Turret type spray visual automatic detection system of perfume sprayer

Abstract

The invention relates to the technical field of automatic detection, and particularly discloses a rotary tower type spray visual automatic detection system of a perfume sprayer, which comprises a visual detection module for capturing an image in a spray process in real time and analyzing a spray area in the image to obtain spray abnormal data; the data processing module is used for calculating an evaluation coefficient based on the abnormal spraying data; the spraying evaluation module is used for evaluating the spraying process based on the evaluation coefficient, judging whether the spraying process is abnormal or not and generating an evaluation signal; the abnormal reason analysis module is used for monitoring visual detection equipment based on the spraying abnormal early warning signal, analyzing whether the generation of the spraying abnormal early warning signal is caused by the visual detection equipment or not, and generating an equipment analysis signal; according to the invention, the abnormity detection capability of the system is improved, the root of the spraying abnormity can be more accurately judged, and a powerful guarantee is provided for stable operation of the perfume sprayer, so that the system can more quickly position the problem when facing the spraying abnormity.

Description

Technical Field

[0001] The invention relates to the technical field of automatic detection, and in particular to a turret-type spray visual automatic detection system for a perfume sprayer. Background Art

[0002] Sprayer is the abbreviation of spray equipment. It uses air suction to turn medicine or other liquids into mist and spray them evenly onto other objects. It is composed of a compressed air device, a thin tube, a nozzle, etc. As an important accessory in the cosmetics field, the spray effect of perfume sprayer directly affects the user experience and the market competitiveness of the product.

[0003] However, the spray detection system in the prior art may not be able to accurately capture minor anomalies in the spray process, such as the uniformity and consistency of the spray and the grayscale changes in the sub-areas, resulting in inaccurate evaluation of the spray effect; and the prior art may misjudge the spray abnormality due to the failure of the detection equipment during spray detection. Summary of the invention

[0004] The object of the present invention is to provide a turret-type spray visual automatic detection system for perfume sprayers to solve the technical problems in the above background.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] In a first aspect, the present invention provides a turret-type spray visual automatic detection system for perfume sprayers, comprising:

[0007] Visual inspection module: captures images of the spraying process in real time, analyzes the spraying area, and obtains spraying abnormality data;

[0008] Among them, the spray abnormality data includes: abnormality degree coefficient and abnormal range characterization value;

[0009] Data processing module: calculate the evaluation coefficient based on the spray abnormality data;

[0010] Spray evaluation module: Based on the evaluation coefficient, it evaluates the spray process, determines whether the spray process is abnormal, and generates an evaluation signal;

[0011] Among them, the evaluation signals include: normal spray signal and abnormal spray warning signal;

[0012] Abnormal cause analysis module: Based on the spray abnormality warning signal, monitor the visual inspection equipment, analyze whether the generation of the spray abnormality warning signal is caused by the visual inspection equipment, and generate an equipment analysis signal;

[0013] The device analysis signals include: device-independent signals and device-related signals.

[0014] As a further solution of the present invention: the process of acquiring the spray abnormality data is as follows:

[0015] Use visual inspection equipment to capture images during the spraying process in real time and obtain all spray image frames during a single spraying process;

[0016] Based on any spray image frame, extract the spray area in the spray image frame, divide the spray area evenly, obtain multiple spray sub-areas, and calculate the grayscale difference ratio of each spray sub-area;

[0017] Based on the grayscale difference ratio of each spray sub-area, the abnormal degree coefficient and the abnormal range characterization value are calculated respectively.

[0018] As a further solution of the present invention: the grayscale difference ratio is obtained as follows:

[0019] Obtain the grayscale mean of each spray sub-area, then perform difference calculation between the grayscale mean of each spray sub-area and the grayscale threshold of each spray sub-area, and take the absolute value to obtain the grayscale difference, then perform ratio calculation between the grayscale difference and the grayscale threshold to obtain the grayscale difference ratio;

[0020] Among them, the grayscale mean is the average value of the grayscale values ​​of each pixel in the spray sub-area.

[0021] As a further solution of the present invention: the process of obtaining the abnormal degree coefficient is:

[0022] The grayscale difference ratios of all spray sub-areas are summed up and calculated to obtain the total grayscale difference ratio;

[0023] Preset a grayscale total difference ratio threshold, and compare and analyze the grayscale total difference ratio with the grayscale total difference ratio threshold;

[0024] If the total grayscale difference ratio is less than or equal to the total grayscale difference ratio threshold, a normal image frame signal is generated;

[0025] If the grayscale total difference ratio>the grayscale total difference ratio threshold, an image frame abnormal signal is generated, and the spray image frame is marked as an abnormal image frame;

[0026] The total grayscale difference ratio of all abnormal image frames during the spraying process is extracted and summed to obtain a grayscale abnormality degree representation value;

[0027] At the same time, the number of all abnormal image frames during the spraying process is extracted, and the ratio is calculated with the total number of all spray image frames during the spraying process to obtain the abnormal persistence characterization value;

[0028] Then, the grayscale abnormality degree characterization value and the abnormality duration characterization value are multiplied to obtain the abnormality degree coefficient.

[0029] As a further solution of the present invention: the process of obtaining the abnormal range characterization value is:

[0030] Based on the same spray sub-area in all spray image frames, the grayscale difference ratio of the spray sub-area in each spray image frame is extracted, and the variance of all grayscale difference ratios is calculated to obtain the grayscale difference ratio variance;

[0031] Preset a grayscale difference ratio variance threshold, and compare and analyze the grayscale difference ratio variance with the grayscale difference ratio variance threshold;

[0032] If the grayscale difference ratio variance ≤ grayscale difference ratio variance threshold, a normal signal of the sub-region is generated;

[0033] If the grayscale difference to variance ratio>the grayscale difference to variance threshold, a sub-area abnormal signal is generated, and the spray sub-area is marked as an abnormal sub-area;

[0034] The number of all abnormal sub-areas is extracted and the ratio is calculated with the total number of spray sub-areas to obtain the abnormal range characterization value.

[0035] As a further solution of the present invention: the process of obtaining the evaluation coefficient is:

[0036] By formula: Calculate the evaluation coefficient PG, where a1 and a2 are preset proportional factors and are both greater than 0, CD is the abnormality degree coefficient, and FW is the abnormal range characterization value.

[0037] As a further solution of the present invention: the process of generating the evaluation signal is:

[0038] Preset an evaluation coefficient threshold, and compare and analyze the evaluation coefficient with the evaluation coefficient threshold;

[0039] If the evaluation coefficient is less than or equal to the evaluation coefficient threshold, a spray normal signal is generated;

[0040] If the evaluation coefficient is greater than the evaluation coefficient threshold, a spray abnormality warning signal is generated.

[0041] As a further solution of the present invention: the process of generating the device analysis signal is:

[0042] Based on the abnormal spray warning signal, the voltage of the visual inspection equipment is monitored in real time to obtain the abnormal voltage time period;

[0043] At the same time, the time corresponding to all abnormal image frames during the spraying process is extracted to obtain the abnormal spraying time period;

[0044] Calculate the correlation coefficient based on the voltage abnormal time period and the spray abnormal time period;

[0045] Preset a correlation coefficient threshold, and compare and analyze the correlation coefficient with the correlation coefficient threshold;

[0046] If the correlation coefficient is ≤ the correlation coefficient threshold, a device-independent signal is generated;

[0047] If the correlation coefficient is greater than the correlation coefficient threshold, a device-related signal is generated.

[0048] As a further solution of the present invention: the process of obtaining the voltage abnormality time period is as follows:

[0049] Monitor the voltage of the visual inspection equipment in real time to obtain the real-time voltage of the visual inspection equipment;

[0050] Draw the real-time voltage curve of the visual inspection equipment in a two-dimensional coordinate system with time as the X-axis and the real-time voltage as the Y-axis. At the same time, draw two straight lines parallel to the X-axis based on the Y-axis value as the voltage upper limit and the voltage lower limit, and mark the interval between the two straight lines as the voltage interval;

[0051] The time when the real-time voltage curve exceeds the voltage interval is extracted to obtain the voltage abnormality time period.

[0052] As a further solution of the present invention: the process of obtaining the correlation coefficient is:

[0053] By formula: Calculate the correlation coefficient GL, where CH is the coincidence time, DY is the total voltage abnormality time, and PY is the total spray abnormality time;

[0054] The total voltage abnormality time is the total time of all voltage abnormality time periods, and the total spray abnormality time is the total time of all spray abnormality time periods.

[0055] Beneficial effects of the present invention:

[0056] (1) The present invention uses a high-speed camera and other equipment to capture spray images in real time, accurately divides the spray area of ​​each image frame, calculates the grayscale mean of each sub-area, and compares it with a preset grayscale threshold to evaluate the uniformity and consistency of the spray. By calculating the grayscale difference ratio and the total grayscale difference ratio, the abnormal frame in the spray image is identified, and the grayscale abnormal degree characterization value and the abnormal duration characterization value, i.e., the abnormal degree coefficient, are calculated accordingly. At the same time, the grayscale difference ratio variance of each spray sub-area is calculated to evaluate the stability of the spray and determine the number and proportion of abnormal sub-areas, i.e., the abnormal range characterization value; the data processing module is based on the above abnormal data, through The evaluation coefficient is calculated by the formula; the spray evaluation module makes a final judgment on the spray process according to the comparison result between the evaluation coefficient and the preset threshold value. If the evaluation coefficient is lower than or equal to the threshold value, the spray process is judged to be normal, and the system sends a normal spray signal; if the evaluation coefficient is higher than the threshold value, the spray process is judged to be abnormal, and the system immediately sends a spray abnormality warning signal; the rotary tower spray visual automatic detection system of the perfume sprayer of the present invention realizes comprehensive monitoring and abnormal warning of the spray process through real-time image capture, grayscale analysis and stability evaluation, combined with data processing and intelligent judgment, and effectively improves the production efficiency and product quality of the perfume sprayer;

[0057] (2) The present invention monitors the voltage state of the visual inspection device, draws a voltage curve in real time, and sets the upper and lower limits of the voltage to determine the voltage abnormality. When the voltage exceeds the set range, it is recorded as the voltage abnormality time period. At the same time, the time when the abnormal image frame appears during the spraying process, that is, the spray abnormality time period, is recorded; the overlapping part of the two time periods is calculated, and the degree of overlap is quantified by the correlation coefficient formula. The closer the correlation coefficient is to 1, the higher the temporal consistency between the voltage abnormality and the spray abnormality, thereby increasing the possibility that the spray abnormality is caused by the failure of the visual inspection device; a preset correlation coefficient threshold is used to determine whether the spray abnormality is related to the visual inspection device. If the correlation coefficient is lower than or equal to the threshold, it is determined that the spray abnormality is not related to the visual inspection device; if it is higher than the threshold, a device-related signal is issued to prompt the operator to check whether the equipment has a fault, so as to avoid false alarms caused by equipment problems. By introducing the abnormal cause analysis module, the present invention not only improves the abnormality detection capability of the system, but also can more accurately determine the root cause of the spray abnormality, providing a strong guarantee for the stable operation of the perfume sprayer, so that the system can locate the problem more quickly and take corresponding solutions when facing the spray abnormality, thereby improving production efficiency and product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The present invention will be further described below in conjunction with the accompanying drawings.

[0059] Figure 1 It is a flowchart of the present invention;

[0060] Figure 2It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] Embodiment 1:

[0063] See also Figure 1 , Figure 2 As shown, a turret-type spray visual automatic detection system for perfume sprayers according to an embodiment of the present invention comprises:

[0064] Visual inspection module: captures images of the spraying process in real time, analyzes the spraying area, and obtains spraying abnormality data;

[0065] Among them, the spray abnormality data includes: abnormality degree coefficient and abnormal range characterization value;

[0066] In some embodiments, a visual inspection device is used to capture images of the spraying process in real time to obtain all spray image frames during a single spraying process;

[0067] It should be explained that visual inspection equipment includes but is not limited to: high-speed cameras;

[0068] It should be explained that the spray image frame is an image of each frame number during the spray process;

[0069] Based on any spray image frame, the spray area in the spray image frame is extracted, and the spray area is evenly divided to obtain multiple spray sub-areas, and the grayscale mean of each spray sub-area is obtained (the grayscale mean is the average value of the grayscale values ​​of each pixel in the spray sub-area), and then the grayscale mean of each spray sub-area is calculated with the grayscale threshold of each spray sub-area, and the absolute value is taken to obtain the grayscale difference, and then the grayscale difference is calculated with the grayscale threshold to obtain the grayscale difference ratio;

[0070] It should be explained that the grayscale threshold of each spray sub-area is set in advance by a person skilled in the art based on the spray effect. The grayscale thresholds of different spray sub-areas are different. The grayscale thresholds of different spray sub-areas are set based on the distance between the center point of the regional sub-area and the nozzle.

[0071] It should be explained that the grayscale difference ratio reflects the degree to which the grayscale of the spray in the spray sub-area deviates from the expected value. The larger the grayscale difference ratio, the greater the difference between the grayscale of the spray in the spray sub-area and the expected value, indicating that the spray anomaly is greater;

[0072] The grayscale difference ratios of all spray sub-areas are summed up and calculated to obtain the total grayscale difference ratio;

[0073] Preset a grayscale total difference ratio threshold, and compare and analyze the grayscale total difference ratio with the grayscale total difference ratio threshold;

[0074] If the grayscale total difference ratio is less than or equal to the grayscale total difference ratio threshold, it means that the difference between the grayscale of the entire spray area in the spray image frame and the expected value is small, that is, a normal signal of the image frame is generated;

[0075] If the grayscale total difference ratio is greater than the grayscale total difference ratio threshold, it means that the grayscale of the entire spray area in the spray image frame is significantly different from the expected value, that is, an image frame abnormal signal is generated, and the spray image frame is marked as an abnormal image frame;

[0076] The total grayscale difference ratio of all abnormal image frames during the spraying process is extracted and summed to obtain a grayscale abnormality degree representation value;

[0077] At the same time, the number of all abnormal image frames during the spraying process is extracted, and the ratio is calculated with the total number of all spray image frames during the spraying process to obtain the abnormal persistence characterization value;

[0078] Then, the grayscale abnormality degree representation value and the abnormality duration representation value are multiplied to obtain the abnormality degree coefficient;

[0079] Based on the same spray sub-area in all spray image frames, the grayscale difference ratio of the spray sub-area in each spray image frame is extracted, and the variance of all grayscale difference ratios is calculated to obtain the grayscale difference ratio variance;

[0080] It should be explained that the grayscale difference ratio variance reflects the fluctuation degree of grayscale change in the spray sub-area, indicating the stability of the spray in the spray sub-area. The larger the value of the grayscale difference ratio variance, the worse the stability of the spray in the spray sub-area.

[0081] Preset a grayscale difference ratio variance threshold, and compare and analyze the grayscale difference ratio variance with the grayscale difference ratio variance threshold;

[0082] If the grayscale difference ratio variance ≤ grayscale difference ratio variance threshold, it means that the spray stability of the spray sub-area is good, that is, a normal signal of the sub-area is generated;

[0083] If the grayscale difference to variance ratio>the grayscale difference to variance threshold, it means that the spray stability of the spray sub-area is poor, that is, a sub-area abnormal signal is generated, and the spray sub-area is marked as an abnormal sub-area;

[0084] The number of all abnormal sub-areas is extracted and the ratio is calculated with the total number of spray sub-areas to obtain the abnormal range characterization value;

[0085] Data processing module: calculate the evaluation coefficient based on the spray abnormality data;

[0086] In some embodiments, by the formula: Calculate the evaluation coefficient PG, where a1 and a2 are preset proportional factors, both greater than 0, CD is the abnormality degree coefficient, and FW is the abnormal range representation value;

[0087] Spray evaluation module: Based on the evaluation coefficient, it evaluates the spray process, determines whether the spray process is abnormal, and generates an evaluation signal;

[0088] Among them, the evaluation signals include: normal spray signal and abnormal spray warning signal;

[0089] In some embodiments, an evaluation coefficient threshold is preset, and the evaluation coefficient is compared and analyzed with the evaluation coefficient threshold;

[0090] If the evaluation coefficient is less than or equal to the evaluation coefficient threshold, it means that the comprehensive abnormality of the spray process is small, and the spray process is judged to be normal, that is, a normal spray signal is generated;

[0091] If the evaluation coefficient is greater than the evaluation coefficient threshold, it means that the comprehensive abnormality of the spray process is relatively large, and the spray process is judged to be abnormal, that is, a spray abnormality warning signal is generated;

[0092] The technical solution of the embodiment of the present invention is mainly as follows: using a high-speed camera and other equipment to capture the spray image in real time, accurately dividing the spray area of ​​each image frame, calculating the grayscale mean of each sub-area, and comparing it with a preset grayscale threshold value to evaluate the uniformity and consistency of the spray, and identifying the abnormal frame in the spray image by calculating the grayscale difference ratio and the total grayscale difference ratio, and calculating the grayscale abnormal degree characterization value and the abnormal duration characterization value, that is, the abnormal degree coefficient, and at the same time, calculating the grayscale difference ratio variance of each spray sub-area to evaluate the stability of the spray and determine the number and proportion of abnormal sub-areas, that is, the abnormal range characterization value; the data processing module is based on the above abnormal The evaluation coefficient is calculated by the formula; the spray evaluation module makes a final judgment on the spray process according to the comparison result between the evaluation coefficient and the preset threshold value. If the evaluation coefficient is lower than or equal to the threshold value, the spray process is judged to be normal, and the system sends a normal spray signal; if the evaluation coefficient is higher than the threshold value, the spray process is judged to be abnormal, and the system immediately sends a spray abnormality warning signal; the rotary tower spray visual automatic detection system of the perfume sprayer of the present invention realizes comprehensive monitoring and abnormal warning of the spray process through real-time image capture, grayscale analysis and stability evaluation, combined with data processing and intelligent judgment, and effectively improves the production efficiency and product quality of the perfume sprayer.

[0093] Embodiment 2:

[0094] Based on Example 1, please refer to Figure 1 , Figure 2 As shown, the rotary tower spray visual automatic detection system for perfume sprayers according to the embodiment of the present invention further includes:

[0095] Abnormal cause analysis module: Based on the spray abnormality warning signal, monitor the visual inspection equipment, analyze whether the generation of the spray abnormality warning signal is caused by the visual inspection equipment, and generate an equipment analysis signal;

[0096] The device analysis signal includes: device-independent signal and device-related signal;

[0097] In some embodiments, based on the spray abnormality warning signal, the voltage of the visual inspection device is monitored in real time to obtain the real-time voltage of the visual inspection device;

[0098] Draw the real-time voltage curve of the visual inspection equipment in a two-dimensional coordinate system with time as the X-axis and the real-time voltage as the Y-axis. At the same time, draw two straight lines parallel to the X-axis based on the Y-axis value as the voltage upper limit and the voltage lower limit, and mark the interval between the two straight lines as the voltage interval;

[0099] Extract the time when the real-time voltage curve exceeds the voltage interval to obtain the voltage abnormality time period;

[0100] At the same time, the time corresponding to all abnormal image frames during the spraying process is extracted to obtain the abnormal spraying time period;

[0101] Compare and overlap the voltage abnormal time period with the spray abnormal time period to obtain the overlap time;

[0102] By formula: Calculate the correlation coefficient GL, where CH is the coincidence time, DY is the total voltage abnormality time, and PY is the total spray abnormality time;

[0103] It should be explained that the total voltage abnormality time is the total time of all voltage abnormality time periods, and the total spray abnormality time is the total time of all spray abnormality time periods;

[0104] It should be explained that the closer the value of the correlation coefficient is to 1, the higher the overlap between the voltage abnormality time period and the spray abnormality time period. When the value of the correlation coefficient is equal to 1, the voltage abnormality time period and the spray abnormality time period completely overlap.

[0105] Preset a correlation coefficient threshold, and compare and analyze the correlation coefficient with the correlation coefficient threshold;

[0106] If the correlation coefficient is less than or equal to the correlation coefficient threshold, it means that the overlap between the voltage abnormal time period and the spray abnormal time period is low, and it is determined that the generation of the spray abnormality warning signal is not caused by the visual detection device, that is, a device-irrelevant signal is generated;

[0107] If the correlation coefficient is greater than the correlation coefficient threshold, it means that the voltage abnormal time period and the spray abnormal time period have a high overlap, and it is determined that the generation of the spray abnormality warning signal is caused by the visual detection device, that is, the device-related signal is generated, thereby avoiding false alarms caused by equipment failure;

[0108] The technical solution of the embodiment of the present invention is mainly as follows: monitoring the voltage state of the visual inspection device, drawing the voltage curve in real time, and setting the upper and lower limits of the voltage to judge the voltage abnormality. When the voltage exceeds the set range, it is recorded as the voltage abnormality time period. At the same time, the time when the abnormal image frame appears during the spraying process is recorded, that is, the spray abnormality time period; calculating the overlapping part of the two time periods, and quantifying the degree of overlap through the correlation coefficient formula. The closer the correlation coefficient is to 1, the higher the temporal consistency between the voltage abnormality and the spray abnormality, thereby increasing the possibility that the visual inspection device failure causes the spray abnormality; presetting the correlation coefficient threshold value to determine whether the spray abnormality is related to the visual inspection device. If the correlation coefficient is lower than or equal to the threshold value, it is determined that the spray abnormality is not related to the visual inspection device; if it is higher than the threshold value, a device-related signal is issued to prompt the operator to check whether the equipment has a fault to avoid false alarms caused by equipment problems. By introducing the abnormal cause analysis module, the embodiment of the present invention not only improves the abnormality detection capability of the system, but also can more accurately determine the root cause of the spray abnormality, providing a strong guarantee for the stable operation of the perfume sprayer, so that the system can locate the problem faster and take corresponding solutions when facing the spray abnormality, thereby improving production efficiency and product quality.

[0109] The above thresholds are set for the convenience of comparison. The thresholds depend on the amount of sample data and the number of bases set by technicians in this field for each set of sample data.

[0110] The above formulas are obtained by collecting a large amount of data and performing software simulation to select a formula close to the actual value. The factors in the formula are set by technicians in this field according to actual conditions; for example: Formula A technician in this field collects multiple groups of spray abnormality data and sets a corresponding evaluation coefficient for each group of spray abnormality data; substitutes the set evaluation coefficient and the collected spray abnormality data into the formula, any two formulas constitute a binary linear equation system, and the calculated factors are screened and averaged to obtain the values ​​of a1 and a2, which are 3.47 and 2.23 respectively;

[0111] The size of the factor is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the factor depends on the amount of spray abnormality data and the preliminary setting of the corresponding evaluation coefficient for each set of spray abnormality data by technical personnel in this field; as long as it does not affect the proportional relationship between the parameter and the quantified value, such as the evaluation coefficient is proportional to the value of the abnormality degree coefficient.

[0112] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A turret spray visual automatic detection system for perfume sprayers, characterized in that: include: Visual inspection module: captures images of the spraying process in real time, analyzes the spraying area, and obtains spraying abnormality data; Among them, the spray abnormality data includes: abnormality degree coefficient and abnormal range characterization value; Data processing module: calculate the evaluation coefficient based on the spray abnormality data; Spray evaluation module: Based on the evaluation coefficient, it evaluates the spray process, determines whether the spray process is abnormal, and generates an evaluation signal; Among them, the evaluation signals include: normal spray signal and abnormal spray warning signal; Abnormal cause analysis module: Based on the spray abnormality warning signal, monitor the visual inspection equipment, analyze whether the generation of the spray abnormality warning signal is caused by the visual inspection equipment, and generate an equipment analysis signal; The device analysis signals include: device-independent signals and device-related signals.

2. The turret spray visual automatic detection system for perfume sprayers according to claim 1, characterized in that: The process of acquiring spray abnormality data is as follows: Use visual inspection equipment to capture images during the spraying process in real time and obtain all spray image frames during a single spraying process; Based on any spray image frame, extract the spray area in the spray image frame, divide the spray area evenly, obtain multiple spray sub-areas, and calculate the grayscale difference ratio of each spray sub-area; Based on the grayscale difference ratio of each spray sub-area, the abnormal degree coefficient and the abnormal range characterization value are calculated respectively.

3. The turret spray visual automatic detection system for perfume sprayers according to claim 2, characterized in that: The process of obtaining the grayscale difference ratio is: Obtain the grayscale mean of each spray sub-area, then perform difference calculation between the grayscale mean of each spray sub-area and the grayscale threshold of each spray sub-area, and take the absolute value to obtain the grayscale difference, then perform ratio calculation between the grayscale difference and the grayscale threshold to obtain the grayscale difference ratio; Among them, the grayscale mean is the average value of the grayscale values ​​of each pixel in the spray sub-area.

4. The turret spray visual automatic detection system for perfume sprayers according to claim 3, characterized in that: The process of obtaining the abnormality degree coefficient is as follows: The grayscale difference ratios of all spray sub-areas are summed up and calculated to obtain the total grayscale difference ratio; Preset a grayscale total difference ratio threshold, and compare and analyze the grayscale total difference ratio with the grayscale total difference ratio threshold; If the total grayscale difference ratio is less than or equal to the total grayscale difference ratio threshold, a normal image frame signal is generated; If the grayscale total difference ratio>the grayscale total difference ratio threshold, an image frame abnormal signal is generated, and the spray image frame is marked as an abnormal image frame; The total grayscale difference ratio of all abnormal image frames during the spraying process is extracted and summed to obtain a grayscale abnormality degree representation value; At the same time, the number of all abnormal image frames during the spraying process is extracted, and the ratio is calculated with the total number of all spray image frames during the spraying process to obtain the abnormal persistence characterization value; Then, the grayscale abnormality degree characterization value and the abnormality duration characterization value are multiplied to obtain the abnormality degree coefficient.

5. The turret spray visual automatic detection system for perfume sprayers according to claim 3, characterized in that: The process of obtaining the abnormal range characterization value is as follows: Based on the same spray sub-area in all spray image frames, the grayscale difference ratio of the spray sub-area in each spray image frame is extracted, and the variance of all grayscale difference ratios is calculated to obtain the grayscale difference ratio variance; Preset a grayscale difference ratio variance threshold, and compare and analyze the grayscale difference ratio variance with the grayscale difference ratio variance threshold; If the grayscale difference ratio variance ≤ grayscale difference ratio variance threshold, a normal signal of the sub-region is generated; If the grayscale difference to variance ratio>the grayscale difference to variance threshold, a sub-area abnormal signal is generated, and the spray sub-area is marked as an abnormal sub-area; The number of all abnormal sub-areas is extracted and the ratio is calculated with the total number of spray sub-areas to obtain the abnormal range characterization value.

6. The turret spray visual automatic detection system for perfume sprayers according to claim 1, characterized in that: The process of obtaining the evaluation coefficient is: By formula: Calculate the evaluation coefficient PG, where a1 and a2 are preset proportional factors and are both greater than 0, CD is the abnormality degree coefficient, and FW is the abnormal range characterization value.

7. The turret spray visual automatic detection system for perfume sprayers according to claim 1, characterized in that: The process of generating the evaluation signal is: Preset an evaluation coefficient threshold, and compare and analyze the evaluation coefficient with the evaluation coefficient threshold; If the evaluation coefficient is less than or equal to the evaluation coefficient threshold, a spray normal signal is generated; If the evaluation coefficient is greater than the evaluation coefficient threshold, a spray abnormality warning signal is generated.

8. The turret spray visual automatic detection system for perfume sprayers according to claim 1, characterized in that: The process of generating device analysis signals is: Based on the abnormal spray warning signal, the voltage of the visual inspection equipment is monitored in real time to obtain the abnormal voltage time period; At the same time, the time corresponding to all abnormal image frames during the spraying process is extracted to obtain the abnormal spraying time period; Calculate the correlation coefficient based on the voltage abnormal time period and the spray abnormal time period; Preset a correlation coefficient threshold, and compare and analyze the correlation coefficient with the correlation coefficient threshold; If the correlation coefficient is ≤ the correlation coefficient threshold, a device-independent signal is generated; If the correlation coefficient is greater than the correlation coefficient threshold, a device-related signal is generated.

9. The turret spray visual automatic detection system for perfume sprayers according to claim 8, characterized in that: The process of obtaining the voltage abnormal time period is as follows: Monitor the voltage of the visual inspection equipment in real time to obtain the real-time voltage of the visual inspection equipment; Draw the real-time voltage curve of the visual inspection equipment in a two-dimensional coordinate system with time as the X-axis and the real-time voltage as the Y-axis. At the same time, draw two straight lines parallel to the X-axis based on the Y-axis value as the voltage upper limit and the voltage lower limit, and mark the interval between the two straight lines as the voltage interval; The time when the real-time voltage curve exceeds the voltage interval is extracted to obtain the voltage abnormality time period.

10. The turret spray visual automatic detection system for perfume sprayers according to claim 1, characterized in that: The process of obtaining the correlation coefficient is: By formula: Calculate the correlation coefficient GL, where CH is the coincidence time, DY is the total voltage abnormality time, and PY is the total spray abnormality time; The total voltage abnormality time is the total time of all voltage abnormality time periods, and the total spray abnormality time is the total time of all spray abnormality time periods.

Images