An artificial intelligence-based performance testing system for home appliance injection molding parts

Abstract

The present invention relates to the field of injection molded parts detection technology, and in particular to an artificial intelligence-based household appliance injection molded parts performance detection system, comprising an injection molding hardness detection platform, wherein the injection molding hardness detection platform is internally provided with an injection molding information unit, an appearance interference unit, a self-checking and correcting unit, a positioning processing unit, a measurement control unit, and a management execution unit; the present invention analyzes from the perspective of the interference of defects of the injection molded parts to be tested, on the one hand, reduces the influence of the defects of the injection molded parts to be tested on the hardness performance detection, and on the other hand, helps to improve the authenticity of the detection data, and on the premise that the injection molded parts to be tested are qualified, by analyzing from two dimensions before the detection and during the detection process, that is, analyzing from two points of installation positioning and facility error before the detection, so as to reduce the influence of error interference on the detection, and by means of information feedback, actual measurement error risk monitoring feedback analysis is performed to understand the actual measured force and hardness performance of the injection molded parts to be tested.

Description

Technical Field

[0001] The present invention relates to the technical field of injection molded parts detection, and in particular to an artificial intelligence-based household appliance injection molded parts performance detection system. Background Art

[0002] Injection molded parts refer to various injection molded products produced by injection molding machines, including various packages, parts, etc. They are mainly made of materials such as polyethylene or polypropylene and added with a variety of organic solvents. After injection molding, injection molded parts are easily deformed due to the influence of materials and external factors. At the same time, the production process of injection molded parts itself will also produce some unqualified products, so detection devices are needed for detection;

[0003] However, in the prior art, it is impossible to conduct interference detection on the injection molded parts themselves before detection, which results in defects in the injection molded parts themselves reducing the accuracy of the detection results, and it is impossible to analyze the installation positioning and facility errors before detection, which in turn affects the effectiveness of subsequent hardness performance test results. At the same time, it is impossible to conduct management adjustments in a timely manner, which is not conducive to the normal detection of the detection equipment, and it is impossible to supervise the downward pressure during the detection process, resulting in uneven deformation and force of the injection molded parts, reducing the effectiveness of the hardness performance of the injection molded parts;

[0004] In view of the above technical defects, a solution is now proposed. Summary of the invention

[0005] The purpose of the present invention is to provide a household appliance injection molding performance detection system based on artificial intelligence to solve the above-mentioned technical defects. The present invention analyzes from the perspective of the interference of defects of the injection molding parts to be tested. On the one hand, it reduces the influence of the defects of the injection molding parts to be tested on the hardness performance detection, and on the other hand, it helps to improve the authenticity of the detection data. On the premise that the injection molding parts to be tested are qualified, the analysis is performed from two dimensions before the detection and during the detection process, that is, the analysis is performed from the two points of installation positioning before the detection and facility error, so as to reduce the influence of error interference on the detection, so as to improve the accuracy of the hardness performance and detection results of the injection molding parts to be tested. Through information feedback, the measured interference data of the detection process is monitored and feedback analyzed for the measured error risk, so as to understand whether the risk of uneven force on the injection molding parts to be tested during the detection process is too large, so as to provide timely feedback and adjustment, and the hardness performance of the injection molding parts to be tested can be intuitively understood through text feedback.

[0006] The purpose of the present invention can be achieved by the following technical solutions: a household appliance injection molded parts performance detection system based on artificial intelligence, including an injection molding hardness detection platform, the injection molding hardness detection platform is internally provided with an injection molding information unit, an appearance interference unit, a self-checking correction unit, a positioning processing unit, a measurement control unit and a management execution unit;

[0007] The injection molding information unit is used to collect appearance data of the injection molded part to be tested, and send the appearance data to the appearance interference unit. After receiving the appearance data, the appearance interference unit immediately performs defect interference supervision operation on the appearance data, and distinguishes the defect interference value to obtain a qualified signal and a unqualified signal;

[0008] The positioning processing unit is used to respond to the qualified signal, collect the positioning data of the injection molded part to be inspected, and perform potential interference supervision and analysis on the positioning data, send the obtained stable signal to the self-inspection correction unit through the actual measurement control unit, and send the obtained positioning signal to the management execution unit;

[0009] The self-checking and correcting unit is used to collect the deviation risk data of the detection end, and perform error supervision feedback evaluation and analysis on the deviation risk data, send the obtained standard signal to the actual measurement control unit, and send the obtained control signal to the management execution unit;

[0010] After receiving the standard signal, the actual measurement control unit immediately collects the actual measured interference data of the hardness testing equipment, performs actual measured error risk monitoring feedback analysis on the actual measured interference data, and sends the limit signal, the standard-reaching signal, and the non-standard-reaching signal to the management execution unit through the self-checking and correcting unit;

[0011] Among them, the appearance data represents the appearance feature image; the positioning data includes the actual contact area and the maximum gap distance; the deviation risk data includes the actual pressure value and the displayed pressure value; the measured interference data includes the pressure deviation value and the appearance deformation feature image.

[0012] Preferably, the defect interference supervision operation process of the appearance interference unit is as follows:

[0013] Set a monitoring cycle and set it as a time threshold, obtain the injection molded parts to be inspected within the time threshold, divide the injection molded parts to be inspected into i sub-region blocks, i is a natural number greater than zero, obtain the appearance feature images of each sub-region block within the time threshold, perform equal-size scaling processing on the appearance feature image, and at the same time, cut the appearance feature image along the image edge line, and perform grayscale processing, set the final appearance feature image as the target analysis image, compare and analyze the target analysis image of each sub-region block with the corresponding preset standard image, obtain the difference value between the target analysis image and the preset standard image, and set it as the difference interference value, and compare and analyze the difference interference value with the preset difference interference value threshold value recorded and stored internally:

[0014] If the difference interference value is greater than the preset difference interference value threshold, the target analysis image corresponding to the difference interference value greater than the preset difference interference value threshold is marked as "1";

[0015] If the difference interference value is less than or equal to the preset difference interference value threshold, the target analysis image corresponding to the difference interference value less than or equal to the preset difference interference value threshold is marked as "0", and the ratio between the number of "1" and the number of "0" is obtained and set as the defect interference value. The defect interference value is compared and analyzed with the preset defect interference value threshold stored in the internal input:

[0016] If the ratio between the defect interference value and the preset defect interference value threshold is less than 1, a qualified signal is generated;

[0017] If the ratio between the defect interference value and the preset defect interference value threshold is greater than or equal to 1, a failure signal is generated.

[0018] Preferably, the potential interference supervision analysis process of the positioning processing unit is as follows:

[0019] The actual contact area between the injection molded part to be inspected and the inspection table in the hardness testing device within the time threshold is obtained, and the actual contact area is compared and analyzed with the stored preset contact area. If the actual contact area is greater than the preset contact area, the injection molded part to be inspected is determined to be in an unbalanced state, and the maximum gap distance between the injection molded part to be inspected and the contact surface of the inspection table in the unbalanced state within the time threshold is obtained, and it is set as the active error value;

[0020] The maximum shaking amplitude of the injection molded part to be inspected after positioning in the hardness testing equipment within the time threshold is obtained, and the maximum shaking amplitude is compared and analyzed with the stored preset shaking amplitude threshold, and the part of the maximum shaking amplitude exceeding the preset shaking amplitude threshold is set as the impact multiplier value.

[0021] Preferably, the activity error value and the impact multiplier value are compared and analyzed with the preset activity error value threshold and the preset impact multiplier value threshold recorded and stored internally:

[0022] If the activity error value is less than the preset activity error value threshold, and the impact multiplier value is less than the preset impact multiplier value threshold, a stable signal is generated;

[0023] If the activity error value is greater than or equal to the preset activity error value threshold, or the influence magnification value is greater than or equal to the preset influence magnification value threshold, a positioning signal is generated.

[0024] Preferably, the error supervision feedback evaluation and analysis process of the self-checking and correcting unit is as follows:

[0025] The actual pressure value and the displayed pressure value of the detection end of the hardness detection device before the detection are obtained within the time threshold, and the difference between the actual pressure value and the displayed pressure value of the detection end is set as the correction deviation value. At the same time, the actual expansion amount and the set expansion amount of the detection end in the hardness detection device within the time threshold are obtained, and the difference between the actual expansion amount and the set expansion amount is set as the expansion error value. The value obtained by multiplying the numerical values ​​corresponding to the correction deviation value and the expansion error value is set as the error interference coefficient;

[0026] Take the line connecting the midpoints of the two wide sides of the testing platform as the X-axis, take the line connecting the midpoints of the two long sides of the testing platform as the Y-axis, set the intersection of the line connecting the midpoints of the two wide sides and the line connecting the midpoints of the two long sides as the origin, and take the upward direction line perpendicular to the origin as the Z-axis. Obtain the actual pressure point coordinates and the set pressure point coordinates of the detection end of the hardness testing equipment within the time threshold, obtain the deviation values ​​between the X-axis, Y-axis and Z-axis, and set the sum of the deviation values ​​between the X-axis, Y-axis and Z-axis as the error interval value.

[0027] Preferably, the error interference coefficient and the error interval value are compared and analyzed with the preset error interference coefficient threshold and the preset error interval value threshold which are recorded and stored internally:

[0028] If the error interference coefficient is less than the preset error interference coefficient threshold, and the error interval value is less than the preset error interval value threshold, a standard signal is generated;

[0029] If the error interference coefficient is greater than or equal to a preset error interference coefficient threshold, or the error interval value is greater than or equal to a preset error interval value threshold, a pipe adjustment signal is generated.

[0030] Preferably, the measurement error risk monitoring feedback analysis process of the measurement control unit is as follows:

[0031] Obtaining a downward pressure deviation value of the injection molded part to be inspected in the hardness testing device within a time threshold, wherein the downward pressure deviation value indicates a maximum deviation value of the injection molded part to be inspected within a downward pressure period, and the downward pressure period indicates a time duration between a start contact moment and an end contact moment between the detection end in the hardness testing device and the injection molded part to be inspected;

[0032] Compare and analyze the pressure deviation value with the preset pressure deviation value threshold stored in the internal storage:

[0033] If the ratio between the downward pressure deviation value and the preset downward pressure deviation value threshold is greater than or equal to 1, a limit signal is generated;

[0034] If the ratio between the downward pressure deviation value and the preset downward pressure deviation value threshold is less than 1, a feedback instruction is generated. When the feedback instruction is generated, the appearance deformation feature image of the injection molded part to be inspected after the inspection within the time threshold is obtained, the appearance deformation feature image after the inspection is obtained and the preset deformation image is used for deformation analysis, the deformation difference value of the injection molded part to be inspected after the inspection is obtained, and the deformation difference value is compared and analyzed with the preset deformation difference value threshold value recorded and stored internally:

[0035] If the ratio between the deformation difference value and the preset deformation difference value threshold is less than 1, a compliance signal is generated;

[0036] If the ratio between the deformation difference value and the preset deformation difference value threshold is greater than or equal to 1, a non-compliance signal is generated.

[0037] The beneficial effects of the present invention are as follows:

[0038] (1) The present invention analyzes from the perspective of the interference of defects of the injection molded parts to be tested, on the one hand, to reduce the influence of the defects of the injection molded parts to be tested on the hardness performance test, and on the other hand, to help improve the authenticity of the test data. On the premise that the injection molded parts to be tested are qualified, the present invention analyzes from two dimensions before the test and during the test, that is, from the two points of installation positioning and facility error before the test, so as to reduce the influence of error interference on the test, that is, to conduct potential interference supervision analysis on the positioning data of the injection molded parts to be tested, so as to make timely positioning adjustments. On the premise that the installation and positioning are normal, the deviation risk data of the testing equipment is evaluated and analyzed by error supervision feedback, so as to make timely calibration adjustments, so as to improve the accuracy of the hardness performance test results of the injection molded parts to be tested.

[0039] (2) The present invention performs measured error risk monitoring feedback analysis on the measured interference data of the detection process by means of information feedback, so as to understand whether the risk of uneven force on the injection molded parts to be inspected during the detection process is too large, so as to provide timely feedback and adjustments, and intuitively understand the hardness performance of the injection molded parts to be inspected by means of text feedback. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The present invention will be further described below in conjunction with the accompanying drawings;

[0041] Figure 1 It is a flowchart of the system of the present invention;

[0042] Figure 2 It is a partial reference diagram of the second embodiment of the present invention. DETAILED DESCRIPTION

[0043] 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.

[0044] Embodiment 1:

[0045] See also Figure 1 to Figure 2 As shown, the present invention is a household appliance injection molded parts performance detection system based on artificial intelligence, including an injection molding hardness detection platform, wherein an injection molding information unit, an appearance interference unit, a self-checking and correcting unit, a positioning processing unit, a measurement control unit and a management execution unit are arranged inside the injection molding hardness detection platform, the injection molding information unit is in a one-way communication connection with the appearance interference unit, the appearance interference unit is in a one-way communication connection with the self-checking and correcting unit and the positioning processing unit, the positioning processing unit is in a one-way communication connection with the measurement control unit and the management execution unit, the self-checking and correcting unit is in a two-way communication connection with the measurement control unit, and the self-checking and correcting unit is in a one-way communication connection with the management execution unit;

[0046] When the injection molding hardness testing platform generates a testing instruction, the testing instruction is sent to the injection molding information unit. After receiving the testing instruction, the injection molding information unit immediately collects the appearance data of the injection molding part to be tested, and the appearance data represents the appearance feature image, and sends the appearance data to the appearance interference unit. After receiving the appearance data, the appearance interference unit immediately performs defect interference supervision operation on the appearance data to understand whether the injection molding part to be tested has defects, so as to reduce the influence of the injection molding part to be tested on the detection. The specific defect interference supervision operation process is as follows:

[0047] Set a monitoring cycle and set it as a time threshold, obtain the injection molded parts to be inspected within the time threshold, divide the injection molded parts to be inspected into i sub-region blocks, i is a natural number greater than zero, obtain the appearance feature images of each sub-region block within the time threshold, perform equal-size scaling processing on the appearance feature image, and at the same time, cut the appearance feature image along the image edge line, and perform grayscale processing, set the final appearance feature image as the target analysis image, compare and analyze the target analysis image of each sub-region block with the corresponding preset standard image, obtain the difference value between the target analysis image and the preset standard image, and set it as the difference interference value, and compare and analyze the difference interference value with the preset difference interference value threshold value recorded and stored internally:

[0048] If the difference interference value is greater than the preset difference interference value threshold, the target analysis image corresponding to the difference interference value greater than the preset difference interference value threshold is marked as "1";

[0049] If the difference interference value is less than or equal to the preset difference interference value threshold, the target analysis image corresponding to the difference interference value less than or equal to the preset difference interference value threshold is marked as "0", and the ratio between the number of "1" and the number of "0" is obtained and set as the defect interference value. The defect interference value is compared and analyzed with the preset defect interference value threshold stored in the internal input:

[0050] If the ratio between the defect interference value and the preset defect interference value threshold is less than 1, a qualified signal is generated and sent to the self-checking and correcting unit and the positioning processing unit;

[0051] If the ratio between the defect interference value and the preset defect interference value threshold is greater than or equal to 1, an unqualified signal is generated and sent to the management execution unit. After receiving the unqualified signal, the management execution unit immediately displays the preset warning text corresponding to the unqualified signal, that is, the preset warning text corresponding to the unqualified signal is "defect interference of the injection molded part to be inspected", so as to timely replace the injection molded part to be inspected, so as to improve the accuracy of the impact resistance performance test of the injection molded part to be inspected, and at the same time help reduce the influence of the injection molded part to be inspected on the test;

[0052] After receiving the qualified signal, the positioning processing unit immediately collects the positioning data of the injection molded parts to be inspected. The positioning data includes the actual contact area and the maximum gap distance, and performs potential interference supervision analysis on the positioning data to determine whether the installation interference error of the injection molded parts to be inspected is too large before the inspection, so as to make timely adjustments to ensure the accuracy of the test results. The specific potential interference supervision analysis process is as follows:

[0053] The actual contact area between the injection molded part to be inspected and the test platform in the hardness testing device within the time threshold is obtained, and the actual contact area is compared and analyzed with the stored preset contact area. If the actual contact area is greater than the preset contact area, the injection molded part to be inspected is determined to be in an unbalanced state, and the maximum gap distance between the injection molded part to be inspected and the contact surface of the test platform in the unbalanced state within the time threshold is obtained, and it is set as the active error value. It should be noted that the larger the value of the active error value, the greater the potential risk of affecting the installation of the injection molded part to be inspected;

[0054] The maximum shaking amplitude of the injection molded part to be inspected after positioning in the hardness testing device within the time threshold is obtained, and the maximum shaking amplitude is compared and analyzed with the stored preset shaking amplitude threshold, and the part of the maximum shaking amplitude exceeding the preset shaking amplitude threshold is set as the impact magnification value. It should be noted that the larger the value of the impact magnification value, the greater the potential impact risk of the installation of the injection molded part to be inspected;

[0055] Compare and analyze the activity error value and impact multiplier value with the preset activity error value threshold and preset impact multiplier value threshold that are stored internally:

[0056] If the activity error value is less than the preset activity error value threshold, and the impact multiplier value is less than the preset impact multiplier value threshold, a stabilization signal is generated, and the stabilization signal is sent to the self-checking and correcting unit via the actual measurement control unit;

[0057] If the active error value is greater than or equal to the preset active error value threshold, or the impact multiplier value is greater than or equal to the preset impact multiplier value threshold, a positioning signal is generated and sent to the management execution unit. After receiving the positioning signal, the management execution unit immediately displays the preset warning text corresponding to the positioning signal, that is, the preset warning text corresponding to the positioning signal is "positioning adjustment" so that the positioning of the injection molded parts to be inspected can be adjusted and the inspection table can be cleaned according to the information feedback, so as to reduce the impact of the installation positioning of the injection molded parts to be inspected on the inspection results.

[0058] Embodiment 2:

[0059] After receiving the qualified signal and the stable signal, the self-checking and correcting unit immediately collects the deviation risk data of the detection end. The deviation risk data includes the actual pressure value and the displayed pressure value, and performs error supervision feedback evaluation and analysis on the deviation risk data to determine whether the actual detection error risk of the detection end is too large before the test, so as to make timely adjustments to improve the accuracy of the hardness performance test results of the injection molded parts to be tested. The specific error supervision feedback evaluation and analysis process is as follows:

[0060] The actual pressure value and the displayed pressure value of the detection end of the hardness detection device before the detection are obtained within the time threshold, and the difference between the actual pressure value and the displayed pressure value of the detection end is set as the correction deviation value. At the same time, the actual expansion and contraction amount and the set expansion and contraction amount of the detection end in the hardness detection device within the time threshold are obtained, and the difference between the actual expansion and contraction amount and the set expansion and contraction amount is set as the expansion error value. The value obtained by multiplying the numerical values ​​corresponding to the correction deviation value and the expansion error value is set as the error interference coefficient. It should be noted that the larger the numerical value of the error interference coefficient is, the greater the detection error risk of the detection end in the hardness detection device is.

[0061] Take the line connecting the midpoints of the two wide sides of the testing platform as the X-axis, take the line connecting the midpoints of the two long sides of the testing platform as the Y-axis, set the intersection of the line connecting the midpoints of the two wide sides and the line connecting the midpoints of the two long sides as the origin, and take the upward direction line perpendicular to the origin as the Z-axis. Obtain the actual pressure point coordinates and the set pressure point coordinates of the detection end of the hardness testing device within the time threshold, obtain the deviation values ​​between the X-axis, the Y-axis and the Z-axis, and set the sum of the deviation values ​​between the X-axis, the Y-axis and the Z-axis as the error interval value. It should be noted that the larger the value of the error interval value, the greater the detection error risk of the detection end in the hardness testing device, and the testing platform is a rectangle;

[0062] Compare and analyze the error interference coefficient and error interval value with the preset error interference coefficient threshold and preset error interval value threshold that are stored internally:

[0063] If the error interference coefficient is less than the preset error interference coefficient threshold, and the error interval value is less than the preset error interval value threshold, a standard signal is generated and sent to the actual measurement control unit;

[0064] If the error interference coefficient is greater than or equal to the preset error interference coefficient threshold, or the error interval value is greater than or equal to the preset error interval value threshold, a pipe adjustment signal is generated and sent to the management execution unit. After receiving the pipe adjustment signal, the management execution unit immediately displays the preset warning text corresponding to the pipe adjustment signal, that is, the preset warning text corresponding to the pipe adjustment signal is "detection calibration", so as to adjust the equipment and the injection molded parts to be inspected according to the information feedback to improve the accuracy of the detection result;

[0065] After receiving the standard signal, the actual measurement control unit immediately collects the actual measured interference data of the hardness testing equipment. The actual measured interference data includes the downward pressure deviation value and the appearance deformation characteristic image, and performs actual measured error risk monitoring feedback analysis on the actual measured interference data to understand whether the risk of uneven force on the injection molded parts to be tested is too large during the testing process, so as to provide timely feedback and adjustment. The specific actual measured error risk monitoring feedback analysis process is as follows:

[0066] Obtain the downward pressure deviation value of the injection molded part to be inspected in the hardness testing device within the time threshold. The downward pressure deviation value indicates the maximum deviation value of the injection molded part to be inspected in the downward pressure period. The downward pressure period indicates the time between the start contact moment and the end contact moment of the detection end in the hardness testing device and the injection molded part to be inspected. It should be noted that the larger the downward pressure deviation value, the greater the detection error risk of the detection end in the hardness testing device;

[0067] Compare and analyze the pressure deviation value with the preset pressure deviation value threshold stored in the internal storage:

[0068] If the ratio between the downward pressure deviation value and the preset downward pressure deviation value threshold is greater than or equal to 1, a limit signal is generated, and the limit signal is sent to the management execution unit through the self-checking and correcting unit. After receiving the limit signal, the management execution unit immediately displays the preset warning text corresponding to the limit signal, that is, the preset warning text corresponding to the limit signal is "injection molded part limit", so as to re-limit and inspect the injection molded part to be inspected, so as to avoid uneven force on the injection molded part to be inspected due to movement, resulting in large errors in the inspection results;

[0069] If the ratio between the downward pressure deviation value and the preset downward pressure deviation value threshold is less than 1, a feedback instruction is generated. When the feedback instruction is generated, the appearance deformation feature image of the injection molded part to be inspected after the inspection within the time threshold is obtained, the appearance deformation feature image after the inspection is obtained and the preset deformation image is used for deformation analysis, the deformation difference value of the injection molded part to be inspected after the inspection is obtained, and the deformation difference value is compared and analyzed with the preset deformation difference value threshold value recorded and stored internally:

[0070] If the ratio between the deformation difference value and the preset deformation difference value threshold is less than 1, a compliance signal is generated;

[0071] If the ratio between the deformation difference value and the preset deformation difference value threshold is greater than or equal to 1, a non-standard signal is generated, and the standard signal and the non-standard signal are sent to the management execution unit through the self-checking and correcting unit. After receiving the standard signal and the non-standard signal, the management execution unit immediately displays the preset warning texts corresponding to the standard signal and the non-standard signal, that is, the preset warning text corresponding to the standard signal is "hardness meets the standard", and the preset warning text corresponding to the non-standard signal is "hardness does not meet the standard", so as to intuitively understand the hardness performance of the injection molded part to be inspected through text feedback;

[0072] In summary, the present invention analyzes from the perspective of the interference of defects of the injection molded parts to be tested, on the one hand, to reduce the influence of the defects of the injection molded parts to be tested on the hardness performance test, and on the other hand, to help improve the authenticity of the test data. On the premise that the injection molded parts to be tested are qualified, the present invention analyzes from two dimensions before the test and during the test, that is, from the two points of installation positioning and facility error before the test, so as to reduce the influence of error interference on the test, that is, to conduct potential interference supervision analysis on the positioning data of the injection molded parts to be tested, so as to judge whether the influence of the installation interference error of the injection molded parts to be tested is too large before the test, so as to timely Adjustments are made. Under the premise of normal installation and positioning, error supervision feedback evaluation and analysis are conducted on the deviation risk data of the testing equipment to determine whether the actual detection error risk at the detection end is too large before detection, so as to make timely calibration adjustments to improve the accuracy of the hardness performance test results of the injection molded parts to be inspected. Through information feedback, actual error risk monitoring feedback analysis is conducted on the measured interference data of the testing process to understand whether the risk of uneven force on the injection molded parts to be inspected during the testing process is too large, so as to make timely feedback adjustments, and the hardness performance of the injection molded parts to be inspected can be intuitively understood through text feedback.

[0073] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0074] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula that is close to the actual value. The coefficients in the formula are set by technical personnel in this field according to actual conditions. The above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited to this. Any technical personnel familiar with the technical field within the technical scope disclosed by the present invention, according to the technical solution and the inventive concept of the present invention, make equivalent replacement or change, which should be covered within the protection scope of the present invention.

Claims

1. A household appliance injection molding performance detection system based on artificial intelligence, characterized in that: It includes an injection molding hardness testing platform, which is internally provided with an injection molding information unit, an appearance interference unit, a self-checking and correcting unit, a positioning processing unit, a measurement control unit and a management execution unit; The injection molding information unit is used to collect appearance data of the injection molded part to be tested, and send the appearance data to the appearance interference unit. After receiving the appearance data, the appearance interference unit immediately performs defect interference supervision operation on the appearance data, and distinguishes the defect interference value to obtain a qualified signal and a unqualified signal; The positioning processing unit is used to respond to the qualified signal, collect the positioning data of the injection molded part to be inspected, and perform potential interference supervision and analysis on the positioning data, send the obtained stable signal to the self-inspection correction unit through the actual measurement control unit, and send the obtained positioning signal to the management execution unit; The self-checking and correcting unit is used to collect the deviation risk data of the detection end, and perform error supervision feedback evaluation and analysis on the deviation risk data, send the obtained standard signal to the actual measurement control unit, and send the obtained control signal to the management execution unit; After receiving the standard signal, the actual measurement control unit immediately collects the actual measured interference data of the hardness testing equipment, performs actual measured error risk monitoring feedback analysis on the actual measured interference data, and sends the limit signal, the standard-reaching signal, and the non-standard-reaching signal to the management execution unit through the self-checking and correcting unit; Among them, the appearance data represents the appearance feature image; the positioning data includes the actual contact area and the maximum gap distance; the deviation risk data includes the actual pressure value and the displayed pressure value; the measured interference data includes the pressure deviation value and the appearance deformation feature image; Among them, the detection end is the detection end of the hardness testing equipment; the actual pressure value and the displayed pressure value are both obtained from the coordinates of the pressure.

2. The artificial intelligence-based household appliance injection molding performance detection system according to claim 1, characterized in that: The defect interference supervision operation process of the appearance interference unit is as follows: Set a monitoring cycle and set it as a time threshold, obtain the injection molded parts to be inspected within the time threshold, divide the injection molded parts to be inspected into i sub-region blocks, i is a natural number greater than zero, obtain the appearance feature images of each sub-region block within the time threshold, perform equal-size scaling processing on the appearance feature image, and at the same time, cut the appearance feature image along the image edge line, and perform grayscale processing, set the final appearance feature image as the target analysis image, compare and analyze the target analysis image of each sub-region block with the corresponding preset standard image, obtain the difference value between the target analysis image and the preset standard image, and set it as the difference interference value, and compare and analyze the difference interference value with the preset difference interference value threshold value recorded and stored internally: If the difference interference value is greater than the preset difference interference value threshold, the target analysis image corresponding to the difference interference value greater than the preset difference interference value threshold is marked as "1"; If the difference interference value is less than or equal to the preset difference interference value threshold, the target analysis image corresponding to the difference interference value less than or equal to the preset difference interference value threshold is marked as "0", and the ratio between the number of "1" and the number of "0" is obtained and set as the defect interference value. The defect interference value is compared and analyzed with the preset defect interference value threshold stored in the internal input: If the ratio between the defect interference value and the preset defect interference value threshold is less than 1, a qualified signal is generated; If the ratio between the defect interference value and the preset defect interference value threshold is greater than or equal to 1, a failure signal is generated.

3. The artificial intelligence-based household appliance injection molding performance detection system according to claim 1, characterized in that: The potential interference supervision analysis process of the positioning processing unit is as follows: The actual contact area between the injection molded part to be inspected and the inspection table in the hardness testing device within the time threshold is obtained, and the actual contact area is compared and analyzed with the stored preset contact area. If the actual contact area is greater than the preset contact area, the injection molded part to be inspected is determined to be in an unbalanced state, and the maximum gap distance between the injection molded part to be inspected and the contact surface of the inspection table in the unbalanced state within the time threshold is obtained, and it is set as the active error value; The maximum shaking amplitude of the injection molded part to be inspected after positioning in the hardness testing equipment within the time threshold is obtained, and the maximum shaking amplitude is compared and analyzed with the stored preset shaking amplitude threshold, and the part of the maximum shaking amplitude exceeding the preset shaking amplitude threshold is set as the impact multiplier value.

4. The artificial intelligence-based household appliance injection molding performance detection system according to claim 3, characterized in that: The activity error value and the impact multiplier value are compared and analyzed with the preset activity error value threshold and the preset impact multiplier value threshold recorded and stored internally: If the activity error value is less than the preset activity error value threshold, and the impact multiplier value is less than the preset impact multiplier value threshold, a stable signal is generated; If the activity error value is greater than or equal to the preset activity error value threshold, or the influence magnification value is greater than or equal to the preset influence magnification value threshold, a positioning signal is generated.

5. The artificial intelligence-based household appliance injection molding performance detection system according to claim 1, characterized in that: The error supervision feedback evaluation and analysis process of the self-checking and correcting unit is as follows: The actual pressure value and the displayed pressure value of the detection end of the hardness detection device before the detection are obtained within the time threshold, and the difference between the actual pressure value and the displayed pressure value of the detection end is set as the correction deviation value. At the same time, the actual expansion amount and the set expansion amount of the detection end in the hardness detection device within the time threshold are obtained, and the difference between the actual expansion amount and the set expansion amount is set as the expansion error value. The value obtained by multiplying the numerical values ​​corresponding to the correction deviation value and the expansion error value is set as the error interference coefficient; Take the line connecting the midpoints of the two wide sides of the testing platform as the X-axis, take the line connecting the midpoints of the two long sides of the testing platform as the Y-axis, set the intersection of the line connecting the midpoints of the two wide sides and the line connecting the midpoints of the two long sides as the origin, and take the upward direction line perpendicular to the origin as the Z-axis. Obtain the actual pressure point coordinates and the set pressure point coordinates of the detection end of the hardness testing equipment within the time threshold, obtain the deviation values ​​between the X-axis, Y-axis and Z-axis, and set the sum of the deviation values ​​between the X-axis, Y-axis and Z-axis as the error interval value.

6. The artificial intelligence-based household appliance injection molding performance detection system according to claim 5, characterized in that: The error interference coefficient and the error interval value are compared and analyzed with the preset error interference coefficient threshold and the preset error interval value threshold that are recorded and stored internally: If the error interference coefficient is less than the preset error interference coefficient threshold, and the error interval value is less than the preset error interval value threshold, a standard signal is generated; If the error interference coefficient is greater than or equal to a preset error interference coefficient threshold, or the error interval value is greater than or equal to a preset error interval value threshold, a pipe adjustment signal is generated.

7. The artificial intelligence-based household appliance injection molding performance detection system according to claim 1, characterized in that: The actual measurement error risk monitoring feedback analysis process of the actual measurement control unit is as follows: Obtaining a downward pressure deviation value of the injection molded part to be inspected in the hardness testing device within a time threshold, wherein the downward pressure deviation value indicates a maximum deviation value of the injection molded part to be inspected within a downward pressure period, and the downward pressure period indicates a time duration between a start contact moment and an end contact moment between the detection end in the hardness testing device and the injection molded part to be inspected; Compare and analyze the pressure deviation value with the preset pressure deviation value threshold stored in the internal storage: If the ratio between the downward pressure deviation value and the preset downward pressure deviation value threshold is greater than or equal to 1, a limit signal is generated; If the ratio between the downward pressure deviation value and the preset downward pressure deviation value threshold is less than 1, a feedback instruction is generated. When the feedback instruction is generated, the appearance deformation feature image of the injection molded part to be inspected after the inspection within the time threshold is obtained, the appearance deformation feature image after the inspection is obtained and the preset deformation image is used for deformation analysis, the deformation difference value of the injection molded part to be inspected after the inspection is obtained, and the deformation difference value is compared and analyzed with the preset deformation difference value threshold value recorded and stored internally: If the ratio between the deformation difference value and the preset deformation difference value threshold is less than 1, a compliance signal is generated; If the ratio between the deformation difference value and the preset deformation difference value threshold is greater than or equal to 1, a non-compliance signal is generated.

Images