Dynamic multi-parameter process monitoring method for security camera lens production process

Abstract

The invention discloses a security camera lens production process dynamic multi-parameter process monitoring method, and relates to the technical field of multi-parameter process monitoring. The method comprises the following steps: collecting process parameters and waviness characteristic data; collecting optical characteristics and physical response data of security camera lens raw materials; discretizing the data, and generating raw material standard data according to material types and performance; collecting real-time polishing data, and calculating to obtain a polishing deviation factor vector; calculating a weight through an entropy weight method to obtain a polishing alarm correction index, giving an alarm and adjusting polishing parameters when the polishing alarm correction index exceeds a threshold value, and obtaining corrected geometric feature data; the method comprises the following steps: collecting data in a coating stage, obtaining coating material response and processing environment data through a two-dimensional feature extraction method, and respectively calculating a material response deviation index and a processing environment disturbance index; and combining the two indexes to obtain the comprehensive deviation index of the coating process. According to the comprehensive deviation index of the coating process, the production process of the security camera lens is monitored in real time.

Description

Technical Field

[0001] The present invention relates to the field of multi-parameter process monitoring engineering, and in particular to a dynamic multi-parameter process monitoring method for a security camera lens production process. Background Art

[0002] The purpose of the dynamic multi-parameter process monitoring method for the security camera lens production process is to ensure the quality stability and consistency of the security camera lenses during the production process through real-time monitoring and intelligent control, thereby improving production efficiency and product yield.

[0003] However, in the traditional lens production process, parameter monitoring of key processes such as polishing and coating is isolated and cannot effectively correlate material properties with changes in the processing environment, resulting in reduced lens production efficiency and affected imaging quality. Summary of the Invention

[0004] In response to the shortcomings of the existing technology, the present invention provides a dynamic multi-parameter process monitoring method for the production process of security camera lenses, which solves the problem that traditional methods cannot effectively correlate material properties with changes in the processing environment.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: A dynamic multi-parameter process monitoring method for a security camera lens production process, comprising the following steps: Step S1: collecting optical property data and physical response data of a security camera lens raw material sample; Step S2: After standardizing the optical characteristic data and physical response data, classify them according to material type and performance to generate raw material standard data; Step S3: collecting real-time polishing data, wherein the real-time polishing data includes real-time geometric feature data and real-time polishing process parameters; calculating a surface roughness deviation rate, a polishing pressure deviation rate, and a thermal stress deviation rate based on the raw material standard data and the real-time polishing data; and combining the surface roughness deviation rate, the polishing pressure deviation rate, and the thermal stress deviation rate to obtain a polishing deviation factor vector; Step S4: weighting the polishing deviation factor using an entropy weight method to obtain a polishing deviation factor weight. Combining the polishing deviation factor vector and the polishing deviation factor weight, a polishing alarm correction index is calculated. When the polishing alarm correction coefficient exceeds a preset threshold, an alarm is immediately triggered and the real-time polishing process parameters are dynamically adjusted to obtain corrected geometric feature data. Step S5: collecting coating stage data during the coating stage, performing feature extraction on the coating stage data using a two-dimensional feature extraction method to obtain coating material response data and coating processing environment data, calculating a material response deviation index based on the coating material response data and raw material standard data, and calculating a processing environment disturbance index based on the coating processing environment data and the corrected geometric feature data; Step S6: combining the material response deviation index with the processing environment disturbance index to calculate a comprehensive coating process deviation index, and performing real-time monitoring of the security camera lens production process based on the comprehensive coating process deviation index.

[0006] Preferably, the collecting of optical property data and physical response data of the security camera lens raw material sample includes: Optical properties test: The raw material samples were placed in a spectral transmission device and the refractive index data was recorded every 1°C or 5%RH under different humidity conditions. Five batches of each material were tested and the average value was taken to eliminate batch differences. Physical response testing: Thermal expansion trend: Monitor the length change of the sample during heating using a laser interferometer and calculate the thermal expansion coefficient :

[0007] Among them, α is a physical quantity that measures the change in length of a material when the temperature changes, ΔL is the change in sample length, is the original length of the sample, ΔT is the temperature change; Mechanical stability: Use a stress tester to apply increasing stress to the sample until it breaks, record the stress-strain curve, and calculate the elastic modulus Yield strength .

[0008] Preferably, it is characterized in that the generating of raw material standard data includes: Standardization: Taking 25°C, 50% RH, and no stress as the reference state, all parameters are normalized to the range of [0, 1] to eliminate dimensional differences; Classification labels and database: assign labels based on material type and performance indicators; Store standardized data, labels and test conditions in a structured database to form a "digital file" for each material and generate standard data for raw materials: material ID, label, refractive index Temperature variation curve, thermal expansion coefficient , elastic modulus , yield strength .

[0009] Preferably, the surface roughness deviation rate, polishing pressure deviation rate and thermal stress deviation rate calculated based on the raw material standard data and the real-time polishing data include: Thermal stress deviation rate calculation: Obtaining measured edge deformation using a laser displacement meter , and the theoretical value By comparison, the thermal stress deviation rate is obtained:

[0010] in, is the thermal stress deviation rate, which reflects the degree of deviation of thermal stress release. is the measured edge deformation, is the theoretical value of edge deformation; Calculation of polishing pressure deviation rate: According to the yield strength of raw materials , determine the pressure safety threshold , calculate the measured pressure Deviation rate:

[0011] in, Indicates the deviation rate of polishing pressure, which is used to quantify the degree of deviation between the actual pressure and the safety threshold. It is the actual measured polishing pressure value, which is obtained in real time through the pressure sensor. It is the safety threshold of polishing pressure. Exceeding this value may cause permanent deformation or damage to the material. Calculation of surface roughness deviation rate: Obtaining measured surface roughness , and the target value contrast:

[0012] in, Indicates the deviation rate of surface roughness, which is used to quantify the degree of deviation between the actual roughness and the target value; It is the surface roughness value actually measured by the surface profiler equipment; It is the surface roughness target value pre-set according to the process requirements. This formula is used to evaluate whether the surface roughness after polishing meets the process requirements. If the value is large, it indicates that the actual roughness deviates significantly from the target value, which may affect the adhesion and uniformity of the subsequent coating. At this time, the polishing parameters need to be adjusted to ensure that the surface quality meets the requirements and provide stable substrate conditions for subsequent processes.

[0013] Preferably, the surface roughness deviation rate, polishing pressure deviation rate and thermal stress deviation rate are combined to obtain a polishing deviation factor vector, which includes: According to thermal stress, pressure, and roughness deviation rate, the polishing deviation factor vector is defined and generated: ), indicating the polishing deviation factor vector It is a vector that includes thermal stress, pressure, and roughness deviation rate. In this form, the multi-factor deviation is comprehensively expressed to facilitate the subsequent analysis of the impact of each factor on the polishing process.

[0014] Preferably, the weight calculation of the polishing deviation factor by the entropy weight method to obtain the polishing deviation factor weight includes: Organize data and build a data matrix ; Thermal stress deviation rate , polishing pressure deviation rate , surface roughness deviation rate The historical data is integrated into a matrix form to provide basic data for subsequent calculations; Standardization

[0015] in, It represents the value of the i-th sample after normalization on the j-th indicator. For the The thermal stress deviation rate, polishing pressure deviation rate, and surface roughness deviation rate of each sample are and are the minimum and maximum values ​​of the indicator respectively. Standardize the data to eliminate the dimension effect and map the data to interval; Calculate entropy: ,

[0016] in, Indicates calculation of Samples in the index The proportion in reflects the data distribution; Represents the information entropy formula, measurement index uncertainty, The larger the index The more evenly the data is distributed, the less important it is to decision making, where n is the number of indicators; Calculate weights:

[0017] in, is the polishing deviation factor weight, represents the entropy value related to the j-th indicator, It represents the entropy value related to the kth indicator, where k is the indicator index, which is used to traverse the three deviation factors of thermal stress deviation rate, polishing pressure deviation rate and surface roughness deviation rate. Calculation indicators The difference coefficient of , and then normalized to get the weight ; This weight is based on the variability of the data itself, objectively reflecting the impact of each deviation factor on the polishing process, and avoiding the deviation of subjective weight setting.

[0018] Preferably, the polishing alarm correction index is calculated by combining the polishing deviation factor vector and the polishing deviation factor weight. When the polishing alarm correction coefficient exceeds a preset threshold, an alarm is immediately triggered and the real-time polishing process parameters are dynamically adjusted. The corrected geometric feature data includes: Polishing alarm correction index: =

[0019] in, is the polishing alarm correction index, At time t, the dynamic weights of thermal stress, polishing pressure, and surface roughness deviation rate, is the deviation rate of deviation factor j; Correction strategy: Red Alert: Immediately suspend the polishing equipment and trigger an audible and visual alarm. At the same time, a work order containing detailed deviation data and attached historical data curves is sent to the engineer terminal to facilitate rapid root cause identification. Yellow warning: Use multi-parameter coupling adjustment strategy: Temperature Regulation: -

[0020] in, Indicates the value after correction of polishing fluid temperature. Indicates the current measured polishing liquid temperature, which is the basic value for temperature adjustment. is the thermal stress temperature regulation coefficient, which is used to quantify the effect of thermal deviation rate on temperature regulation. is the thermal stress deviation rate, The bigger, The larger the value of , the more the amount is subtracted from the measured temperature, reflecting the dominant role of thermal deviation in temperature regulation; is the pressure-temperature cross-influence coefficient, which is used to measure the indirect effect of the pressure deviation rate on the temperature; is the polishing pressure deviation rate, pressure deviation rate The bigger, The larger the value of , the further it is deducted from the measured temperature to ensure that the pressure deviation can also participate in temperature regulation; Roughness adjustment coefficient, used to quantify the effect of surface roughness deviation rate on surface roughness adjustment, is the surface roughness deviation rate; Pressure Regulation:

[0021] in, is the corrected polishing pressure, is the actual measured polishing pressure value, is the thermal stress deviation rate, is the polishing pressure deviation rate, is the surface roughness deviation rate. By taking into account the thermal stress deviation rate, polishing pressure deviation rate, and surface roughness deviation rate, the actual measured polishing pressure is corrected to optimize the polishing process and improve the polishing quality. After each adjustment, the corrected , It is the corrected measured edge deformation value. The edge deformation value is measured in real time by the ruler after the corrected polishing process is applied to the material.

[0022] Preferably, the material response deviation index is calculated based on the coating material response data and the raw material standard data, including: will record With the collection Used to calculate the actual thermal expansion coefficient:

[0023] in, is the actual measured thermal expansion coefficient, is the corrected measured edge deformation value, is the original length of the material, It is the temperature rise of the substrate, which can then be used to evaluate the matching degree of material properties; Material Response Deviation Index formula:

[0024] in, It is the material response deviation index, which comprehensively measures the deviation between the substrate characteristics and the raw material benchmark values, and evaluates the matching degree of the material characteristics to the coating process; 、 、 They are the weight of thermal expansion coefficient, elastic modulus and refractive index. Through orthogonal experiments, we can determine the influence of each factor on the comprehensive performance index, and then determine 、 、 The weight of is the actual measured thermal expansion coefficient; Base value of coefficient of thermal expansion; is the actual measured elastic modulus; Base value of elastic modulus; The actual measured refractive index, is the base value of the refractive index; Preferably, the calculation of the processing environment disturbance index based on the coating processing environment data and the corrected geometric feature data includes: Processing environment disturbance index formula:

[0025] in, It is the processing environment disturbance index, which is used to measure the stability of environmental parameters during the coating stage. A higher index indicates a more unstable environment. 、 、, Respectively represent the importance weights of the evaporation rate, vacuum chamber pressure, and substrate temperature rise on the coating process; It is the actual measured evaporation rate, reflecting the deposition rate of the film material; It is the set evaporation rate target value, which is the ideal value of the process; It is the allowable fluctuation threshold of the evaporation rate, which is used to define the deviation range; It is the actual measured vacuum chamber pressure, which affects the film purity and deposition quality; The target is the set vacuum chamber pressure target value, which is the ideal pressure for the process; is the allowable fluctuation threshold of the vacuum chamber pressure; Base temperature rise, is the set base temperature rise value, It is the fluctuation threshold allowed for the base temperature rise.

[0026] Preferably, the combining of the material response deviation index and the processing environment disturbance index to calculate the coating process comprehensive deviation index comprises: The material response deviation index is combined with the processing environment disturbance index to calculate the coating process comprehensive deviation index:

[0027] in: is the comprehensive deviation index of the coating process, Over time Dynamically changing weight factor, used to adjust the weight of material response deviation index in comprehensive deviation index; mid-term hour, ; Dynamic adjustment will be made according to material stability in the later stage; It is an environmental correction factor, which is calculated in real time based on the equipment status and workshop temperature and humidity sensor data; is the material response deviation index, which reflects the matching degree between the substrate characteristics and the standard data of the raw materials; It is the processing environment disturbance index, which measures the stability of environmental parameters such as evaporation rate, vacuum chamber pressure, and substrate temperature rise.

[0028] Beneficial effects This invention provides a dynamic multi-parameter process monitoring method for the production process of security camera lenses, which involves the intelligent manufacturing equipment industry and deep learning technology. It has the following beneficial effects: (1) This dynamic multi-parameter process monitoring method for the production process of security camera lenses collects optical property data and physical response data of raw material samples of security camera lenses, discretizes these data to make them more standardized, and then carefully classifies them by material type and performance, and stores them in a structured database. The standardized database generated in this way provides an accurate reference benchmark for subsequent polishing, coating and other processes. It not only ensures that the selection of raw materials is based on scientific data, but also facilitates the effective traceability of material performance throughout the entire production process, thereby improving the scientificity and reliability of production.

[0029] (2) This dynamic multi-parameter process monitoring method for the production process of security camera lenses calculates thermal stress, pressure, and roughness deviation rate in real time, combines the entropy weight method to determine the deviation factor weight, and generates a polishing alarm correction index. When the threshold is exceeded, the polishing parameters are dynamically adjusted to achieve real-time optimization of the polishing process, effectively improving the surface accuracy and geometric feature consistency of the lens and reducing the quality defect rate in the polishing process.

[0030] (3) This dynamic multi-parameter process monitoring method for the production process of security camera lenses calculates the material response deviation index and the processing environment disturbance index during the coating stage, and then obtains a comprehensive deviation index. Through multi-dimensional data correlation analysis, comprehensive real-time monitoring of the coating process is achieved to ensure the stability of the coating quality and the overall performance of the lens. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 This is a flow chart of a dynamic multi-parameter process monitoring method for the production process of security camera lenses proposed by the present invention.

[0032] Figure 2 This is a flow chart of obtaining a polishing alarm correction index for a dynamic multi-parameter process monitoring method for a security camera lens production process proposed by the present invention.

[0033] Figure 3 This is a flow chart of obtaining the comprehensive deviation index of the coating process by a dynamic multi-parameter process monitoring method for the production process of security camera lenses proposed by the present invention. DETAILED DESCRIPTION

[0034] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0035] See also Figure 1 The present invention provides a technical solution: a dynamic multi-parameter process monitoring method for the production process of security camera lenses. Specifically, the following dynamic multi-parameter process monitoring method for the production process of security camera lenses is provided. Figure 1 , the method comprises the following steps: Step S1: collecting optical property data and physical response data of a security camera lens raw material sample; Equipment calibration and test environment establishment First, calibrate the spectral transmission device, laser interferometer system, and stress detector: Calibrate the wavelength accuracy of the spectral transmission device (e.g., the error is controlled within ±0.1nm) and set the test band (e.g., visible light 400-760nm or infrared band); The stress tester calibrates the pressure sensor (error <1%) and calibrates the loading rate (such as tensile stress increasing by 10N per second); Laser interferometer calibration displacement resolution (e.g., nanometer level, used to measure tiny deformations during thermal expansion of materials).

[0036] Build a temperature and humidity controlled laboratory and set up multiple test conditions: Temperature gradient: 20℃, 25℃, 30℃ (simulating different production environment temperatures); Humidity gradient: 30%RH, 50%RH, 70%RH (to test the impact of high humidity environment on optical plastics); Stress type: tensile stress, compressive stress (0-100MPa, covering the common processing stress range).

[0037] Multi-parameter testing of raw materials Optical properties test: The raw material samples were placed in a spectral transmission device and the refractive index data were recorded every 1°C or 5%RH under different humidity conditions (for example, the refractive index of a certain glass is 1.52 at 25°C and 50%RH, and rises to 1.53 at 30°C). Five batches of each material were tested and the average value was taken to eliminate batch differences.

[0038] Physical response testing: Thermal expansion trend: The length change of the sample during heating (heating rate 5°C / min) was monitored by laser interferometer to calculate the thermal expansion coefficient. : The linear thermal expansion coefficient (α) is a physical quantity that measures the change in length of a material when the temperature changes. It is defined as:

[0039] Among them, α is a physical quantity that measures the change in length of a material when the temperature changes, ΔL is the change in sample length (cm), is the original length of the sample (cm), and ΔT is the temperature change (°C). For example, if the original length of a material is 10 cm, it will stretch 0.002 cm after the temperature rises by 10°C. ); Mechanical stability: Use a stress tester to apply increasing stress to the sample until it breaks, record the stress-strain curve, and calculate the elastic modulus (stress Force / cross-sectional area, strain Deformation / original length); yield strength (The stress value when the material produces a specified plastic strain, such as the stress corresponding to 0.2% plastic strain Indicates that exceeding this stress will result in irreversible deformation).

[0040] Step S2: After standardizing the optical characteristic data and physical response data, classify them according to material type and performance to generate raw material standard data; Standardization: Taking 25°C, 50% RH, and no stress as the reference state, all parameters are normalized to the range [0,1] (e.g., the refractive index of 1.52 is normalized to 0.8, and the thermal expansion coefficient of 2×10^-6 / °C is normalized to 0.6) to eliminate dimension differences (avoiding direct comparison of Pa with the dimensionless refractive index).

[0041] Classification labels and databases: Assign labels based on material type (such as "Optical Glass Class A" and "Optical Glass Class B") and performance indicators (such as α>1×10^-6 / ℃ is marked as "high expansion" and E>70GPa is marked as "high rigidity"), for example, "Class B-High Expansion-Low Rigidity".

[0042] Store standardized data, labels and test conditions in a structured database (such as MySQL) to form a "digital file" for each material and generate standard data for raw materials: material ID, label, refractive index Temperature variation curve, thermal expansion coefficient , elastic modulus , yield strength .

[0043] Step S3: Collect real-time polishing data, which includes real-time geometric feature data and real-time polishing process parameters. Based on the raw material standard data and the real-time polishing data, calculate the surface roughness deviation rate, polishing pressure deviation rate and thermal stress deviation rate. Combine the surface roughness deviation rate, polishing pressure deviation rate and thermal stress deviation rate to obtain a polishing deviation factor vector.

[0044] Sensor deployment and data collection Integrate non-contact displacement sensors (such as laser displacement meters with an accuracy of ±1μm) and surface interferometers (for measuring surface roughness with a resolution of nanometers) inside the polishing equipment to monitor lens surface changes in real time: Real-time geometric feature data: The displacement sensor is installed above the polishing plate to monitor the deformation of the lens edge profile. (e.g. “edge lift”); The surface interferometer scans the lens surface regularly to generate surface roughness (such as PV value, RMS value); Synchronous collection of equipment operating parameters (real-time polishing process parameters): Polishing pressure (0.1-0.5MPa), polishing liquid temperature T (20-30℃); Environmental parameters: real-time temperature and humidity (affecting the thermal response of materials).

[0045] Calculation of theoretical thermal stress release rate Utilize the thermal expansion coefficient of raw materials , original length of material , material combined with polishing fluid temperature changes , calculate the theoretical value of edge deformation:

[0046] in, is the theoretical value of edge deformation; is the thermal expansion coefficient of the raw material, It is the original length of the material, reflecting the material's ability to resist deformation; It is the change in polishing fluid temperature that drives the generation of thermal stress; this formula quantifies the thermal stress deformation of the material caused by temperature and provides a benchmark for subsequent deviation analysis.

[0047] Thermal stress deviation rate calculation: Obtaining measured edge deformation using a laser displacement meter , and the theoretical value By comparison, the thermal stress deviation rate is obtained:

[0048] in, is the thermal stress deviation rate, which reflects the degree of deviation of thermal stress release. is the measured edge deformation, is the theoretical value of edge deformation.

[0049] Calculation of polishing pressure deviation rate: According to the yield strength of raw materials , determine the pressure safety threshold , calculate the measured pressure Deviation rate:

[0050] in, Indicates the deviation rate of polishing pressure, which is used to quantify the degree of deviation between the actual pressure and the safety threshold. It is the actual measured polishing pressure value, which is obtained in real time through the pressure sensor. It is the safety threshold of polishing pressure. Exceeding this value may cause permanent deformation or damage to the material.

[0051] Calculation of surface roughness deviation rate: Obtaining measured surface roughness , and the target value contrast:

[0052] in, Indicates the deviation rate of surface roughness, which is used to quantify the degree of deviation between the actual roughness and the target value; It is the surface roughness value actually measured by equipment such as a surface profilometer; It is the target surface roughness value pre-set according to the process requirements. This formula is used to evaluate whether the surface roughness after polishing meets the process requirements. If the value is large, it indicates that the actual roughness deviates significantly from the target value, which may affect the adhesion and uniformity of the subsequent coating. In this case, it is necessary to adjust the polishing parameters (such as polishing disk speed and pressure) to ensure that the surface quality meets the requirements and provide stable substrate conditions for subsequent processes.

[0053] According to thermal stress, pressure, and roughness deviation rate, the polishing deviation factor vector is defined and generated: ), indicating the polishing deviation factor vector It is a vector that includes thermal stress, pressure, and roughness deviation rate. In this form, the multi-factor deviation is comprehensively expressed to facilitate the subsequent analysis of the impact of each factor on the polishing process.

[0054] Step S4: weighting the polishing deviation factor using an entropy weight method to obtain a polishing deviation factor weight. Combining the polishing deviation factor vector and the polishing deviation factor weight, a polishing alarm correction index is calculated. When the polishing alarm correction coefficient exceeds a preset threshold, an alarm is immediately triggered and the real-time polishing process parameters are dynamically adjusted to obtain corrected geometric feature data. Organize data and build a data matrix .

[0055] Thermal stress deviation rate , polishing pressure deviation rate , surface roughness deviation rate The historical data are integrated into matrix form to provide basic data for subsequent calculations.

[0056] Standardization

[0057] in, It represents the value of the i-th sample after normalization on the j-th indicator. For the The thermal stress deviation rate, polishing pressure deviation rate, and surface roughness deviation rate of each sample are and are the minimum and maximum values ​​of the indicator respectively. (heat, pressure, roughness) data are standardized to eliminate the dimension effect and map the data to interval.

[0058] Calculate entropy: ,

[0059] in, Indicates calculation of Samples in the index The proportion in reflects the data distribution; Represents the information entropy formula, measurement index uncertainty, The larger the index The more evenly the data is distributed, the less important it is for decision making, where n is the number of indicators.

[0060] Calculate weights:

[0061] in, is the polishing deviation factor weight, represents the entropy value related to the j-th indicator, It represents the entropy value related to the kth indicator, where k is the indicator index, which is used to traverse the three deviation factors of thermal stress deviation rate, polishing pressure deviation rate and surface roughness deviation rate. Calculation indicators The difference coefficient of (the smaller the entropy value, the larger the difference coefficient, the higher the weight), and then normalized to get the weight The weight is based on the variability of the data itself, objectively reflecting the influence of each deviation factor (heat, pressure, roughness) on the polishing process, avoiding the deviation of subjective weight setting.

[0062] Introducing dynamic weight mechanism, weight Over time Changes to reflect the importance of recent data. Set the time decay factor ( ), historical weight is the initial weight.

[0063]

[0064] in, At time t, the dynamic weights of thermal stress, polishing pressure, and surface roughness deviation rate, j is the deviation factor (thermal stress, polishing pressure, surface roughness), t is time, is the initial weight of the polishing deviation factor, m is the time step, and T is the current time step.

[0065] Polishing alarm correction index: =

[0066] in, is the polishing alarm correction index, At time t, the dynamic weights of thermal stress, polishing pressure, and surface roughness deviation rate, is the deviation rate of the deviation factor j (e.g. is the thermal stress deviation rate, is the polishing pressure deviation rate, is the surface roughness deviation rate).

[0067] Correction strategy: Red Alert (alarm coefficient ≥ 60%): Immediately suspend the polishing equipment and trigger an audible and visual alarm. Simultaneously, a work order containing detailed deviation data (delta heat, delta pressure, and delta phase) is sent to the engineer's terminal, along with a historical data curve (alarm coefficients and deviation changes for the past 10 batches) to facilitate rapid root cause identification.

[0068] Yellow warning (30% ≤ alarm coefficient < 60%): adopt multi-parameter coupling adjustment strategy: Temperature Regulation: -

[0069] in, Indicates the value after correction of polishing fluid temperature. Indicates the current measured polishing liquid temperature, which is the basic value for temperature adjustment. is the thermal stress temperature adjustment coefficient (e.g. ), which is used to quantify the effect of thermal deviation rate on temperature regulation. is the thermal stress deviation rate, The bigger, The larger the value of , the more the amount is subtracted from the measured temperature, reflecting the dominant role of thermal deviation in temperature regulation; is the pressure-temperature cross-influence coefficient (e.g. ), used to measure the indirect effect of pressure deviation rate on temperature; is the polishing pressure deviation rate, pressure deviation rate The bigger, The larger the value of , the further it is deducted from the measured temperature to ensure that the pressure deviation can also participate in temperature regulation; Roughness adjustment coefficient, used to quantify the effect of surface roughness deviation rate on surface roughness adjustment, is the surface roughness deviation rate.

[0070] Pressure Regulation:

[0071] in, is the corrected polishing pressure, is the actual measured polishing pressure value, is the thermal stress deviation rate, is the polishing pressure deviation rate, is the surface roughness deviation rate. By taking into account the thermal stress deviation rate, polishing pressure deviation rate, and surface roughness deviation rate, the actual measured polishing pressure is corrected to optimize the polishing process and improve the polishing quality.

[0072] After each adjustment, the corrected , It is the corrected measured edge deformation value (the edge deformation value is measured in real time by a ruler after the corrected polishing process is applied to the material).

[0073] Step S5: Collect the coating stage data of the coating stage, perform feature extraction on the coating stage data through a two-dimensional feature extraction method, obtain coating material response data and coating processing environment data, calculate the material response deviation index based on the coating material response data and the raw material standard data, and calculate the processing environment disturbance index based on the coating processing environment data and the corrected geometric feature data.

[0074] After the lens has been polished, it enters the coating stage. Collect the coating data of the coating stage: Evaporation rate collection: Measurement Principle: A quartz crystal microbalance (QCM) is used. The frequency of its crystal vibration is inversely proportional to the mass of film deposited on the surface. The evaporation rate is calculated in real time from this frequency change. The QCM probe is placed near the coating source to ensure accurate sensing of film deposition. Before each coating batch, the QCM is calibrated using a standard film deposition rate to ensure measurement accuracy. A data acquisition system reads the QCM output signal once per second, converts it to an evaporation rate (in mg / s), and stores it in a process database.

[0075] Vacuum chamber pressure ( collection: Measurement principle: Using a Pirani vacuum gauge, the cavity pressure is determined by measuring the relationship between gas thermal conductivity and pressure. Multiple Pirani vacuum gauges are installed on the vacuum cavity (such as the top and sides of the cavity) to prevent local pressure differences from affecting the measurement. The data acquisition system collects data from each vacuum gauge every 2 seconds, takes the average value as the current cavity pressure (unit: Pa), and displays and stores it in real time.

[0076] Base temperature rise ( )collection: Measurement principle: Using an infrared thermal imager, the temperature is measured by detecting changes in infrared radiation intensity on the substrate surface. The thermal imager is aimed at the substrate surface to ensure that the measurement area covers key areas (such as the center and edges). Before each batch of coating, the thermal imager is calibrated with a thermocouple to ensure measurement accuracy. The thermal imager generates a temperature image every second, extracts the average substrate temperature, and calculates the difference from the initial temperature. (Unit: °C), stored in the database.

[0077] Actual measured thermal expansion coefficient It is measured by laser interferometer, which calculates the thermal expansion coefficient by monitoring the change of the material's size (such as length) during temperature changes; the actual elastic modulus is generally measured using a stress detector, which applies tensile or compressive stress to the material, records the stress (σ) and strain (ε) data, and then uses the formula Calculate the elastic modulus .

[0078] Exception handling: If a parameter exceeds the threshold (such as If the deviation is within ±5% of the target value, the system will immediately trigger an audible and visual alarm, and highlight the abnormal parameters on the operation interface to prompt the operator to check.

[0079] All collected data is synchronized in real time to the workshop monitoring screen and the engineer's mobile terminal, facilitating remote monitoring and decision-making.

[0080] Performing feature extraction on the coating stage data by a two-dimensional feature extraction method to obtain coating material response data and coating processing environment data; Among them, the coating material response data includes the actual measured thermal expansion coefficient , the actual measured elastic modulus , the actual measured refractive index ; Coating processing environment data include evaporation rate F, substrate temperature rise , vacuum chamber pressure .

[0081] will record (corrected measured edge deformation value) and the collected (base temperature rise) is used to calculate the actual thermal expansion coefficient:

[0082] in, is the actual measured thermal expansion coefficient, is the corrected measured edge deformation value, is the original length of the material, It is the temperature rise of the substrate, which is used to evaluate the matching degree of material properties.

[0083] Material Response Deviation Index formula:

[0084] in, It is the material response deviation index, which comprehensively measures the deviation between the substrate characteristics and the raw material benchmark values, and evaluates the matching degree of the material characteristics to the coating process; 、 、 They are the weight of thermal expansion coefficient, elastic modulus and refractive index respectively. Through orthogonal experiments, each factor (i.e. , E, n) on the comprehensive performance indicators, and then determine 、 、 The weight of .

[0085] ; is the actual measured thermal expansion coefficient; Base value of thermal expansion coefficient (raw material); is the actual measured elastic modulus; Base value of elastic modulus; The actual measured refractive index, is the base value of the refractive index; Processing environment disturbance index formula:

[0086] in, It is the processing environment disturbance index, which is used to measure the stability of environmental parameters during the coating stage. A higher index indicates a more unstable environment. 、 、, Respectively represent the importance weights of the evaporation rate, vacuum chamber pressure, and substrate temperature rise on the coating process; It is the actual measured evaporation rate (unit: such as mg / s), reflecting the deposition rate of the film material; It is the set evaporation rate target value, which is the ideal value of the process; It is the allowable fluctuation threshold of the evaporation rate, which is used to define the deviation range; It is the actual measured vacuum chamber pressure (unit: such as Pa), which affects the film purity and deposition quality; The target is the set vacuum chamber pressure target value, which is the ideal pressure for the process; is the allowable fluctuation threshold of the vacuum chamber pressure; Base temperature rise, is the set base temperature rise value, It is the fluctuation threshold allowed for the base temperature rise.

[0087] Step S6: combining the material response deviation index with the processing environment disturbance index to calculate a comprehensive coating process deviation index, and performing real-time monitoring and intelligent control of the security camera lens production process based on the comprehensive coating process deviation index.

[0088] The material response deviation index is combined with the processing environment disturbance index to calculate the coating process comprehensive deviation index:

[0089] in: is the comprehensive deviation index of the coating process, Over time Dynamically changing weight factor, used to adjust the weight of material response deviation index in comprehensive deviation index. hour, (focus on material properties); mid-term hour, ; Dynamic adjustment will be made according to material stability in the later stage; It is an environmental correction factor, which is calculated in real time through sensor data such as equipment status, workshop temperature and humidity (for example, when the equipment is seriously aged, Increase to strengthen the influence of material properties on the comprehensive index); It is the material response deviation index, which reflects the matching degree between the substrate characteristics (thermal expansion coefficient, elastic modulus, refractive index, etc.) and the standard data of the raw material. It is the processing environment disturbance index, which measures the stability of environmental parameters such as evaporation rate, vacuum chamber pressure, and substrate temperature rise.

[0090] Set the threshold judgment like , it is determined to be in normal state, indicating that the fluctuations of material properties and environmental parameters in the current coating process are within the controllable range, and have little impact on the quality of the film layer. The current coating parameters are maintained to continue the operation, and the data is continuously monitored to prevent subsequent fluctuations.

[0091] like , triggering root cause analysis, it is necessary to deeply explore the core factors that cause the comprehensive index to exceed the standard in order to accurately control it.

[0092] like and : Root cause: Determined to be "fluctuation in raw material properties." This indicates that key properties of the substrate, such as the thermal expansion coefficient, elastic modulus, or refractive index, deviate significantly from the initial model, which is the primary factor affecting coating quality. Environmental parameters, however, are relatively stable.

[0093] Control: trace the established raw material standard data, re-measure the substrate characteristics through high-precision testing equipment (such as laser interferometer to measure thermal expansion, dynamic mechanical analyzer to measure elastic modulus, ellipsometer to measure refractive index), and update the thermal expansion coefficient , elastic modulus , refractive index , ensure that the model matches the actual material.

[0094] If testing finds that the raw material properties are beyond the reasonable tolerance range, the raw material batch will be replaced in a timely manner, and the warehouse inspection and model update will be carried out again to ensure the stability of the material properties from the source.

[0095] like and : Root cause: Determined as "abnormal data during the coating stage." This indicates significant fluctuations in environmental parameters such as evaporation rate, vacuum chamber pressure, and substrate temperature rise, posing a threat to the stability of the coating process, while material properties are relatively stable.

[0096] Control: Calibrate the evaporation rate control device, check the sensor accuracy and signal transmission link of the quartz crystal microbalance, adjust the control algorithm parameters to ensure that the evaporation rate is stable at the target value within the range.

[0097] Perform multi-point calibration on the Pirani vacuum gauge, check the sealing of the vacuum chamber and the performance of the exhaust system, repair the leaks or replace the aging parts to restore the vacuum chamber pressure. .

[0098] Optimize the substrate temperature control logic based on the infrared thermal imager data and adjust the power output curve of the heating or cooling device to ensure that the substrate temperature rises Meet the process requirements.

[0099] like and : Root cause: Determined to be "synergistic failure of materials and environment." This refers to the simultaneous existence of fluctuations in material properties and abnormal environmental parameters, with the interaction between the two exacerbating the negative impact on coating quality.

[0100] Regulation: Replace less sensitive materials, such as using a low thermal expansion coefficient substrate to reduce the impact of material property fluctuations on thermal stress; select materials that are resistant to environmental changes to reduce the interference of environmental parameter fluctuations on their performance.

[0101] Strengthen environmental control, upgrade the vacuum chamber pressure control system (such as using more precise pressure sensors and closed-loop control algorithms) to improve stability; optimize the evaporation rate control module (such as introducing a real-time feedback compensation mechanism) to achieve more precise film deposition rate control, and take a two-pronged approach to improve coating process conditions.

[0102] This method associates the raw material response model with the dynamic behavior modeling of the polishing process and the film layer accumulation disturbance sensitivity identification mechanism. Instead of monitoring a single process parameter in isolation, it realizes information integration and trend correlation judgment between multiple process segments, significantly improving the mass production quality and economic benefits of security camera lenses, and providing an innovative solution for the manufacturing of high-precision optical components.

[0103] It should be noted that, in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions. The sentence "including an element defined by..." does not exclude the presence of other identical elements in the process, method, article or device that includes the element."

[0104] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A dynamic multi-parameter process monitoring method for a security camera lens production process, characterized in that: The method comprises the following steps: Step S1: collecting optical property data and physical response data of a security camera lens raw material sample; Step S2: After standardizing the optical characteristic data and physical response data, classify them according to material type and performance to generate raw material standard data; Step S3: collecting real-time polishing data, wherein the real-time polishing data includes real-time geometric feature data and real-time polishing process parameters; calculating a surface roughness deviation rate, a polishing pressure deviation rate, and a thermal stress deviation rate based on the raw material standard data and the real-time polishing data; and combining the surface roughness deviation rate, the polishing pressure deviation rate, and the thermal stress deviation rate to obtain a polishing deviation factor vector; Step S4: weighting the polishing deviation factor using an entropy weight method to obtain a polishing deviation factor weight. Combining the polishing deviation factor vector and the polishing deviation factor weight, a polishing alarm correction index is calculated. When the polishing alarm correction coefficient exceeds a preset threshold, an alarm is immediately triggered and the real-time polishing process parameters are dynamically adjusted to obtain corrected geometric feature data. Step S5: collecting coating stage data during the coating stage, performing feature extraction on the coating stage data using a two-dimensional feature extraction method to obtain coating material response data and coating processing environment data, calculating a material response deviation index based on the coating material response data and raw material standard data, and calculating a processing environment disturbance index based on the coating processing environment data and the corrected geometric feature data; Step S6: combining the material response deviation index with the processing environment disturbance index to calculate a comprehensive coating process deviation index, and performing real-time monitoring of the security camera lens production process based on the comprehensive coating process deviation index.

2. The method for dynamic multi-parameter process monitoring of a security camera lens production process according to claim 1, characterized in that: The optical property data and physical response data of the raw material samples of the security camera lenses are collected, including: Optical properties test: The raw material samples were placed in a spectral transmission device and the refractive index data was recorded every 1°C or 5%RH under different humidity conditions. Five batches of each material were tested and the average value was taken to eliminate batch differences. Physical response testing: Thermal expansion trend: Monitor the length change of the sample during heating using a laser interferometer and calculate the thermal expansion coefficient : ； Among them, α is a physical quantity that measures the change in length of a material when the temperature changes, ΔL is the change in sample length, is the original length of the sample, ΔT is the temperature change; Mechanical stability: Use a stress tester to apply increasing stress to the sample until it breaks, record the stress-strain curve, and calculate the elastic modulus Yield strength .

3. The method for dynamic multi-parameter process monitoring of a security camera lens production process according to claim 2, characterized in that: The generating of raw material standard data includes: Standardization: Taking 25°C, 50% RH, and no stress as the reference state, all parameters are normalized to the range [0, 1] to eliminate dimensional differences; Classification labels and database: assign labels based on material type and performance indicators; Store standardized data, labels and test conditions in a structured database to form a "digital file" for each material and generate standard data for raw materials: material ID, label, refractive index Temperature variation curve, thermal expansion coefficient , elastic modulus , yield strength .

4. The method for dynamic multi-parameter process monitoring of a security camera lens production process according to claim 3, characterized in that: The surface roughness deviation rate, polishing pressure deviation rate and thermal stress deviation rate are calculated based on the raw material standard data and the real-time polishing data, including: Thermal stress deviation rate calculation: Obtaining measured edge deformation using a laser displacement meter , and the theoretical value By comparison, the thermal stress deviation rate is obtained: ； in, is the thermal stress deviation rate, which reflects the degree of deviation of thermal stress release. is the measured edge deformation, is the theoretical value of edge deformation; Calculation of polishing pressure deviation rate: According to the yield strength of raw materials , determine the pressure safety threshold , calculate the measured pressure Deviation rate: ； in, Indicates the deviation rate of polishing pressure, which is used to quantify the degree of deviation between the actual pressure and the safety threshold. It is the actual measured polishing pressure value, which is obtained in real time through the pressure sensor. It is the safety threshold of polishing pressure. Exceeding this value may cause permanent deformation or damage to the material. Calculation of surface roughness deviation rate: Obtaining measured surface roughness , and the target value contrast: ； in, Indicates the deviation rate of surface roughness, which is used to quantify the degree of deviation between the actual roughness and the target value; It is the surface roughness value actually measured by the surface profiler equipment; It is the surface roughness target value pre-set according to the process requirements. This formula is used to evaluate whether the surface roughness after polishing meets the process requirements. If the value is large, it indicates that the actual roughness deviates significantly from the target value, which may affect the adhesion and uniformity of the subsequent coating. At this time, the polishing parameters need to be adjusted to ensure that the surface quality meets the requirements and provide stable substrate conditions for subsequent processes.

5. The method for dynamic multi-parameter process monitoring of a security camera lens production process according to claim 4, characterized in that: The surface roughness deviation rate, polishing pressure deviation rate and thermal stress deviation rate are combined to obtain a polishing deviation factor vector, including: According to thermal stress, pressure, and roughness deviation rate, the polishing deviation factor vector is defined and generated: ), indicating the polishing deviation factor vector It is a vector that includes thermal stress, pressure, and roughness deviation rate. In this form, the multi-factor deviation is comprehensively expressed to facilitate the subsequent analysis of the impact of each factor on the polishing process.

6. The method for dynamic multi-parameter process monitoring of a security camera lens production process according to claim 5, characterized in that: The weight calculation of the polishing deviation factor by the entropy weight method to obtain the polishing deviation factor weight includes: Organize data and build a data matrix ; Thermal stress deviation rate , polishing pressure deviation rate , surface roughness deviation rate The historical data is integrated into a matrix form to provide basic data for subsequent calculations; Standardization: ； in, It represents the value of the i-th sample after normalization on the j-th index. For the The thermal stress deviation rate, polishing pressure deviation rate, and surface roughness deviation rate of each sample are and are the minimum and maximum values ​​of the indicator respectively. The data is standardized to eliminate the dimension effect and map the data to interval; Calculate entropy: , ； in, Indicates calculation of Samples in the index The proportion in reflects the data distribution; Represents the information entropy formula, measurement index uncertainty, The larger the index The more evenly the data is distributed, the less important it is to decision making, where n is the number of indicators; Calculate weights: ； in, is the polishing deviation factor weight, represents the entropy value related to the j-th indicator, It represents the entropy value related to the kth indicator, where k is the indicator index, which is used to traverse the three deviation factors of thermal stress deviation rate, polishing pressure deviation rate and surface roughness deviation rate. Calculation indicators The difference coefficient of , and then normalized to get the weight ; This weight is based on the variability of the data itself, objectively reflecting the impact of each deviation factor on the polishing process, and avoiding the deviation of subjective weight setting.

7. The method for dynamic multi-parameter process monitoring of a security camera lens production process according to claim 6, characterized in that: The polishing alarm correction index is calculated by combining the polishing deviation factor vector and the polishing deviation factor weight. When the polishing alarm correction coefficient exceeds a preset threshold, an alarm is immediately triggered and the real-time polishing process parameters are dynamically adjusted to obtain corrected geometric feature data, including: Polishing alarm correction index: = ； in, is the polishing alarm correction index, At time t, the dynamic weights of thermal stress, polishing pressure, and surface roughness deviation rate, is the deviation rate of deviation factor j; Correction strategy: Red Alert: Immediately suspend the polishing equipment and trigger an audible and visual alarm. At the same time, a work order containing detailed deviation data and attached historical data curves is sent to the engineer terminal to facilitate rapid root cause identification. Yellow warning: Use multi-parameter coupling adjustment strategy: Temperature Regulation: - ； in, Indicates the value after correction of polishing fluid temperature. Indicates the current measured polishing liquid temperature, which is the basic value for temperature adjustment. is the thermal stress temperature regulation coefficient, which is used to quantify the effect of thermal deviation rate on temperature regulation. is the thermal stress deviation rate, The bigger, The larger the value of , the more the amount is subtracted from the measured temperature, reflecting the dominant role of thermal deviation in temperature regulation; is the pressure-temperature cross-influence coefficient, which is used to measure the indirect effect of the pressure deviation rate on the temperature; is the polishing pressure deviation rate, pressure deviation rate The bigger, The larger the value of , the further it is deducted from the measured temperature to ensure that the pressure deviation can also participate in temperature regulation; Roughness adjustment coefficient, used to quantify the effect of surface roughness deviation rate on surface roughness adjustment, is the surface roughness deviation rate; Pressure Regulation: ； in, is the corrected polishing pressure, is the actual measured polishing pressure value, is the thermal stress deviation rate, is the polishing pressure deviation rate, is the surface roughness deviation rate. By taking into account the thermal stress deviation rate, polishing pressure deviation rate, and surface roughness deviation rate, the actual measured polishing pressure is corrected to optimize the polishing process and improve the polishing quality. After each adjustment, the corrected , It is the corrected measured edge deformation value. The edge deformation value is measured in real time by the ruler after the corrected polishing process is applied to the material.

8. The method for dynamic multi-parameter process monitoring of a security camera lens production process according to claim 7, characterized in that: The material response deviation index is calculated based on the coating material response data and the raw material standard data, including: will record With the collection Used to calculate the actual thermal expansion coefficient: ； in, is the actual measured thermal expansion coefficient, is the corrected measured edge deformation value, is the original length of the material, It is the temperature rise of the substrate, which can then be used to evaluate the matching degree of material properties; Material Response Deviation Index formula: ； in, It is the material response deviation index, which comprehensively measures the deviation between the substrate characteristics and the raw material benchmark values, and evaluates the matching degree of the material characteristics to the coating process; 、 、 They are the weight of thermal expansion coefficient, elastic modulus and refractive index. Through orthogonal experiments, we can determine the influence of each factor on the comprehensive performance index, and then determine 、 、 The weight of is the actual measured thermal expansion coefficient; Base value of coefficient of thermal expansion; is the actual measured elastic modulus; Base value of elastic modulus; The actual measured refractive index, It is the reference value of the refractive index.

9. The method for dynamic multi-parameter process monitoring of a security camera lens production process according to claim 8, characterized in that: The process of calculating the process environment disturbance index based on the coating process environment data and the corrected geometric feature data includes: Processing environment disturbance index formula: ； in, It is the processing environment disturbance index, which is used to measure the stability of environmental parameters during the coating stage. A higher index indicates a more unstable environment. 、 、, Respectively represent the importance weights of the evaporation rate, vacuum chamber pressure, and substrate temperature rise on the coating process; It is the actual measured evaporation rate, reflecting the deposition rate of the film material; It is the set evaporation rate target value, which is the ideal value of the process; It is the allowable fluctuation threshold of the evaporation rate, which is used to define the deviation range; It is the actual measured vacuum chamber pressure, which affects the film purity and deposition quality; The target is the set vacuum chamber pressure target value, which is the ideal pressure for the process; is the allowable fluctuation threshold of the vacuum chamber pressure; Base temperature rise, is the set base temperature rise value, It is the allowable fluctuation threshold of the base temperature rise.

10. The method for dynamic multi-parameter process monitoring of a security camera lens production process according to claim 9, characterized in that: The material response deviation index is combined with the processing environment disturbance index to calculate the coating process comprehensive deviation index, including: The material response deviation index is combined with the processing environment disturbance index to calculate the coating process comprehensive deviation index: ； in: is the comprehensive deviation index of the coating process, Over time Dynamically changing weight factor, used to adjust the weight of material response deviation index in comprehensive deviation index; mid-term hour, ; Dynamic adjustment will be made according to material stability in the later stage; It is an environmental correction factor, which is calculated in real time based on the equipment status and workshop temperature and humidity sensor data; is the material response deviation index, which reflects the matching degree between the substrate characteristics and the standard data of the raw materials; It is the processing environment disturbance index, which measures the stability of environmental parameters such as evaporation rate, vacuum chamber pressure, and substrate temperature rise.

Images