A Dynamic Analysis System for Fan Component Production Data Oriented to Intelligent Manufacturing

Abstract

The present invention relates to the technical field of production data analysis of fan components, and specifically to a dynamic analysis system for production data of fan components for intelligent manufacturing. The present invention realizes the quality monitoring of the whole process by collecting and analyzing data in the processing, assembly and testing links during the production process of small fan components. In addition, quality monitoring is also realized through the quality prediction of the next link; at the same time, the deviation correction amount calculated in this link is fed back to the previous link to automatically correct the working parameters, and closed-loop monitoring and control are carried out on each link of the production of small fan components, improving the data analysis effect in the production process of small fan components, providing scientific support for improving the quality control effect of the production process, and thus ensuring the production quality of intelligent manufacturing products with small fan components as key accessories.

Description

Technical Field

[0001] The present invention relates to the technical field of production data analysis of fan components, and particularly to a dynamic analysis system for production data of fan components for intelligent manufacturing. Background Art

[0002] The key data in the production process of small fan components covers various types of data generated in steps such as component processing, assembly, and performance testing. The data in these links will directly or indirectly affect the production quality of fan components and then reflect their performance on fan products. For example, the processing technology in the processing data directly affects the dimensional accuracy and surface quality of fan components, affects the assembly accuracy, and then reflects to the running stability of fan products; for another example, the accuracy control in the processing data can ensure more precise fitting between components, reduce machine wear, and then reflects to the running balance of fan products. Therefore, it is necessary to perform efficient and high-quality analysis on the production data of small fan components.

[0003] In the prior art, the research on small fan components mainly focuses on the optimization design of their hardware, so that the fan products with them as accessories have better working quality, but there is a lack of targeted consideration and analysis of the production process of the fan components themselves. This may lead to inaccurate dimensions or imprecise fitting of the core components of the fan components, thereby affecting the quality of the fan components and resulting in the inability to meet the application requirements of subsequent products.

[0004] To improve the quality control effect in the production process of fan components, the present application proposes a dynamic analysis system for production data of fan components for intelligent manufacturing. Summary of the Invention

[0005] The purpose of the present invention is to provide a dynamic analysis system for production data of fan components for intelligent manufacturing. By collecting and analyzing data in the processing, assembly, and testing links in the production process of small fan components, full-process quality monitoring is realized. In addition, quality monitoring is also realized through quality prediction of the next link; at the same time, the deviation correction amount calculated in this link is fed back to the previous link to automatically correct the working parameters, and closed-loop monitoring and control are carried out on each link in the production of small fan components, improving the data analysis effect in the production process of small fan components, providing scientific support for improving the quality control effect in the production process, and thus ensuring the production quality of intelligent manufacturing products with small fan components as key accessories.

[0006] To achieve the above purpose, the present invention provides a dynamic analysis system for production data of fan components for intelligent manufacturing, including: a data acquisition module: used to collect production data in the production process of fan components, including processing data, assembly data, and performance test data;

[0007] Feature extraction module: extract machining features from machining data, extract assembly features from assembly data, and obtain performance features from performance test data; Data analysis module: obtain predicted assembly quality data based on machining features, judge machining anomalies according to the deviation between the predicted assembly quality data and the actual assembly quality data; obtain predicted performance quality data based on assembly features, judge assembly anomalies according to the deviation between the predicted performance quality data and the actual performance quality data; obtain quality data of the fan assembly based on performance features, and judge quality anomalies;

[0008] Feedback control module: analyze the regression coefficients to obtain the ranking of assembly influence features; calculate the correction amount of the machining data according to the ranking of the assembly influence features, and feedback the machining correction amount to the machining equipment to adjust the machining data; analyze the regression coefficients to obtain the ranking of performance influence features; calculate the correction amount of the assembly data according to the ranking of the performance influence features, and feedback the assembly correction amount to the assembly equipment to adjust the assembly data;

[0009] Quality monitoring module: trigger a quality warning when an anomaly occurs, and transmit the deviation, the corresponding working parameters, and the actual quality data to the terminal device.

[0010] Further, the steps for obtaining machining features include: extracting the deviation amount between the machining size and the required size of the part; calculating the surface roughness of the part; recording the deviation amount and the surface roughness as machining precision features; obtaining the cutting force fluctuation, vibration signal, and temperature change during the machining process, and recording them as machining dynamic features;

[0011] Integrate the machining precision features and the machining dynamic features into machining features.

[0012] Further, the steps for obtaining assembly features include: extracting the mating force and assembly error of the part, and recording them as assembly precision features; extracting the peak force and force fluctuation of the assembly force during the assembly process, and recording them as assembly force features; extracting statistical features from the assembly time of the part, and recording them as assembly time features; integrating the assembly precision features, the assembly force features, and the assembly time features into machining features.

[0013] Further, performance features are used to obtain the quality data of the fan assembly; the specific steps include: analyzing the vibration spectrum and noise level of the fan assembly, and extracting vibration and noise features; testing the operating conditions of the fan assembly under different loads, and extracting the load change and the power consumption under different loads, and recording them as load test features;

[0014] Integrate the vibration and noise features and the load test features into performance features, and obtain the quality data of the fan assembly according to the performance features; judge the quality anomaly of the fan assembly through the deviation between the quality data and the quality requirements.

[0015] Further, the processing features, assembly features, and performance features are respectively input into the prediction regression model to obtain predicted assembly quality data, predicted performance quality data, and quality data; the prediction regression model is constructed based on the correlation analysis of historical production data and historical actual quality data.

[0016] Further, the steps for judging processing anomalies include: By calculating the deviation between the predicted assembly quality data and the actual assembly quality data ; when is greater than the threshold , output a processing anomaly.

[0017] Further, the steps for judging assembly anomalies include: By calculating the deviation between the predicted performance quality data and the actual performance quality data ; when is greater than the threshold , output an assembly anomaly.

[0018] Further, the steps for adjusting the processing data according to the processing correction amount include: The sorting of assembly influence features is expressed as , where is the th assembly influence feature value, is the number of assembly influence features; the sorting of assembly influence features is in descending order;

[0019] The calculation formula for the processing correction amount is:

[0020] ;

[0021] where is the weight of the th assembly influence feature, set according to the sorting of assembly influence features; is a non-linear transformation function, is the processing adjustment coefficient, is the correction offset;

[0022] Adjust the processing data according to the processing correction amount .

[0023] Further, the steps for adjusting the assembly data according to the assembly correction amount include: The sorting of assembly influence features is expressed as , where is the th performance influence feature value, is the number of performance - influencing features; the performance - influencing features are sorted in descending order; the assembly correction amount The calculation formula is:

[0024] ;

[0025] where, is the weight of the th performance - influencing feature, is the assembly adjustment coefficient, is the logarithmic function. Adjust the assembly data according to the assembly correction amount .

[0026] Furthermore, continuously monitor the data analysis module, and trigger a quality warning when machining anomalies, assembly anomalies, and quality anomalies occur; output the anomaly category, corresponding deviation, working parameters, and actual quality data, and transmit them to the terminal device.

[0027] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0028] 1. The present invention realizes the full - process monitoring of the production process of small - scale fan components through the data acquisition module, covering three key links: machining, assembly, and performance testing. By collecting various production data, including machining accuracy, assembly accuracy, vibration, and noise data, and combining the analysis of the feature extraction module, the key features extracted are used as the data basis for subsequent anomaly judgment, enabling an accurate and comprehensive understanding of the production status of each production link. This full - process monitoring can keep the quality of small - scale fan components in dynamic control at each production link, providing auxiliary decision - making support for the improvement of the production quality of small - scale fan components.

[0029] 2. The present invention mines and analyzes the correlation relationship between historical production data and historical quality data through the prediction regression model, and predicts the quality data of the next link based on this correlation relationship. Then, according to the deviation between the predicted quality and the actual quality / required quality, it can identify possible quality anomaly problems in advance and provide accurate quality warnings. If an anomaly occurs in the machining link, it can be identified and warned in the assembly link, avoiding the transfer of quality defects to downstream links. It can also find out the influencing factors that may cause the anomaly according to the situation of the anomaly occurrence.

[0030] 3. Based on the regression coefficients in the prediction regression model, when a quality anomaly is detected, the present invention calculates the corresponding correction amount and feeds it back to the previous step. When a current machining anomaly is detected based on the deviation between the predicted assembly quality and the actual assembly quality, the present invention, through the feedback control module, ranks the machining features that cause the assembly deviation according to the regression coefficients, then calculates the correction amount for each machining feature based on this ranking, and feeds this correction amount back to the machining equipment for adjustment of the machining data. The processing method for assembly anomalies is the same. The closed-loop control mechanism of the present invention ensures that each link in the production process can be adjusted in a timely manner according to the actual situation, avoids the accumulation and transmission of deviations, optimizes the quality control of the entire production process, and thus guarantees the quality of subsequent intelligent manufacturing fan products. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 is a schematic diagram of the working process of the dynamic analysis system for the production data of small fan components;

[0032] Figure 2 is a structural diagram of the dynamic analysis of the production data of fan components;

[0033] Figure 3 is a data flow diagram of machining data;

[0034] Figure 4 is a data flow diagram of assembly data. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0036] An intelligent fan component production enterprise A introduces a dynamic analysis system for the production data of fan components for intelligent manufacturing to control the quality of the production process of small fan components in order to improve the overall production quality and optimize the production efficiency of small fan components. The system working flow chart is shown in Figure 1 given Figure 1 as a schematic diagram of the working process of the dynamic analysis system for the production data of small fan components. The following will describe the specific implementation of the dynamic analysis system for the production data of fan components through Embodiment 1 and Embodiment 2.

[0037] Embodiment 1

[0038] In this embodiment, the key steps in the production of the fan assembly are the processing stage, the assembly stage, and the performance testing stage; the production data during the production process of the fan assembly is collected through the data acquisition module, including processing data, assembly data, and performance testing data. Processing data refers to the information related to processing quality during the processing of the small fan assembly, assembly data refers to the information related to assembly quality during the assembly of the small fan assembly, and performance testing data refers to the information that can reflect the actual operating state of the fan during the performance testing stage. Some examples of the production data are given in Table 1.

[0039] Table 1 Some examples of production data

[0040]

[0041] It should be noted that the data listed in Table 1 is not all the data on which the subsequent data processing and analysis in this embodiment are based, and all the data in the production process of the small fan assembly can be used as the basis for the subsequent processing and analysis in this embodiment. The collection of each type of production data in Table 1 can be achieved through a variety of mature existing technologies (such as sensors), which will not be elaborated in this embodiment.

[0042] Refer to Figure 2 , Figure 2 which is the dynamic analysis structure diagram of the production data of the fan assembly provided for this embodiment.

[0043] Furthermore, refer to Figure 3 and Figure 4 , Figure 3 and Figure 4 which are the processing data flow diagram and the assembly data flow diagram provided for this embodiment respectively.

[0044] In this embodiment, the feature extraction module is used to extract processing features from the processing data, extract assembly features from the assembly data, and obtain performance features from the performance testing data. Specifically:

[0045] Measure the deviation between the actual processing size and the required size of the component; scan the surface of the component, and calculate the surface roughness of the component according to the integral formula where, is the surface roughness; is the measured length, is the surface height of the component, and both the measured length and the surface height are obtained by scanning.

[0046] Record the deviation and the surface roughness as the processing precision features.

[0047] Obtain the cutting force fluctuation, vibration signal, and temperature change during the processing, and record them as the processing dynamic features; the specific steps include: continuously monitor the change of the cutting force over time during the processing to obtain the cutting force fluctuation; then The cutting force fluctuation at a moment is:

[0048] ;

[0049] wherein, is the cutting force fluctuation at a moment, is the average cutting force of the monitoring time, is the cutting force at a moment.

[0050] Continuously monitor the vibration signal of the processing equipment to obtain the vibration spectrum; monitor the temperature changes of the processing equipment and components; record the cutting force fluctuation, vibration spectrum and temperature change as the processing dynamic characteristics;

[0051] Integrate the processing precision characteristics and processing dynamic characteristics into a processing feature matrix. Table 2 gives some examples of the processing feature data of multiple fan components during the processing process.

[0052] Table 2 Some examples of processing feature data

[0053]

[0054] In this embodiment, the processing features in the processing process of the fan component are obtained through the feature extraction module, including the processing precision and other fluctuation data generated with time change, which can provide accurate key data for the quality analysis and process optimization in the subsequent links and reduce the complexity of the subsequent data processing. The processing precision characteristics and processing dynamic characteristics extract the key quality parameters in the processing process of the fan component, providing a reliable basis for quality monitoring and abnormal discrimination.

[0055] Measure the mating force between parts during the assembly process of the components; calculate the assembly error according to the actual measured assembly value and the target value, and record the mating force and assembly error as the assembly precision characteristics; continuously monitor the assembly force during the assembly process, calculate the force peak value and force fluctuation, and record them as the assembly force characteristics; the acquisition method of the force peak value is expressed as , wherein is the force peak value, is the maximum value operation, is the moment of the assembly force.

[0056] Extract statistical features from the assembly time of the components and record them as the assembly time characteristics; the specific steps include: by recording the assembly time, calculating the average assembly time, the longest assembly time and the shortest assembly time; integrating the assembly precision characteristics, assembly force characteristics and assembly time characteristics into an assembly feature matrix. Table 3 gives some examples of the assembly feature data of multiple fan components during the assembly process.

[0057] Table 3 Example of Assembly Feature Sign Data Part

[0058]

[0059] The assembly features obtained in this embodiment can comprehensively and accurately monitor the assembly process of the fan components. The mating force and assembly error reflect the accuracy of the assembly process, the peak value and fluctuation of the assembly force reflect the mechanical stability during the assembly process, and the assembly time feature can reflect the assembly efficiency; these assembly features provide key data support for subsequent quality prediction and production optimization.

[0060] Monitor the vibration spectrum and noise level when the fan component is running, and extract the vibration and noise features. Test the operation of the fan component under different loads, and extract the load change and power consumption under different loads, which are recorded as load test features;

[0061] Integrate the vibration and noise features and the load test features into the performance feature matrix. Table 4 gives an example of the performance feature data part during the performance test of multiple fan groups.

[0062] Table 4 Example of Performance Feature Data Part

[0063]

[0064] Obtain the quality data of the fan component by using the weighted formula for the vibration and noise features and the load test features; the weighted formula is:

[0065] ;

[0066] where is the quality data, is the vibration and noise feature, is the load test feature; and are the weights of the noise and vibration feature and the load test feature respectively, which are set by those skilled in the art according to actual needs.

[0067] Judge the quality abnormality of the fan component through the deviation between the quality data and the quality requirement. The deviation between the quality data and the quality requirement is the difference between the two; when the absolute value of the difference is greater than the set threshold , it is determined that the current fan component has a quality abnormality; it is expressed as:

[0068] ;

[0069] where is the result of the quality abnormality determination. If there is a quality abnormality, then ; otherwise, 。

[0070] In this embodiment, the performance of the fan assembly in the performance test stage is grasped from the perspectives of vibration, noise, load, and power consumption. These performances can reflect the quality presentation of the fan assembly applied to actual production. These performance characteristics provide real-time feedback on the quality of the fan assembly and can also be used as a basis for judging whether the quality is abnormal. By judging the deviation between the performance characteristics and the quality requirements, the quality abnormality of the fan assembly can be identified in a timely manner, providing a real-time decision-making reference for the management party.

[0071] Furthermore, in this embodiment, a data analysis module is used to obtain predicted assembly quality data according to the processing characteristics, and judge the processing abnormality according to the deviation between the predicted assembly quality data and the actual assembly quality data; obtain predicted performance quality data according to the assembly characteristics, and judge the assembly abnormality according to the deviation between the predicted performance quality data and the actual performance quality data. Specifically:

[0072] The processing characteristics and the assembly characteristics are respectively input into a prediction regression model to obtain the predicted assembly quality data and the predicted performance quality data respectively; the prediction regression model is constructed based on the correlation analysis of historical production data and historical actual quality data.

[0073] The training steps of the prediction regression model are as follows: the historical production data and the historical actual quality results are cleaned and then normalized; the normalization method adopted in this embodiment is the Min-Max normalization method. A linear relationship between the historical processing characteristics in the historical production data and the historical assembly quality, and between the historical assembly characteristics and the historical performance quality is established through a linear regression model. The model of the linear regression is expressed as:

[0074] ;

[0075] where is the predicted assembly quality data, is the predicted performance quality data; and are respectively the th historical processing characteristic and its corresponding weight coefficient, and are respectively the th historical assembly characteristic and its corresponding weight coefficient; and are respectively the numbers of the historical processing characteristics and the historical assembly characteristics, and are respectively the biases of the predicted assembly quality data and the predicted performance quality data.

[0076] In this embodiment, the established linear regression model is iteratively optimized by the mean square error.

[0077] In this embodiment, the correlation between historical production data and historical quality data is obtained through a predictive regression method to construct a predictive regression model; the assembly quality and performance quality of the fan component are predicted from the processing features and assembly features, which can improve the predictive ability during the production process of the fan component and provide data for the feedback optimization of subsequent working parameters.

[0078] The steps for judging processing anomalies include: by calculating the deviation between the predicted assembly quality data and the actual assembly quality data ; when is greater than the threshold output processing anomalies.

[0079] The steps for judging assembly anomalies include: by calculating the deviation between the predicted performance quality data and the actual performance quality data ; when is greater than the threshold output assembly anomalies.

[0080] In this embodiment, the threshold and the threshold are respectively set to 0.030 and 0.050; Table 5 gives some examples of judging processing anomalies and assembly anomalies;

[0081] Table 5 Examples of Judging Processing Anomalies and Assembly Anomalies

[0082]

[0083] In this embodiment, it is judged whether there are anomalies in the current processing process by calculating the deviation between the predicted assembly quality and the actual assembly quality; if there are anomalies in the processing process, it will affect the accuracy of the subsequent assembly combination. For example, if there are anomalies in the processing dimensions, the components cannot be closely combined during the assembly process; if the processing temperature is too high or too low, problems such as assembly expansion and contraction will occur. This step is beneficial to improving the accuracy during the processing of small fan components and reducing quality problems caused by processing errors.

[0084] In this embodiment, it is judged whether there are anomalies in the current assembly process by calculating the deviation between the predicted performance quality and the actual performance; if there are anomalies in the assembly process, it will affect the operating performance of the subsequent fan component. For example, inaccurate assembly or uneven assembly force may cause misalignment between the components of the fan component. This step is beneficial to ensuring that the assembly of the fan component can meet the expected performance standards and preventing the final quality of the product from being affected by assembly anomalies. ​​

[0085] Further, in this embodiment, a feedback control module is used to analyze the regression coefficients to obtain the sorting of assembly influence features; the correction amount of the processing data is calculated according to the sorting of the assembly influence features, and the processing correction amount is fed back to the processing equipment to adjust the processing data;

[0086] Analyze the regression coefficients to obtain the sorting of performance influence features; calculate the correction amount of the assembly data according to the sorting of the performance influence features, and feed back the assembly correction amount to the assembly equipment to adjust the assembly data. Specifically:

[0087] According to the and calculated in the linear regression model in the previous step, sort them in descending order to obtain the sorting of assembly influence features and performance influence features respectively, and discard the influence features with weight coefficients lower than the sensitive value.

[0088] The step of adjusting the processing data according to the processing correction amount includes: the sorting of the assembly influence features is expressed as where is the th assembly influence feature value, is the number of assembly influence features; the sorting of the assembly influence features is in descending order; the processing correction amount is calculated by the formula:

[0089] ;

[0090] where is the weight of the th assembly influence feature, set according to the sorting of the assembly influence features; is a non-linear transformation function, is a processing adjustment coefficient, is a correction offset;

[0091] Adjust the processing data according to the processing correction amount .

[0092] The step of adjusting the assembly data according to the assembly correction amount includes: the sorting of the assembly influence features is expressed as

[0093] where is the th performance influence feature value, is the number of performance influence features; the sorting of the performance influence features is in descending order; the assembly correction amount is calculated by the formula:

[0094] ;

[0095] Among them, is the weight of the th performance - influencing feature, is the assembly adjustment coefficient, is the logarithmic function.

[0096] Adjust the assembly data according to the said assembly correction amount Adjust the said assembly data.

[0097] In this embodiment, for the production process of the fan components of this batch of enterprise A intelligent fan components, some examples of the machining correction amount and the assembly correction amount are given in Table 6.

[0098] Table 6 Some examples of machining correction amount

[0099]

[0100] It should be noted that this embodiment takes the machining parameters and the assembly parameters as calculation examples of the machining correction amount and the assembly correction amount, and only some examples of the machining parameters and the assembly parameters are given in Table 6. Based on the understanding of this application by those skilled in the art, other machining data and assembly data can all calculate the correction amount through the above - mentioned method and simple deformations of the above - mentioned method.

[0101] By ranking the features affecting the assembly quality in this embodiment, it is possible to preferentially adjust the machining data or steps that have a greater impact on the assembly quality, timely and accurately adjust the machining process, and ensure the accuracy and stability of the machining process. The machining correction amount calculated based on the non - linear relationship between the machining data and the assembly quality accurately reflects, from a local perspective, the degree to which the machining data needs to be adjusted under the current actual assembly situation, improving the accuracy and flexibility of the quality monitoring of the machining process.

[0102] By ranking the features affecting the performance quality in this embodiment, it is possible to preferentially adjust the assembly data or steps that have a greater impact on the performance quality, timely compensate and correct the defects in the feedback assembly process, improve the accuracy of the fan component assembly, and thus ensure the stability of the subsequent product quality. Through non - linear changes and logarithmic functions, adaptive adjustments are made to different performance - related assembly data from the perspective of global quality, reducing the errors in the assembly process.

[0103] Furthermore, in this embodiment, the quality monitoring module triggers a quality warning when an abnormality occurs, and transmits the deviation, the corresponding working parameters, and the actual quality data to the terminal device. Specifically:

[0104] Continuously monitor the data analysis module, trigger a quality warning when the machining abnormality, the assembly abnormality, and the quality abnormality occur; output the abnormality category, the corresponding deviation, the working parameters, and the actual quality data, and transmit them to the terminal device.

[0105] In this embodiment, through the quality monitoring module, it is possible to continuously monitor and promptly detect abnormalities in all links of the small fan assembly during processing, assembly, and performance testing. Once an abnormality is detected, an alarm is triggered and the abnormality category, deviation, working parameters, and actual quality data are output, presented to the relevant staff as a decision-making reference, providing support for the quality control of the small fan assembly during the production process.

[0106] Embodiment Two

[0107] This embodiment will explain the influence of processing data on assembly quality and the influence of assembly data on performance quality based on the production links of the small fan assembly; the main data explanations are given below.

[0108] Analysis of the influence of processing data on assembly quality;

[0109] Processing dimension error: Affects the fitting tightness and assembly stability, determines whether the fan assembly meets the design tightness requirements after assembly, and improper fitting may cause component looseness or abnormal biting during equipment operation;

[0110] Surface roughness: Has a direct impact on the friction coefficient and wear resistance of the contact surface. Larger surface roughness may increase the fitting resistance or reduce the tight effect;

[0111] Shaft-hole coaxiality: Affects the concentricity of rotating components. Excessive deviation may cause excessive vibration amplitude after assembly.

[0112] Analysis of the influence of assembly data on performance quality;

[0113] Assembly force: Affects the sealing performance and load transfer capacity of contact components. Too small assembly force may cause the fan assembly to loosen, while too large may cause irreversible permanent deformation or contact stress concentration;

[0114] Assembly clearance: Determines the friction coefficient and sliding resistance of relative movement of components. Too large a clearance may cause vibration and noise to exceed reasonable standards, while too small may cause jamming or friction overheating;

[0115] Torque uniformity: Uneven torque will cause speed fluctuations and reduce the running smoothness of the transmission device in the fan assembly;

[0116] Assembly angle: The influence on the assembly angle of components is directly related to the alignment and cooperation efficiency between fan assemblies.

[0117] In view of the problem that the prior art ignores data analysis in the production process of small fan components, the present application proposes a dynamic analysis system for fan component production data oriented to intelligent manufacturing, aiming to improve the quality control effect in the production process of fan components. The present application first collects and analyzes data in the processing, assembly, and testing links of the production process of small fan components to achieve quality monitoring of the entire process. In addition, quality monitoring is also achieved through quality prediction of the next link; at the same time, the deviation correction amount calculated in this link is fed back to the previous link to automatically correct the working parameters, and closed-loop monitoring and control are carried out on each link of the small fan components, improving the data analysis effect in the production process of small fan components, providing scientific support for improving the quality control effect in the production process, and thus ensuring the production quality of intelligent manufacturing products with small fan components as key accessories.

[0118] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A dynamic analysis system for fan component production data in the context of intelligent manufacturing, characterized in that Including: A data acquisition module: used to acquire production data during the production process of the fan component, including machining data, assembly data, and performance test data; A feature extraction module: extracting machining features from the machining data, assembly features from the assembly data, and performance features from the performance test data; A data analysis module: obtaining predicted assembly quality data based on the machining features, and judging machining anomalies according to the deviation between the predicted assembly quality data and the actual assembly quality data; Obtaining predicted performance quality data based on the assembly features, and judging assembly anomalies according to the deviation between the predicted performance quality data and the actual performance quality data; Obtaining the quality data of the fan component based on the performance features, and judging quality anomalies; A feedback control module: analyzing the regression coefficients to obtain the ranking of assembly influence features; Calculating the correction amount of the machining data according to the ranking of the assembly influence features, and feeding back the machining correction amount to the machining equipment to adjust the machining data; Analyzing the regression coefficients to obtain the ranking of performance influence features; Calculating the correction amount of the assembly data according to the ranking of the performance influence features, and feeding back the assembly correction amount to the assembly equipment to adjust the assembly data; A quality monitoring module: triggering a quality warning when machining anomalies, assembly anomalies, and quality anomalies occur, and transmitting the anomaly-related data to the terminal device; Processing correction amount The calculation formula is as follows: ； Among them, is the weight of the th assembly influence feature, which is set according to the sorting of assembly influence features; is a non - linear transformation function, is the processing adjustment coefficient, is the correction offset; According to the machining correction amount Adjust the machining data. The specific steps include: The assembly influence feature sorting is expressed as , where is the th assembly influence feature value is the number of assembly influence features is the sorting function; The assembly influence feature sorting is in descending order.

2. The dynamic analysis system for production data of a fan assembly for intelligent manufacturing according to claim 1, wherein, The steps for obtaining the machining features include: Extracting the deviation amount between the machining size of the component and the required size; calculating the surface roughness of the component; recording the deviation amount and the surface roughness as machining accuracy features; obtaining the cutting force fluctuation, vibration signal, and temperature change during the machining process, and recording them as machining dynamic features; Integrating the machining accuracy features and the machining dynamic features into the machining features.

3. The dynamic analysis system for production data of a fan component for intelligent manufacturing according to claim 1, wherein The steps for obtaining the assembly features include: Extracting the mating force and assembly error of the component, and recording them as assembly accuracy features; extracting the assembly force during the assembly process to calculate the force peak value and force fluctuation, and recording them as assembly force features; extracting statistical features from the assembly time of the component, and recording them as assembly time features; integrating the assembly accuracy features, the assembly force features, and the assembly time features into the assembly features.

4. The dynamic analysis system for the production data of a fan component for intelligent manufacturing according to claim 1, wherein The performance features are used to obtain the quality data of the fan component; the specific steps include: Analyzing the vibration spectrum and noise level of the fan component, and extracting vibration and noise features; testing the operating conditions of the fan component under different loads, and extracting the load change and power consumption under different loads, and recording them as load test features; Integrating the vibration and noise features and the load test features into the performance features, and obtaining the quality data of the fan component according to the performance features; judging the quality anomaly of the fan component through the deviation between the quality data and the quality requirements.

5. The dynamic analysis system for production data of a fan component for intelligent manufacturing according to claim 1, characterized in that, Inputting the machining features and the assembly features into the prediction regression model respectively to obtain the predicted assembly quality data and the predicted performance quality data; the prediction regression model is constructed based on the correlation analysis of historical production data and historical actual quality data.

6. The dynamic analysis system for production data of a fan component for intelligent manufacturing according to claim 1, characterized in that, The steps for judging the machining anomaly include: By calculating the predicted assembly quality data and the actual assembly quality data to obtain the deviation ; when it is greater than the threshold output a machining anomaly 7. A dynamic analysis system for the production data of a fan component for intelligent manufacturing according to claim 1, characterized in that, The steps for judging the assembly anomaly include: By calculating the deviation between the predicted performance quality data and the actual performance quality data ; when is greater than a threshold output an assembly anomaly .

8. The dynamic analysis system for production data of a fan component for intelligent manufacturing according to claim 1, characterized in that The steps for adjusting the assembly data according to the assembly correction amount include: The sorting of the assembly influence features is expressed as , where is the th performance influence feature value, is the number of performance influence features; the sorting of the performance influence features is in descending order; The assembly correction amount The calculation formula is as follows: ； Among them, is the weight of the th performance influence feature, is the assembly adjustment coefficient, is the logarithmic function; According to the assembly correction amount Adjust the assembly data.

9. The dynamic analysis system for production data of a fan component for intelligent manufacturing according to claim 1, wherein Continuously monitor the data analysis module, trigger a quality warning when the processing anomaly, the assembly anomaly, and the quality anomaly occur; output the anomaly category, the corresponding deviation, the working parameters, and the actual quality data, and transmit them to the terminal device.

Images