Part roughness data analysis system and method based on Internet of Things

Abstract

The invention discloses a part roughness data analysis system and method based on the Internet of Things, and relates to the technical field of big data analysis. The angle adjustment value of a light conversion structure is calculated by accurately collecting end point and reflection point data of a part surface roughness measurement device, the light emission direction is ensured to be consistent with the measurement standard, and the measurement accuracy is improved. And measurement errors caused by light shielding are avoided, so that the data reliability and the measurement precision are improved, the influence of invalid data on part roughness analysis is reduced, and the measurement adaptability and stability are enhanced. By analyzing historical data and combining time sequence prediction and a vector regression prediction model, the next adjustment time and angle of the light conversion structure are accurately predicted. Based on the prediction result, the system can judge whether the light emission structure is abnormal or not in real time and ensure that the light emission angle is within a reasonable range, so that the measurement error caused by improper adjustment is avoided, the part surface roughness measurement process is optimized, and the data accuracy is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis, and in particular to a system and method for analyzing part roughness data based on the Internet of Things. Background Art

[0002] In the field of aerospace engineering, part surface roughness significantly impacts airflow friction, heat exchange efficiency, and component fatigue life. Precisely controlling surface roughness can improve engine performance, optimize airflow stability, and reduce energy loss. Currently, part surface roughness measurement primarily utilizes fiber optic sensing and tracking measurement devices. Light emitted by a light source is transmitted through a fiber optic sensor and illuminates the inner surface of the part being measured. The reflected light signal is collected by an optical power meter. The greater the surface roughness, the weaker the collected light intensity. This change in light intensity allows for quantitative assessment of the part's surface roughness.

[0003] During actual measurement, fiber optic sensor tracking measurement devices are affected by a variety of factors, including environmental factors, changes in part position, and accumulated errors during the tracking measurement process. This can lead to deviations in the accuracy of the collected data. This deviation can adversely affect the accurate analysis of part surface roughness. Summary of the Invention

[0004] The purpose of the present invention is to provide a part roughness data analysis system and method based on the Internet of Things to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solution: a method for analyzing part roughness data based on the Internet of Things, the method comprising the following steps: The part surface roughness measuring device uses the incident light emitted by the light source to pass through the internal light conversion device and illuminate the inner surface of the part to be measured. The reflected light from the inner surface of the part to be measured is then collected and analyzed, and the roughness of the part is analyzed by analyzing the reflected light on the part surface. The roughness of the part surface is collected by optical sensors such as optical power meters after reflection. The rougher the surface of the measured part, the smaller the light intensity value collected by the optical power meter. Based on the received light intensity, the surface roughness value is quantitatively evaluated.

[0006] Step S1: obtaining the two endpoint data of the light outlet of the part surface roughness measuring device in the direction of motion, as well as the reflection point position data of the internal light conversion structure, and calculating the angle adjustment value of the light conversion structure based on the length data of the light outlet in the direction of motion and the reflection point position data; Step S1-1: Obtain the data of two endpoints of the light outlet of the part surface roughness measuring device in the moving direction through a grating sensor. The two endpoint data obtained include the position data of the first light-emitting point and the position data of the second light-emitting point in the moving direction. The first light-emitting point is represented as the endpoint of the light outlet far from the moving direction in the moving direction, and the second light-emitting point is represented as the endpoint of the light outlet in the same direction as the moving direction in the moving direction. When the part surface roughness measuring device is parallel to the horizontal direction, a perpendicular line is drawn from the reflection point to the connection line between the first light-emitting point and the second light-emitting point, and there is a perpendicular point O. Step S1-2: Obtain the position data of the reflection point of the light conversion structure inside the part surface roughness measuring device through an optical sensor. Combine the two endpoint data of the light outlet to construct a two-dimensional coordinate system for position data mapping, and analyze and calculate the angle adjustment value of the light conversion structure through the vector angle formula. The vector angle formula is as follows: ; In the formula, O i represents the included angle of the reflected light of the i-th endpoint; V ver represents the direction vector from the reflection point to the perpendicular point O. During the measurement, the reflected light always remains perpendicular to the part surface; V i represents the direction vector from the reflection point to the i-th endpoint; 丨V ver 丨 represents the magnitude of the direction vector perpendicular to the part surface from the reflection point; 丨V i 丨 represents the magnitude of the direction vector from the reflection point to the i-th endpoint; Step S1-3: Substitute the position data of the first light-emitting point into the vector angle formula to calculate the included angle one of the first light-emitting point, and substitute the position data of the second light-emitting point into the vector angle formula to calculate the included angle two of the second light-emitting point. The angle adjustment value of the light conversion structure is represented as the angle range between the included angle one and the included angle two.

[0007] Calculate the edge data of the light outlet in the moving direction of the part surface roughness measuring device to prevent the light from being blocked by the edge of the light outlet after passing through the light conversion structure, resulting in the loss of the reflected light on the part surface, thereby affecting the data coherence of the measurement. Repeated intermittent measurements will cause error accumulation and affect the analysis of the part surface roughness.

[0008] By accurately collecting the endpoint data and the reflection point data, using the vector angle formula to calculate the angle adjustment value of the light conversion structure, ensuring the precise control of the light emission direction, calculating and adjusting the angle of the light conversion structure with high precision, avoiding measurement errors caused by light deviation, and thus improving the accuracy of part roughness measurement.

[0009] Step S2: Collecting height data of the light outlet of the part surface roughness measuring device and the light emitting structure from the part surface, and then calculating the angle of the light emitted by the light emitting structure based on the distance between the light outlet of the part surface roughness measuring device and the light emitting structure, recording it as the light incidence angle, and combining it with the angle adjustment value to determine whether the light emitted by the light emitting structure is abnormal; Step S2-1: Using an optical sensor to collect height data of the light outlet of the part surface roughness measuring device and the light emitting structure from the part surface, construct an extension line in the direction opposite to the reflection point of the light outlet, and then construct a right triangle with a perpendicular line through the light emitting structure as the extension line. Based on the distance between the light outlet of the part surface roughness measuring device and the light emitting structure, the angle of the light emitted by the light emitting structure is calculated using the sine theorem, and recorded as the angle of incidence of the light; Step S2-2: Using an optical sensor to collect the direction of reflected light from the part surface, the angle of the light conversion structure is adjusted based on the direction of the reflected light to ensure that the light is perpendicular to the part surface after passing through the light conversion structure. The law of light reflection and the angle of incidence of the light are combined, and the relationship between the angle of incidence and the direction of the reflected light is used to ensure that the normal direction is always perpendicular to the light conversion structure. The light conversion structure is then adjusted using a neural network for calculation. Step S2-3: Determine whether the reflected light intersects the line connecting the first light exit point and the second light exit point based on the position information after the light conversion structure is adjusted. When the reflected light intersects the line connecting the first light-emitting point and the second light-emitting point, it is determined that the direction of the light is perpendicular to the surface of the part after being adjusted by the light conversion structure and is not blocked, and the light is normal light; When there is no intersection between the reflected light and the line connecting the first light exit point and the second light exit point, it is determined that the direction of the light is perpendicular to the surface of the part after being adjusted by the light conversion structure, the light is blocked, and the light is abnormal light.

[0010] When the light outlet of the part surface roughness measuring device is offset downward or upward at a right angle relative to the part, the position of the part remains unchanged, and the light output range of the light outlet becomes smaller. After the light is adjusted by the light conversion structure, it needs to remain vertically irradiated on the part surface. The edge of the light outlet will block the light, affecting the measurement of the part surface roughness measuring device.

[0011] By precisely calculating the incident angle of light and adjusting the light conversion structure, we ensure that the light always strikes the part surface perpendicularly, avoiding measurement errors caused by light obstruction. This step effectively detects and corrects light anomalies, improving the accuracy and stability of part surface roughness measurements.

[0012] Step S3: creating an angle adjustment set, wherein the angle adjustment set is used to store the adjustment time and adjustment angle of the light conversion structure inside the part surface roughness measuring device, and the adjustment time and adjustment angle corresponding to the light without abnormality after adjustment by the light conversion structure are stored in the form of key-value pairs; In step S3, an angle adjustment set is created, and the angle adjustment set is used to store the adjustment time and adjustment angle of the light conversion structure inside the part surface roughness measuring device; when the light passes through the light conversion structure inside the part surface roughness measuring device after adjustment, the judgment result is identified. When the judgment result is normal light, the adjustment time and adjustment angle of the light conversion structure are stored. The storage adopts the form of key-value pairs, with the adjustment time as the key of the angle adjustment set and the adjustment angle as the value of the angle adjustment set.

[0013] By creating an angle adjustment set, the system can record the adjustment history of the light conversion structure, including adjustment time and angle, to facilitate subsequent analysis and prediction. This set provides data support for further light adjustment and abnormality judgment, helping to optimize the light adjustment process and improve measurement stability. By analyzing and predicting the historical data in the angle adjustment set, the system can accurately predict the next adjustment time and angle of the light conversion structure, thereby optimizing the adjustment process and ensuring that the light emitted by the light emitting structure is within the normal range.

[0014] Step S4: predicting the next adjustment time and adjustment angle of the light conversion structure inside the part surface roughness measuring device based on the angle adjustment set, and determining whether the light emitted by the light emitting structure is abnormal based on the predicted adjustment angle of the light conversion structure and the angle adjustment value of the light conversion structure; Step S4-1: Analyze and extract the adjustment time in the angle adjustment set, and predict the adjustment time of the light conversion structure in combination with the time series prediction. The prediction calculation uses the following formula: ; Where, T t+1 It represents the predicted next adjustment time of the light conversion structure; u represents the average value of the angle adjustment set; It is expressed as the impact value of the historical p adjustment times on the predicted adjustment time in the angle adjustment set; H i Expressed as autoregressive coefficient; T t+1 It is represented as the adjustment time of historical i moments in the angle adjustment set; It is expressed as the impact of the historical q errors on the predicted adjustment time in the angle adjustment set; Y i Expressed as moving average coefficient; G t-1 It is represented as the error term of the historical j times in the angle adjustment set; Step S4-2: Analyze and extract the adjustment angles in the angle adjustment set, and use the vector regression prediction model to predict the next adjustment angle of the light conversion structure. The adjustment angle prediction is calculated using the following formula: ; Where, J T It represents the adjustment angle of the light conversion structure at the next T time predicted by the angle adjustment set; N represents the number of data samples in the angle adjustment set; a i Expressed as Lagrange multiplier; K(x i , x T ) represents the sample data x in the angle adjustment set i and sample data x T The similarity between i Represents the angle data adjusted at the i-th moment in the angle adjustment set; x T It represents the angle data adjusted at the Tth moment in the angle adjustment set; b represents the bias term; Based on the predicted and calculated adjustment angle of the light conversion structure and the current angle of the light conversion structure, combined with the angle adjustment value, the light emitted from the position of the part surface roughness measuring device at the current moment is judged. When the predicted and calculated adjustment angle of the light conversion structure exceeds the preset angle adjustment value range of the light conversion structure, the light emitted from the position of the part surface roughness measuring device at the current moment is judged to be abnormal light; when the predicted and calculated adjustment angle of the light conversion structure does not exceed the preset angle adjustment value range of the light conversion structure, the light emitted from the position of the part surface roughness measuring device at the current moment is judged to be normal light.

[0015] Step S5: Based on the abnormality judgment result of the light emitted by the light emitting structure, an early warning is issued when the abnormal light condition is satisfied within the predicted adjustment time; The judgment result after the prediction calculation is analyzed. When the judgment result is abnormal light, it is judged that after the angle of the light conversion structure is adjusted, the light emitted by the part surface roughness measuring device will be blocked. Within the predicted adjustment time, an early warning of light abnormality is issued to the system.

[0016] By analyzing the predicted abnormal light judgment results, it is possible to promptly detect whether the light emitting structure is blocked, ensuring that the light abnormality warning is triggered within the predicted adjustment time, so as to deal with potential problems in advance.

[0017] Furthermore, a part roughness data analysis system based on the Internet of Things includes a data acquisition module, an angle calculation module, a light anomaly judgment module, a prediction analysis module, and an anomaly warning module; The data acquisition module is used to collect position information and light parameters of the part surface roughness measuring device; the angle calculation module is used to calculate the adjustment angle of the light conversion structure and the incident angle of the light based on the collected data; the light anomaly judgment module is used to judge whether the emitted light is abnormal; the prediction analysis module is used to predict the next adjustment time and angle of the light conversion structure based on historical data; and the abnormality warning module is used to issue a warning prompt to the system when it is determined that the light is abnormal. The output end of the data acquisition module is electrically connected to the input end of the angle calculation module; the output end of the angle calculation module is electrically connected to the input end of the light anomaly judgment module; the output end of the light anomaly judgment module is electrically connected to the input end of the prediction and analysis module; the output end of the prediction and analysis module is electrically connected to the input end of the abnormality warning module.

[0018] The data acquisition module includes an endpoint data acquisition unit and a reflection point data acquisition unit; the endpoint data acquisition unit is used to collect two endpoint data of the light outlet of the part surface roughness measuring device in the direction of movement; the reflection point data acquisition unit is used to collect the position information of the reflection point in the light conversion structure; The angle calculation module includes an angle adjustment range calculation unit and a light incident angle calculation unit; the angle adjustment range calculation unit is used to calculate the angle adjustment range of the light conversion structure according to the endpoint data and the reflection point data; the light incident angle calculation unit is used to calculate the incident angle of the light according to the height data of the light emitting structure and the part surface; The light anomaly judgment module includes a light anomaly judgment unit and a reflection direction verification unit; the light anomaly judgment unit is used to judge whether the emitted light is abnormal and determine whether there is any obstruction; the reflection direction verification unit is used to verify whether the direction of the reflected light is consistent with the predetermined light path; The prediction analysis module includes an adjustment time prediction unit and an adjustment angle prediction unit; the adjustment time prediction unit is used to predict the adjustment time of the next light conversion structure based on historical adjustment data; the adjustment angle prediction unit is used to predict the next adjustment angle based on historical angle adjustment data; The abnormal warning module includes an abnormal light recognition unit and a time-limited warning issuing unit; the abnormal light recognition unit is used to identify the abnormal state of light when the prediction result is abnormal light; the time-limited warning issuing unit is used to issue a time-limited warning prompt of light abnormality to the system within the predicted adjustment time.

[0019] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention precisely collects endpoint and reflection point data from a part surface roughness measurement device and calculates the angle adjustment value of the light conversion structure to ensure that the light emission direction is consistent with the measurement standard. This process effectively avoids measurement errors caused by light obstruction, improves data reliability and measurement accuracy, and reduces the impact of invalid data on part roughness analysis, thereby improving measurement adaptability and stability.

[0020] 2. This invention analyzes historical data and combines time series prediction with vector regression prediction models to accurately predict the next adjustment time and angle of the light conversion structure. Based on the prediction results, the system can determine in real time whether there are any anomalies in the light emitted by the light emitting structure, ensuring that the light emission angle is within a reasonable range. This prediction method can proactively identify problems such as light deviation or occlusion, avoiding measurement errors caused by improper adjustments, thereby optimizing the part surface roughness measurement process and ensuring data accuracy.

[0021] 3. The present invention effectively tracks the operating status of the part surface roughness measurement device through real-time data monitoring. When the system predicts that the light emitted by the light emitting structure is abnormal, it promptly issues an early warning signal to the system. If light is blocked, timely adjustment strategies can be implemented, thus avoiding measurement errors and improving the automation level and responsiveness of the entire measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 Schematic diagram of the process of the part roughness data analysis method based on the Internet of Things of the present invention; Figure 2 This is a schematic structural diagram of the part roughness data analysis system based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0023] 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.

[0024] Example 1: Figure 1 As shown, the present invention provides a technical solution, a part roughness data analysis method based on the Internet of Things, and the part roughness data analysis method includes the following steps: Step S1: Obtain the data of two endpoints of the light outlet of the part surface roughness measuring device in the moving direction, and the position data of the reflection point of the internal light conversion structure. Analyze and calculate the angle adjustment value of the light conversion structure based on the length data of the light outlet in the moving direction and the position data of the reflection point. Step S1-1: Obtain the data of two endpoints of the light outlet of the part surface roughness measuring device in the moving direction through a grating sensor. The two endpoint data obtained include the position data of the first light point and the position data of the second light point in the moving direction. The first light point is represented as the endpoint of the light outlet far from the moving direction in the moving direction, and the second light point is represented as the endpoint of the light outlet in the same direction as the moving direction in the moving direction. When the part surface roughness measuring device is parallel to the horizontal direction, draw a perpendicular line from the reflection point to the line connecting the first light point and the second light point, and there is a perpendicular point O. Step S1-2: Obtain the position data of the reflection point of the internal light conversion structure of the part surface roughness measuring device through an optical sensor. Combine the two endpoint data of the light outlet, construct a two-dimensional coordinate system for position data mapping, and analyze and calculate the angle adjustment value of the light conversion structure through the vector included angle formula. The vector included angle formula is as follows: ; [[ID=⑨]]In the formula, O i represents the included angle of the reflected light of the i-th endpoint; V ver represents the direction vector from the reflection point to the perpendicular point O. During the measurement, the reflected light always remains perpendicular to the part surface; V i represents the direction vector from the reflection point to the i-th endpoint; |V ver | represents the magnitude of the direction vector perpendicular to the part surface from the reflection point; |V i | represents the magnitude of the direction vector from the reflection point to the i-th endpoint; Step S1-3: Substitute the position data of the first light point into the vector included angle formula to calculate the included angle one of the first light point, and substitute the position data of the second light point into the vector included angle formula to calculate the included angle two of the second light point. The angle adjustment value of the light conversion structure is represented as the angle range of the included angle one and the included angle two.

[0025] For example, obtain the data of two endpoints of the light outlet of the part surface roughness measuring device in the moving direction through a grating sensor, map the position data to the constructed two-dimensional coordinate system. The position of the first light point is (2, 2), the position of the second light point is (2, 4), and the position of the reflection point of the internal light conversion structure of the part surface roughness measuring device is (3, 5); According to the formula calculation, the included angle of the reflected light of the first light point is: · According to the formula, the angle of the reflected light from the second light-emitting point is: ; According to the calculated values of O1 and O2, the angle adjustment value of the light conversion structure at the light outlet of the part surface roughness measurement device can be further calculated as follows: O=O1-O2=71.57°-45°=26.57°; The angle adjustment value range of the light conversion structure at the light outlet of the part surface roughness measuring device is [0°, 26.57°].

[0026] Step S2: Collecting height data of the light outlet of the part surface roughness measuring device and the light emitting structure from the part surface, and then calculating the angle of the light emitted by the light emitting structure based on the distance between the light outlet of the part surface roughness measuring device and the light emitting structure, recording it as the light incidence angle, and combining it with the angle adjustment value to determine whether the light emitted by the light emitting structure is abnormal; Step S2-1: Using an optical sensor to collect height data of the light outlet of the part surface roughness measuring device and the light emitting structure from the part surface, construct an extension line in the direction opposite to the reflection point of the light outlet, and then construct a right triangle with a perpendicular line through the light emitting structure as the extension line. Based on the distance between the light outlet of the part surface roughness measuring device and the light emitting structure, the angle of the light emitted by the light emitting structure is calculated using the sine theorem, and recorded as the angle of incidence of the light; Step S2-2: Using an optical sensor to collect the direction of reflected light from the part surface, the angle of the light conversion structure is adjusted based on the direction of the reflected light to ensure that the light is perpendicular to the part surface after passing through the light conversion structure. The law of light reflection and the angle of incidence of the light are combined, and the relationship between the angle of incidence and the direction of the reflected light is used to ensure that the normal direction is always perpendicular to the light conversion structure. The light conversion structure is then adjusted using a neural network for calculation. Step S2-3: Determine whether the reflected light intersects the line connecting the first light exit point and the second light exit point based on the position information after the light conversion structure is adjusted. When the reflected light intersects the line connecting the first light-emitting point and the second light-emitting point, it is determined that the direction of the light is perpendicular to the surface of the part after being adjusted by the light conversion structure and is not blocked, and the light is normal light; When there is no intersection between the reflected light and the line connecting the first light exit point and the second light exit point, it is determined that the direction of the light is perpendicular to the surface of the part after being adjusted by the light conversion structure, the light is blocked, and the light is abnormal light.

[0027] Step S3: creating an angle adjustment set, wherein the angle adjustment set is used to store the adjustment time and adjustment angle of the light conversion structure inside the part surface roughness measuring device, and the adjustment time and adjustment angle corresponding to the light without abnormality after adjustment by the light conversion structure are stored in the form of key-value pairs; In step S3, an angle adjustment set is created, and the angle adjustment set is used to store the adjustment time and adjustment angle of the light conversion structure inside the part surface roughness measuring device; when the light passes through the light conversion structure inside the part surface roughness measuring device after adjustment, the judgment result is identified. When the judgment result is normal light, the adjustment time and adjustment angle of the light conversion structure are stored. The storage adopts the form of key-value pairs, with the adjustment time as the key of the angle adjustment set and the adjustment angle as the value of the angle adjustment set.

[0028] Step S4: predicting the next adjustment time and adjustment angle of the light conversion structure inside the part surface roughness measuring device based on the angle adjustment set, and determining whether the light emitted by the light emitting structure is abnormal based on the predicted adjustment angle of the light conversion structure and the angle adjustment value of the light conversion structure; Step S4-1: Analyze and extract the adjustment time in the angle adjustment set, and predict the adjustment time of the light conversion structure in combination with the time series prediction. The prediction calculation uses the following formula: ; Where, T t+1 It represents the predicted next adjustment time of the light conversion structure; u represents the average value of the angle adjustment set; It is expressed as the impact value of the historical p adjustment times on the predicted adjustment time in the angle adjustment set; H i Expressed as autoregressive coefficient; T t+1 It is represented as the adjustment time of historical i moments in the angle adjustment set; It is expressed as the impact of the historical q errors on the predicted adjustment time in the angle adjustment set; Y i Expressed as moving average coefficient; G t-1 It is represented as the error term of the historical j times in the angle adjustment set; Step S4-2: Analyze and extract the adjustment angles in the angle adjustment set, and use the vector regression prediction model to predict the next adjustment angle of the light conversion structure. The adjustment angle prediction is calculated using the following formula: ; Where, J T It represents the adjustment angle of the light conversion structure at the next T time predicted by the angle adjustment set; N represents the number of data samples in the angle adjustment set; a i Expressed as Lagrange multiplier; K(xi , x T ) represents the sample data x in the angle adjustment set i and sample data x T The similarity between i Represents the angle data adjusted at the i-th moment in the angle adjustment set; x T It represents the angle data adjusted at the Tth moment in the angle adjustment set; b represents the bias term.

[0029] For example, the existing measurement data is as follows: Angle adjustment set [(10s, 5°), (15s, 7°), (12s, 6°), (18s, 8°), (14s, 7°)]; Autoregressive coefficient H i =【0.5,0.3,0.2】;moving average coefficient Y i =【0.4,0.6】; error term G t-1 =【0.1,0.05】;angle adjustment ensemble mean u=15;Lagrange multiplier a i =【1.2,0.8,0.5】;Number of samples N=5;Sample similarity K(x i , x T ) = [0.9, 0.7, 0.5, 0.8, 0.6]; bias term b = 0.2; the current angle of the light conversion structure is 15°; the angle adjustment value of the light conversion structure is [0°, 26.57°]; According to the adjustment time prediction calculation formula, we can get: T t+1 =15+(0.5*14+0.3*18+0.2*12)-(0.4*0.1+0.6*0.05)=29.73s; According to the adjustment angle prediction calculation formula, we can get: J T =J 29.73 =1.2*0.9+0.8*0.7+0.5*0.5+0.2=1.08+0.56+0.2=2.09°; According to the angle adjustment value [0°, 26.57°] of the light conversion structure, it can be seen that the time for the next adjustment of the light conversion structure is 29.73s, and the adjusted angle is within the angle adjustment value. The adjusted light is normal light.

[0030] Based on the predicted and calculated adjustment angle of the light conversion structure and the current angle of the light conversion structure, combined with the angle adjustment value, the light emitted from the position of the part surface roughness measuring device at the current moment is judged. When the predicted and calculated adjustment angle of the light conversion structure exceeds the preset angle adjustment value range of the light conversion structure, the light emitted from the position of the part surface roughness measuring device at the current moment is judged to be abnormal light; when the predicted and calculated adjustment angle of the light conversion structure does not exceed the preset angle adjustment value range of the light conversion structure, the light emitted from the position of the part surface roughness measuring device at the current moment is judged to be normal light.

[0031] Step S5: Based on the abnormality judgment result of the light emitted by the light emitting structure, an early warning is issued when the abnormal light condition is satisfied within the predicted adjustment time; The judgment result after the prediction calculation is analyzed. When the judgment result is abnormal light, it is judged that after the angle of the light conversion structure is adjusted, the light emitted by the part surface roughness measuring device will be blocked. Within the predicted adjustment time, an early warning of light abnormality is issued to the system.

[0032] Example 2, as Figure 2 As shown, the present invention provides a part roughness data analysis system based on the Internet of Things, which includes a data acquisition module, an angle calculation module, a light anomaly judgment module, a prediction analysis module and an anomaly warning module; The data acquisition module is used to collect position information and light parameters of the part surface roughness measuring device; the angle calculation module is used to calculate the adjustment angle of the light conversion structure and the incident angle of the light based on the collected data; the light anomaly judgment module is used to judge whether the emitted light is abnormal; the prediction analysis module is used to predict the next adjustment time and angle of the light conversion structure based on historical data; and the abnormality warning module is used to issue a warning prompt to the system when it is determined that the light is abnormal. The output end of the data acquisition module is electrically connected to the input end of the angle calculation module; the output end of the angle calculation module is electrically connected to the input end of the light anomaly judgment module; the output end of the light anomaly judgment module is electrically connected to the input end of the prediction and analysis module; the output end of the prediction and analysis module is electrically connected to the input end of the abnormality warning module.

[0033] The data acquisition module includes an endpoint data acquisition unit and a reflection point data acquisition unit; the endpoint data acquisition unit is used to collect two endpoint data of the light outlet of the part surface roughness measuring device in the direction of movement; the reflection point data acquisition unit is used to collect the position information of the reflection point in the light conversion structure; The angle calculation module includes an angle adjustment range calculation unit and a light incident angle calculation unit; the angle adjustment range calculation unit is used to calculate the angle adjustment range of the light conversion structure according to the endpoint data and the reflection point data; the light incident angle calculation unit is used to calculate the incident angle of the light according to the height data of the light emitting structure and the part surface; The light anomaly judgment module includes a light anomaly judgment unit and a reflection direction verification unit; the light anomaly judgment unit is used to judge whether the emitted light is abnormal and determine whether there is any obstruction; the reflection direction verification unit is used to verify whether the direction of the reflected light is consistent with the predetermined light path; The prediction analysis module includes an adjustment time prediction unit and an adjustment angle prediction unit; the adjustment time prediction unit is used to predict the adjustment time of the next light conversion structure based on historical adjustment data; the adjustment angle prediction unit is used to predict the next adjustment angle based on historical angle adjustment data; The abnormal warning module includes an abnormal light recognition unit and a time-limited warning issuing unit; the abnormal light recognition unit is used to identify the abnormal state of light when the prediction result is abnormal light; the time-limited warning issuing unit is used to issue a time-limited warning prompt of light abnormality to the system within the predicted adjustment time.

[0034] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A method for analyzing part roughness data based on the Internet of Things, characterized in that: The part roughness data analysis method comprises the following steps: Step S1, obtaining the two end point data of the light outlet of the part surface roughness measuring device in the moving direction and the reflection point position data of the internal light conversion structure, and calculating the angle adjustment value of the light conversion structure according to the length data of the light outlet in the moving direction and the reflection point position data; Step S2, collecting height data of the light outlet of the part surface roughness measuring device and the light emitting structure from the part surface, and then calculating the angle of the light emitted by the light emitting structure according to the distance between the light outlet of the part surface roughness measuring device and the light emitting structure, recording it as the light incident angle, and judging whether the light emitted by the light emitting structure is abnormal in combination with the angle adjustment value; Step S3, creating an angle adjustment set, wherein the angle adjustment set is used to store the adjustment time and adjustment angle of the light conversion structure inside the part surface roughness measuring device, and the adjustment time and adjustment angle corresponding to the light that has no abnormality after adjustment by the light conversion structure are stored in the form of key-value pairs; Step S4, predicting the next adjustment time and adjustment angle of the light conversion structure inside the part surface roughness measuring device according to the angle adjustment set, and judging whether the light emitted by the light emitting structure is abnormal according to the predicted adjustment angle of the light conversion structure combined with the angle adjustment value of the light conversion structure; Step S5: Based on the abnormal light emission result of the light emitting structure, an early warning is issued when the abnormal light condition is satisfied within the predicted adjustment time.

2. The method for analyzing part roughness data based on the Internet of Things according to claim 1, characterized in that: The specific steps of step S1 are as follows: Step S1-1, acquiring two endpoint data of the light outlet of the part surface roughness measuring device in the moving direction through a grating sensor, wherein the acquired two endpoint data include position data of a first light outlet point and position data of a second light outlet point in the moving direction, wherein the first light outlet point is represented as an endpoint in the moving direction where the light outlet is away from the moving direction, and the second light outlet point is represented as an endpoint in the moving direction where the light outlet is in the same direction as the moving direction, and when the part surface roughness measuring device is parallel to the horizontal direction, a perpendicular line connecting the first light outlet point and the second light outlet point through the reflection point has a perpendicular point O; Step S1-2, obtain the reflection point position data of the light conversion structure inside the part surface roughness measuring device through the optical sensor, combine the two end point data of the light outlet, construct a two-dimensional coordinate system for position data mapping, and calculate the angle adjustment value of the light conversion structure through the vector angle formula. The vector angle formula is as follows: ； Where, O i represents the included angle of the reflected light of the i-th endpoint; V ver represents the direction vector from the reflection point to the perpendicular point O. During the measurement, the reflected light always remains perpendicular to the surface of the part; V i represents the direction vector from the reflection point to the i-th endpoint; |V ver | represents the magnitude of the direction vector perpendicular from the reflection point to the surface of the part; |V i | represents the magnitude of the direction vector from the reflection point to the i-th endpoint; Step S1-3, substitute the position data of the first light emitting point into the vector angle formula to calculate the angle 1 of the first light emitting point, substitute the position data of the second light emitting point into the vector angle formula to calculate the angle 2 of the second light emitting point, and the angle adjustment value of the light conversion structure is expressed as the angle range of angle 1 and angle 2.

3. The method for analyzing part roughness data based on the Internet of Things according to claim 2, characterized in that: The specific steps of step S2 are as follows: Step S2-1, collecting height data of the light outlet of the part surface roughness measuring device and the light emitting structure from the part surface through an optical sensor, constructing an extension line in the opposite direction of the reflection point in the light outlet, and then constructing a right triangle through the light emitting structure as a perpendicular line of the extension line, and calculating the angle of the light emitted by the light emitting structure according to the distance between the light outlet of the part surface roughness measuring device and the light emitting structure by the sine theorem, which is recorded as the incident angle of the light; Step S2-2, using an optical sensor to collect the direction of reflected light on the surface of the part, adjusting the angle of the light conversion structure according to the direction of the reflected light, ensuring that the light is irradiated vertically on the surface of the part after passing through the light conversion structure, combining the law of light reflection and the incident angle of the light, using the relationship between the incident angle of the light and the direction of the reflected light, ensuring that the normal direction is always perpendicular to the light conversion structure, and then using a neural network to calculate and adjust the light conversion structure; Step S2-3: judging whether the reflected light has an intersection with the line connecting the first light exit point and the second light exit point according to the position information after the light conversion structure is adjusted: When the reflected light and the line connecting the first light-emitting point and the second light-emitting point have an intersection, it is determined that after the light is adjusted by the light conversion structure, its direction is perpendicular to the surface of the part and will not be blocked, and the light is normal light; When there is no intersection between the reflected light and the line connecting the first light emitting point and the second light emitting point, it is determined that the direction of the light is perpendicular to the surface of the part after being adjusted by the light conversion structure, the light is blocked, and the light is abnormal light.

4. The method for analyzing part roughness data based on the Internet of Things according to claim 3 is characterized in that: In step S3, an angle adjustment set is created, and the angle adjustment set is used to store the adjustment time and adjustment angle of the light conversion structure inside the part surface roughness measuring device; when the light is adjusted by the light conversion structure inside the part surface roughness measuring device, the judgment result is identified, and when the judgment result is normal light, the adjustment time and adjustment angle of the light conversion structure are stored, and the storage is in the form of a key-value pair, with the adjustment time as the key of the angle adjustment set, and the adjustment angle as the value of the angle adjustment set.

5. The method for analyzing part roughness data based on the Internet of Things according to claim 4 is characterized in that: The specific steps of step S4 are as follows: Step S4-1: Analyze and extract the adjustment time in the angle adjustment set, and predict and calculate the adjustment time of the light conversion structure in combination with the time series prediction. The prediction calculation uses the following formula: ； Where, T t+1 It is represented as the predicted next adjustment time of the light conversion structure; u is represented as the average value of the angle adjustment set; It is represented by the impact value of the historical p adjustment times on the predicted adjustment time in the angle adjustment set; H i Expressed as autoregressive coefficient; T t+1 It is represented as the adjustment time of the historical i moments in the angle adjustment set; It is expressed as the impact value of the historical q errors on the predicted adjustment time in the angle adjustment set; Y i Expressed as a moving average coefficient; G t-1 It is represented as the error term of the jth history in the angle adjustment set; Step S4-2: Analyze and extract the adjustment angles in the angle adjustment set, and use the vector regression prediction model to predict the next adjustment angle of the light conversion structure. The adjustment angle prediction is calculated using the following formula: ； In the formula, J T It is represented by the adjustment angle of the light conversion structure at the next T moment predicted by the angle adjustment set; N is represented by the number of data samples in the angle adjustment set; a i Expressed as Lagrange multiplier; K(x i , x T ) represents the sample data x in the angle adjustment set i And sample data x T The similarity between i Represents the angle data adjusted at the i-th moment in the angle adjustment set; x T It represents the angle data adjusted at the Tth moment in the angle adjustment set; b represents the bias term.

6. The method for analyzing part roughness data based on the Internet of Things according to claim 5, characterized in that: In step S4, the light emitted from the position of the part surface roughness measuring device at the current moment is judged based on the predicted and calculated adjustment angle of the light conversion structure and the current angle of the light conversion structure, combined with the upper limit of the angle adjustment. When the predicted and calculated adjustment angle of the light conversion structure exceeds the preset angle adjustment value range of the light conversion structure, it is judged that the light emitted from the position of the part surface roughness measuring device at the current moment is abnormal light; when the predicted and calculated adjustment angle of the light conversion structure does not exceed the preset angle adjustment value range of the light conversion structure, it is judged that the light emitted from the position of the part surface roughness measuring device at the current moment is normal light.

7. The method for analyzing part roughness data based on the Internet of Things according to claim 6, characterized in that: In step S5, the judgment result after the prediction calculation is analyzed. When the judgment result is abnormal light, it is judged that after the angle of the light conversion structure is adjusted, the light emitted by the part surface roughness measuring device will be blocked. Within the predicted adjustment time, an abnormal light warning is issued to the system to prompt.

8. A part roughness data analysis system based on the Internet of Things, which is applied to the part roughness data analysis method based on the Internet of Things according to any one of claims 1 to 7, characterized in that: The part roughness data analysis system includes a data acquisition module, an angle calculation module, a light anomaly judgment module, a prediction analysis module and an anomaly warning module; The data acquisition module is used to collect the position information and light parameters of the part surface roughness measuring device; the angle calculation module is used to calculate the adjustment angle of the light conversion structure and the light incident angle according to the collected data; the light anomaly judgment module is used to judge whether the emitted light is abnormal; the prediction analysis module is used to predict the next adjustment time and angle of the light conversion structure through historical data; the abnormal warning module is used to issue a warning prompt to the system when judging that the light is abnormal; The output end of the data acquisition module is electrically connected to the input end of the angle calculation module; the output end of the angle calculation module is electrically connected to the input end of the light anomaly judgment module; the output end of the light anomaly judgment module is electrically connected to the input end of the prediction and analysis module; the output end of the prediction and analysis module is electrically connected to the input end of the abnormal warning module.

9. The part roughness data analysis system based on the Internet of Things according to claim 8, characterized in that: The data acquisition module includes an endpoint data acquisition unit and a reflection point data acquisition unit; the endpoint data acquisition unit is used to collect two endpoint data of the light outlet of the part surface roughness measurement device in the moving direction; the reflection point data acquisition unit is used to collect the position information of the reflection point in the light conversion structure; The angle calculation module includes an angle adjustment range calculation unit and a light incident angle calculation unit; the angle adjustment range calculation unit is used to calculate the angle adjustment range of the light conversion structure according to the endpoint data and the reflection point data; the light incident angle calculation unit is used to calculate the incident angle of the light according to the height data of the light emitting structure and the surface of the part; The light anomaly judgment module includes a light anomaly judgment unit and a reflection direction verification unit; the light anomaly judgment unit is used to judge whether the emitted light is abnormal and determine whether there is any obstruction; the reflection direction verification unit is used to verify whether the direction of the reflected light is consistent with the predetermined light path.

10. The part roughness data analysis system based on the Internet of Things according to claim 8, characterized in that: The prediction analysis module includes an adjustment time prediction unit and an adjustment angle prediction unit; the adjustment time prediction unit is used to predict the adjustment time of the next light conversion structure based on historical adjustment data; the adjustment angle prediction unit is used to predict the next adjustment angle based on historical angle adjustment data; The abnormal warning module includes an abnormal light recognition unit and a time-limited warning issuing unit; the abnormal light recognition unit is used to identify the abnormal state of light when the prediction result is abnormal light; the time-limited warning issuing unit is used to issue a time-limited warning prompt of light abnormality to the system within the predicted adjustment time.

Images