CN110232769A - Distributed retail terminal modularization method for early warning based on big data statistics - Google Patents
Distributed retail terminal modularization method for early warning based on big data statistics Download PDFInfo
- Publication number
- CN110232769A CN110232769A CN201910442139.4A CN201910442139A CN110232769A CN 110232769 A CN110232769 A CN 110232769A CN 201910442139 A CN201910442139 A CN 201910442139A CN 110232769 A CN110232769 A CN 110232769A
- Authority
- CN
- China
- Prior art keywords
- big data
- early warning
- terminal unit
- data
- acquisition
- 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
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
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F9/00—Details other than those peculiar to special kinds or types of apparatus
- G07F9/02—Devices for alarm or indication, e.g. when empty; Advertising arrangements in coin-freed apparatus
- G07F9/026—Devices for alarm or indication, e.g. when empty; Advertising arrangements in coin-freed apparatus for alarm, monitoring and auditing in vending machines or means for indication, e.g. when empty
Abstract
The present invention relates to retail terminal field, the distributed retail terminal modularization method for early warning based on big data statistics is disclosed, method includes the following steps: big data acquisition modeling and failure predication.Big data acquisition modeling is to collect and record the key parameter progress of terminal unit in the memory in big data cloud platform in real time, carries out feature extraction and digital modeling according to fault type.Multiclass feature fusion solves, and obtains the Real time Efficiency of the prediction normal operating conditions of terminal unit.Predicted value is compared with terminal unit work Real time Efficiency, if exceeding tolerable error range, otherwise multistage early warning mechanism starting then thinks that system is normal.Monitoring method combination big data modeling and actual demand, and using Feature fusion and multistage method for early warning, it had both ensured the accuracy of prediction data, and had in turn ensured the real-time and validity of monitoring method.
Description
Technical field
The present invention relates to retail terminal field, the distributed retail terminal modularization early warning based on big data statistics is disclosed
Method.
Background technique
With the quickening pace of modern life, fast food becomes essential part in people's daily life.The hair of fast food
Exhibition is determined by social progress and economic development, be living standards of the people improve with life style improve there is an urgent need to be
It is adaptation social and economic construction to people, and work is accelerated with rhythm of life, and socialization is moved towards in home services and unit logistics service
Inevitable outcome.Fast food is the industry of an important living environment and investment environment；It is the national economic development and catering trade
Develop new growth point；It is that prior restaurant moves towards the breach of modern food and drink and first marches；It is people's Leisure Consumption, travelling disappears
Take, the important component of the consumption such as purchase and consumption；It is that country expands domestic demand, receives social employment and expand the important of re-employment
Channel；It is Chinese development export-oriented economy and the fresh combatants with international food and drink market linkage.
However, the explosion type of fast food develops bring food hygiene problem, operator and manager annoying always.Nothing
The appearance of people's retail terminal can effectively solve the problems, such as to think element bring food hygiene and safety.Meanwhile it can greatly save
About operation cost and promotion efficiency of operation.But since most of retail terminal equipment is all placed more dispersed, this is just led
It has caused daily maintenance and has detected relatively difficult.Network operator is difficult to know position and the failure cause of faulty equipment at the first time.Separately
Outer many failures itself are avoidable, such as factors such as ageing equipment, if with look-ahead and the work of response can be replaced
Make component and in time maintenance, whole efficiency of operation can be greatly promoted and saves operation cost.
Summary of the invention
Goal of the invention: to solve the above-mentioned problems, which proposes the distributed retail terminal based on big data statistics
Modularization method for early warning.
Technical solution:
The distributed retail terminal modularization method for early warning based on big data statistics is disclosed, this method includes following step
It is rapid: big data acquisition modeling and failure predication.Big data acquisition modeling is to be acquired the key parameter of terminal unit in real time
And be recorded in the memory in big data cloud platform, feature extraction and digital modeling are carried out according to fault type.Multiclass feature
Fusion solves, and obtains the Real time Efficiency of the prediction normal operating conditions of terminal unit.Predicted value and terminal unit work is real-time
Efficiency compares, if exceeding tolerable error range, otherwise multistage early warning mechanism starting then thinks that system is normal.
The key parameter is the data provided based on area sensor；Including work environment data, terminal unit object
Manage data and terminal unit electric power data.The environmental data includes ambient humidity, temperature and specific volatile gas concentration
Equal environmental datas.The terminals physical data include structural stress, work noise and semiconductors integrality.The terminal
Unit of power data include operating voltage, electric current and draw power；
The multistage early warning includes being divided first based on the matched fault type of the big data aspect of model and deterioration degree
Grade early warning, intermediate early warning and advanced early warning.
The big data acquisition, which is characterized in that acquisition mode may include sensor acquisition and Image Acquisition.Wherein
Sensor acquisition may include audio sensor, temperature sensor, humidity sensor, pressure sensor, gas sensor etc..Figure
As acquisition includes the image data based on the acquisitions such as infrared camera and depth camera.
The distributed retail terminal modularization method for early warning based on big data statistics, which is characterized in that described
Multiclass feature fusion, which solves, to be modeled based on fault type in history big data.Establish fault type W and terminal unit
The weight matrix Q of key parameter X.According to NMF criterion of identification:
Wherein F is norm solution.Existence anduniquess weight matrix Q*For the optimal solution of above formula.It can determine one group of key ginseng
The corresponding weight matrix of number, so that it may obtain corresponding fault type.
The distributed retail terminal modularization method for early warning based on big data statistics, which is characterized in that described
The real-time predicted value of terminal unit working condition is that can predict that the moment equipment works normally in real time based on big data mathematical model
State, and compared with actual working state pair.When comparison result is greater than set threshold value, it is believed that equipment is in fail operation shape
State, on the contrary think normal, it continues to test.
Relative to other methods, the main innovation point of this method is:
1, big data is collected environment by the method counted using big data, and physically and electrically the Primary Components parameter such as power is logical
It crosses multiclass feature fusion to solve, the prediction closer to truth can be obtained, improve the accuracy of system.
2, using grading forewarning system method, different warning grades can be divided for fault type and fault degree, improving should
The applicability of system.Grading forewarning system method effectively quickly accurately can find faulty equipment position and failure cause, keep away simultaneously
Exempt from the problem of being computed repeatedly invalid big data, improves the real-time of early warning system.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described.
Fig. 1 is the principle of the present invention schematic diagram；
Fig. 2 is grading forewarning system schematic diagram.
Specific embodiment
Below in conjunction with attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground description.
As shown in Figure 1, method includes the following steps: big data acquisition modeling and failure predication.Big data acquisition modeling
It is to collect and record the key parameter progress of terminal unit in the memory in big data cloud platform in real time, according to failure classes
Type carries out feature extraction and digital modeling.Multiclass feature fusion solves, and obtains the reality of the prediction normal operating conditions of terminal unit
When efficiency.Predicted value is compared with terminal unit work Real time Efficiency, if exceeding tolerable error range, multistage early warning plane
System starting, otherwise then thinks that system is normal.The key parameter is the data provided based on area sensor；Including building ring
Border data, terminal unit physical data and terminal unit electric power data.The environmental data includes ambient humidity, temperature and spy
Determine the environmental datas such as escaping gas concentration.The terminals physical data include structural stress, work noise and semiconductors
Integrality.The terminal unit electric power data includes operating voltage, electric current and draw power；
As shown in Fig. 2, the multistage early warning includes based on the matched fault type of the big data aspect of model and deteriorating journey
The primary warning spent and divided, intermediate early warning and advanced early warning.So these warning grades and, such as ring related to various early warning types
Temperature pre-warning in the early warning of border, humidity early warning and specific volatile gas alarm.Detection device working environment when main purpose
Whether situation is abnormal.Wherein polluted in detection device with the presence or absence of specific volatile when specific volatile gas alarm main purpose
Object, such as gasoline, rot food and burning property smog.Physics early warning includes structural stress early warning again, and noise early warning and form are complete
Property early warning.Wherein structural stress early warning is whether monitoring device the problems such as structure dislocation, deformation or connection relaxation occurs.Noise
Early warning is mainly whether detection device operation generates improper noise in the process.Morphological integrity early warning is mainly that detection device is old
Change, the service condition of abrasion and consumption-type device.Electric power early warning includes voltage early warning, electric current early warning and mean power early warning.It is main
Want whether detection device has circuit and loading problem when working.
The big data acquisition, which is characterized in that acquisition mode may include sensor acquisition and Image Acquisition.Wherein
Sensor acquisition may include audio sensor, temperature sensor, humidity sensor, pressure sensor, gas sensor etc..Figure
As acquisition includes the image data based on the acquisitions such as infrared camera and depth camera.
The distributed retail terminal modularization method for early warning based on big data statistics, which is characterized in that described
Multiclass feature fusion, which solves, to be modeled based on fault type in history big data.Establish fault type W and terminal unit
The weight matrix Q of key parameter X.According to NMF criterion of identification:
Wherein F is norm solution.Existence anduniquess weight matrix Q*For the optimal solution of above formula.It can determine one group of key ginseng
The corresponding weight matrix of number, so that it may obtain corresponding fault type.
The distributed retail terminal modularization method for early warning based on big data statistics, which is characterized in that described
The real-time predicted value of terminal unit working condition is that can predict that the moment equipment works normally in real time based on big data mathematical model
State, and compared with actual working state pair.When comparison result is greater than set threshold value, it is believed that equipment is in fail operation shape
State, on the contrary think normal, it continues to test.
Claims (4)
1. based on the distributed retail terminal modularization method for early warning of big data statistics, method includes the following steps: big data
Acquisition modeling and failure predication；Big data acquisition modeling is to collect and record the key parameter progress of terminal unit big in real time
In memory in data cloud platform, feature extraction and digital modeling are carried out according to fault type；Multiclass feature fusion solves, and obtains
Obtain the Real time Efficiency of the prediction normal operating conditions of terminal unit；Predicted value is compared with terminal unit work Real time Efficiency,
If exceeding tolerable error range, otherwise multistage early warning mechanism starting then thinks that system is normal；
The key parameter is the data provided based on area sensor；Including work environment data, terminal unit physics number
According to terminal unit electric power data；The environmental data includes ambient humidity, temperature and specific volatile gas concentration environment
Data；The terminals physical data include structural stress, work noise and semiconductors integrality；The terminal unit electricity
Force data includes operating voltage, electric current and draw power；
The multistage early warning includes being divided primary pre- based on the matched fault type of the big data aspect of model and deterioration degree
It is alert, intermediate early warning and advanced early warning.
2. the distributed retail terminal modularization method for early warning as described in claim 1 based on big data statistics, feature exist
In acquisition mode may include sensor acquisition and Image Acquisition；Wherein sensor acquisition may include audio sensor, temperature
Sensor, humidity sensor, pressure sensor, gas sensor；Image Acquisition includes being based on infrared camera and depth camera
The image data of acquisition.
3. the distributed retail terminal modularization method for early warning as described in claim 1 based on big data statistics, feature exist
In the multiclass feature fusion, which solves, to be modeled based on fault type in history big data；Establish fault type W and end
Hold the weight matrix Q of the key parameter X of unit；According to NMF criterion of identification:
Wherein F is norm solution.Existence anduniquess weight matrix Q*For the optimal solution of above formula；Can determine one group of key parameter with
Corresponding weight matrix, so that it may obtain corresponding fault type.
4. the distributed retail terminal modularization method for early warning as described in claim 1 based on big data statistics, feature exist
In the real-time predicted value of terminal unit working condition is that can predict that the moment sets in real time based on big data mathematical model
Standby normal operating conditions, and compared with actual working state pair；When comparison result is greater than set threshold value, it is believed that equipment is in event
Hinder working condition, otherwise think normal, continues to test.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910442139.4A CN110232769A (en) | 2019-05-24 | 2019-05-24 | Distributed retail terminal modularization method for early warning based on big data statistics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910442139.4A CN110232769A (en) | 2019-05-24 | 2019-05-24 | Distributed retail terminal modularization method for early warning based on big data statistics |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110232769A true CN110232769A (en) | 2019-09-13 |
Family
ID=67861109
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910442139.4A Pending CN110232769A (en) | 2019-05-24 | 2019-05-24 | Distributed retail terminal modularization method for early warning based on big data statistics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110232769A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111464647A (en) * | 2020-04-02 | 2020-07-28 | 科锐特（厦门）净化科技有限公司 | Smart cloud clean room control method and system |
| CN113607413A (en) * | 2021-08-26 | 2021-11-05 | 上海航数智能科技有限公司 | Bearing component fault monitoring and predicting method based on controllable temperature and humidity |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103150579A (en) * | 2013-02-25 | 2013-06-12 | 东华大学 | Abnormal human behavior detecting method based on video sequence |
| US20140163935A1 (en) * | 2012-12-11 | 2014-06-12 | International Business Machines Corporation | System and method for maintenance planning and failure prediction for equipment subject to periodic failure risk |
| WO2014117245A1 (en) * | 2013-01-31 | 2014-08-07 | Spielo International Canada Ulc | Faults and performance issue prediction |
| CN107818631A (en) * | 2017-10-30 | 2018-03-20 | 中米（北京）农业科技股份有限公司 | A kind of source of early warning and method for early warning based on automatic vending machine |
| EP3462264A1 (en) * | 2017-09-29 | 2019-04-03 | Siemens Aktiengesellschaft | System, method and control unit for diagnosis and life prediction of one or more electro-mechanical systems |
| CN109743018A (en) * | 2018-11-21 | 2019-05-10 | 中国葛洲坝集团电力有限责任公司 | Photovoltaic power station grading forewarning system method based on big data statistics |
| CN109791511A (en) * | 2016-09-29 | 2019-05-21 | 惠普发展公司，有限责任合伙企业 | Unit failure prediction |
-
2019
- 2019-05-24 CN CN201910442139.4A patent/CN110232769A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140163935A1 (en) * | 2012-12-11 | 2014-06-12 | International Business Machines Corporation | System and method for maintenance planning and failure prediction for equipment subject to periodic failure risk |
| WO2014117245A1 (en) * | 2013-01-31 | 2014-08-07 | Spielo International Canada Ulc | Faults and performance issue prediction |
| CN103150579A (en) * | 2013-02-25 | 2013-06-12 | 东华大学 | Abnormal human behavior detecting method based on video sequence |
| CN109791511A (en) * | 2016-09-29 | 2019-05-21 | 惠普发展公司，有限责任合伙企业 | Unit failure prediction |
| EP3462264A1 (en) * | 2017-09-29 | 2019-04-03 | Siemens Aktiengesellschaft | System, method and control unit for diagnosis and life prediction of one or more electro-mechanical systems |
| CN107818631A (en) * | 2017-10-30 | 2018-03-20 | 中米（北京）农业科技股份有限公司 | A kind of source of early warning and method for early warning based on automatic vending machine |
| CN109743018A (en) * | 2018-11-21 | 2019-05-10 | 中国葛洲坝集团电力有限责任公司 | Photovoltaic power station grading forewarning system method based on big data statistics |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111464647A (en) * | 2020-04-02 | 2020-07-28 | 科锐特（厦门）净化科技有限公司 | Smart cloud clean room control method and system |
| CN113607413A (en) * | 2021-08-26 | 2021-11-05 | 上海航数智能科技有限公司 | Bearing component fault monitoring and predicting method based on controllable temperature and humidity |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111734885B (en) | Converter valve on-line monitoring and evaluating method and system | |
| CN109416531A (en) | The different degree decision maker of abnormal data and the different degree determination method of abnormal data | |
| CN108196170B (en) | Fault arc detection system and method | |
| CN112561736A (en) | Fault diagnosis system and method for relay protection device of intelligent substation | |
| CN114446020B (en) | Linkage early warning management method, system, storage medium and equipment | |
| CN115865649B (en) | Intelligent operation and maintenance management control method, system and storage medium | |
| CN110232769A (en) | Distributed retail terminal modularization method for early warning based on big data statistics | |
| CN110703743A (en) | Equipment failure prediction and detection system and method | |
| CN115796708B (en) | Big data intelligent quality inspection method, system and medium for engineering construction | |
| CN112242036A (en) | Fire alarm method and system for transformer substation | |
| KR102315580B1 (en) | Fire predictive analysis device and method of building | |
| CN115358155A (en) | Power big data abnormity early warning method, device, equipment and readable storage medium | |
| US11934522B2 (en) | System and method for detecting malicious activities and anomalies in building systems | |
| CN115660262A (en) | Intelligent engineering quality inspection method, system and medium based on database application | |
| CN114666117A (en) | Network security situation measuring and predicting method for power internet | |
| CN117439916A (en) | Network security test evaluation system and method | |
| CN116380496B (en) | Automobile door fatigue endurance test method, system and medium | |
| CN113553542A (en) | New energy automobile power battery state evaluation method based on data analysis | |
| CN115169650B (en) | Equipment health prediction method for big data analysis | |
| CN114765574B (en) | Network anomaly delimitation positioning method and device | |
| CN111960207B (en) | Elevator running environment abnormity detection method and detection system based on multivariate analysis | |
| KR20160026492A (en) | Anomaly detection method using confidence interval estimation based on time series analysis | |
| CN114882589A (en) | Granary safety operation early warning system and method based on intelligent video analysis | |
| CN110689144B (en) | Management method and device of intelligent recovery device | |
| CN110309838A (en) | Video detection area contour of object based on exponential transform detects preprocess method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190913 |
|
| WD01 | Invention patent application deemed withdrawn after publication |