307361A (en) * 2023-01-30 2023-06-23 江苏中农物联网科技有限公司 Quick adjustment and control method for aquaculture environmental factors
CN116643951A (en) * 2023-07-24 2023-08-25 青岛冠成软件有限公司 Cold chain logistics transportation big data monitoring and collecting method
CN116701848A (en) * 2023-08-09 2023-09-05 江苏盖亚环境科技股份有限公司 Continuous detection data processing system of integrated equipment
CN116823125A (en) * 2023-08-31 2023-09-29 酒仙网络科技股份有限公司 White spirit storage abnormality early warning system based on multisource data
CN117113107A (en) * 2023-10-24 2023-11-24 广东顺德爱顺机电科技有限公司 Rotor die casting abnormal error data processing method
CN117474427A (en) * 2023-12-27 2024-01-30 大连金马衡器有限公司 Intelligent pallet cold chain tracing method based on Internet of things technology

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104794484A (en) * 2015-04-07 2015-07-22 浙江大学 Time series data nearest-neighbor classifying method based on subsection orthogonal polynomial decomposition
CN110399910A (en) * 2019-07-08 2019-11-01 东华大学 Fire abnormal point online test method based on sliding window and HWKS theoretical frame
CN113139610A (en) * 2021-04-29 2021-07-20 国网河北省电力有限公司电力科学研究院 Abnormity detection method and device for transformer monitoring data
US20210272028A1 (en) * 2018-07-09 2021-09-02 Suez Groupe Placement of physico-chemical parameter sensors in a fluid

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104794484A (en) * 2015-04-07 2015-07-22 浙江大学 Time series data nearest-neighbor classifying method based on subsection orthogonal polynomial decomposition
US20210272028A1 (en) * 2018-07-09 2021-09-02 Suez Groupe Placement of physico-chemical parameter sensors in a fluid
CN110399910A (en) * 2019-07-08 2019-11-01 东华大学 Fire abnormal point online test method based on sliding window and HWKS theoretical frame
CN113139610A (en) * 2021-04-29 2021-07-20 国网河北省电力有限公司电力科学研究院 Abnormity detection method and device for transformer monitoring data

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
王红君等: "钢铁企业高炉煤气发生量异常数据检测", 《化工自动化及仪表》 *

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116307361A (en) * 2023-01-30 2023-06-23 江苏中农物联网科技有限公司 Quick adjustment and control method for aquaculture environmental factors
CN116307361B (en) * 2023-01-30 2023-12-22 连云港陈晔水产科技有限公司 Quick adjustment and control method for aquaculture environmental factors
CN116295539A (en) * 2023-05-18 2023-06-23 山东省地质矿产勘查开发局八〇一水文地质工程地质大队(山东省地矿工程勘察院) Underground space monitoring method based on urban underground space exploration data
CN116295539B (en) * 2023-05-18 2023-08-11 山东省地质矿产勘查开发局八〇一水文地质工程地质大队(山东省地矿工程勘察院) Underground space monitoring method based on urban underground space exploration data
CN116643951B (en) * 2023-07-24 2023-10-10 青岛冠成软件有限公司 Cold chain logistics transportation big data monitoring and collecting method
CN116643951A (en) * 2023-07-24 2023-08-25 青岛冠成软件有限公司 Cold chain logistics transportation big data monitoring and collecting method
CN116701848A (en) * 2023-08-09 2023-09-05 江苏盖亚环境科技股份有限公司 Continuous detection data processing system of integrated equipment
CN116701848B (en) * 2023-08-09 2023-12-08 江苏盖亚环境科技股份有限公司 Continuous detection data processing system of integrated equipment
CN116823125A (en) * 2023-08-31 2023-09-29 酒仙网络科技股份有限公司 White spirit storage abnormality early warning system based on multisource data
CN116823125B (en) * 2023-08-31 2023-10-31 酒仙网络科技股份有限公司 White spirit storage abnormality early warning system based on multisource data
CN117113107A (en) * 2023-10-24 2023-11-24 广东顺德爱顺机电科技有限公司 Rotor die casting abnormal error data processing method
CN117113107B (en) * 2023-10-24 2023-12-29 广东顺德爱顺机电科技有限公司 Rotor die casting abnormal error data processing method
CN117474427A (en) * 2023-12-27 2024-01-30 大连金马衡器有限公司 Intelligent pallet cold chain tracing method based on Internet of things technology
CN117474427B (en) * 2023-12-27 2024-03-26 大连金马衡器有限公司 Intelligent pallet cold chain tracing method based on Internet of things technology

Also Published As

Publication number Publication date
CN114912852B (en) 2022-09-23

Similar Documents

Publication Publication Date Title
CN114912852B (en) Abnormity monitoring and early warning system for storage tank of refrigeration bin
CN116659589A (en) Donkey-hide gelatin cake preservation environment monitoring method based on data analysis
EP3039360B1 (en) A computer-implemented method of monitoring the operation of a cargo shipping reefer container
CN102667352B (en) Refrigerant leak detection system and method
EP0843244B1 (en) Diagnostic trend analysis for aircraft engines
CN108692711B (en) Method for realizing ocean data processing based on low-altitude sounding rocket
CN112978128B (en) Cold-chain logistics transportation commodity quality monitoring and management system based on big data and image analysis technology
CN116701983B (en) Cold-chain logistics real-time monitoring data processing method and system
CN113435593B (en) Refrigeration equipment frosting prediction method based on sensor time sequence data analysis
CN112734323A (en) Smart cold-chain logistics commodity whole-course visual data management cloud platform based on big data and cloud computing
CN114996661B (en) Refrigerator car temperature monitoring method and system
CN107085593A (en) Environment control method and system
CN116843236A (en) Food storage supervision system based on artificial intelligence
CN112985494A (en) Cold chain wisdom logistics transportation on-line real-time supervision cloud platform based on big data and artificial intelligence
CN115311829A (en) Accurate alarm method and system based on mass data
WO2018051568A1 (en) Plant abnormality diagnosis device and plant abnormality diagnosis system
CN108519171B (en) method for judging grain condition of stored grains
CN114297264A (en) Method and system for detecting abnormal segments of time sequence signal
US20110043638A1 (en) Optronic Infrared System with Predictive Maintenance Following a Sudden Drift
CN114048642B (en) Method for analyzing performance trend of aero-engine
CN110243598A (en) Processing method, device and the storage medium of train bearing temperature
CN113836813B (en) Blast furnace tuyere water leakage detection method based on data analysis
WO2020183781A1 (en) Abnormality diagnosis device
CN117235421B (en) High temperature alarm system based on RFID
Wu et al. A fusion method for estimate of trajectory

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
PE01 Entry into force of the registration of the contract for pledge of patent right
PE01 Entry into force of the registration of the contract for pledge of patent right

Denomination of invention: An anomaly monitoring and warning system for refrigerated storage containers

Effective date of registration: 20230914

Granted publication date: 20220923

Pledgee: Liaocheng Branch of Postal Savings Bank of China Co.,Ltd.

Pledgor: SHANDONG XINYA EQUIPMENT MANUFACTURING Co.,Ltd.

Registration number: Y2023980056749