CN117148001A - New energy automobile fills electric pile fault prediction system based on artificial intelligence - Google Patents
New energy automobile fills electric pile fault prediction system based on artificial intelligence Download PDFInfo
- Publication number
- CN117148001A CN117148001A CN202311098061.1A CN202311098061A CN117148001A CN 117148001 A CN117148001 A CN 117148001A CN 202311098061 A CN202311098061 A CN 202311098061A CN 117148001 A CN117148001 A CN 117148001A
- Authority
- CN
- China
- Prior art keywords
- value
- time
- charging
- analysis
- real
- 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
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 14
- 238000004458 analytical method Methods 0.000 claims abstract description 134
- 238000011897 real-time detection Methods 0.000 claims abstract description 72
- 238000012544 monitoring process Methods 0.000 claims abstract description 43
- 238000001514 detection method Methods 0.000 claims description 37
- 238000004364 calculation method Methods 0.000 claims description 32
- 238000000034 method Methods 0.000 claims description 31
- 238000011156 evaluation Methods 0.000 claims description 30
- 238000005259 measurement Methods 0.000 claims description 28
- 239000000779 smoke Substances 0.000 claims description 23
- 238000004891 communication Methods 0.000 claims description 5
- 238000012935 Averaging Methods 0.000 claims description 2
- 238000010223 real-time analysis Methods 0.000 abstract description 4
- 238000012423 maintenance Methods 0.000 description 5
- 238000007689 inspection Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000012797 qualification Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/003—Environmental or reliability tests
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L53/00—Methods of charging batteries, specially adapted for electric vehicles; Charging stations or on-board charging equipment therefor; Exchange of energy storage elements in electric vehicles
- B60L53/60—Monitoring or controlling charging stations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/165—Indicating that current or voltage is either above or below a predetermined value or within or outside a predetermined range of values
- G01R19/16566—Circuits and arrangements for comparing voltage or current with one or several thresholds and for indicating the result not covered by subgroups G01R19/16504, G01R19/16528, G01R19/16533
- G01R19/16571—Circuits and arrangements for comparing voltage or current with one or several thresholds and for indicating the result not covered by subgroups G01R19/16504, G01R19/16528, G01R19/16533 comparing AC or DC current with one threshold, e.g. load current, over-current, surge current or fault current
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/165—Indicating that current or voltage is either above or below a predetermined value or within or outside a predetermined range of values
- G01R19/16566—Circuits and arrangements for comparing voltage or current with one or several thresholds and for indicating the result not covered by subgroups G01R19/16504, G01R19/16528, G01R19/16533
- G01R19/16576—Circuits and arrangements for comparing voltage or current with one or several thresholds and for indicating the result not covered by subgroups G01R19/16504, G01R19/16528, G01R19/16533 comparing DC or AC voltage with one threshold
-
- 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
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/70—Energy storage systems for electromobility, e.g. batteries
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/7072—Electromobility specific charging systems or methods for batteries, ultracapacitors, supercapacitors or double-layer capacitors
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02T90/10—Technologies relating to charging of electric vehicles
- Y02T90/12—Electric charging stations
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Power Engineering (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Transportation (AREA)
- Environmental & Geological Engineering (AREA)
- Game Theory and Decision Science (AREA)
- Mechanical Engineering (AREA)
- Educational Administration (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The invention belongs to the technical field of charge pile supervision, and particularly relates to a new energy automobile charge pile fault prediction system based on artificial intelligence, which comprises a server, a real-time detection and analysis module, a fault tracing module, a fortune table tracing module and a fault prediction reminding module; according to the invention, the target charging pile i is subjected to real-time detection analysis, so that a real-time detection qualified signal or a real-time detection unqualified signal is generated, the historical fault of the corresponding target charging pile i is analyzed when the real-time detection qualified signal is generated, the time-of-day tracing qualified signal or the time-of-day tracing early warning signal is generated, the operation performance of the target charging pile i in an analysis period is analyzed when the time-of-day tracing qualified signal is generated, effective monitoring of a plurality of groups of charging piles in a monitoring area is realized, the fault risk degree of the charging piles is reasonably and accurately predicted, the monitoring personnel can timely check and maintain the corresponding charging piles, and the safe and stable operation of the monitored new energy automobile charging piles is ensured.
Description
Technical Field
The invention relates to the technical field of charging pile supervision, in particular to a new energy automobile charging pile fault prediction system based on artificial intelligence.
Background
The charging pile is a charging device for providing energy supplement for new energy electric vehicles, is similar to an oiling machine in a gas station, can charge various types of electric vehicles according to different voltage levels, generally provides two charging modes of conventional charging and quick charging, is usually installed in public buildings and residential parking lots or charging stations, and is used for carrying out corresponding charging operation and cost data printing by using a specific charging card to swipe a card on a man-machine interaction operation interface provided by the charging pile;
various faults can occur to the charging piles of the new energy automobiles after long-time use, the charging efficiency is influenced, meanwhile, the safety of users is threatened, at present, effective monitoring of a plurality of groups of charging piles in a supervision area is difficult, reasonable and accurate prediction of fault risks of the charging piles is difficult, supervision staff are not facilitated to master the fault risk degree of each charging pile in detail, and checking and maintenance of corresponding charging piles are timely carried out, so that the supervision difficulty is increased, and safe and stable operation of each charging pile of the new energy automobiles is difficult to ensure;
in view of the above technical drawbacks, a solution is now proposed.
Disclosure of Invention
The invention aims to provide a new energy automobile charging pile fault prediction system based on artificial intelligence, which solves the problems that in the prior art, effective monitoring of a plurality of groups of charging piles in a supervision area is difficult, reasonable and accurate prediction of fault risks of the charging piles is difficult, and supervision personnel are not favorable for grasping the fault risk degree of each charging pile in detail and checking and maintaining corresponding charging piles in time, so that safe and stable operation of the charging piles is difficult to ensure.
In order to achieve the above purpose, the present invention provides the following technical solutions:
the new energy automobile fills electric pile fault prediction system based on artificial intelligence, including server, real-time detection analysis module, fault tracing module, fortune table tracing module and fault prediction warning module; the server acquires a new energy automobile charging pile to be monitored, and marks the corresponding new energy automobile charging pile as a target charging pile i, wherein i is a natural number greater than 1; the real-time detection analysis module carries out real-time detection analysis on the target charging pile i, so as to generate a real-time detection qualified signal or a real-time detection unqualified signal, and the real-time detection unqualified signal is sent to the fault prediction reminding module through the server; when the fault prediction reminding module receives the real-time detection unqualified signals, corresponding fault prediction reminding information is generated and sent to the supervision terminal;
the real-time detection analysis module sends the real-time detection qualified signal to the fault tracing module through the server, the fault tracing module analyzes the historical fault of the target charging pile i when receiving the real-time detection qualified signal, so as to obtain the real-time failure evaluation coefficient of the target charging pile i, generates a failure tracing qualified signal or a failure tracing early warning signal, and sends the failure tracing early warning signal to the fault prediction reminding module through the server; when the fault prediction reminding module receives the fault tracing early warning signal, corresponding fault prediction reminding information is generated and sent to the supervision terminal;
the fault tracing module sends the time tracing qualified signal to the operation table tracing module through the server, when the operation table tracing module receives the time tracing qualified signal, the analysis period of the target charging pile i is determined, the operation performance of the target charging pile i in the analysis period is analyzed, the operation table tracing qualified signal or the operation table tracing unqualified signal of the target charging pile i is generated according to the analysis period, and the operation table tracing unqualified signal is sent to the fault prediction reminding module through the server; and when the fault prediction reminding module receives the operation table tracing disqualification signal, generating corresponding fault prediction reminding information and sending the corresponding fault prediction reminding information to the supervision terminal.
Further, the specific analysis process of the real-time detection analysis comprises the following steps:
acquiring an operation state of the target charging pile i, wherein the operation state comprises an idle state and a working state; when the target charging pile i is in an idle state or a working state, acquiring an internal Wen Shun increment, an internal humidity instantaneous increment and an internal smoke instantaneous increment of the target charging pile i in a detection period, respectively comparing the internal Wen Shun increment, the internal humidity instantaneous increment and the internal smoke instantaneous increment with a preset internal Wen Shun increment value, a preset internal humidity instantaneous increment value and a preset internal smoke instantaneous increment value, and generating a real-time detection failure signal if at least one of the internal Wen Shun increment, the internal humidity instantaneous increment and the internal smoke instantaneous increment exceeds a corresponding preset threshold value;
if the internal Wen Shun increment, the internal humidity instantaneous increment and the internal smoke instantaneous increment do not exceed the corresponding preset thresholds, acquiring the internal temperature data, the internal humidity data and the internal smoke data of the target charging pile i in the detection period, and performing numerical calculation on the internal temperature data, the internal humidity data and the internal smoke data to acquire an internal measurement analysis value; the vibration measurement data and the noise measurement data of the target charging pile i are obtained through internal auxiliary detection analysis, and numerical calculation is carried out on the vibration measurement data and the noise measurement data to obtain an internal auxiliary analysis value; and respectively comparing the internal analysis value and the internal auxiliary analysis value with a preset internal analysis threshold value and an internal auxiliary analysis threshold value in numerical value, and generating a real-time detection failure signal if at least one of the internal analysis value and the internal auxiliary analysis value exceeds the corresponding preset threshold value.
Further, the specific analysis process of the internal auxiliary detection analysis is as follows:
acquiring a vibration curve graph and a noise curve graph of a target charging pile i in a detection period, and accordingly acquiring the time length when the vibration amplitude of the target charging pile i exceeds a corresponding preset threshold value and the time length when the noise intensity exceeds the corresponding preset threshold value, and marking the time length as the vibration overtime length and the noise overtime length respectively; the maximum value and the minimum value of the vibration amplitude of the target charging pile i in the detection period are collected, the maximum value and the minimum value of the vibration amplitude are subjected to difference calculation to obtain vibration difference data, and noise difference data are obtained in a similar way; and weighting and summing the vibration overtime and the vibration difference data to obtain vibration measurement data, and weighting and summing the noise overtime and the noise difference data to obtain noise measurement data.
Further, if the internal analysis value and the internal auxiliary analysis value do not exceed the corresponding preset threshold values, performing state-division evaluation analysis, wherein the analysis process of the state-division evaluation analysis is specifically as follows:
if the target charging pile i is in an idle state, generating a real-time detection qualified signal;
if the target charging pile i is in a working state, collecting a voltage flow timeout value, a voltage stability value and a current stability value of the target charging pile i in a detection period, respectively comparing the voltage flow timeout value, the voltage stability value and the current stability value with a preset voltage flow timeout threshold value, a preset voltage stability threshold value and a preset current stability threshold value, and if at least one of the voltage flow timeout value, the voltage stability value and the current stability value exceeds a corresponding preset threshold value, generating a real-time detection failure signal;
if the voltage current timeout value, the voltage stability value and the current stability value do not exceed the corresponding preset thresholds, carrying out numerical calculation on the voltage current timeout value, the voltage stability value and the current stability value to obtain a charging hidden danger coefficient, carrying out numerical comparison on the charging hidden danger coefficient and a preset charging hidden danger coefficient threshold, and if the charging hidden danger coefficient exceeds the preset charging hidden danger coefficient threshold, generating a real-time detection failure signal; if the charging hidden danger coefficient does not exceed the preset charging hidden danger coefficient threshold value, a charging cable analysis value is called from the server, the charging cable analysis value is compared with the preset charging cable analysis threshold value in a numerical mode, and if the charging cable analysis value exceeds the preset charging cable analysis threshold value, a real-time detection failure signal is generated; and if the analysis value of the charging cable does not exceed the preset charging cable analysis threshold value, generating a real-time detection qualified signal.
Further, the server is in communication connection with the charging cable monitoring module, and the charging cable monitoring module is used for monitoring and analyzing the corresponding charging cable when the target charging pile i is in a working state, so as to obtain a charging cable analysis value, and sending the charging cable analysis value to the server for storage; the specific analysis and acquisition method of the charging cable analysis value is as follows:
acquiring a plurality of monitoring points preset on a charging cable to which a target charging pile i belongs, acquiring average current, average voltage and average temperature of the monitoring points corresponding to a detection period, performing difference calculation on the average current of the corresponding monitoring points compared with the median value of a preset average current range, taking an absolute value to obtain line flow data, acquiring line pressure data and line temperature data in the same way, performing numerical calculation on the line flow data, the line pressure data and the line temperature data to obtain line point detection values, and performing numerical comparison on the line point detection values and preset line point detection threshold values;
if the line point detection value exceeds a preset line point detection threshold value, marking the corresponding monitoring point as a hidden danger point; calculating the ratio of the number of hidden danger points to the number of monitoring points to obtain a cable hidden danger value; calculating the average current of two adjacent groups of monitoring points by means of difference value calculation and taking absolute value to obtain adjacent current difference value, and calculating the average value of all adjacent current difference values to obtain adjacent current difference data, and similarly obtaining adjacent differential pressure data and adjacent differential temperature data; and carrying out numerical calculation on the adjacent flow difference data, the adjacent pressure difference data, the adjacent temperature difference data and the cable hidden danger value of the charging cable to which the target charging pile i belongs to obtain a charging cable analysis value.
Further, the specific operation process of the fault tracing module includes:
acquiring each fault occurrence time of a target charging pile i, performing time difference calculation on two adjacent groups of fault occurrence time to obtain fault interval time, acquiring all fault interval time of the target charging pile i in the history operation process, arranging all fault interval time according to the sequence from the large value to the small value, eliminating the fault interval time positioned in the front j position and the rear j position, and performing summation calculation and averaging on all the rest fault interval time to obtain a time-averaged time;
collecting the occurrence time of the adjacent last fault of the target charging pile i, calculating the time difference between the current time and the occurrence time of the adjacent last fault to obtain a real-time event value, and subtracting the real-time event average time length from the real-time event value to obtain a real-time event evaluation coefficient; comparing the real-time evaluation coefficient with a preset real-time evaluation coefficient threshold value, and generating a time tracing early warning signal if the real-time evaluation coefficient exceeds the preset real-time evaluation coefficient threshold value; if the real-time evaluation coefficient does not exceed the preset real-time evaluation coefficient threshold, generating a time-of-failure tracing qualified signal; and sending the qualified time tracing signals to the operation table tracing module through the server.
Further, the specific operation process of the operation table tracing module comprises the following steps:
marking the interval time between the last fault occurrence time and the current time of the target charging pile i as an analysis time, collecting the charging times and the charging time of the target charging pile i in the analysis time, respectively comparing the charging times and the charging time with a preset charging times threshold value and a preset charging time threshold value, and generating a running form tracing disqualification signal if the charging times or the charging time exceeds the corresponding preset threshold value;
if the charging times and the charging duration do not exceed the corresponding preset thresholds, collecting charging efficiency data of the target charging pile i in each charging in the analysis period, and collecting charging speed fluctuation values and average charging speed data of the target charging pile i in each charging in the analysis period; carrying out numerical calculation on the charging efficiency data, the charging speed fluctuation value and the average charging speed data to obtain a charging current value;
comparing the charging current value with a preset charging performance threshold value, and judging that the corresponding charging process is poor in performance if the charging current value does not exceed the preset charging performance threshold value; and marking the number of times of the poor performance of the charging process of the target charging pile i in the analysis period as a poor charging frequency, carrying out numerical calculation on the poor charging frequency, the charging frequency and the charging time to obtain a running table tracing value, carrying out numerical comparison on the running table tracing value and a preset running table tracing threshold value, generating a running table tracing disqualification signal if the running table tracing value exceeds the preset running table tracing threshold value, and generating a running table tracing qualification signal if the running table tracing value does not exceed the preset running table tracing threshold value.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the invention, the target charging pile i is subjected to real-time detection analysis, so that a real-time detection qualified signal or a real-time detection unqualified signal is generated, and the real-time detection unqualified signal is sent to the fault prediction reminding module through the server, so that corresponding supervisory personnel can timely check and maintain the target charging pile i, the potential safety hazard is eliminated, and the safe and stable operation of the target charging pile i is ensured; when the real-time detection qualified signal is generated, the historical faults of the corresponding target charging pile i are analyzed, so that the time-to-time traceable qualified signal or the time-to-time traceable early warning signal is generated, and the corresponding supervisory personnel can perform comprehensive inspection and maintenance on the corresponding target charging pile i in time, so that the fault risk of the corresponding target charging pile i is eliminated;
2. according to the invention, the analysis period of the target charging pile i is determined when the qualified signal is traced when the accident is generated, and the operation performance of the target charging pile i in the analysis period is analyzed, so that the operation table tracing qualified signal or the operation table tracing unqualified signal of the target charging pile i is generated, the effective monitoring of a plurality of groups of charging piles in the monitoring area is realized, the fault risks of all the charging piles are reasonably and accurately predicted, the monitoring personnel can master the fault risk degree of each charging pile in detail, the corresponding charging pile is inspected and maintained in time, the operation monitoring difficulty of the charging pile of the new energy automobile is remarkably reduced, and the safe and stable operation of the monitored charging pile of the new energy automobile is further ensured.
Drawings
For the convenience of those skilled in the art, the present invention will be further described with reference to the accompanying drawings;
FIG. 1 is a system block diagram of a first embodiment of the present invention;
fig. 2 is a system block diagram of a second embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Embodiment one: as shown in fig. 1, the new energy automobile charging pile fault prediction system based on artificial intelligence provided by the invention comprises a server, a real-time detection and analysis module, a fault tracing module, a fortune table tracing module and a fault prediction reminding module, wherein the server is in communication connection with the real-time detection and analysis module, the fault tracing module, the fortune table tracing module and the fault prediction reminding module, and the fault prediction reminding module is in communication connection with a supervision terminal; the method comprises the steps that a server obtains new energy automobile charging piles to be monitored, corresponding new energy automobile charging piles are marked as target charging piles i, and the fact that i represents the number of the new energy automobile charging piles and i is a natural number larger than 1 is needed;
the real-time detection analysis module carries out real-time detection analysis on the target charging pile i, so as to generate a real-time detection qualified signal or a real-time detection unqualified signal, and the real-time detection unqualified signal is sent to the fault prediction reminding module through the server; when the fault prediction reminding module receives the real-time detection failure signal, corresponding fault prediction reminding information is generated and sent to the supervision terminal, so that corresponding supervision personnel can timely check and maintain the target charging pile i, potential safety hazards are eliminated, and safe and stable operation of the target charging pile i is ensured; the specific analysis process of the real-time detection analysis is as follows:
acquiring an operation state of a target charging pile i, wherein the operation state comprises an idle state and a working state, the working state is a state of charging a new energy automobile, and the idle state is a state of not charging; when the target charging pile i is in an idle state or a working state, acquiring an internal Wen Shun increment, an internal humidity instantaneous increment and an internal smoke instantaneous increment of the target charging pile i in a detection period, wherein the internal Wen Shun increment is a data value representing the instantaneous temperature increment of the target charging pile i, the internal humidity instantaneous increment is a data value representing the instantaneous humidity increment of the target charging pile i, and the internal smoke increment is a data value representing the instantaneous smoke concentration increment of the target charging pile i;
respectively comparing the internal Wen Shun increment, the internal humidity instantaneous increment and the internal smoke instantaneous increment with preset internal Wen Shun increment thresholds, internal humidity instantaneous increment thresholds and internal smoke instantaneous increment thresholds, and generating a real-time detection disqualification signal if at least one of the internal Wen Shun increment, the internal humidity instantaneous increment and the internal smoke instantaneous increment exceeds the corresponding preset threshold, which indicates that the potential safety hazard existing in the charging pile is larger;
if the internal Wen Shun increment, the internal humidity instantaneous increment and the internal smoke instantaneous increment do not exceed the corresponding preset thresholds, acquiring the internal temperature data, the internal humidity data and the internal smoke data of the target charging pile i in the detection period, wherein the internal temperature data, the internal humidity data and the internal smoke data respectively represent the data values of the internal temperature, the internal humidity and the internal smoke concentration; internal temperature data QWi, internal humidity data QSi and internal smoke data QYi are subjected to numerical calculation through a formula nci=a1× QWi +a2× QSi +a3× QYi to obtain an internal measurement analysis value NCi; wherein a1, a2 and a3 are preset weight coefficients, and a3 is more than a1 and more than a2 and more than 0; moreover, the larger the numerical value of the internal measurement analysis value NCi is, the larger the internal potential safety hazard of the target charging pile i is, and the more faults are likely to occur;
vibration measurement data and noise measurement data of the target charging pile i are obtained through internal auxiliary detection analysis, and the vibration measurement data and the noise measurement data are specifically: acquiring a vibration curve graph and a noise curve graph of a target charging pile i in a detection period, and accordingly acquiring the time length when the vibration amplitude of the target charging pile i exceeds a corresponding preset threshold value and the time length when the noise intensity exceeds the corresponding preset threshold value, and marking the time length as the vibration overtime length and the noise overtime length respectively; the maximum value and the minimum value of the vibration amplitude of the target charging pile i in the detection period are collected, the maximum value and the minimum value of the vibration amplitude are subjected to difference calculation to obtain vibration difference data, and noise difference data are obtained in a similar way;
weighting and summing the vibration overtime length ZSi and the vibration difference data ZPi to obtain vibration measurement data ZCi through a formula ZCi =b1×zsi+b2× ZPi, and weighting and summing the noise overtime length FSi and the noise difference data FPi to obtain noise measurement data TCi through a formula tci=b3×fsi+b4× FPi; wherein b1, b2, b3 and b4 are preset weight coefficients, and the values of b1, b2, b3 and b4 are all larger than zero;
numerical calculation is carried out on vibration measurement data ZCi and noise measurement data TCi through a formula nfi= (eg1 x ZCi +eg2 x TCi)/(eg1+eg2) to obtain an internal auxiliary analysis value NFi; wherein, eg1 and eg2 are preset proportionality coefficients, eg1 > eg2 > 1; and, the larger the value of the internal auxiliary analysis value NFi is, the more abnormal the operation of the target charging pile i is, and the greater the possibility of faults is; and respectively carrying out numerical comparison on the internal measurement analysis value NCi and the internal auxiliary analysis value NFi and a preset internal measurement analysis threshold value and an internal auxiliary analysis threshold value, and generating a real-time detection failure signal if at least one item in the internal measurement analysis value NCi and the internal auxiliary analysis value NFi exceeds the corresponding preset threshold value.
If the internal analysis value NCi and the internal auxiliary analysis value NFi do not exceed the corresponding preset thresholds, carrying out state-division evaluation analysis, wherein the analysis process of the state-division evaluation analysis specifically comprises the following steps: if the target charging pile i is in an idle state, generating a real-time detection qualified signal;
if the target charging pile i is in a working state, collecting a voltage flow timeout value, a voltage stability value and a current stability value of the target charging pile i in a detection period, wherein the voltage flow timeout value is a data value representing the duration and the value of the voltage which is not in a preset voltage range and the current which is not in a preset current range; the voltage stability value and the current stability value are data magnitude values representing the voltage fluctuation condition and the current fluctuation condition, and the larger the fluctuation degree of the voltage and the current is, the larger the values of the voltage stability value and the current stability value are, and the more unstable the charging process is;
respectively comparing the voltage current timeout value, the voltage stability value and the current stability value with a preset voltage current timeout threshold value, a preset voltage stability threshold value and a preset current stability threshold value, and generating a real-time detection failure signal if at least one of the voltage current timeout value, the voltage stability value and the current stability value exceeds the corresponding preset threshold value; if the current timeout value, the voltage stability value and the current stability value do not exceed the corresponding preset thresholds, calculating the current timeout value YLi, the voltage stability value YWi and the current stability value LWi according to a formula CYi =fu1× YLi +fu2× YWi +fu3× LWi to obtain a charging hidden danger coefficient CYi, wherein fu1, fu2 and fu3 are preset weight coefficients, and the values of fu1, fu2 and fu3 are all larger than zero; and, the larger the value of the charging hidden trouble coefficient CYi is, the worse the charging condition is, and the greater the possibility of faults is;
comparing the charging hidden danger coefficient CYi with a preset charging hidden danger coefficient threshold value in a numerical mode, and generating a real-time detection failure signal if the charging hidden danger coefficient CYi exceeds the preset charging hidden danger coefficient threshold value; if the charging hidden danger coefficient CYi does not exceed the preset charging hidden danger coefficient threshold, a charging cable analysis value XFi is called from the server, the charging cable analysis value XFi is compared with a preset charging cable analysis threshold in a numerical mode, and if the charging cable analysis value XFi exceeds the preset charging cable analysis threshold, a real-time detection failure signal is generated; if the charging cable analysis value XFi does not exceed the preset charging cable analysis threshold, a real-time detection pass signal is generated.
The real-time detection analysis module sends the real-time detection qualified signal to the fault tracing module through the server, the fault tracing module analyzes the historical fault of the target charging pile i when receiving the real-time detection qualified signal, so as to obtain the real-time failure evaluation coefficient of the target charging pile i, generates a failure tracing qualified signal or a failure tracing early warning signal, and sends the failure tracing early warning signal to the fault prediction reminding module through the server; when the fault prediction reminding module receives the fault tracing early warning signal, corresponding fault prediction reminding information is generated and sent to the supervision terminal, so that corresponding supervision personnel can timely perform comprehensive inspection and maintenance on the target charging pile i, and possible fault risks are eliminated; the specific operation process of the fault tracing module is as follows:
acquiring each fault occurrence time of a target charging pile i, performing time difference calculation on two adjacent groups of fault occurrence time to obtain fault interval time, acquiring all fault interval time of the target charging pile i in the history operation process, arranging all fault interval time according to the sequence from the large value to the small value, and eliminating the fault interval time positioned in the front j bits and the rear j bits, wherein j is preferably not less than 2; and the rest fault interval time is summed and calculated and the average value is taken to obtain the time-of-failure average time length, so that the data accuracy is ensured, and the accuracy of the analysis result is improved;
collecting the occurrence time of the adjacent last fault of the target charging pile i, calculating the time difference between the current time and the occurrence time of the adjacent last fault to obtain a real-time event value, and subtracting the real-time event average time length from the real-time event value to obtain a real-time event evaluation coefficient; the larger the value of the real-time failure evaluation coefficient is, the larger the risk of failure is, and the more the real-time failure evaluation coefficient is required to be checked and maintained comprehensively in time; comparing the real-time evaluation coefficient with a preset real-time evaluation coefficient threshold value, and generating a time tracing early warning signal if the real-time evaluation coefficient exceeds the preset real-time evaluation coefficient threshold value; if the real-time evaluation coefficient does not exceed the preset real-time evaluation coefficient threshold value, generating a time-of-failure tracing qualified signal.
The fault tracing module sends the time tracing qualified signal to the operation table tracing module through the server, when the operation table tracing module receives the time tracing qualified signal, the analysis period of the target charging pile i is determined, the operation performance of the target charging pile i in the analysis period is analyzed, the operation table tracing qualified signal or the operation table tracing unqualified signal of the target charging pile i is generated according to the analysis period, and the operation table tracing unqualified signal is sent to the fault prediction reminding module through the server; when the fault prediction reminding module receives the operation table tracing disqualified signals, corresponding fault prediction reminding information is generated and sent to the supervision terminal, so that corresponding supervision personnel can timely check and maintain the target charging pile i, potential safety hazards are eliminated, and safe and stable operation of the target charging pile i is ensured; the specific operation process of the operation table tracing module is as follows:
marking the interval time between the last fault occurrence time and the current time of the target charging pile i as an analysis time period, and collecting the charging times and the charging time length of the target charging pile i in the analysis time period, wherein the charging time length is a data value representing the total charging time length of the target charging pile i in the analysis time period; it should be noted that, the larger the charging frequency is, the longer the charging time is, and the larger the fault risk of the target charging pile i is; respectively carrying out numerical comparison on the charging times and the charging time and a preset charging times threshold and a preset charging time threshold, and if the charging times or the charging time exceeds the corresponding preset threshold, generating a running form tracing disqualification signal;
if the charging times and the charging duration do not exceed the corresponding preset thresholds, collecting charging efficiency data of each charging of the target charging pile i in an analysis period, wherein the charging efficiency data are data values representing the ratio of the electric quantity of the target charging pile i charged into the new energy automobile to the electric quantity of the target charging pile i output by the new energy automobile, and the larger the numerical value of the charging efficiency data is, the smaller the charging loss is, and the more normal the charging process is; collecting a charging speed fluctuation value and average charging speed data of the target charging pile i in each charging in an analysis period; the charging speed fluctuation value is a data value representing the degree of charging speed fluctuation, and the larger the value of the charging speed fluctuation value is, the more unstable the charging speed in the charging process is;
numerical calculation is performed on the charging efficiency data CTi, the charging speed fluctuation value CHi and the average charging speed data CFi through a formula CXi = (ht1+ht3×cfi)/(ht2×chi+1.216) to obtain a charging current value CXi; wherein, ht1, ht2 and ht3 are preset proportionality coefficients, and the values of ht1, ht2 and ht3 are all larger than zero; and, the larger the value of the charging current value CXi is, the better the charging condition corresponding to the charging process is indicated; comparing the charging current value CXi with a preset charging performance threshold value, and judging that the corresponding charging process is poor if the charging current value CXi does not exceed the preset charging performance threshold value;
marking the number of times of the difference in the charging process of the target charging pile i in the analysis period as a difference charging frequency CPi, and carrying out numerical calculation on the difference charging frequency CPi, the charging frequency CRi and the charging time CEi through a formula YSi=sq1, CPi+sq2, CRi+sq3, so as to obtain a running table tracing value YSi, wherein sq1, sq2 and sq3 are preset weight coefficients, and sq1 is more than sq2 is more than sq3 is more than 0; moreover, the larger the value of the operation table tracing value YSi is, the worse the operation tracing condition of the target charging pile i is, and the easier the operation fault is; and carrying out numerical comparison on the operation table tracing value YSi and a preset operation table tracing threshold, if the operation table tracing value YSi exceeds the preset operation table tracing threshold, generating an operation table tracing disqualification signal, and if the operation table tracing value YSi does not exceed the preset operation table tracing threshold, generating an operation table tracing qualification signal.
Embodiment two: as shown in fig. 2, the difference between the present embodiment and embodiment 1 is that the server is in communication connection with the charging cable monitoring module, and the charging cable monitoring module is configured to monitor and analyze the corresponding charging cable when the target charging pile i is in a working state, so as to obtain a charging cable analysis value XFi, and send the charging cable analysis value to the server for storage, so as to provide data support for real-time detection and analysis, and help to understand the safety condition of the charging cable to which the target charging pile i belongs, and further help to ensure charging safety; the specific analysis and acquisition method of the charging cable analysis value XFi is as follows:
acquiring a plurality of monitoring points preset on a charging cable to which a target charging pile i belongs, wherein the distances between two adjacent groups of monitoring points are the same, acquiring average current, average voltage and average temperature of the monitoring points corresponding to a detection period, performing difference calculation on the average current of the corresponding monitoring points compared with the median value of a preset average current range, taking an absolute value to obtain line flow data XLI, acquiring line pressure data XYi and line temperature data XWi in a similar way, and performing numerical calculation on the line flow data, the line pressure data and the line temperature data through a formula XCi =bf1 xLi+bf2 x XYi +bf3 x XYi to obtain a line point detection value XCi; wherein bf1, bf2 and bf3 are preset weight coefficients, and the values of bf1, bf2 and bf3 are all larger than zero; and, the larger the value of the line point detection value XCi is, the greater the risk degree of the corresponding monitoring point is;
comparing the line point detection value XCi of the corresponding monitoring point with a preset line point detection threshold value; if the line point detection value XCi exceeds a preset line point detection threshold, marking the corresponding monitoring point as a hidden danger point, and calculating the ratio of the number of hidden danger points to the number of monitoring points to obtain a cable hidden danger value XHi; calculating the average current of two adjacent groups of monitoring points by difference value, taking absolute value to obtain adjacent current difference value, calculating the average value of all adjacent current difference values to obtain adjacent current difference data KLi, and similarly obtaining adjacent differential pressure data RLi and adjacent differential temperature data WLi;
calculating the adjacent flow difference data KLi, the adjacent pressure difference data RLi, the adjacent temperature difference data WLi and the cable hidden danger value XHi of the charging cable to which the target charging pile i belongs to obtain a charging cable analysis value XFi through a formula XFi =et1×KLi+et2×RLi+et3×WLi+et4× XHi; wherein, et1, et2, et3, et4 are preset weight coefficients, and et4 > et3 > et1 > et2 > 0; and, the magnitude of the charging cable analysis value XFi is in a proportional relation with the adjacent flow difference data KLi, the adjacent pressure difference data RLi, the adjacent temperature difference data WLi and the cable hidden trouble value XHi, and the larger the magnitude of the charging cable analysis value XFi is, the greater the current operation risk degree of the charging cable to which the target charging pile i belongs is, the greater the possibility of faults is, and the more unfavorable is the safety charging of the new energy electric automobile ensured.
The working principle of the invention is as follows: when the system is used, the real-time detection analysis module is used for carrying out real-time detection analysis on the target charging pile i, so that a real-time detection qualified signal or a real-time detection unqualified signal is generated, the real-time detection unqualified signal is sent to the fault prediction reminding module through the server, so that corresponding supervision personnel can timely carry out inspection and maintenance on the target charging pile i, the potential safety hazard is eliminated, and the safe and stable operation of the target charging pile i is ensured; when the real-time detection qualified signal is generated, the historical faults of the corresponding target charging pile i are analyzed through a fault tracing module, so that the time-of-use tracing qualified signal or the time-of-use tracing early-warning signal is generated, the time-of-use tracing early-warning signal is sent to a fault prediction reminding module through a server, and accordingly, corresponding supervisory personnel can timely perform comprehensive inspection and maintenance of the corresponding target charging pile i, and possible fault risks are eliminated; and when the qualified signals are traced back during generation of the faults, the analysis period of the target charging pile i is determined through the operation table tracing module, and the operation performance of the target charging pile i in the analysis period is analyzed, so that the operation table tracing qualified signals or operation table tracing unqualified signals of the target charging pile i are generated, the corresponding monitoring personnel can check and maintain the corresponding target charging pile i in time, the potential safety hazards are eliminated, the safe and stable operation of the target charging pile i is further ensured, the effective monitoring of a plurality of groups of charging piles in the monitoring area is realized, the fault risk of all the charging piles is reasonably and accurately predicted, the monitoring personnel can master the fault risk degree of each charging pile in detail, and check and maintain the corresponding charging pile in time, and the operation monitoring difficulty of the charging pile of the new energy automobile is remarkably reduced.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation. The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (7)
1. The new energy automobile fills electric pile trouble prediction system based on artificial intelligence, characterized by that, including server, real-time detection analysis module, trouble trace back module, fortune table trace back module and trouble predict the warning module; the server acquires a new energy automobile charging pile to be monitored, and marks the corresponding new energy automobile charging pile as a target charging pile i, wherein i is a natural number greater than 1; the real-time detection analysis module carries out real-time detection analysis on the target charging pile i, so as to generate a real-time detection qualified signal or a real-time detection unqualified signal, and the real-time detection unqualified signal is sent to the fault prediction reminding module through the server; when the fault prediction reminding module receives the real-time detection unqualified signals, corresponding fault prediction reminding information is generated and sent to the supervision terminal;
the real-time detection analysis module sends the real-time detection qualified signal to the fault tracing module through the server, the fault tracing module analyzes the historical fault of the target charging pile i when receiving the real-time detection qualified signal, so as to obtain the real-time failure evaluation coefficient of the target charging pile i, generates a failure tracing qualified signal or a failure tracing early warning signal, and sends the failure tracing early warning signal to the fault prediction reminding module through the server; when the fault prediction reminding module receives the fault tracing early warning signal, corresponding fault prediction reminding information is generated and sent to the supervision terminal;
the fault tracing module sends the time tracing qualified signal to the operation table tracing module through the server, when the operation table tracing module receives the time tracing qualified signal, the analysis period of the target charging pile i is determined, the operation performance of the target charging pile i in the analysis period is analyzed, the operation table tracing qualified signal or the operation table tracing unqualified signal of the target charging pile i is generated according to the analysis period, and the operation table tracing unqualified signal is sent to the fault prediction reminding module through the server; and when the fault prediction reminding module receives the operation table tracing disqualification signal, generating corresponding fault prediction reminding information and sending the corresponding fault prediction reminding information to the supervision terminal.
2. The new energy automobile fills electric pile fault prediction system based on artificial intelligence of claim 1, wherein the specific analysis process of real-time detection analysis includes:
acquiring an operation state of the target charging pile i, wherein the operation state comprises an idle state and a working state; when the target charging pile i is in an idle state or a working state, acquiring the internal Wen Shun increment, the internal humidity instantaneous increment and the internal smoke instantaneous increment of the target charging pile i in a detection period, and generating a real-time detection failure signal if at least one of the internal Wen Shun increment, the internal humidity instantaneous increment and the internal smoke instantaneous increment exceeds a corresponding preset threshold;
if the internal Wen Shun increment, the internal humidity instantaneous increment and the internal smoke instantaneous increment do not exceed the corresponding preset thresholds, acquiring the internal temperature data, the internal humidity data and the internal smoke data of the target charging pile i in the detection period, and performing numerical calculation on the internal temperature data, the internal humidity data and the internal smoke data to acquire an internal measurement analysis value; the vibration measurement data and the noise measurement data of the target charging pile i are obtained through internal auxiliary detection analysis, and numerical calculation is carried out on the vibration measurement data and the noise measurement data to obtain an internal auxiliary analysis value; and if at least one of the internal analysis value and the internal auxiliary analysis value exceeds a corresponding preset threshold value, generating a real-time detection failure signal.
3. The new energy automobile fills electric pile fault prediction system based on artificial intelligence of claim 2, wherein the specific analysis process of interior auxiliary detection analysis is as follows:
acquiring a vibration curve graph and a noise curve graph of a target charging pile i in a detection period, and accordingly acquiring the time length when the vibration amplitude of the target charging pile i exceeds a corresponding preset threshold value and the time length when the noise intensity exceeds the corresponding preset threshold value, and marking the time length as the vibration overtime length and the noise overtime length respectively; the maximum value and the minimum value of the vibration amplitude of the target charging pile i in the detection period are collected, the maximum value and the minimum value of the vibration amplitude are subjected to difference calculation to obtain vibration difference data, and noise difference data are obtained in a similar way; and weighting and summing the vibration overtime and the vibration difference data to obtain vibration measurement data, and weighting and summing the noise overtime and the noise difference data to obtain noise measurement data.
4. The new energy automobile charging pile fault prediction system based on artificial intelligence according to claim 1, wherein if the internal measurement analysis value and the internal auxiliary analysis value do not exceed the corresponding preset thresholds, performing state-division evaluation analysis, wherein the analysis process of the state-division evaluation analysis is specifically as follows:
if the target charging pile i is in an idle state, generating a real-time detection qualified signal;
if the target charging pile i is in a working state, collecting a voltage flow timeout value, a voltage stability value and a current stability value of the target charging pile i in a detection period, and if at least one of the voltage flow timeout value, the voltage stability value and the current stability value exceeds a corresponding preset threshold value, generating a real-time detection failure signal;
if the voltage current timeout value, the voltage stability value and the current stability value do not exceed the corresponding preset threshold values, carrying out numerical calculation on the voltage current timeout value, the voltage stability value and the current stability value to obtain a charging hidden danger coefficient; if the charging hidden danger coefficient exceeds a preset charging hidden danger coefficient threshold value, generating a real-time detection failure signal; if the charging hidden danger coefficient does not exceed the preset charging hidden danger coefficient threshold value, a charging cable analysis value is called from the server, the charging cable analysis value is compared with the preset charging cable analysis threshold value in a numerical mode, and if the charging cable analysis value exceeds the preset charging cable analysis threshold value, a real-time detection failure signal is generated; and if the analysis value of the charging cable does not exceed the preset charging cable analysis threshold value, generating a real-time detection qualified signal.
5. The new energy automobile charging pile fault prediction system based on artificial intelligence according to claim 4, wherein the server is in communication connection with a charging cable monitoring module, the charging cable monitoring module is used for monitoring and analyzing a corresponding charging cable when a target charging pile i is in a working state, so as to obtain a charging cable analysis value, and the charging cable analysis value is sent to the server for storage; the specific analysis and acquisition method of the charging cable analysis value is as follows:
acquiring a plurality of monitoring points preset on a charging cable to which a target charging pile i belongs, acquiring average current, average voltage and average temperature of the monitoring points corresponding to a detection period, performing difference calculation on the average current of the corresponding monitoring points compared with the median value of a preset average current range, taking an absolute value to obtain line flow data, acquiring line pressure data and line temperature data in the same way, and performing numerical calculation on the line flow data, the line pressure data and the line temperature data to obtain line point detection values;
if the line point detection value exceeds a preset line point detection threshold value, marking the corresponding monitoring point as a hidden danger point; calculating the ratio of the number of hidden danger points to the number of monitoring points to obtain a cable hidden danger value; calculating the average current of two adjacent groups of monitoring points by means of difference value calculation and taking absolute value to obtain adjacent current difference value, and calculating the average value of all adjacent current difference values to obtain adjacent current difference data, and similarly obtaining adjacent differential pressure data and adjacent differential temperature data; and carrying out numerical calculation on the adjacent flow difference data, the adjacent pressure difference data, the adjacent temperature difference data and the cable hidden danger value of the charging cable to which the target charging pile i belongs to obtain a charging cable analysis value.
6. The new energy automobile fills electric pile fault prediction system based on artificial intelligence of claim 1, wherein the specific operation process of the fault tracing module includes:
acquiring each fault occurrence time of a target charging pile i, performing time difference calculation on two adjacent groups of fault occurrence time to obtain fault interval time, acquiring all fault interval time of the target charging pile i in the history operation process, arranging all fault interval time according to the sequence from the large value to the small value, eliminating the fault interval time positioned in the front j position and the rear j position, and performing summation calculation and averaging on all the rest fault interval time to obtain a time-averaged time;
collecting the occurrence time of the adjacent last fault of the target charging pile i, calculating the time difference between the current time and the occurrence time of the adjacent last fault to obtain a real-time event value, and subtracting the real-time event average time length from the real-time event value to obtain a real-time event evaluation coefficient; if the real-time evaluation coefficient exceeds a preset real-time evaluation coefficient threshold value, generating a time-of-failure tracing early warning signal; if the real-time evaluation coefficient does not exceed the preset real-time evaluation coefficient threshold, generating a time-of-failure tracing qualified signal; and sending the qualified time tracing signals to the operation table tracing module through the server.
7. The new energy automobile fills electric pile fault prediction system based on artificial intelligence of claim 6, wherein the specific operation process of fortune table retrospective module includes:
marking the interval time between the last fault occurrence time and the current time of the target charging pile i as an analysis time, collecting the charging times and the charging time of the target charging pile i in the analysis time, and generating a running form tracing disqualification signal if the charging times or the charging time exceeds a corresponding preset threshold; if the charging times and the charging duration do not exceed the corresponding preset thresholds, collecting charging efficiency data of the target charging pile i in each charging in the analysis period, and collecting charging speed fluctuation values and average charging speed data of the target charging pile i in each charging in the analysis period; carrying out numerical calculation on the charging efficiency data, the charging speed fluctuation value and the average charging speed data to obtain a charging current value;
if the charging current value does not exceed the preset charging performance threshold, judging that the corresponding charging process is poor in performance; marking the number of times of the poor charging process of the analysis period target charging pile i as a poor charging frequency, and carrying out numerical calculation on the poor charging frequency, the charging frequency and the charging duration to obtain a running table traceability value; and if the operation table tracing value does not exceed the preset operation table tracing threshold, generating an operation table tracing disqualification signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311098061.1A CN117148001A (en) | 2023-08-29 | 2023-08-29 | New energy automobile fills electric pile fault prediction system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311098061.1A CN117148001A (en) | 2023-08-29 | 2023-08-29 | New energy automobile fills electric pile fault prediction system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117148001A true CN117148001A (en) | 2023-12-01 |
Family
ID=88909328
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311098061.1A Pending CN117148001A (en) | 2023-08-29 | 2023-08-29 | New energy automobile fills electric pile fault prediction system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117148001A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117371670A (en) * | 2023-12-07 | 2024-01-09 | 深圳汇能新能源科技有限公司 | Reliability analysis system of new energy electric automobile fills electric pile |
| CN117477495A (en) * | 2023-12-28 | 2024-01-30 | 国网山西省电力公司太原供电公司 | Current transformer state monitoring system and method |
| CN117644794A (en) * | 2024-01-26 | 2024-03-05 | 昱洁电气科技(无锡)有限公司 | Intelligent period control system based on charging pile |
-
2023
- 2023-08-29 CN CN202311098061.1A patent/CN117148001A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117371670A (en) * | 2023-12-07 | 2024-01-09 | 深圳汇能新能源科技有限公司 | Reliability analysis system of new energy electric automobile fills electric pile |
| CN117371670B (en) * | 2023-12-07 | 2024-03-12 | 深圳汇能新能源科技有限公司 | Reliability analysis system of new energy electric automobile fills electric pile |
| CN117477495A (en) * | 2023-12-28 | 2024-01-30 | 国网山西省电力公司太原供电公司 | Current transformer state monitoring system and method |
| CN117477495B (en) * | 2023-12-28 | 2024-03-12 | 国网山西省电力公司太原供电公司 | Current transformer state monitoring system and method |
| CN117644794A (en) * | 2024-01-26 | 2024-03-05 | 昱洁电气科技(无锡)有限公司 | Intelligent period control system based on charging pile |
| CN117644794B (en) * | 2024-01-26 | 2024-04-09 | 昱洁电气科技(无锡)有限公司 | Intelligent period control system based on charging pile |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117148001A (en) | New energy automobile fills electric pile fault prediction system based on artificial intelligence | |
| CN114640173B (en) | Early warning model of transformer and generator based on many characteristic quantities | |
| CN114819415B (en) | Power equipment fault prediction system based on data analysis | |
| CN104767482B (en) | A kind of photovoltaic module is aging and short trouble inline diagnosis method | |
| CN109765459B (en) | Single-phase earth fault positioning method and system based on in-situ study and judgment | |
| US20210278464A1 (en) | Condition assessment method and device for an outdoor post-mounted vacuum switch | |
| CN117040138B (en) | Power distribution cabinet operation dynamic safety evaluation system | |
| CN110703009B (en) | Abnormal analysis and processing method for line loss rate of transformer area | |
| CN115566804B (en) | Electric power monitoring system based on distributed optical fiber sensing technology | |
| CN104972926A (en) | Method for detecting and locating battery fault of electric vehicle | |
| CN116757482B (en) | Fault supervision and maintenance system for new energy power battery production | |
| CN116360367A (en) | Industrial equipment Internet of things data acquisition method and system | |
| CN109613372B (en) | Power grid fault diagnosis method based on multi-element power grid database | |
| CN114414940A (en) | Fault judgment method based on basic data of electricity utilization information acquisition system | |
| CN102095953A (en) | On-line detection method for performance of accumulator charger | |
| CN109884553B (en) | Real-time online diagnosis method and system for internal resistance consistency of super-capacitor energy storage power supply | |
| CN107274112B (en) | Diagnostic algorithm model for improving dissolved gas in oil | |
| CN110836835A (en) | Intelligent SF6 density on-line monitoring data analysis and information feedback system | |
| CN101620250B (en) | Self-adaptive monitoring method for measuring quality | |
| CN115455358A (en) | Electrical parameter trend early warning and fault diagnosis method based on nonlinear regression model | |
| CN111986469A (en) | Intelligent diagnosis method for field terminal fault | |
| CN204086497U (en) | Battery pack intelligent diagnosis system in relay station and microwave station | |
| CN116256691B (en) | Electric energy meter misalignment online monitoring method and system | |
| CN113552449B (en) | Four-level protection safety electricity consumption monitoring system and monitoring method | |
| CN117791869A (en) | Data online monitoring method and system based on intelligent power distribution cabinet |
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 |