COB light source detection system and method based on Internet of Things

Abstract

The invention discloses a COB light source detection system and method based on the Internet of Things, and relates to the technical field of fault monitoring data analysis, and the method specifically comprises the following steps: obtaining sensor data and production equipment operation data; an internet of things network in the production line is constructed and used for transmitting data; data preprocessing is carried out, key feature variables are extracted by analyzing the preprocessed data, and correlation analysis is carried out; establishing a multivariable control model according to a correlation analysis result, and calculating a combined control threshold according to historical data; collecting real-time data, calculating the deviation degree of the real-time data and historical data according to the multivariable control model, and comparing the combined control threshold to carry out abnormity judgment; and according to a correlation analysis result, contribution degree analysis is carried out on the abnormal deviation degree, and positioning inspection is carried out according to the contribution degree. A detection model and a control standard are established through data driving, and the production management level is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fault monitoring data analysis, and specifically to a COB light source detection system and method based on the Internet of Things. Background Art

[0002] The fully automatic production line for COB spectroscopy micro-lighting packaging is an automatic production equipment integrating automatic feeding, automatic spectroscopy, micro-lighting, and packaging (loading blister boxes). It is equipped with a high-precision industrial camera to automatically identify the position and angle of the materials on the tray and transmit them back to the control system. After the robotic arm automatically grabs the COB light source and places it on the transfer track, the spectroscopy automatic high-precision spectroscopy system detects the product data and transmits it back to the control system, and then transports the materials to the next station to light the materials with low voltage. Traditional COB light source detection methods often rely on the detection of a single index, such as only detecting luminous flux or current, which cannot comprehensively reflect the actual performance of the COB light source and potential problems in the production process. At the same time, the relationship between the operating state of the equipment and the quality of the light source during the production process lacks systematic research, making it difficult to accurately identify and locate the key factors affecting the quality of the light source. Summary of the Invention

[0003] The purpose of the present invention is to provide a COB light source detection system and method based on the Internet of Things to solve the problems raised in the prior art.

[0004] To achieve the above purpose, the present invention provides the following technical solution: A COB light source detection method based on the Internet of Things, the COB light source detection method specifically includes the following steps:

[0005] Step S100: Install light sensors, current sensors, and temperature sensors at the spectroscopy station and the micro-lighting station of the fully automatic production line for COB spectroscopy micro-lighting packaging; obtain sensor data;

[0006] Step S200: Obtain the operation data of the production equipment through the control terminal of the fully automatic production line for COB spectroscopy micro-lighting packaging;

[0007] Step S300: Build an Internet of Things network inside the production line and transmit the sensor data and the operation data of the production equipment to the local data center;

[0008] Step S400: Perform data preprocessing, extract key feature variables by analyzing the preprocessed data, and perform correlation analysis on the key feature variables;

[0009] Step S500: Use the key feature variables as the basis, establish a multi-variable control model according to the results of the correlation analysis, and calculate the combined control threshold according to historical data;

[0010] Step S600: Collect the real-time data of key feature variables, calculate the deviation between the real-time data and the historical data according to the multi-variable control model, and compare the combined control threshold for anomaly judgment;

[0011] Step S700: According to the results of the correlation analysis, perform a contribution analysis on the abnormal deviation, and conduct a location check according to the magnitude of the contribution.

[0012] In step S100, install optical sensors, current sensors, and temperature sensors at the spectroscopic station and the micro-lighting station of the fully automatic COB spectroscopic micro-lighting packaging production line; obtain sensor data, specifically:

[0013] The optical sensor collects the luminous flux data of the light source;

[0014] The current sensor monitors the drive current;

[0015] The temperature sensor obtains the light source temperature and the ambient temperature;

[0016] The light source temperature includes the spectroscopic track temperature and the micro-lighting track temperature.

[0017] In step S200, obtain the production equipment operation data through the control terminal of the fully automatic COB spectroscopic micro-lighting packaging production line, specifically:

[0018] The production equipment operation data includes the operation time, the number of actions, and the motor speed of each station in the production line.

[0019] In step S300, construct an Internet of Things network inside the production line, and transmit the sensor data and the production equipment operation data to the local data center, specifically:

[0020] The local data center integrates a database and has the functions of data storage and data retrieval.

[0021] In step S400, perform data preprocessing. By analyzing the preprocessed data, extract key feature variables and conduct a correlation analysis on the key feature variables. The specific steps are as follows:

[0022] Step S401: Obtain historical sensor data and production equipment operation data through data retrieval;

[0023] Step S402: Perform data preprocessing on the obtained historical sensor data and production equipment operation data. The data preprocessing includes data cleaning, removing outliers, and data standardization;

[0024] Preferably, the data standardization selects the Z-score standardization method, specifically:

[0025] z = (x - μ) / σ; where z represents the data after standardization; x represents the original data; μ represents the mean of the original data; σ represents the standard deviation of the original data;

[0026] Step S403: Using the pre - processed historical sensor data and production equipment operation data as reference quantities, conduct a normal simulation. According to the normal simulation results, determine the sensor data and production equipment operation data that conform to the normal distribution as key feature variables;

[0027] Preferably, the specific steps of the normal simulation are as follows:

[0028] Step1: Using the pre - processed historical sensor data and production equipment operation data as reference quantities, calculate the Mahalanobis distance, specifically: ; where represents the Mahalanobis distance; Z represents the vector composed of the reference quantities after standardization; represents the vector composed of the means of the reference quantities after standardization; represents the matrix transpose symbol; S represents the covariance matrix, whose dimension is the same as that of the vector composed of the reference quantities; represents the inverse matrix of the covariance matrix;

[0029] Step2: Sort in descending order and calculate the quantiles of the chi - square distribution, specifically:

[0030] ; where n represents the number of reference quantities, n is a positive integer; i represents the rank of the reference quantity after the descending order, i is a positive integer, i ∈ [1, n]; represents the quantile of the chi - square distribution with the rank of the reference quantity being i; p represents the dimension of the vector composed of the reference quantities; is the chi - square distribution representation;

[0031] Step3: Plot the sorted values and the quantiles of the chi - square distribution as a scatter plot;

[0032] Step4: When the points in the scatter plot are approximately distributed on a straight line, it is determined that the reference quantities conform to the multivariate normal distribution, and the reference quantities that conform to the multivariate normal distribution are determined as key feature variables;

[0033] Step S404: Conduct a correlation analysis on the key feature variables to obtain the magnitude of the correlation between different key feature variables.

[0034] Preferably, the calculation formula for the correlation analysis is specifically:

[0035] ;

[0036] Among them, represents the correlation magnitude of the key feature variables and , a represents the quantity label of the key feature variables; m represents the number of historical observations, m is a positive integer; j represents the quantity label of the historical observations, j is a positive integer, j ∈ [1, m]; represents the j-th historical observation of the key feature variable ; represents the j-th historical observation of the key feature variable ; represents the historical observation average value of the key feature variable ; represents the historical observation average value of the key feature variable ;

[0037] In step S500, with the key feature variables as the basis, a multivariate control model is established according to the results of the correlation analysis, and the joint control threshold is calculated based on historical data. Specifically:

[0038] Step S501, obtain historical key feature variable data, and standardize the key feature variable data using the data standardization method described in step S402;

[0039] Step S502, according to the key feature variables conforming to the normal distribution, establish a multivariate control model by combining the standardized key feature variable data with the results of the correlation analysis;

[0040] Preferably, the representation formula of the multivariate control model is:

[0041] ; where represents the deviation degree between the real-time data and the historical data; represents the vector composed of the standardized key feature variables; represents the inverse matrix of the matrix constructed by the correlation magnitude between the key feature variables;

[0042] Step S503, according to the historical key feature variable data, set the confidence interval and calculate the joint control threshold.

[0043] Preferably, set a 95% confidence interval and calculate the joint control threshold. Specifically:

[0044] ; where represents the joint control threshold; represents the F distribution with degrees of freedom p and m - p at the significance level The critical value below; According to the set 95% confidence interval, .

[0045] In step S600, real-time data of key feature variables is collected, the deviation degree between the real-time data and historical data is calculated according to the multivariate control model, and the joint control threshold is compared for anomaly judgment. Specifically:

[0046] Step S601: Collect real-time data of key feature variables;

[0047] Step S602: Standardize the real-time data of the key feature variables;

[0048] Step S603: Calculate the deviation degree between the real-time data and historical data according to the multivariate control model;

[0049] Step S604: Compare the deviation degree between the real-time data and historical data with the joint control threshold, and determine the deviation degree greater than the joint control threshold as an anomaly.

[0050] In step S700, according to the correlation analysis result, contribution degree analysis is performed on the abnormal deviation degree, and location inspection is performed according to the contribution degree size. Specifically:

[0051] According to the calculated correlation sizes between different key feature variables, calculate the contribution degrees of different key feature variables to the abnormal deviation degree respectively;

[0052] Preferably, the calculation of the contribution degrees of different key feature variables to the abnormal deviation degree is specifically: ; where represents the contribution degree of the a-th key feature variable to the abnormal deviation degree; represents the real-time data of the a-th key feature variable after data standardization; represents the vector the a-th element of;

[0053] Sort the contribution degrees in descending order;

[0054] Perform location inspection on the key feature variables according to the descending order.

[0055] An Internet of Things-based COB light source detection system, the COB light source detection system includes a data acquisition module, an Internet of Things network transmission module, a local data center module, a data preprocessing module, a feature extraction and analysis module, a data modeling module, an anomaly judgment module, and a contribution degree analysis and location module;

[0056] The data acquisition module is used to collect sensor data and production equipment operation data;

[0057] The Internet of Things network transmission module is used to build the Internet of Things network inside the production line and is responsible for transmitting the data collected by the data collection module to the local data center;

[0058] The local data center module integrates a database for data storage and data retrieval;

[0059] The data preprocessing module is used to perform data preprocessing operations on the collected data. The data preprocessing includes data cleaning, outlier removal, and data standardization;

[0060] The feature extraction and analysis module is used to perform normal simulation with the preprocessed data as the reference quantity, determine the key feature variables according to the simulation results, and perform correlation analysis on the key feature variables to obtain the correlation magnitudes between different key feature variables;

[0061] The data modeling module is used to establish a multivariable control model based on the key feature variables and the correlation analysis results, and calculate the combined control threshold according to the historical key feature variable data;

[0062] The anomaly judgment module is used to collect the real-time data of the key feature variables, calculate the deviation degree between the real-time data and the historical data according to the multivariable control model, and compare it with the combined control threshold to judge whether an anomaly occurs;

[0063] The contribution analysis and positioning module is used to perform contribution analysis on the anomaly deviation degree according to the correlation analysis results, calculate the contribution degrees of different key feature variables to the anomaly deviation degree, and perform positioning inspection on the key feature variables after sorting the contribution degrees in descending order.

[0064] The output end of the data collection module is connected to the input end of the Internet of Things network transmission module; the output end of the Internet of Things network transmission module is connected to the input end of the local data center module; the output end of the local data center module is connected to the input end of the data preprocessing module; the output end of the data preprocessing module is respectively connected to the input end of the anomaly judgment module and the input end of the feature extraction and analysis module; the output end of the feature extraction and analysis module is respectively connected to the input end of the data modeling module and the input end of the contribution analysis and positioning module; the output end of the data modeling module is connected to the input end of the anomaly judgment module; the output end of the anomaly judgment module is connected to the input end of the contribution analysis and positioning module.

[0065] The data collection module includes a sensor data collection unit, an operation data collection unit, and a time alignment unit;

[0066] The sensor data acquisition unit is used to collect sensor data through optical sensors, current sensors, and temperature sensors installed at the optical splitting station and the micro-lighting station of the fully automatic production line for COB optical splitting and micro-lighting packaging;

[0067] The operation data acquisition unit is used to collect the operation data of production equipment; the operation data of production equipment includes the operation time, action times, and motor speed of each station in the production line;

[0068] The time alignment unit is used to align the acquisition time of sensor data with the operation data of production equipment;

[0069] The output end of the sensor data acquisition unit is connected to the input end of the time alignment unit; the output end of the operation data acquisition unit is connected to the input end of the time alignment unit.

[0070] Compared with the prior art, the beneficial effects of the present invention are as follows: By installing a variety of sensors at key stations of the production line and obtaining the operation data of production equipment, the present invention realizes multi-dimensional real-time monitoring, breaks through the limitations of traditional single-index detection, and more comprehensively and accurately reflects the performance of COB light sources and the production status; With the help of data preprocessing, feature extraction, multi-variable control models, and joint control thresholds, anomalies can be discovered in a timely and accurate manner, the key variables can be quickly located through contribution analysis, the accuracy of anomaly detection and the efficiency of troubleshooting are greatly improved, and quality hazards and downtime are reduced; Using the Internet of Things to construct a network to transmit data to the local data center for in-depth analysis, a detection model and control standards are established driven by data, providing a scientific basis for the quality control of light sources and improving the production management level. Description of the Drawings

[0071] Figure 1 It is a step schematic diagram of a COB light source detection method based on the Internet of Things according to the present invention;

[0072] Figure 2 It is a structural schematic diagram of a COB light source detection system based on the Internet of Things according to the present invention;

[0073] Figure 3 It is a normal simulation scatter plot in an embodiment of a COB light source detection method based on the Internet of Things according to the present invention. Detailed Embodiments

[0074] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0075] Embodiment: As Figures 1 - 3 shown, the present invention provides a technical solution, a method for detecting COB light sources based on the Internet of Things. As Figure 1 shown, it specifically includes the following steps:

[0076] Step S100: Install optical sensors, current sensors, and temperature sensors at the spectral splitting station and the micro-lighting station of the fully automatic production line for COB spectral splitting and micro-lighting packaging; obtain sensor data;

[0077] Step S200: Obtain the operation data of the production equipment through the control terminal of the fully automatic production line for COB spectral splitting and micro-lighting packaging;

[0078] Step S300: Build an Internet of Things network inside the production line, and transmit the sensor data and the operation data of the production equipment to the local data center;

[0079] Step S400: Perform data preprocessing, extract key feature variables by analyzing the preprocessed data, and perform correlation analysis on the key feature variables;

[0080] Step S500: Use the key feature variables as the basis, establish a multivariable control model according to the results of the correlation analysis, and calculate the combined control threshold according to the historical data;

[0081] Step S600: Collect the real-time data of the key feature variables, calculate the deviation degree between the real-time data and the historical data according to the multivariable control model, and compare with the combined control threshold for anomaly judgment;

[0082] Step S700: Perform contribution analysis on the abnormal deviation degree according to the results of the correlation analysis, and perform positioning inspection according to the contribution degree;

[0083] In step S100, install optical sensors, current sensors, and temperature sensors at the spectral splitting station and the micro-lighting station of the fully automatic production line for COB spectral splitting and micro-lighting packaging; obtain sensor data, specifically:

[0084] Sensor deployment: Install the following sensors at the spectral splitting station and the micro-lighting station:

[0085] Optical sensor: Collect luminous flux (unit: lm, range 0 - 3000 lm, accuracy ±2%);

[0086] Current sensor: Monitor the drive current (unit: A, range 0 - 1 A, accuracy ±0.5%);

[0087] Temperature sensor: Measure the light source temperature (temperature of the spectral splitting track and the micro-lighting track, unit: °C, accuracy ±0.5 °C);

[0088] In step S200, production equipment operation data is obtained through the control terminal of the full-automatic COB spectrophotometric micro-lighting packaging production line. Specifically:

[0089] The operation time, number of actions, and motor speed (unit: rpm) of each station are collected through the PLC;

[0090] Some examples are as follows: Among the spectrophotometric track temperature and the micro-lighting track temperature, the one with a larger difference from the average temperature is selected for recording;

[0091]

[0092] In step S300, an Internet of Things network inside the production line is constructed, and sensor data and production equipment operation data are transmitted to the local data center. Specifically:

[0093] The local data center integrates a database, which has the functions of data storage and data retrieval.

[0094] In step S400, data preprocessing is performed. By analyzing the preprocessed data, key feature variables are extracted, and correlation analysis is performed on the key feature variables. The specific steps are as follows:

[0095] Step S401: Historical sensor data and production equipment operation data are obtained through data retrieval;

[0096] Step S402: The obtained historical sensor data and production equipment operation data are preprocessed, including data cleaning, outlier removal, and data standardization;

[0097] Step S403: Using the preprocessed historical sensor data and production equipment operation data as reference quantities, normal simulation is performed. According to the normal simulation results, the sensor data and production equipment operation data that conform to the normal distribution are determined as key feature variables;

[0098] Step1: Using the preprocessed historical sensor data and production equipment operation data as reference quantities, the Mahalanobis distance is calculated. Specifically: ; where represents the Mahalanobis distance; Z represents the vector composed of the standardized reference quantities; represents the vector composed of the means of the standardized reference quantities; represents the matrix transpose symbol; S represents the covariance matrix, whose dimension is the same as that of the vector composed of the reference quantities; represents the inverse matrix of the covariance matrix;

[0099] Step2: Sort in descending order, and calculate the quantile of the chi-square distribution. Specifically:

[0100] ; where n represents the number of reference quantities, and n is a positive integer; i represents the rank of the reference quantity after the descending order, and i is a positive integer, i ∈ [1, n]; represents the quantile of the chi-square distribution with the rank of the reference quantity being i; p represents the dimension of the vector composed of the reference quantities; is the chi-square distribution representation;

[0101] Step3. Plot the sorted value and the quantile of the chi-square distribution of the scatter plot;

[0102] Step4. When the points in the scatter plot are approximately distributed on a straight line, it is determined that the reference quantity conforms to the multivariate normal distribution, and the reference quantity that conforms to the multivariate normal distribution is determined as the key characteristic variable;

[0103] Simulate three reference quantities (luminous flux, drive current, light source temperature) of the COB light source. Under stable operating conditions, collect n reference quantity data values to obtain the mean vector: μ = [1500, 0.6, 35];

[0104] Luminous flux variance: 50 2 ;

[0105] Drive current variance: 0.05 2 ;

[0106] Temperature variance: 2 2 ;

[0107] Correlation coefficient between luminous flux and current: 0.8;

[0108] Correlation coefficient between luminous flux and temperature: -0.3;

[0109] Correlation coefficient between current and temperature: 0.2;

[0110] Obtain the covariance matrix S as:

[0111] ;

[0112] Among them, the number of reference quantities n = 1000, the dimension of the vector composed of the reference quantities p = 3, plot the sorted value and the quantile of the chi-square distribution of the scatter plot, as Figure 3 shown;

[0113] Therefore, it can be known that the luminous flux, drive current, and light source temperature approximately conform to the multivariate normal distribution, and the luminous flux, drive current, and light source temperature are determined as the key characteristic variables.

[0114] Step S404: Conduct a correlation analysis on the key feature variables to obtain the correlation magnitudes between different key feature variables.

[0115] The calculation formula for the correlation analysis is:

[0116] ;

[0117] Wherein, represents the correlation magnitude between the key feature variable and ; a represents the quantity label of the key feature variables; m represents the number of historical observations, and m is a positive integer; j represents the quantity label of the historical observations, j is a positive integer, and j ∈ [1, m]; represents the j-th historical observation of the key feature variable ; represents the j-th historical observation of the key feature variable ; represents the average value of the historical observations of the key feature variable ; represents the average value of the historical observations of the key feature variable ;

[0118] It is calculated that:

[0119] The correlation magnitude between luminous flux and current is 0.82;

[0120] The correlation magnitude between luminous flux and temperature is -0.28;

[0121] The correlation magnitude between current and temperature is 0.19;

[0122] In step S500, taking the key feature variables as the basis, a multivariate control model is established according to the results of the correlation analysis, and the joint control threshold is calculated based on the historical data. Specifically:

[0123] Step S501: Obtain the historical key feature variable data, and standardize the key feature variable data using the data standardization method in step S402;

[0124] Step S502: Since the key feature variables conform to a normal distribution, a multivariate control model is established by combining the key feature variable data after completing data standardization with the results of the correlation analysis;

[0125] The representation formula of the multivariate control model is:

[0126] ; wherein, represents the deviation degree between the real-time data and the historical data; represents the vector composed of the standardized key feature variables; The inverse matrix of the matrix constructed to represent the correlation magnitude between key feature variables;

[0127] Normalized data matrix: Dimension 1000×3 (light: flux, current, temperature):

[0128] Use the computing library in Python for batch calculation:

[0129] ;

[0130] Step S503: Set the confidence interval according to the historical key feature variable data, and calculate the combined control threshold:

[0131] Combined control threshold: Set a 95% confidence level, degrees of freedom p = 3, m = 1000, and calculate to obtain:

[0132] t lim 2 =(1000−1)×3 / (1000−3)×F 0.05 (3,997)≈8.03;

[0133] In step S600, collect the real-time data of the key feature variables, calculate the deviation degree between the real-time data and the historical data according to the multivariate control model, and compare with the combined control threshold for anomaly judgment. Specifically:

[0134] Step S601: Collect the real-time data of the key feature variables;

[0135] Step S602: Standardize the real-time data of the key feature variables;

[0136] Step S603: Calculate the deviation degree between the real-time data and the historical data according to the multivariate control model;

[0137] Step S604: Compare the deviation degree between the real-time data and the historical data with the combined control threshold, and determine the deviation degree greater than the combined control threshold as an anomaly.

[0138] In step S700, according to the result of the correlation analysis, conduct a contribution degree analysis on the abnormal deviation degree, and conduct a location check according to the contribution degree size. Specifically:

[0139] According to the calculated correlation magnitude between different key feature variables, calculate the contribution degree of different key feature variables to the abnormal deviation degree respectively;

[0140] Obtain the real-time data:

[0141] Luminous flux (lm): 1420.5;

[0142] Drive current (A): 0.55;

[0143] Temperature (°C): 37.8;

[0144] Perform data standardization to eliminate the dimension; The data standardization method selects the Z-score standardization method;

[0145] Real-time data after standardization processing: W = [−1.59, −1.0, 1.4];

[0146] Deviation calculation:

[0147] ;

[0148] There is ; Judged as normal.

[0149] Such as Figure 2 As shown in the figure, an Internet of Things-based COB light source detection system includes a data acquisition module, an Internet of Things network transmission module, a local data center module, a data preprocessing module, a feature extraction and analysis module, a data modeling module, an anomaly judgment module, and a contribution analysis and positioning module;

[0150] The data acquisition module is used to collect sensor data and production equipment operation data;

[0151] The Internet of Things network transmission module is used to build the Internet of Things network inside the production line and is responsible for transmitting the data collected by the data acquisition module to the local data center;

[0152] The local data center module integrates a database for data storage and data retrieval;

[0153] The data preprocessing module is used to perform data preprocessing operations on the collected data. The data preprocessing includes data cleaning, outlier removal, and data standardization;

[0154] The feature extraction and analysis module is used to perform normal simulation with the preprocessed data as the reference quantity, determine the key feature variables according to the simulation results, and perform correlation analysis on the key feature variables to obtain the correlation magnitude between different key feature variables;

[0155] The data modeling module is used to establish a multi-variable control model based on the key feature variables and the results of the correlation analysis, and calculate the joint control threshold according to the historical key feature variable data;

[0156] The anomaly judgment module is used to collect the real-time data of the key feature variables, calculate the deviation between the real-time data and the historical data according to the multi-variable control model, and compare it with the joint control threshold to judge whether an anomaly occurs;

[0157] The contribution analysis and positioning module is used to perform contribution analysis on the abnormal deviation degree according to the results of the correlation analysis, calculate the contribution degrees of different key feature variables to the abnormal deviation degree, and perform positioning inspection on the key feature variables after sorting the contribution degrees in descending order.

[0158] The output end of the data acquisition module is connected to the input end of the Internet of Things network transmission module; the output end of the Internet of Things network transmission module is connected to the input end of the local data center module; the output end of the local data center module is connected to the input end of the data preprocessing module; the output end of the data preprocessing module is respectively connected to the input end of the abnormal judgment module and the input end of the feature extraction and analysis module; the output end of the feature extraction and analysis module is respectively connected to the input end of the data modeling module and the input end of the contribution analysis and positioning module; the output end of the data modeling module is connected to the input end of the abnormal judgment module; the output end of the abnormal judgment module is connected to the input end of the contribution analysis and positioning module.

[0159] The data acquisition module includes a sensor data acquisition unit, an operation data acquisition unit, and a time alignment unit;

[0160] The sensor data acquisition unit is used to acquire sensor data through optical sensors, current sensors, and temperature sensors installed at the optical splitting station and the micro-lighting station of the fully automatic production line for COB optical splitting and micro-lighting packaging.

[0161] The operation data acquisition unit is used to acquire production equipment operation data; the production equipment operation data includes the operation time, action times, and motor speed of each station in the production line.

[0162] The time alignment unit is used to align the acquisition time of the sensor data with the production equipment operation data.

[0163] The output end of the sensor data acquisition unit is connected to the input end of the time alignment unit; the output end of the operation data acquisition unit is connected to the input end of the time alignment unit.

[0164] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present invention. Any reference signs in the claims should not be regarded as limiting the claimed rights.

Claims

1. A COB light source detection method based on the Internet of Things, characterized in that: The COB light source detection method specifically comprises the following steps: Step S100, installing a light sensor, a current sensor and a temperature sensor at the spectrophotometric station and the micro-lighting station of the COB spectrophotometric micro-lighting packaging fully automatic production line; acquiring sensor data; Step S200, obtaining production equipment operation data through the control end of the COB spectroscopic micro-lighting packaging automatic production line; Step S300: construct an Internet of Things network inside the production line to transmit the sensor data and production equipment operation data to a local data center; Step S400: perform data preprocessing, extract key feature variables by analyzing the preprocessed data, and perform correlation analysis on the key feature variables; Step S500: Taking the key characteristic variables as the basis, establishing a multivariate control model according to the results of the correlation analysis, and calculating the joint control threshold according to historical data; Step S600, collecting real-time data of key characteristic variables, calculating the deviation between the real-time data and historical data according to the multivariable control model, and comparing the real-time data with the joint control threshold to make an abnormality judgment; Step S700: According to the result of the correlation analysis, a contribution analysis is performed on the abnormal deviation, and a positioning check is performed according to the contribution.

2. The COB light source detection method based on the Internet of Things according to claim 1, characterized in that: In step S100, light sensors, current sensors and temperature sensors are installed at the spectroscopic station and micro-lighting station of the COB spectroscopic micro-lighting packaging automatic production line; sensor data is obtained, specifically: The light sensor collects luminous flux data of the light source; The current sensor monitors the driving current; The temperature sensor acquires the light source temperature and the ambient temperature; The light source temperature includes the temperature of the split light track and the temperature of the micro-lighting track.

3. The COB light source detection method based on the Internet of Things according to claim 2, characterized in that: In step S200, the production equipment operation data is obtained through the control end of the COB spectroscopic micro-lighting packaging automatic production line, specifically: The production equipment operation data includes the operation time, the number of actions and the motor speed of each station in the production line.

4. The COB light source detection method based on the Internet of Things according to claim 1, characterized in that: In step S300, an IoT network is constructed inside the production line to transmit the sensor data and the production equipment operation data to the local data center, specifically: The local data center integrates a database and has the functions of data storage and data retrieval.

5. The COB light source detection method based on the Internet of Things according to claim 4 is characterized in that: In step S400, data preprocessing is performed, and key feature variables are extracted by analyzing the preprocessed data, and correlation analysis is performed on the key feature variables, which specifically includes the following steps: Step S401, obtaining historical sensor data and production equipment operation data through data retrieval; Step S402: performing data preprocessing on the acquired historical sensor data and production equipment operation data, wherein the data preprocessing includes data cleaning, outlier removal and data standardization; Step S403: Perform normal simulation using the pre-processed historical sensor data and production equipment operation data as reference quantities, and determine the sensor data and production equipment operation data that conform to the normal distribution as key feature variables according to the normal simulation results; Step S404: performing correlation analysis on the key feature variables to obtain the correlation between different key feature variables.

6. The COB light source detection method based on the Internet of Things according to claim 5, characterized in that: In step S500, a multivariate control model is established based on the key characteristic variables and the results of the correlation analysis, and a joint control threshold is calculated based on historical data, specifically: Step S501, obtaining historical key feature variable data, and performing data standardization on the key feature variable data; Step S502: According to the key characteristic variables being in accordance with normal distribution, a multivariate control model is established by combining the key characteristic variable data after data standardization with the result of the correlation analysis; Step S503: according to the historical key characteristic variable data, set the confidence interval and calculate the joint control threshold.

7. The COB light source detection method based on the Internet of Things according to claim 6, characterized in that: In step S600, real-time data of key characteristic variables are collected, the deviation between the real-time data and historical data is calculated according to the multivariable control model, and abnormality judgment is performed by comparing the joint control threshold, specifically: Step S601, collecting real-time data of key characteristic variables; Step S602: standardizing the real-time data of the key feature variables; Step S603: Calculate the deviation between the real-time data and the historical data according to the multivariable control model; Step S604: compare the deviation between the real-time data and the historical data with the joint control threshold, and determine that the deviation is greater than the joint control threshold as abnormal.

8. The COB light source detection method based on the Internet of Things according to claim 7, characterized in that: In step S700, based on the result of the correlation analysis, a contribution analysis is performed on the abnormal deviation, and a positioning check is performed based on the contribution, specifically: According to the calculated correlation between different key feature variables, the contribution of different key feature variables to the abnormal deviation is calculated respectively; sorting the contribution degrees in descending order; The key feature variables are checked for location according to the descending sorting.

9. A COB light source detection system based on the Internet of Things, characterized by: The COB light source detection system includes a data acquisition module, an Internet of Things network transmission module, a local data center module, a data preprocessing module, a feature extraction and analysis module, a data modeling module, an abnormality judgment module and a contribution analysis and positioning module; The data acquisition module is used to collect sensor data and production equipment operation data; The IoT network transmission module is used to build an IoT network inside the production line and is responsible for transmitting the data collected by the data collection module to the local data center; The local data center module integrates a database for data storage and data retrieval; The data preprocessing module is used to perform data preprocessing operations on the collected data, and the data preprocessing includes data cleaning, removal of outliers and data standardization; The feature extraction and analysis module is used to perform normal simulation using the preprocessed data as a reference, determine key feature variables according to the simulation results, and perform correlation analysis on the key feature variables to obtain the correlation between different key feature variables; The data modeling module is used to establish a multivariate control model based on the key characteristic variables and the results of the correlation analysis, and calculate the joint control threshold based on the historical key characteristic variable data; The abnormality judgment module is used to collect real-time data of key characteristic variables, calculate the deviation between real-time data and historical data according to the multivariable control model, and compare it with the joint control threshold to determine whether an abnormality occurs; The contribution analysis and positioning module is used to perform contribution analysis on the abnormal deviation according to the results of the correlation analysis, calculate the contribution of different key feature variables to the abnormal deviation, sort the contribution in descending order, and then perform positioning check on the key feature variables.

10. The COB light source detection system based on the Internet of Things according to claim 9, characterized in that: The data acquisition module includes a sensor data acquisition unit, an operation data acquisition unit and a time alignment unit; The sensor data acquisition unit is used to collect sensor data through the light sensor, current sensor and temperature sensor installed in the spectroscopic station and micro-lighting station of the COB spectroscopic micro-lighting packaging fully automatic production line; The operation data collection unit is used to collect the operation data of the production equipment; the operation data of the production equipment includes the operation time, the number of actions and the motor speed of each station in the production line; The time alignment unit is used to align the acquisition time of the sensor data with the production equipment operation data; The output end of the sensor data acquisition unit is connected to the input end of the time alignment unit; the output end of the operation data acquisition unit is connected to the input end of the time alignment unit.

Images