CN111060839A - Universal LED power supply intelligent detection method and system - Google Patents
Universal LED power supply intelligent detection method and system Download PDFInfo
- Publication number
- CN111060839A CN111060839A CN201911417779.6A CN201911417779A CN111060839A CN 111060839 A CN111060839 A CN 111060839A CN 201911417779 A CN201911417779 A CN 201911417779A CN 111060839 A CN111060839 A CN 111060839A
- Authority
- CN
- China
- Prior art keywords
- data
- power supply
- led power
- lamp
- intelligent
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- 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
- G01R31/40—Testing power supplies
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M11/00—Testing of optical apparatus; Testing structures by optical methods not otherwise provided for
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M11/00—Testing of optical apparatus; Testing structures by optical methods not otherwise provided for
- G01M11/02—Testing optical properties
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Circuit Arrangement For Electric Light Sources In General (AREA)
Abstract
The invention discloses a universal LED power supply intelligent detection method and a universal LED power supply intelligent detection system. The invention belongs to the field of equipment abnormity detection of the Internet of things. The invention discloses a universal intelligent detection system for LED power supply faults, which comprises a sensor device, a wireless communication module and a data and control platform, wherein the sensor device is used for detecting abnormal protection such as LED power supply output voltage, output current, dimming port control of an intelligent power supply, short circuit and the like, and ambient temperature, humidity and brightness changes. By means of sensors such as current, voltage, temperature and humidity, brightness and color, power supply current and voltage, ambient brightness and temperature and other environmental data are collected to a data platform, the current and voltage changes of the power supply and the lamp and the ambient environmental data changes are comprehensively analyzed by a machine learning algorithm, and intelligent detection of the LED power supply is achieved on the premise of sufficiently protecting user privacy.
Description
Technical Field
The invention relates to the field of LED power supply detection, in particular to a universal LED power supply intelligent detection method and system.
Background
In the field of LED power supply detection, it often takes a lot of manpower and time to comprehensively detect various performances of an LED power supply, especially in the process of being put into mass production or being used in the market. Most of the existing detection methods need field operation, for example, power supply short circuit protection needs to be detected firstly, power supply output needs to be short-circuited, whether a circuit is protected or not needs to be tested, then the LED power supply is controlled to be switched on and switched off through a switch, the brightness of the LED power supply is watched, and the like, and then the change of a lamp is observed or the brightness data of the lamp is monitored to judge the quality of the power supply.
However, with the above detection method, there are the following disadvantages: 1. a large amount of manpower and time are required to be invested; 2, in the detection process, if the reasons such as field wiring errors occur, misjudgment is easily caused to detection personnel, so that a normal product or a normal LED power supply in use is treated as a defective product, and product waste or repeated rework is caused; 3. the power supply is short-circuited, and a bad LED power supply often burns many elements and even LED lamps.
In the market, some intelligent LED power supplies can only detect that a lamp is on, but what abnormality occurs in a specific intelligent LED power supply (such as an excessive current, an abnormal dimming and color mixing function) cannot be known, and the intelligent LED power supply has no universality.
Techniques related to the present invention include:
1. a method for routine detection of LED power supply.
For example: an LED lamp and an LED power supply detection and display device (application number: CN 201520722855.5).
The invention discloses an LED lamp and an LED power supply detection and display device, which comprises a power supply input module, an overcurrent protection module and a data processing and display module, wherein the overcurrent protection module is used for protecting the LED lamp and the LED power supply; the power input module is respectively and electrically connected with the overcurrent protection module and the data processing and display module; the overcurrent protection module is connected with an interface module, the interface module is electrically connected with the data processing and displaying module, and the data processing and displaying module is further connected with a human-computer interaction module. The data processing and display module acquires alternating current signal data of the LED lamp and direct current signal data and alternating current signal data of the LED power supply, acquires and displays various parameter values, and the overcurrent protection module can prevent the detected LED lamp and the LED power supply from being damaged and can ensure the safety of testing workers.
For example: an intelligent detection system for LED power supply (application number: CN 201320027478.4).
The invention discloses an intelligent LED power detection system, and aims to provide an intelligent LED power detection system which is simple in detection method, high in detection efficiency and capable of greatly improving detection quality. The device comprises an upper computer (1), a lower computer detection control unit (2) and a tested device access unit (3), wherein the lower computer detection control unit (2) is used for detecting peripheral tested LED power modules through the tested device access unit (3), and the upper computer (1) is used for controlling the detection process of the lower computer detection control unit (2) on the tested LED power modules and recording detection data in real time. The invention is applied to the field of LED power supply detection.
For example: an LED power supply detection system, a smelting tool and a device (application number: CN 201720879871.4).
The invention discloses an LED power supply detection system, a jig and a device, wherein the detection jig comprises a power supply placing unit, an output connecting unit and an input connecting unit, wherein the output connecting unit and the input connecting unit are rotatably connected to two ends of the power supply placing unit; the output connection unit is provided with a first pressing block and an output connection end, the power supply placing unit is provided with a first switch, when the output connection unit rotates to a first preset point position, the output connection end is connected with the output end of the power supply to be tested, and the first pressing block enables the first switch to be switched on; the input connecting unit is provided with a second pressing block and an input connecting end, the power supply placing unit is also provided with a second switch, when the input connecting unit rotates to a second preset point position, the input connecting end is connected with the input end of the power supply to be tested, and the second pressing block enables the second switch to be switched on; the detection circuit of the detection device is turned on according to the turning-on of the first switch and the second switch. Simple structure, the security is strong, and difficult emergence is electrocuted, situations such as short circuit, the commonality is strong.
The traditional technology has the following technical problems:
1. consuming time and labor. The existing detection methods of various power supplies mostly need to consume a large amount of labor and time cost, and special corresponding driving modules need to be searched for on-site detection and special modes of various power supply parameters, so that the purpose is only to improve the reliability and safety of detection without substantial innovation;
2. the operation is complicated and unsafe. In the current various power supply detection methods, various detection auxiliary equipment (a chassis, a detection circuit and the like) needs to be additionally installed, and after the installation is finished, the detection operation is complex and can be carried out by related professionals; the power supply test system and the load lamp are not protected, and test equipment can be damaged;
3. the resources are wasted. After the detection is finished, the equipment for detection cannot continuously play the detection or other roles, so that the resource waste is caused;
4. the accuracy is poor. The visual fatigue of people can cause the missing detection or the interference of external factors, and the defective products are mixed into the good products.
Disclosure of Invention
The invention provides a universal LED power supply intelligent detection method and a universal LED power supply intelligent detection system, and discloses a universal LED power supply intelligent detection system which integrates sensors of current, voltage, short-circuit protection, temperature, humidity, brightness and the like, a wireless communication module and a data control platform, and comprehensively analyzes lamp voltage and current data and surrounding environment data by combining a machine learning algorithm to realize intelligent detection of an LED power supply. The universal LED power supply intelligent detection system can detect abnormal conditions and alarm of the lamp in real time without consuming manpower and time after being installed and used; the intelligent power supply intelligently does not need to manually match a control module, and the inspection is finished; and (4) carrying out flow detection, abnormal parameters and full-process recording, accurately finding out a problem point for maintenance rework and quickly repairing. 2. The invention integrates various physical sensors relevant to the performance of the detection lamp, a wireless communication module, a data platform and a machine learning model. The collected lamp voltage and current and the surrounding environment data are comprehensively analyzed on a data platform, and a machine learning model aiming at various abnormal conditions of the power supply is generated, so that the intelligent detection of the LED power supply is realized. The intelligent lamp power supply can detect all sensible abnormal conditions of the lamp, has universality, and is applicable to both traditional lamp power supplies and intelligent lamp power supplies; 3. the system is simple to operate, safe and reliable, only needs simple and uniform installation modes for various types of power supplies, does not need human intervention, finds that the LED power supply is abnormal and automatically alarms after the system processes and analyzes data acquired remotely through a data platform, cuts off the power supply, protects the LED power supply and the lamp, avoids the loss of the test system caused by the abnormal power supply, can simultaneously detect the lamp in real time, and does not cause resource waste; the detection workload of enterprises producing power supplies and lamps is greatly reduced; 4. the accuracy is high, and to all power in the detection, realize the batch real-time detection to each trouble of lamps and lanterns, unusual real-time recording and warning avoid personnel to detect the error that brings with the environment, produce the defective products.
In order to solve the above technical problem, the present invention provides a general LED power supply intelligent detection system, including: the system comprises a processing chip, a communication module (Wi-Fi + RF2.4G), a voltage sensor, a current sensor, a circuit protection module, a temperature and humidity sensor, a brightness sensor, a color sensor and a data platform; the voltage and current module collects voltage and current information of intelligent and non-intelligent power supplies, and the temperature and humidity, brightness and color sensors collect temperature and humidity around the led power supplies, brightness information of load lamps and colors/color temperatures; sensor data are uploaded to a data platform through a communication module, the data are processed and classified on the data platform, a group of event processing analysis models (class analyzers) are integrated and respectively correspond to abnormal conditions of each LED power supply, and the event processing analysis models (class analyzers) are generated in a supervision machine learning mode; processing the special abnormity, cutting off the power supply, and protecting the power supply and the test equipment; the intelligent LED power supply is connected with the corresponding control interface according to the requirement, and dimming and color mixing detection and lamp switching detection are achieved.
A universal LED power supply intelligent detection method utilizing the universal LED power supply intelligent detection system comprises the following steps:
acquiring and uploading original data to a cloud platform;
screening original data of the cloud platform, calculating and comparing with an event processing analysis model (a category analyzer), and outputting whether the data is abnormal or not;
and step three, issuing the events and results output by the cloud platform to the wireless control module, and controlling the intelligent control interface and the protection device by the wireless control module according to the received instructions to give out warnings and record detection results.
In one embodiment, the first step specifically includes: acquiring and reporting power parameter data to a wireless communication module through a data acquisition module;
the wireless communication template transmits the data to the data reporting module;
data reporting module transmits data to cloud platform
The data acquisition module is as follows:
in one embodiment, the second step specifically includes:
2.1 when model training is carried out, different types of LED power supplies (common power supplies) and intelligent LED power supplies (adjustable brightness, color temperature and color) are used for training respectively, training is carried out under different scenes to enhance the uniqueness of each model, and the intelligent LED power supplies and power parameter interfaces select corresponding control interfaces;
the positions of the LED power supply and the load lamps and sensors are as follows:
2.2, when training a specific model, each specific abnormal condition needs to be simulated, and the abnormal conditions comprise:
LED power output is abnormal (only power is connected and the lamp is not connected, and the lamp is switched on and off to operate);
brightness adjustment is abnormal (the number of lamp strips or lamp beads of the lamp is reduced, and various brightnesses are adjusted as much as possible);
abnormal color temperature regulation (warm color lamp strips and cold color lamp strips of the lamp are respectively reduced, and various color temperatures are regulated as much as possible);
abnormal color adjustment (respectively reducing colored lamp strips corresponding to the lamps and adjusting different colors as much as possible);
current anomaly (the lamp current difference is larger as much as possible by testing with other power supplies with different current parameters);
voltage abnormity (a lamp which is not matched with a power supply is connected, and the lamp voltage difference is larger as far as possible);
no short-circuit protection abnormity (short circuit of lamp access line)
2.3 event processing analysis model training method
Step 1: pre-screening the acquired original data in the cloud platform;
step 2: then classifying the screened data;
and step 3: the classified data is packed, so that the data compression and confidentiality functions are realized; forming a characteristic data packet and marking a data type label;
and 4, step 4: and (4) transmitting the characteristic data packet to a data platform machine learning device, training an event recognition model together with the data type label, and forming an event processing analysis model (class analyzer). (the machine learner only uses during the model training phase, either as an off-line tool or online via an automated script.)
After training and cross validation, the event processing analysis model (class analyzer) is updated to a data platform, and can be used in a production environment.
2.4 the trained system can recognize the abnormal event of the power supply.
In one embodiment, the pre-screening algorithm proceeds as follows:
and in the model training stage, recording the voltage and current of a batch of LED power supplies with normal performance, normally opening a load LED lamp to acquire the characteristic values of normal brightness and color temperature (if the lamp with adjustable brightness, color temperature and color is a lamp with maximum brightness, any single color temperature or any single color, the characteristic values are recorded), calculating the average value and the standard deviation, and forming a corresponding data table after learning.
In one embodiment, step 2.4 specifically includes:
step 1: screening the acquired original data in the cloud platform;
step 2: then classifying the screened data;
and step 3: packing the classified data to form a characteristic numerical value packet;
and 4, step 4: and the characteristic numerical value packet is directly sent to an event processing analysis model (a category analyzer) in the data platform for calculation and comparison, and the identified event type and the credibility are output after the model identification is successful.
In one embodiment, the step three specifically includes:
3.1, aiming at the abnormal conditions of various LED power supplies, making judgment, transmitting the judgment to a data issuing module, controlling a power-off protection device of a protection device, providing abnormal warning and recording a detection result;
3.2 aiming at the normal condition of various LED power supplies, making judgment, transmitting the judgment to a data issuing module, giving a normal warning and recording a detection result.
Based on the same inventive concept, the present application also provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of any of the methods when executing the program.
Based on the same inventive concept, the present application also provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of any of the methods.
Based on the same inventive concept, the present application further provides a processor for executing a program, wherein the program executes to perform any one of the methods.
The invention has the beneficial effects that:
the intelligent detection of the LED power supply is realized, the detection is real-time and automatic, the LED power supply can be normally protected when abnormal, and the damage to equipment and lamps caused by the abnormal detection is reduced; and can detect most intelligent and traditional LED power on the market, have extensive commonality and scalability.
Drawings
Fig. 1 is a schematic structural diagram of a general LED power supply intelligent detection method system of the present invention.
FIG. 2 is a flowchart of training an event processing analysis model in the general LED power supply intelligent detection of the present invention.
FIG. 3 is a flow chart of the identification of abnormal events of lamps in production environment in the general LED power supply intelligent detection of the present invention.
FIG. 4 is a sensor and lamp layout diagram for the general LED power supply intelligent detection of the present invention.
Detailed Description
The present invention is further described below in conjunction with the following figures and specific examples so that those skilled in the art may better understand the present invention and practice it, but the examples are not intended to limit the present invention.
The invention belongs to the field of equipment abnormity detection of the Internet of things. The invention discloses a universal intelligent detection system for LED power supply faults, which comprises a sensor device, a wireless communication module and a data and control platform, wherein the sensor device is used for detecting abnormal protection such as LED power supply output voltage, output current, dimming port control of an intelligent power supply, short circuit and the like, and ambient temperature, humidity and brightness changes. By means of sensors such as current, voltage, temperature and humidity, brightness and color, power supply current and voltage, ambient brightness and temperature and other environmental data are collected to a data platform, the current and voltage changes of the power supply and the lamp and the ambient environmental data changes are comprehensively analyzed by a machine learning algorithm, and intelligent detection of the LED power supply is achieved on the premise of sufficiently protecting user privacy.
The invention relates to a universal LED power supply intelligent detection system which comprises an Internet of things processing chip STM32F205RGY6, a communication module (Wi-Fi + RF2.4G), a voltage sensor, a current sensor, a circuit protection module, a temperature, humidity and brightness sensor, a color sensor and a data platform, the voltage and current module can collect voltage and current information of most intelligent and non-intelligent power supplies on the market, the temperature and humidity, brightness and color sensors can collect temperature and humidity, load lamp brightness information and color/color temperature around the LED power supplies, sensor data are uploaded to the data platform through the communication module, data are processed and classified on the data platform, a group of event processing and analyzing models (category analyzers) are integrated and respectively correspond to abnormal conditions of each LED power supply, and the event processing and analyzing models (category analyzers) are generated in a supervision machine learning mode. And processing the special abnormity, cutting off the power supply, and protecting the power supply and the test equipment. The intelligent LED power supply is connected with the corresponding control interface according to the requirement, and dimming and color mixing detection and lamp switching detection are achieved.
Step one, collecting and uploading original data to a cloud platform
Acquiring and reporting power parameter data to a wireless communication module through a data acquisition module;
the wireless communication template transmits the data to the data reporting module;
data reporting module transmits data to cloud platform
The data acquisition module is as follows:
| serial number | Module name | Capturing content |
| 1 | Voltage acquisition module | Voltage information of power supply output |
| 2 | Current acquisition module | Current information of power supply output |
| 3 | Temperature and humidity acquisition module | Temperature and humidity information around power supply |
| 4 | Brightness acquisition module | Load lamp brightness information |
| 5 | Color acquisition module | Load fixture color/color temperature information |
| 6 | Wireless communication module | Transmitting the collected data to a data reporting module through a wireless module |
And step two, screening the original data of the cloud platform, calculating and comparing with an event processing analysis model (a category analyzer), and outputting whether the data is abnormal or not.
The LED power supply intelligent detection system needs to be trained properly before use, and an event processing analysis model (a category analyzer) is generated on a data platform, so that the LED power supply intelligent detection system aims at various abnormal conditions of lamps.
2.1 when training the model, respectively using different types of LED power supplies (common power supplies) and intelligent LED power supplies (adjustable brightness, color temperature and color) to train, and also training in different scenes to enhance the uniqueness of each model, wherein the intelligent LED power supplies and the power parameter interfaces select corresponding control interfaces.
The positions of the LED power supply and the load lamps and sensors are as follows:
2.2, when training a specific model, each specific abnormal condition needs to be simulated, and the abnormal conditions comprise:
LED power output is abnormal (only power is connected and the lamp is not connected, and the lamp is switched on and off to operate);
brightness adjustment is abnormal (the number of lamp strips or lamp beads of the lamp is reduced, and various brightnesses are adjusted as much as possible);
abnormal color temperature regulation (warm color lamp strips and cold color lamp strips of the lamp are respectively reduced, and various color temperatures are regulated as much as possible);
abnormal color adjustment (respectively reducing colored lamp strips corresponding to the lamps and adjusting different colors as much as possible);
current anomaly (the lamp current difference is larger as much as possible by testing with other power supplies with different current parameters);
voltage abnormity (a lamp which is not matched with a power supply is connected, and the lamp voltage difference is larger as far as possible);
no short-circuit protection abnormity (short circuit of lamp access line)
2.3 event processing analysis model training method
Step 1: pre-screening the acquired original data in the cloud platform;
the pre-screening algorithm proceeds as follows:
and in the model training stage, the voltage and current of a batch of LED power supplies with normal performance (such as 10 power supplies) are recorded, the load LED lamp is normally opened to collect the characteristic values of normal brightness and color temperature (if the lamp is a lamp with adjustable brightness, color temperature and color, the brightness is maximum, any single color temperature or any single color is recorded), the average value and the standard deviation are calculated, and a corresponding data table is formed after learning.
Step 2: then classifying the screened data;
and step 3: the classified data is packed, so that the data compression and confidentiality functions are realized; forming a characteristic data packet and marking a data type label;
and 4, step 4: and (4) transmitting the characteristic data packet to a data platform machine learning device, training an event recognition model together with the data type label, and forming an event processing analysis model (class analyzer). (the machine learner only uses during the model training phase, either as an off-line tool or online via an automated script.)
After training and cross validation, the event processing analysis model (class analyzer) is updated to a data platform, and can be used in a production environment.
2.4 the trained system can recognize the abnormal event of the power supply
Step 1: screening the acquired original data in the cloud platform;
step 2: then classifying the screened data;
and step 3: packing the classified data to form a characteristic numerical value packet;
and 4, step 4: and the characteristic numerical value packet is directly sent to an event processing analysis model (a category analyzer) in the data platform for calculation and comparison, and the identified event type and the credibility are output after the model identification is successful.
And step three, issuing the events and results output by the cloud platform to the wireless control module, and controlling the intelligent control interface and the protection device by the wireless control module according to the received instructions to give out warnings and record detection results.
3.1 aiming at the abnormal conditions of various LED power supplies, making judgment, transmitting the judgment to a data issuing module, controlling the power-off protection equipment of the protection device, providing abnormal warning and recording a detection result.
3.2 aiming at the normal conditions of various LED power supplies, making judgment, transmitting the judgment to a data issuing module, giving a normal warning and recording a detection result.
A specific application scenario of the present invention is given below:
for example: a common LED power supply, an intelligent LED power supply and an intelligent LED power supply are respectively arranged in an LED power supply production detection workshop, wherein a current and voltage sensor acquisition part in the intelligent LED power supply detection system is arranged between the power supply and a lamp, a protection circuit is arranged at the input end of the power supply, a medium temperature and humidity, brightness and color sensor acquisition part in the system is required to be arranged at a position which is parallel to the lamp and is about 20cm away from the lamp, the installation positions of a wireless communication module and a wireless control module part are not limited, when a user switches on or off the lamp on site or remotely, adjusts the brightness, the color temperature and the like, the intelligent LED power supply detection system can detect current and voltage change data output by the power supply and environment data such as the brightness and the like around the lamp and upload the data to a data platform in real time through the wireless communication module, judging whether the lamp is abnormal or not, and if the lamp is detected to be normal, carrying out alarm processing; if the abnormality occurs, the protection device is started, and the abnormality alarm processing (e.g. mail sending related person) is carried out.
The production detection workshop is only an example, and the method is suitable for various other scenes, such as: special offices, hospitals, workshops, stores, etc.
The above-mentioned embodiments are merely preferred embodiments for fully illustrating the present invention, and the scope of the present invention is not limited thereto. The equivalent substitution or change made by the technical personnel in the technical field on the basis of the invention is all within the protection scope of the invention. The protection scope of the invention is subject to the claims.
Claims (10)
1. The utility model provides a general LED power intellectual detection system which characterized in that includes: the system comprises a processing chip, a communication module (Wi-Fi + RF2.4G), a voltage sensor, a current sensor, a circuit protection module, a temperature and humidity sensor, a brightness sensor, a color sensor and a data platform; the voltage and current module collects voltage and current information of intelligent and non-intelligent power supplies, and the temperature and humidity, brightness and color sensors collect temperature and humidity around the led power supplies, brightness information of load lamps and colors/color temperatures; sensor data are uploaded to a data platform through a communication module, the data are processed and classified on the data platform, a group of event processing analysis models (class analyzers) are integrated and respectively correspond to abnormal conditions of each LED power supply, and the event processing analysis models (class analyzers) are generated in a supervision machine learning mode; processing the special abnormity, cutting off the power supply, and protecting the power supply and the test equipment; the intelligent LED power supply is connected with the corresponding control interface according to the requirement, and dimming and color mixing detection and lamp switching detection are achieved.
2. A universal LED power intelligent detection method using the universal LED power intelligent detection system of claim 1, comprising:
acquiring and uploading original data to a cloud platform;
screening original data of the cloud platform, calculating and comparing with an event processing analysis model (a category analyzer), and outputting whether the data is abnormal or not;
and step three, issuing the events and results output by the cloud platform to the wireless control module, and controlling the intelligent control interface and the protection device by the wireless control module according to the received instructions to give out warnings and record detection results.
3. The universal LED power intelligent detection method according to claim 1, wherein the first step specifically comprises: acquiring and reporting power parameter data to a wireless communication module through a data acquisition module;
the wireless communication template transmits the data to the data reporting module;
data reporting module transmits data to cloud platform
The data acquisition module is as follows:
4. the universal LED power supply intelligent detection method according to claim 1, wherein the second step specifically comprises:
2.1 when model training is carried out, different types of LED power supplies (common power supplies) and intelligent LED power supplies (adjustable brightness, color temperature and color) are used for training respectively, training is carried out under different scenes to enhance the uniqueness of each model, and the intelligent LED power supplies and power parameter interfaces select corresponding control interfaces;
the positions of the LED power supply and the load lamps and sensors are as follows:
2.2, when training a specific model, each specific abnormal condition needs to be simulated, and the abnormal conditions comprise:
LED power output is abnormal (only power is connected and the lamp is not connected, and the lamp is switched on and off to operate);
brightness adjustment is abnormal (the number of lamp strips or lamp beads of the lamp is reduced, and various brightnesses are adjusted as much as possible);
abnormal color temperature regulation (warm color lamp strips and cold color lamp strips of the lamp are respectively reduced, and various color temperatures are regulated as much as possible);
abnormal color adjustment (respectively reducing colored lamp strips corresponding to the lamps and adjusting different colors as much as possible);
current anomaly (the lamp current difference is larger as much as possible by testing with other power supplies with different current parameters);
voltage abnormity (a lamp which is not matched with a power supply is connected, and the lamp voltage difference is larger as far as possible);
no short-circuit protection abnormity (short circuit of lamp access line)
2.3 event processing analysis model training method
Step 1: pre-screening the acquired original data in the cloud platform;
step 2: then classifying the screened data;
and step 3: the classified data is packed, so that the data compression and confidentiality functions are realized; forming a characteristic data packet and marking a data type label;
and 4, step 4: and (4) transmitting the characteristic data packet to a data platform machine learning device, training an event recognition model together with the data type label, and forming an event processing analysis model (class analyzer). (the machine learner only uses during the model training phase, either as an off-line tool or online via an automated script.)
After training and cross validation, the event processing analysis model (class analyzer) is updated to a data platform, and can be used in a production environment.
2.4 the trained system can recognize the abnormal event of the power supply.
5. The universal LED power intelligent detection method as claimed in claim 4, wherein the pre-screening algorithm is processed as follows:
and in the model training stage, recording the voltage and current of a batch of LED power supplies with normal performance, normally opening a load LED lamp to acquire the characteristic values of normal brightness and color temperature (if the lamp with adjustable brightness, color temperature and color is a lamp with maximum brightness, any single color temperature or any single color, the characteristic values are recorded), calculating the average value and the standard deviation, and forming a corresponding data table after learning.
6. The universal LED power supply intelligent detection method according to claim 4, wherein the step 2.4 specifically comprises:
step 1: screening the acquired original data in the cloud platform;
step 2: then classifying the screened data;
and step 3: packing the classified data to form a characteristic numerical value packet;
and 4, step 4: and the characteristic numerical value packet is directly sent to an event processing analysis model (a category analyzer) in the data platform for calculation and comparison, and the identified event type and the credibility are output after the model identification is successful.
7. The universal LED power supply intelligent detection method according to claim 1, wherein the third step specifically comprises:
3.1, aiming at the abnormal conditions of various LED power supplies, making judgment, transmitting the judgment to a data issuing module, controlling a power-off protection device of a protection device, providing abnormal warning and recording a detection result;
3.2 aiming at the normal condition of various LED power supplies, making judgment, transmitting the judgment to a data issuing module, giving a normal warning and recording a detection result.
8. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 7 are implemented when the program is executed by the processor.
9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
10. A processor, characterized in that the processor is configured to run a program, wherein the program when running performs the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911417779.6A CN111060839A (en) | 2019-12-31 | 2019-12-31 | Universal LED power supply intelligent detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911417779.6A CN111060839A (en) | 2019-12-31 | 2019-12-31 | Universal LED power supply intelligent detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111060839A true CN111060839A (en) | 2020-04-24 |
Family
ID=70305894
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911417779.6A Pending CN111060839A (en) | 2019-12-31 | 2019-12-31 | Universal LED power supply intelligent detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111060839A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112566338A (en) * | 2020-11-16 | 2021-03-26 | 上海鸽恩照明科技有限公司 | Illumination operation and maintenance system based on short-distance transmission wireless networking cloud server |
| CN113640700A (en) * | 2021-07-29 | 2021-11-12 | 北京建院图茂科技有限公司 | High-power LED lighting fault monitoring system and method based on current data |
| CN113776776A (en) * | 2021-09-06 | 2021-12-10 | 朗戈智能系统(上海)有限公司 | General type lamps and lanterns detect controller |
| CN116381542A (en) * | 2023-06-05 | 2023-07-04 | 深圳和润达科技有限公司 | Health diagnosis method and device of power supply equipment based on artificial intelligence |
| CN116471722A (en) * | 2023-04-11 | 2023-07-21 | 浙江雨林电子科技有限公司 | Intelligent detection and adjustment method and system for running state of LED driving power supply |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203164392U (en) * | 2013-01-19 | 2013-08-28 | 珠海格林赛威科技有限公司 | LED power source intelligent detection system |
| CN104297699A (en) * | 2014-09-26 | 2015-01-21 | 航天东方红卫星有限公司 | Satellite power supply health condition tracking and detecting method based on intelligent interpretation |
| CN204989434U (en) * | 2015-09-16 | 2016-01-20 | 黄振彬 | LED lamp and LED power detecting and display device |
| KR101821722B1 (en) * | 2016-12-28 | 2018-01-24 | (주)온테스트 | Power measuring system for Home Energy Management System based on solar module and machine learning system for power measuring |
| CN206990771U (en) * | 2017-06-15 | 2018-02-09 | 广东上普壹明实业有限公司 | L ED power supply fault detection device |
| CN107843287A (en) * | 2017-10-26 | 2018-03-27 | 苏州数言信息技术有限公司 | Integrated sensor device and the environment event recognition methods based on it |
| CN109541498A (en) * | 2018-11-30 | 2019-03-29 | 苏州数言信息技术有限公司 | A kind of general lamp failure intelligent detecting method and system |
| CN109799726A (en) * | 2019-03-15 | 2019-05-24 | 中国计量大学 | A kind of smart home system of combination living environment detection |
-
2019
- 2019-12-31 CN CN201911417779.6A patent/CN111060839A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203164392U (en) * | 2013-01-19 | 2013-08-28 | 珠海格林赛威科技有限公司 | LED power source intelligent detection system |
| CN104297699A (en) * | 2014-09-26 | 2015-01-21 | 航天东方红卫星有限公司 | Satellite power supply health condition tracking and detecting method based on intelligent interpretation |
| CN204989434U (en) * | 2015-09-16 | 2016-01-20 | 黄振彬 | LED lamp and LED power detecting and display device |
| KR101821722B1 (en) * | 2016-12-28 | 2018-01-24 | (주)온테스트 | Power measuring system for Home Energy Management System based on solar module and machine learning system for power measuring |
| CN206990771U (en) * | 2017-06-15 | 2018-02-09 | 广东上普壹明实业有限公司 | L ED power supply fault detection device |
| CN107843287A (en) * | 2017-10-26 | 2018-03-27 | 苏州数言信息技术有限公司 | Integrated sensor device and the environment event recognition methods based on it |
| CN109541498A (en) * | 2018-11-30 | 2019-03-29 | 苏州数言信息技术有限公司 | A kind of general lamp failure intelligent detecting method and system |
| CN109799726A (en) * | 2019-03-15 | 2019-05-24 | 中国计量大学 | A kind of smart home system of combination living environment detection |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112566338A (en) * | 2020-11-16 | 2021-03-26 | 上海鸽恩照明科技有限公司 | Illumination operation and maintenance system based on short-distance transmission wireless networking cloud server |
| CN113640700A (en) * | 2021-07-29 | 2021-11-12 | 北京建院图茂科技有限公司 | High-power LED lighting fault monitoring system and method based on current data |
| CN113776776A (en) * | 2021-09-06 | 2021-12-10 | 朗戈智能系统(上海)有限公司 | General type lamps and lanterns detect controller |
| CN116471722A (en) * | 2023-04-11 | 2023-07-21 | 浙江雨林电子科技有限公司 | Intelligent detection and adjustment method and system for running state of LED driving power supply |
| CN116471722B (en) * | 2023-04-11 | 2023-09-01 | 浙江雨林电子科技有限公司 | Intelligent detection and adjustment method and system for running state of LED driving power supply |
| CN116381542A (en) * | 2023-06-05 | 2023-07-04 | 深圳和润达科技有限公司 | Health diagnosis method and device of power supply equipment based on artificial intelligence |
| CN116381542B (en) * | 2023-06-05 | 2023-07-25 | 深圳和润达科技有限公司 | Health diagnosis method and device of power supply equipment based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111060839A (en) | Universal LED power supply intelligent detection method and system | |
| CN109541498B (en) | Universal lamp fault intelligent detection method and system | |
| CN104794555B (en) | A kind of LED production and test data management system based on Internet of Things | |
| CN211728981U (en) | Torque wrench management system | |
| CN103995197A (en) | Aging test equipment for electronic products | |
| CN109088804B (en) | Household appliance maintenance misoperation early warning system associated with Bluetooth APP | |
| CN107576435A (en) | The online fault locator of tightening technique and its method of Kernel-based methods data analysis | |
| CN105891679A (en) | Fault detection system and method for electric power grid | |
| CN114137302B (en) | Electric energy metering instrument verification whole process monitoring system | |
| CN110609187A (en) | Intelligent management system based on SF6 electrical equipment data detection and intelligent analysis | |
| CN114035555A (en) | PLC controller fault detection system | |
| CN116611953A (en) | Electric energy meter production and manufacturing real-time data management method and system based on Internet of things | |
| CN104391255A (en) | Switching power supply fault simulator | |
| CN202204537U (en) | Humiture detection apparatus capable of multimetering | |
| CN111353465A (en) | Transformer substation personnel behavior analysis method and system based on deep learning technology | |
| CN113691669B (en) | Android mobile phone APP control vehicle full-process test analysis system and method | |
| CN105738729A (en) | Uninterruptible power supply rectification control interface board test system and method | |
| CN113283510B (en) | Secondary equipment health condition analysis method based on full-service mixed data | |
| CN115099713A (en) | Smart power grid operation log collection and analysis management system based on big data | |
| CN115047311A (en) | Card full life cycle management method, system, computer product and storage medium | |
| CN209070084U (en) | A kind of electrical part test macro | |
| CN208722001U (en) | A kind of air-conditioning real-time monitoring system with automatic control function | |
| CN202631994U (en) | Automatic control and intelligent analysis system used for insulator contamination test | |
| CN202584239U (en) | Intelligent flow analysis system and handheld inspecting instrument | |
| CN219496605U (en) | Traceable battery pack detection device |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200424 |