An enameled wire paint film online detection device and detection system

Abstract

The present invention relates to an online detection device and detection system for paint film of enameled wire, and relates to the field of paint film detection, including: a parameter receiving unit, used for receiving paint film generation monitoring control parameters and paint film generation expected control parameters; an abnormality prediction unit, used for performing abnormality probability prediction and obtaining paint film abnormality probability; an abnormality identification unit, used for identifying suspected abnormal enameled wires; a contact detection unit, used for performing contact detection and obtaining a first quality detection result; a normal identification unit, used for performing paint film-free abnormal identification and obtaining a second quality detection result; a result feedback unit, used for feeding back the quality detection result to a client. The present application solves the technical problems of low detection efficiency and low abnormal product detection rate in the existing enameled wire paint film quality detection, and pre-screens products with suspected quality problems through virtual detection, and then performs contact detection on the suspected abnormal products, thereby achieving the technical effect of improving the abnormal product detection rate and detection efficiency.

Description

Technical Field

[0001] The present invention relates to the field of paint film detection, and in particular to an enameled wire paint film online detection device and a detection system. Background Art

[0002] Enameled wire is an insulated wire commonly used in electrical equipment such as motors and transformers, and its paint film directly affects the performance and reliability of electrical equipment. Therefore, it is crucial to effectively detect the paint film of the enameled wire. At present, the paint film detection of enameled wire mainly adopts methods such as manual detection or automatic optical detection. Manual detection relies on the experience and skills of the operator, has low detection efficiency, and is easily affected by subjective factors, resulting in unstable detection results. Although automatic optical detection can improve the detection efficiency, it is difficult to accurately judge the actual quality problems of the paint film by relying solely on optical image information, and the detection rate of abnormal products is not high. In addition, the existing enameled wire paint film detection usually adopts a contact detection system, which requires the detection equipment to be in direct contact with the enameled wire. Although this method can obtain relatively accurate detection results, the detection efficiency is limited and it is not suitable for online detection needs in mass production environments. Summary of the invention

[0003] The present invention aims to solve the technical problems of low detection efficiency and low abnormal product detection rate in the existing enameled wire paint film quality detection, and provides an enameled wire paint film online detection device and a detection system.

[0004] The technical solution of the present invention to solve the above technical problems is as follows:

[0005] In a first aspect, the present invention provides an online detection device for paint film of an enameled wire, comprising: a parameter receiving unit, used to receive paint film generation monitoring control parameters and paint film generation expected control parameters of the enameled wire to be inspected; an abnormality prediction unit, used to predict the abnormal probability of the paint film generation monitoring control parameters and the paint film generation expected control parameters through a primary detection network, and obtain the paint film abnormality probability; an abnormality identification unit, used to identify the enameled wire to be inspected as a suspected abnormal enameled wire when the paint film abnormality probability is greater than or equal to the paint film abnormality probability threshold; a contact detection unit, used to perform contact detection on the enameled wire to be inspected with the suspected abnormal enameled wire identification through a secondary detection device, and obtain a first quality detection result; a normal identification unit, used to identify the enameled wire to be inspected as having no paint film abnormality when the paint film abnormality probability is less than the paint film abnormality probability threshold, and obtain a second quality detection result; a result feedback unit, used to feed back the first quality detection result or the second quality detection result to a client.

[0006] In a second aspect, the present invention provides an online detection system for paint film of enameled wire, and the execution steps include: receiving paint film generation monitoring control parameters and paint film generation expected control parameters of the enameled wire to be inspected; predicting the paint film generation monitoring control parameters and the paint film generation expected control parameters through a primary detection network to obtain a paint film abnormality probability; when the paint film abnormality probability is greater than or equal to a paint film abnormality probability threshold, marking the enameled wire to be inspected as a suspected abnormal enameled wire; through a secondary detection device, performing contact detection on the enameled wire to be inspected with the suspected abnormal enameled wire mark to obtain a first quality detection result; when the paint film abnormality probability is less than the paint film abnormality probability threshold, marking the enameled wire to be inspected as having no paint film abnormality to obtain a second quality detection result; and feeding back the first quality detection result or the second quality detection result to the client.

[0007] In a third aspect, the present application provides an electronic device, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is used to execute an enameled wire paint film online detection device provided in the present application.

[0008] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, and the computer program is used to execute an enameled wire paint film online detection device provided by the present application.

[0009] The beneficial effects of the present invention are:

[0010] The parameter receiving unit receives the paint film generation monitoring control parameters and the paint film generation expected control parameters of the enameled wire to be inspected, providing the necessary data basis for subsequent abnormality prediction; the abnormality prediction unit uses the primary detection network to predict the abnormal probability of the paint film generation monitoring control parameters and the paint film generation expected control parameters, obtains the paint film abnormality probability, realizes the virtual detection of the paint film of the enameled wire, and improves the detection efficiency; the abnormal identification unit uses the abnormality identification unit to identify the enameled wire to be inspected as suspected abnormal enameled wire, provides a target for subsequent contact detection, and improves the detection rate of abnormal products; the contact detection unit uses the secondary detection The equipment performs contact detection on the enameled wire to be inspected with the suspected abnormal enameled wire mark to obtain the first quality detection result, and further performs contact detection on the suspected abnormal enameled wire marked by the virtual detection to obtain a more accurate quality detection result; through the normal identification unit, when the probability of paint film abnormality is less than the paint film abnormality probability threshold, the enameled wire to be inspected is marked as non-paint film abnormal to obtain the second quality detection result, and the enameled wire that is not marked as suspected abnormal by the virtual detection is directly judged as a qualified product to obtain the second quality detection result, thereby reducing unnecessary contact detection and improving detection efficiency; through the result feedback unit, the first quality detection result or the second quality detection result is fed back to the client. By combining virtual detection and contact detection, the detection efficiency of the enameled wire paint film quality is improved while the detection rate of abnormal products is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A schematic structural diagram of an online detection device for enameled wire paint film provided by the present invention;

[0012] Figure 2 A schematic flow chart of the execution steps of an online detection system for enameled wire paint film provided by the present invention;

[0013] Figure 3 A schematic diagram of the structure of an electronic device provided by the present invention;

[0014] Figure 4 A schematic diagram of the structure of a computer-readable storage medium provided by the present invention.

[0015] In the accompanying drawings, the components represented by the reference numerals are as follows:

[0016] Parameter receiving unit 11, abnormality prediction unit 12, abnormality identification unit 13, contact detection unit 14, normal identification unit 15, result feedback unit 16, electronic device 200, memory 210, processor 220, first computer program 211, computer readable storage medium 300, second computer program 311. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0018] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0019] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0020] Embodiment 1:

[0021] like Figure 1 As shown, an embodiment of the present invention provides an enameled wire paint film online detection device, comprising:

[0022] The parameter receiving unit 11 is used to receive the paint film generation monitoring control parameters and the paint film generation expected control parameters of the enameled wire to be inspected.

[0023] Specifically, the specific function of the parameter receiving unit 11 is to receive two types of key parameter data, namely, the paint film generation monitoring control parameters and the paint film generation expected control parameters of the enameled wire to be inspected.

[0024] The paint film generation monitoring and control parameters refer to a series of parameters closely related to the paint film quality that are collected in real time by various sensors installed on the enameled wire production equipment during the actual production process, such as the real-time rotation speed of the paint conveying roller, the actual temperature distribution of the paint film evaporation area, the actual temperature distribution of the paint film curing area, the actual conveying speed of the enameled wire, etc. These monitoring data reflect the dynamic changes of the equipment operation status and process parameters during the paint film generation process.

[0025] The expected control parameters for paint film formation refer to a series of target control parameters that are pre-set according to the technical requirements and process specifications of the product, including the target rotation speed of the paint roller, the target temperature distribution of the paint film evaporation area, the target temperature distribution of the paint film curing area, the target conveying speed of the enameled wire, etc. These expected data represent the process control standards under normal production conditions.

[0026] During the enameled wire paint film detection process, the parameter receiving unit 11 communicates with the sensor array deployed on the enameled wire production equipment and the paint film generation control terminal to receive and collect the above two types of data, providing a basis for subsequent prediction and analysis of the enameled wire paint film.

[0027] The abnormality prediction unit 12 is used to predict the abnormality probability of the paint film generation monitoring control parameters and the paint film generation expected control parameters through the primary detection network to obtain the paint film abnormality probability.

[0028] Specifically, the core function of the abnormality prediction unit 12 is to use the pre-trained primary detection network model to analyze and process the paint film generation monitoring control parameters and the paint film generation expected control parameters collected by the parameter receiving unit 11, and predict the probability of quality abnormalities in the current enameled wire paint film, thereby deriving a quantified paint film abnormality probability.

[0029] First, the abnormal prediction unit 12 compares the paint film generation monitoring control parameters collected by the parameter receiving unit 11 with the corresponding paint film generation expected control parameters one by one, calculates the degree of deviation between the actual value and the expected value of each parameter, and obtains a series of deviation coefficients, such as the paint roller speed deviation coefficient, the evaporation temperature deviation coefficient, the curing temperature deviation coefficient, the enameled wire conveying speed deviation coefficient, etc. Then, the abnormal prediction unit 12 combines the various deviation coefficients in a preset matrix form to construct a paint film generation control deviation matrix as the input of the primary detection network model. The primary detection network model is an intelligent analysis model based on a machine learning algorithm. Through learning and training a large amount of historical data, it can automatically extract key features from the paint film generation control deviation matrix and capture the inherent laws and correlations of paint film quality abnormalities. The abnormal prediction unit 12 inputs the constructed paint film generation control deviation matrix into the primary detection network model, and the primary detection network model outputs a decimal value between 0 and 1, which represents the probability of quality abnormality of the current enameled wire paint film, that is, the paint film abnormality probability. Among them, the closer the paint film abnormality probability is to 1, the greater the possibility that the paint film quality is abnormal; conversely, the closer the paint film abnormality probability is to 0, the greater the possibility that the paint film quality is normal.

[0030] The abnormal prediction unit 12 continuously receives the monitoring data and expected data from the parameter receiving unit 11 in real time, and performs dynamic prediction and evaluation through the primary detection network model to realize virtual online abnormal detection of the paint film of the enameled wire. Compared with the traditional offline sampling or online contact detection system, by analyzing the production parameter deviation of each enameled wire in real time, the quality abnormality risk of each section of enameled wire can be continuously evaluated, covering the entire production line, improving the detection rate of abnormal paint film, and reducing quality risks; at the same time, virtual detection does not require actual contact detection of each enameled wire, which greatly improves the detection efficiency and saves time and cost. In addition, by continuously monitoring the changing trend of the probability of paint film abnormality, abnormal fluctuations can be discovered in the first time, the paint film quality risk can be quickly judged, and production parameters can be adjusted or maintenance operations can be carried out in time, thereby effectively reducing the probability of quality accidents.

[0031] The abnormality identification unit 13 is used to identify the enameled wire to be inspected as a suspected abnormal enameled wire when the paint film abnormality probability is greater than or equal to the paint film abnormality probability threshold.

[0032] Specifically, the main function of the abnormality identification unit 13 is to judge the quality status of each enameled wire to be inspected according to the paint film abnormality probability output by the abnormality prediction unit 12, and to specifically identify the enameled wire suspected of having paint film quality abnormalities for subsequent further contact detection.

[0033] First, the abnormal identification unit 13 receives the paint film abnormal probability calculated in real time by the abnormal prediction unit 12, and compares it with the preset paint film abnormal probability threshold. When the paint film abnormal probability of a certain enameled wire to be inspected is greater than or equal to the threshold, the abnormal identification unit 13 determines that the paint film of the enameled wire has an abnormal risk and needs further inspection and confirmation. At this time, the abnormal identification unit 13 automatically adds a special mark to the enameled wire to identify the suspected abnormal enameled wire. For example, the words "suspected abnormal" are noted in its production information, or a specific color mark is added to its appearance. The suspected abnormal enameled wire identification can effectively distinguish the enameled wire with higher quality risk from the normal enameled wire, which is convenient for subsequent contact detection. Among them, the paint film abnormal probability threshold is comprehensively determined based on factors such as the quality requirements of the enameled wire products, historical production data, and actual production experience. At the same time, the abnormal identification unit 13 supports setting different abnormal probability thresholds for enameled wires of different models and specifications to adapt to the differences in quality characteristics of different enameled wires.

[0034] Through the automatic judgment and identification function of the abnormal identification unit 13, potential quality abnormality risks in the enameled wire production process can be discovered and warned in a timely manner, which not only helps to strengthen quality supervision and prevent quality accidents, but also provides strong support for improving production efficiency and saving quality inspection resources. Through the identification of suspected abnormal enameled wires, high-risk products can be quickly located, and resources can be concentrated to carry out targeted contact detection without the need to conduct a comprehensive inspection of each enameled wire, thereby improving the accuracy and efficiency of quality control.

[0035] The contact detection unit 14 is used to perform contact detection on the enameled wire to be inspected having the suspected abnormal enameled wire mark through a secondary detection device to obtain a first quality detection result.

[0036] Specifically, the main function of the contact detection unit 14 is to use a special secondary detection device to perform actual contact detection on the enameled wire marked as suspected abnormal by the abnormality identification unit 13 to obtain a more detailed and accurate quality detection result, namely the first quality detection result.

[0037] The contact detection unit 14 is equipped with secondary detection equipment that matches the enameled wire production line, such as a corona detector, a paint film optical detector, a paint film thickness gauge, etc. These devices directly contact the surface of the enameled wire to accurately measure and evaluate the paint film from different angles and dimensions. When the abnormal identification unit 13 identifies a certain enameled wire as suspected abnormal, the contact detection unit 14 guides the enameled wire to the secondary detection equipment for detection. During the detection process of the secondary detection equipment, the contact detection unit 14 selects an appropriate detection system and parameters according to the specific model and detection requirements of the enameled wire. For example, using the corona detection method, by applying a high-voltage electric field on the surface of the enameled wire, it is detected whether there is a corona discharge phenomenon caused by the damage of the paint film insulation; using a paint film thickness gauge, the paint film thickness is measured at multiple positions along the circumference and axial direction of the enameled wire to evaluate the uniformity of the distribution of the paint film thickness, etc.

[0038] Through the contact detection of the secondary detection equipment, the contact detection unit 14 can obtain more quality information and data about the suspected abnormal enameled wire, such as the type, location, size, density, etc. of the defect, to form a comprehensive quality assessment result, that is, the first quality detection result. The first quality detection result can not only confirm whether the enameled wire really has quality abnormalities, but also provide important basis for abnormal cause analysis, process optimization, quality improvement, etc. Compared with the conventional full detection method, the hierarchical detection strategy of the contact detection unit 14 improves the detection rate while reducing the detection cost and time. By focusing on the suspected abnormal enameled wire, without affecting normal production, more in-depth and detailed quality inspections are carried out in a targeted manner, unqualified products are discovered and isolated in time, and quality problems are prevented from expanding. At the same time, compared with the primary detection, although the secondary detection adopts a contact method, since it only targets a small number of suspected abnormal products, the overall detection efficiency is still higher than the full detection, reducing unnecessary waste of resources.

[0039] The normal identification unit 15 is used to identify the enameled wire to be inspected as having no paint film abnormality when the paint film abnormality probability is less than the paint film abnormality probability threshold, so as to obtain a second quality inspection result.

[0040] Specifically, the main function of the normal identification unit 15 is to judge the quality status of each enameled wire to be inspected according to the paint film abnormality probability output by the abnormal prediction unit 12, and to specifically identify the enameled wires assessed to have normal paint film quality, thereby generating a second quality inspection result.

[0041] First, after receiving the paint film abnormality probability calculated in real time by the abnormality prediction unit 12 and comparing it with the preset paint film abnormality probability threshold, when the paint film abnormality probability of a certain enameled wire to be inspected is less than the threshold, it is determined that the paint film quality of the enameled wire meets the standard and there is no obvious abnormality risk. At this time, the normal identification unit 15 automatically adds a special mark to the enameled wire, such as indicating the words "paint film normal" in its production information, or adding a specific color mark on its appearance. By marking the paint film without abnormality, the enameled wire with stable and reliable paint film quality can be effectively distinguished from other enameled wires to form a second quality inspection result.

[0042] Through the identification function of the normal identification unit 15, products with normal quality in the enameled wire production process can be quickly identified and confirmed, which helps to improve the efficiency of quality inspection, reduce unnecessary waste of inspection resources, and also provides an important basis for subsequent product classification, packaging, delivery and other links. The second quality inspection result enables production management personnel to timely grasp the overall qualification rate and yield rate of product quality and optimize product inventory and delivery plans. At the same time, by comparing and analyzing the first quality inspection results and the second quality inspection results, the overall level and stability of the paint film can be evaluated, providing data support for quality improvement and optimization.

[0043] The result feedback unit 16 is configured to feed back the first quality detection result or the second quality detection result to the client.

[0044] Specifically, the main function of the result feedback unit 16 is to transmit and display the first quality detection result generated by the contact detection unit 14 and the second quality detection result generated by the normal identification unit 15 to the client in real time through a specific communication interface and data format, so as to realize the sharing and interaction of quality detection information.

[0045] First, the result feedback unit 16 is connected to the contact detection unit 14 and the normal identification unit 15 respectively, and receives the output quality inspection results in real time. For the first quality inspection result, the result feedback unit 16 extracts the key quality information of the suspected abnormal enameled wire, such as defect type, defect location, defect degree, etc., and packages this information into a structured data packet according to the preset data format and communication protocol. For the second quality inspection result, the result feedback unit 16 directly encapsulates the quality qualified information of the normal enameled wire. Subsequently, the result feedback unit 16 sends the encapsulated quality inspection result data to the client in real time through a wired or wireless communication interface. The client is a computer terminal or mobile device equipped with special software, such as a quality management workstation, a field monitoring platform, a mobile APP, etc. After receiving the data packet sent by the result feedback unit 16, the client automatically parses and processes the data and presents it to the user in a visual manner. For example, based on the first quality inspection result, the client intuitively displays the defect distribution and statistics of suspected abnormal enameled wires in the form of lists, charts, color marks, etc. on the interface; based on the second quality inspection result, the client calculates and displays key quality indicators such as the pass rate and yield rate of the current enameled wire production in real time.

[0046] Through the real-time feedback mechanism of the result feedback unit 16, quality management personnel can grasp the quality dynamics of enameled wire production anytime and anywhere, timely discover and warn quality anomalies, and quickly locate the causes of anomalies based on the detailed defect information fed back, and formulate corrective and preventive measures. Through the human-computer interactive quality feedback mode, the response speed and decision-making efficiency of quality management are improved, so that the production site can achieve early discovery, early processing, and early resolution of quality problems.

[0047] Furthermore, the embodiment of the present application also includes:

[0048] Communicate with the sensor array and receive the paint conveying roller speed monitoring value, evaporation longitudinal temperature monitoring curve, evaporation transverse temperature monitoring value, curing longitudinal temperature monitoring curve, curing transverse temperature monitoring value, and enameled wire conveying speed monitoring value of the enameled wire to be inspected;

[0049] Communicate with the paint film generation control end and receive the expected value of the paint conveying roller speed, the expected evaporation longitudinal temperature curve, the expected evaporation transverse temperature, the expected curing longitudinal temperature curve, the expected curing transverse temperature, and the expected value of the enameled wire conveying speed of the enameled wire to be inspected;

[0050] Add the paint roller speed monitoring value, the evaporation longitudinal temperature monitoring curve, the evaporation transverse temperature monitoring value, the curing longitudinal temperature monitoring curve, the curing transverse temperature monitoring value, and the enameled wire conveying speed monitoring value into the paint film generation monitoring control parameters;

[0051] The expected value of the paint roller rotation speed, the expected evaporation longitudinal temperature curve, the expected evaporation transverse temperature, the expected curing longitudinal temperature curve, the expected curing transverse temperature, and the expected value of the enameled wire conveying speed are added to the expected control parameters for paint film generation.

[0052] In a feasible implementation, first, the parameter receiving unit 11 establishes a communication connection with the sensor array installed on the enameled wire production equipment, and receives in real time the measured values ​​of a series of paint film generation process parameters monitored by the sensor array, including the paint roller speed monitoring value, the evaporation longitudinal temperature monitoring curve, the evaporation transverse temperature monitoring value, the curing longitudinal temperature monitoring curve, the curing transverse temperature monitoring value, the enameled wire conveying speed monitoring value, etc. Among them, the paint roller speed monitoring value reflects the actual speed of the paint roller; the evaporation longitudinal temperature monitoring curve and the evaporation transverse temperature monitoring value respectively reflect the actual temperature distribution of the paint film evaporation area along the enameled wire travel direction and the vertical travel direction; the curing longitudinal temperature monitoring curve and the curing transverse temperature monitoring value respectively reflect the actual temperature distribution of the paint film curing area along the enameled wire travel direction and the vertical travel direction; the enameled wire conveying speed monitoring value reflects the actual speed of the enameled wire passing through the production line. These monitoring values ​​comprehensively and truly record the actual process parameters of each link in the paint film generation process of the enameled wire to be inspected. Secondly, the parameter receiving unit 11 establishes a communication connection with the paint film generation control terminal, and receives in real time the expected values ​​of a series of paint film generation process parameters, including the expected value of the paint conveying roller speed, the expected curve of the longitudinal temperature of evaporation, the expected value of the transverse temperature of evaporation, the expected curve of the longitudinal temperature of curing, the expected value of the transverse temperature of curing, the expected value of the conveying speed of the enameled wire, etc. These expected values ​​are quantitative indicators of the key parameters of each link in the paint film generation process according to the product design requirements and process regulations, representing the best process state that should be achieved and maintained in the production process, and are an important basis for quality evaluation.

[0053] Subsequently, the parameter receiving unit 11 adds monitoring parameters such as the paint roller speed monitoring value, the evaporation longitudinal temperature monitoring curve, the evaporation transverse temperature monitoring value, the curing longitudinal temperature monitoring curve, the curing transverse temperature monitoring value, and the enameled wire conveying speed monitoring value into the paint film to generate monitoring control parameters; and adds expected parameters such as the paint roller speed expected value, the evaporation longitudinal temperature expected curve, the evaporation transverse temperature expected value, the curing longitudinal temperature expected curve, the curing transverse temperature expected value, and the enameled wire conveying speed expected value into the paint film to generate an expected control parameter data set. In this way, the parameter receiving unit 11 realizes the separate reception of monitoring parameters and expected parameters, which is convenient for subsequent correlation analysis.

[0054] Through real-time communication with the sensor array and the paint film generation control end, the monitoring parameters and expected parameters of the paint film generation process are accurately and comprehensively acquired, providing a complete data basis for online detection of paint films.

[0055] Furthermore, the embodiment of the present application also includes:

[0056] The paint roller speed monitoring value, the evaporation longitudinal temperature monitoring curve, the evaporation transverse temperature monitoring value, the solidification longitudinal temperature monitoring curve, the solidification transverse temperature monitoring value, and the enameled wire conveying speed monitoring value are compared with the paint roller speed expected value, the evaporation longitudinal temperature expected curve, the evaporation transverse temperature expected value, the solidification longitudinal temperature expected curve, the solidification transverse temperature expected value, and the enameled wire conveying speed expected value to obtain the paint roller speed deviation coefficient, the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the solidification longitudinal temperature deviation coefficient, the solidification transverse temperature deviation coefficient, and the enameled wire conveying speed deviation coefficient;

[0057] Constructing a paint film generation control deviation matrix according to the paint conveying roller speed deviation coefficient, the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the curing longitudinal temperature deviation coefficient, the curing transverse temperature deviation coefficient and the enameled wire conveying speed deviation coefficient;

[0058] The paint film generation control deviation matrix is ​​input into the primary detection network, and the paint film abnormality probability is output.

[0059] In a feasible implementation, first, the abnormal prediction unit 12 obtains the paint film generation monitoring control parameters and the paint film generation expected control parameters from the parameter receiving unit 11, and compares the corresponding parameter items one by one. Specifically, the abnormal prediction unit 12 compares the paint roller speed monitoring value with the paint roller speed expected value, compares the evaporation longitudinal temperature monitoring curve with the evaporation longitudinal temperature expected curve, compares the evaporation transverse temperature monitoring value with the evaporation transverse temperature expected value, compares the curing longitudinal temperature monitoring curve with the curing longitudinal temperature expected curve, compares the curing transverse temperature monitoring value with the curing transverse temperature expected value, and compares the enameled wire conveying speed monitoring value with the enameled wire conveying speed expected value. Through the comparison, the abnormal prediction unit 12 accurately quantifies the degree of deviation between the monitoring value and the expected value of each parameter, thereby obtaining a set of deviation coefficients, including the paint roller speed deviation coefficient, the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the curing longitudinal temperature deviation coefficient, the curing transverse temperature deviation coefficient, and the enameled wire conveying speed deviation coefficient. These deviation coefficients intuitively reflect the gap between the process parameters of each link in the paint film generation process and the optimal state, and provide important indicators for judging paint film abnormalities. Secondly, the abnormality prediction unit 12 constructs a paint film generation control deviation matrix according to the above set of deviation coefficients in a preset matrix form. This matrix comprehensively characterizes the degree of deviation of all parameters and quantitatively describes the overall abnormality level of the current enameled wire paint film generation process. Afterwards, the abnormality prediction unit 12 inputs the constructed paint film generation control deviation matrix into the pre-trained primary detection network, and outputs the paint film abnormality probability of the current enameled wire paint film to be inspected through calculation and analysis.

[0060] Through the abnormality prediction unit 12, based on the deviation coefficient and the deviation matrix, combined with the primary detection network, the probability of paint film abnormality is obtained, the parameter abnormalities in the production process are discovered in time, the paint film quality risks are accurately predicted, and strong support is provided for online detection of paint films.

[0061] Furthermore, the embodiment of the present application also includes:

[0062] Construct the coefficient of deviation evaluation function:

[0063] ,

[0064] in, Characterize the paint conveying roller speed deviation coefficient or the evaporation longitudinal temperature deviation coefficient or the evaporation transverse temperature deviation coefficient or the curing longitudinal temperature deviation coefficient or the curing transverse temperature deviation coefficient or the enameled wire conveying speed deviation coefficient, the i-th order monitoring value representing the paint conveying roller speed monitoring value, the evaporation longitudinal temperature monitoring curve, the evaporation transverse temperature monitoring value, the curing longitudinal temperature monitoring curve, the curing transverse temperature monitoring value, or the enameled wire conveying speed monitoring value, Characterizes the i-th order expected value of the expected value of the paint conveying roller speed, the expected curve of the evaporation longitudinal temperature, the expected value of the evaporation transverse temperature, the expected curve of the curing longitudinal temperature, the expected value of the curing transverse temperature, or the expected value of the enameled wire conveying speed, Q represents the number of characteristic values;

[0065] According to the deviation coefficient evaluation function, the paint roller speed monitoring value, the evaporation longitudinal temperature monitoring curve, the evaporation transverse temperature monitoring value, the solidification longitudinal temperature monitoring curve, the solidification transverse temperature monitoring value, and the enameled wire conveying speed monitoring value are compared with the expected value of the paint roller speed, the expected evaporation longitudinal temperature curve, the expected evaporation transverse temperature value, the expected solidification longitudinal temperature curve, the expected solidification transverse temperature value, and the expected value of the enameled wire conveying speed to obtain the paint roller speed deviation coefficient, the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the solidification longitudinal temperature deviation coefficient, the solidification transverse temperature deviation coefficient, and the enameled wire conveying speed deviation coefficient.

[0066] In a preferred embodiment, a quantitative evaluation method of the deviation coefficient is proposed to more accurately and reasonably measure the degree of deviation of various key parameters in the paint film generation process, so as to provide more reliable data support for subsequent paint film abnormality prediction.

[0067] When the abnormal prediction unit 12 performs the deviation coefficient calculation step, it first constructs a deviation coefficient evaluation function as follows: The deviation coefficient evaluation function is based on the mathematical principle of absolute value proportional difference and quantifies the deviation coefficient of any key parameter. Indicates the deviation coefficient of a key parameter, which may be any one of the paint roller speed deviation coefficient, evaporation longitudinal temperature deviation coefficient, evaporation transverse temperature deviation coefficient, curing longitudinal temperature deviation coefficient, curing transverse temperature deviation coefficient or enameled wire conveying speed deviation coefficient; The i-th monitoring value representing the key parameter may be a paint roller speed monitoring value, a point on the evaporation longitudinal temperature monitoring curve, an evaporation transverse temperature monitoring value, a point on the curing longitudinal temperature monitoring curve, a curing transverse temperature monitoring value or an enameled wire conveying speed monitoring value; represents the i-th expected value of the key parameter, which can be the expected value of the paint roller speed, a point on the expected curve of the evaporation longitudinal temperature, the expected value of the evaporation transverse temperature, a point on the expected curve of the curing longitudinal temperature, the expected value of the curing transverse temperature or the expected value of the enameled wire conveying speed; Q represents the number of pairs of monitored values ​​and expected values ​​involved in the calculation, that is, the number of eigenvalues.

[0068] The physical meaning of the deviation coefficient evaluation function is to obtain the standardized deviation coefficient by calculating the sum of the absolute values ​​of the difference between the monitored value and the expected value of a key parameter and dividing it by the sum of the monitored value and the expected value. The larger the deviation coefficient, the greater the deviation between the monitored value and the expected value, and the higher the abnormal level of the process parameter; conversely, the smaller the deviation coefficient, the closer the monitored value is to the expected value, and the more stable the process parameter.

[0069] Based on the above deviation coefficient evaluation function, the abnormal prediction unit 12 can calculate the deviation coefficient of each key parameter. Specifically, the abnormal prediction unit 12 matches and pairs the monitoring data such as the paint roller speed monitoring value, the evaporation longitudinal temperature monitoring curve, the evaporation transverse temperature monitoring value, the curing longitudinal temperature monitoring curve, the curing transverse temperature monitoring value, and the enameled wire conveying speed monitoring value with the expected data such as the paint roller speed expectation value, the evaporation longitudinal temperature expectation curve, the evaporation transverse temperature expectation value, the curing longitudinal temperature expectation curve, the curing transverse temperature expectation value, and the enameled wire conveying speed expectation value, and substitutes them into the deviation coefficient evaluation function. After mathematical operations such as accumulation, absolute value calculation, and division, the paint roller speed deviation coefficient, the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the curing longitudinal temperature deviation coefficient, the curing transverse temperature deviation coefficient, and the enameled wire conveying speed deviation coefficient can be obtained.

[0070] Through the deviation coefficient evaluation function, the deviation of the paint film generation process is accurately quantified, overcoming the limitations of traditional deviation measurement methods. The deviation coefficient evaluation function fully considers the relative difference between the monitored value and the expected value, and can objectively reflect the actual deviation of the process parameters, providing a reliable data basis for abnormal prediction and quality analysis.

[0071] Furthermore, the embodiment of the present application also includes:

[0072] According to the model of the enameled wire to be inspected, the primary detection network is retrieved, the paint film generation control deviation matrix is ​​processed, and the paint film abnormality probability is obtained;

[0073] The primary detection network construction step includes:

[0074] Collecting paint film generation record data of a preset enameled wire model, wherein the paint film generation record data includes paint film generation record monitoring control parameters and paint film generation record expected control parameters;

[0075] Constructing a paint film generation control record deviation matrix according to the paint film generation record monitoring control parameters and the paint film generation record expected control parameters;

[0076] Taking the paint film generation control record deviation matrix as a constraint, collecting paint film quality detection record data, and counting the proportion of quality abnormality record data of the paint film quality detection record data, which is set as the paint film abnormality probability identification value;

[0077] The paint film abnormality probability identification value is used as supervision data, and the paint film generation control record deviation matrix is ​​used as input data to train a BP neural network to obtain the primary detection network.

[0078] In a feasible implementation, when performing abnormal prediction, the abnormal prediction unit 12 first automatically retrieves the primary detection network corresponding to the model of the enameled wire to be inspected. Since different models of enameled wires have differences in production process, material formula, quality requirements, etc., the key parameters and abnormal laws of the paint film generation process may also be different. In order to fully consider these differences and improve the applicability of the prediction model, a dedicated primary detection network is pre-built and stored for each enameled wire model. The abnormal prediction unit 12 quickly retrieves the matching primary detection network by identifying the model information of the enameled wire to be inspected, thereby ensuring the effectiveness of the prediction analysis. After retrieving the primary detection network of the adapted model, the abnormal prediction unit 12 inputs the generated paint film generation control deviation matrix into the primary detection network, and outputs the paint film abnormality probability that characterizes the quality state of the current enameled wire paint film after data processing and feature extraction. Among them, the primary detection network automatically learns the abnormal laws and patterns in the paint film generation process from massive, high-dimensional historical data, and establishes a nonlinear mapping relationship between the deviation matrix and the quality state, thereby realizing fast and accurate prediction of new samples.

[0079] In order to obtain a high-quality primary detection network, first, for the preset enameled wire model, the paint film generation record data is collected in the historical database, including the monitoring values ​​and expected values ​​of various key parameters collected during the paint film generation process, that is, including the paint film generation record monitoring control parameters and the paint film generation record expected control parameters. Then, referring to the deviation coefficient calculation method described above, each piece of paint film generation record data is converted into the corresponding paint film generation control record deviation matrix as the input data for training. Secondly, on the basis of the above-mentioned paint film generation control record deviation matrix, the corresponding paint film quality inspection record data is further collected, and the proportion of data entries of abnormal products in the paint film quality inspection record data to the total data volume is counted as the paint film abnormal probability identification value of the paint film generation control record deviation matrix, which is used as the supervisory data set for training. Afterwards, the paint film generation control record deviation matrix is ​​used as the input, and the corresponding paint film abnormal probability value is used as the output, and the BP neural network is used to train the primary detection network. The BP neural network can fit the complex nonlinear relationship between input and output through a multi-layer network structure and a back propagation algorithm. After multiple rounds of iterative training and parameter tuning, the BP neural network learned the quality influencing rules in the paint film generation process from a large number of samples, forming a primary detection network with generalization ability.

[0080] Through the adaptive calling and construction of the primary detection network, the historical production and quality data of different types of enameled wires are fully utilized to build a customized primary detection network, thereby improving the pertinence and accuracy of paint film quality prediction and making the abnormal prediction results closer to the actual production situation.

[0081] Furthermore, the embodiment of the present application also includes:

[0082] Traversing the paint roller speed deviation coefficient, the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the curing longitudinal temperature deviation coefficient, the curing transverse temperature deviation coefficient and the enameled wire conveying speed deviation coefficient to perform paint film defect frequency matching, and obtain paint roller speed deviation high-frequency defects, evaporation longitudinal temperature deviation high-frequency defects, evaporation transverse temperature deviation high-frequency defects, curing longitudinal temperature deviation high-frequency defects, curing transverse temperature deviation high-frequency defects and enameled wire conveying speed deviation high-frequency defects;

[0083] According to the paint roller speed deviation coefficient, the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the curing longitudinal temperature deviation coefficient, the curing transverse temperature deviation coefficient and the enameled wire conveying speed deviation coefficient, the paint roller speed deviation high-frequency defect, the evaporation longitudinal temperature deviation high-frequency defect, the evaporation transverse temperature deviation high-frequency defect, the curing longitudinal temperature deviation high-frequency defect, the curing transverse temperature deviation high-frequency defect and the enameled wire conveying speed deviation high-frequency defect are sorted from large to small to obtain a high-frequency defect sorting result;

[0084] The second-level detection device is used to perform contact detection on the enameled wire to be inspected having the suspected abnormal enameled wire mark according to the high-frequency defect sorting result to obtain the first quality detection result.

[0085] In a feasible implementation, when the contact detection unit 14 detects the suspected abnormal enameled wire, it first obtains the deviation coefficients of various parameters of the enameled wire from the abnormal prediction unit 12, including the paint roller speed deviation coefficient, the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the curing longitudinal temperature deviation coefficient, the curing transverse temperature deviation coefficient and the enameled wire conveying speed deviation coefficient. Then, the contact detection unit 14 traverses the above deviation coefficients and matches them with the pre-constructed paint film defect frequency mapping table. The mapping table is based on a large amount of historical quality data, statistically analyzes the association between various typical paint film defect types and key parameter deviations, and establishes a probabilistic correspondence. Through matching, the contact detection unit 14 quickly determines the most likely high-frequency defect type according to the deviation coefficient of the current enameled wire, including the paint roller speed deviation high-frequency defect, the evaporation longitudinal temperature deviation high-frequency defect, the evaporation transverse temperature deviation high-frequency defect, the curing longitudinal temperature deviation high-frequency defect, the curing transverse temperature deviation high-frequency defect and the enameled wire conveying speed deviation high-frequency defect.

[0086] After obtaining the high-frequency defect type of the suspected abnormal enameled wire, the contact detection unit 14 further prioritizes the high-frequency defect type according to the numerical values ​​of each deviation coefficient. Specifically, the contact detection unit 14 arranges the paint roller speed deviation coefficient, the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the curing longitudinal temperature deviation coefficient, the curing transverse temperature deviation coefficient and the enameled wire conveying speed deviation coefficient in order from large to small values ​​to obtain an ordered sequence of deviation coefficients. Then, the contact detection unit 14 sorts the paint roller speed deviation high-frequency defect, the evaporation longitudinal temperature deviation high-frequency defect, the evaporation transverse temperature deviation high-frequency defect, the curing longitudinal temperature deviation high-frequency defect, the curing transverse temperature deviation high-frequency defect and the enameled wire conveying speed deviation high-frequency defect in the same order, thereby obtaining a priority sequence of high-frequency defects, that is, the high-frequency defect sorting result. In other words, the larger the deviation coefficient, the higher the abnormality of the corresponding process parameter, and the greater the risk of the corresponding defect type caused by it, and it should be detected first.

[0087] Subsequently, the contact detection unit 14 controls the secondary detection equipment in a targeted manner according to the high-frequency defect sorting results, and conducts contact detection on the suspected abnormal enameled wire. Specifically, the secondary detection equipment detects different areas and different features of the suspected abnormal enameled wire in turn according to the priority order of the defect type. For example, when the high-frequency defect of the paint roller speed deviation has the highest priority, the secondary detection equipment will focus on detecting the coating thickness uniformity and roughness on the surface of the enameled wire; when the high-frequency defect of the curing longitudinal temperature deviation has the highest priority, the secondary detection equipment will focus on detecting the structural integrity and adhesion strength inside the enameled wire. The secondary detection equipment obtains various defect parameters and quality data of the suspected abnormal enameled wire through a variety of physical and chemical testing methods, and generates a comprehensive detection report, i.e., the first quality detection result.

[0088] Through intelligent contact detection, the intrinsic connection between parameter deviation and paint film defects is fully utilized to realize the automatic prediction of the defect type and priority of suspected abnormal enameled wire, which improves the pertinence and effectiveness of contact detection. Therefore, under the condition of limited detection resources, the detection of high-risk defects can be covered to the maximum extent, the detection cost and time can be reduced, and the overall quality control efficiency can be improved. At the same time, by sorting the priority of defect types, quality risk points can be located more accurately, providing a decision-making basis for quickly diagnosing the cause of abnormalities and formulating corrective measures.

[0089] Furthermore, the embodiment of the present application also includes:

[0090] Retrieve the first paint film quality detection record data in which the paint roller speed deviation coefficient is greater than or equal to the deviation coefficient threshold, and the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the curing longitudinal temperature deviation coefficient, the curing transverse temperature deviation coefficient and the enameled wire conveying speed deviation coefficient are all less than the deviation coefficient threshold;

[0091] The paint film defects whose paint film defect triggering frequency is greater than or equal to the defect triggering frequency threshold in the first paint film quality detection record data are counted and set as the paint transport roller speed deviation high-frequency defects.

[0092] In a preferred embodiment, when performing high-frequency defect matching and sorting, the contact detection unit 14 updates and optimizes the matching rules in real time to adapt to changes in production processes and quality conditions.

[0093] First, the contact detection unit 14 regularly retrieves historical detection records within a period of time, and performs data screening and classification according to preset conditions. Specifically, taking the high-frequency defect of the paint roller speed deviation as an example, the contact detection unit 14 retrieves all detection record data (i.e., the first paint film quality detection record data) that meet the following conditions: the paint roller speed deviation coefficient is greater than or equal to the preset deviation coefficient threshold, and the deviation coefficients of other key parameters (including evaporation longitudinal temperature, evaporation transverse temperature, curing longitudinal temperature, curing transverse temperature and enameled wire conveying speed) are all less than the deviation coefficient threshold. The first paint film quality detection record data represents a series of paint film quality problems caused when the paint roller speed seriously deviates from the expected value and other process parameters are basically normal, which is typical and representative. Then, the contact detection unit 14 performs statistical analysis on the first paint film quality detection record data, calculates the occurrence frequency of various paint film defects, and compares it with the preset defect trigger frequency threshold. When the trigger frequency of a certain type of defect is greater than or equal to the defect trigger frequency threshold, it can be determined that there is a significant correlation between the defect and the paint roller speed deviation, and it is classified as a paint roller speed deviation high-frequency defect. Through statistical inference methods, the contact detection unit 14 can continuously discover and summarize new high-frequency defect types, enrich and improve matching rules, and enable them to more comprehensively and accurately reflect actual production conditions.

[0094] Through the high-frequency defect self-learning method, the high-frequency defect rules are automatically extracted from the massive historical detection data, and the matching rules are continuously improved and updated to adapt to the dynamic changes of the production environment. The high-frequency defect self-learning method improves the adaptability and robustness of contact detection, which can not only save the time and cost of manually summarizing the rules, but also discover hidden associations that are difficult to detect with human experience, providing important support for online detection of paint films.

[0095] An enameled wire paint film online detection device provided by an embodiment of the present invention has at least the following technical effects:

[0096] The parameter receiving unit is used to receive the paint film generation monitoring control parameters and the paint film generation expected control parameters of the enameled wire to be inspected, providing the necessary data basis for the subsequent abnormality prediction. The abnormality prediction unit is used to predict the abnormal probability of the paint film generation monitoring control parameters and the paint film generation expected control parameters through the primary detection network, obtain the paint film abnormality probability, realize the rapid virtual detection of the paint film quality of the enameled wire, and greatly improve the detection efficiency. The abnormality identification unit is used to identify the enameled wire to be inspected as suspected abnormal enameled wire when the paint film abnormality probability is greater than or equal to the paint film abnormality probability threshold, provide a clear detection target for subsequent contact detection, and improve the detection rate of abnormal products. The contact detection unit is used to perform contact detection on the enameled wire to be inspected with the suspected abnormal enameled wire mark through the secondary detection equipment, obtain the first quality detection result, and perform further contact detection on the suspected abnormal enameled wire identified by the virtual detection, so as to obtain more accurate and reliable quality detection results, and ensure the effective identification of abnormal products. The normal identification unit is used to identify the enameled wire to be inspected as having no paint film abnormality when the paint film abnormality probability is less than the paint film abnormality probability threshold, obtain the second quality inspection result, reduce unnecessary contact inspection, and further improve the overall inspection efficiency. The result feedback unit is used to feed back the first quality inspection result or the second quality inspection result to the client, realizing efficient and accurate enameled wire paint film inspection.

[0097] Embodiment 2:

[0098] like Figure 2 As shown, based on the same inventive concept as the online detection device for enameled wire paint film provided in the first embodiment, the embodiment of the present invention further provides an online detection system for enameled wire paint film, and the execution steps include:

[0099] Receiving the paint film generation monitoring control parameters and the paint film generation expected control parameters of the enameled wire to be inspected;

[0100] By means of a primary detection network, abnormal probability prediction is performed on the paint film generation monitoring control parameter and the paint film generation expected control parameter to obtain a paint film abnormal probability;

[0101] When the paint film abnormality probability is greater than or equal to the paint film abnormality probability threshold, the enameled wire to be inspected is marked as a suspected abnormal enameled wire;

[0102] Conducting contact detection on the enameled wire to be inspected having the suspected abnormal enameled wire mark by means of a secondary detection device to obtain a first quality detection result;

[0103] When the paint film abnormality probability is less than the paint film abnormality probability threshold, the enameled wire to be inspected is marked as having no paint film abnormality to obtain a second quality inspection result;

[0104] The first quality detection result or the second quality detection result is fed back to the client.

[0105] Further, receiving the paint film generation monitoring control parameters and the paint film generation expected control parameters of the enameled wire to be inspected, including:

[0106] Communicate with the sensor array and receive the paint conveying roller speed monitoring value, evaporation longitudinal temperature monitoring curve, evaporation transverse temperature monitoring value, curing longitudinal temperature monitoring curve, curing transverse temperature monitoring value, and enameled wire conveying speed monitoring value of the enameled wire to be inspected;

[0107] Communicate with the paint film generation control end and receive the expected value of the paint conveying roller speed, the expected evaporation longitudinal temperature curve, the expected evaporation transverse temperature, the expected curing longitudinal temperature curve, the expected curing transverse temperature, and the expected value of the enameled wire conveying speed of the enameled wire to be inspected;

[0108] Add the paint roller speed monitoring value, the evaporation longitudinal temperature monitoring curve, the evaporation transverse temperature monitoring value, the curing longitudinal temperature monitoring curve, the curing transverse temperature monitoring value, and the enameled wire conveying speed monitoring value into the paint film generation monitoring control parameters;

[0109] The expected value of the paint roller rotation speed, the expected evaporation longitudinal temperature curve, the expected evaporation transverse temperature, the expected curing longitudinal temperature curve, the expected curing transverse temperature, and the expected value of the enameled wire conveying speed are added to the expected control parameters for paint film generation.

[0110] Furthermore, the paint film generation monitoring control parameters and the paint film generation desired control parameters are predicted for abnormal probability through the primary detection network to obtain the paint film abnormal probability, including:

[0111] The paint roller speed monitoring value, the evaporation longitudinal temperature monitoring curve, the evaporation transverse temperature monitoring value, the solidification longitudinal temperature monitoring curve, the solidification transverse temperature monitoring value, and the enameled wire conveying speed monitoring value are compared with the paint roller speed expected value, the evaporation longitudinal temperature expected curve, the evaporation transverse temperature expected value, the solidification longitudinal temperature expected curve, the solidification transverse temperature expected value, and the enameled wire conveying speed expected value to obtain the paint roller speed deviation coefficient, the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the solidification longitudinal temperature deviation coefficient, the solidification transverse temperature deviation coefficient, and the enameled wire conveying speed deviation coefficient;

[0112] Constructing a paint film generation control deviation matrix according to the paint conveying roller speed deviation coefficient, the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the curing longitudinal temperature deviation coefficient, the curing transverse temperature deviation coefficient and the enameled wire conveying speed deviation coefficient;

[0113] The paint film generation control deviation matrix is ​​input into the primary detection network, and the paint film abnormality probability is output.

[0114] Further, the paint roller speed monitoring value, the evaporation longitudinal temperature monitoring curve, the evaporation transverse temperature monitoring value, the curing longitudinal temperature monitoring curve, the curing transverse temperature monitoring value, and the enameled wire conveying speed monitoring value are compared with the paint roller speed expected value, the evaporation longitudinal temperature expected curve, the evaporation transverse temperature expected value, the curing longitudinal temperature expected curve, the curing transverse temperature expected value, and the enameled wire conveying speed expected value to obtain the paint roller speed deviation coefficient, the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the curing longitudinal temperature deviation coefficient, the curing transverse temperature deviation coefficient, and the enameled wire conveying speed deviation coefficient, including:

[0115] Construct the coefficient of deviation evaluation function:

[0116] ,

[0117] in, Characterize the paint conveying roller speed deviation coefficient or the evaporation longitudinal temperature deviation coefficient or the evaporation transverse temperature deviation coefficient or the curing longitudinal temperature deviation coefficient or the curing transverse temperature deviation coefficient or the enameled wire conveying speed deviation coefficient, the i-th order monitoring value representing the paint conveying roller speed monitoring value, the evaporation longitudinal temperature monitoring curve, the evaporation transverse temperature monitoring value, the curing longitudinal temperature monitoring curve, the curing transverse temperature monitoring value, or the enameled wire conveying speed monitoring value, Characterizes the i-th order expected value of the expected value of the paint conveying roller speed, the expected curve of the evaporation longitudinal temperature, the expected value of the evaporation transverse temperature, the expected curve of the curing longitudinal temperature, the expected value of the curing transverse temperature, or the expected value of the enameled wire conveying speed, Q represents the number of characteristic values;

[0118] According to the deviation coefficient evaluation function, the paint roller speed monitoring value, the evaporation longitudinal temperature monitoring curve, the evaporation transverse temperature monitoring value, the solidification longitudinal temperature monitoring curve, the solidification transverse temperature monitoring value, and the enameled wire conveying speed monitoring value are compared with the expected value of the paint roller speed, the expected evaporation longitudinal temperature curve, the expected evaporation transverse temperature value, the expected solidification longitudinal temperature curve, the expected solidification transverse temperature value, and the expected value of the enameled wire conveying speed to obtain the paint roller speed deviation coefficient, the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the solidification longitudinal temperature deviation coefficient, the solidification transverse temperature deviation coefficient, and the enameled wire conveying speed deviation coefficient.

[0119] Furthermore, the paint film generation control deviation matrix is ​​input into the primary detection network, and the paint film abnormality probability is output, including:

[0120] According to the model of the enameled wire to be inspected, the primary detection network is retrieved, the paint film generation control deviation matrix is ​​processed, and the paint film abnormality probability is obtained;

[0121] The primary detection network construction step includes:

[0122] Collecting paint film generation record data of a preset enameled wire model, wherein the paint film generation record data includes paint film generation record monitoring control parameters and paint film generation record expected control parameters;

[0123] Constructing a paint film generation control record deviation matrix according to the paint film generation record monitoring control parameters and the paint film generation record expected control parameters;

[0124] Taking the paint film generation control record deviation matrix as a constraint, collecting paint film quality detection record data, and counting the proportion of quality abnormality record data of the paint film quality detection record data, which is set as the paint film abnormality probability identification value;

[0125] The paint film abnormality probability identification value is used as supervision data, and the paint film generation control record deviation matrix is ​​used as input data to train a BP neural network to obtain the primary detection network.

[0126] Further, the method further comprises: performing contact detection on the enameled wire to be inspected having the suspected abnormal enameled wire mark by means of a secondary detection device to obtain a first quality detection result;

[0127] Traversing the paint roller speed deviation coefficient, the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the curing longitudinal temperature deviation coefficient, the curing transverse temperature deviation coefficient and the enameled wire conveying speed deviation coefficient to perform paint film defect frequency matching, and obtain paint roller speed deviation high-frequency defects, evaporation longitudinal temperature deviation high-frequency defects, evaporation transverse temperature deviation high-frequency defects, curing longitudinal temperature deviation high-frequency defects, curing transverse temperature deviation high-frequency defects and enameled wire conveying speed deviation high-frequency defects;

[0128] According to the paint roller speed deviation coefficient, the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the curing longitudinal temperature deviation coefficient, the curing transverse temperature deviation coefficient and the enameled wire conveying speed deviation coefficient, the paint roller speed deviation high-frequency defect, the evaporation longitudinal temperature deviation high-frequency defect, the evaporation transverse temperature deviation high-frequency defect, the curing longitudinal temperature deviation high-frequency defect, the curing transverse temperature deviation high-frequency defect and the enameled wire conveying speed deviation high-frequency defect are sorted from large to small to obtain a high-frequency defect sorting result;

[0129] The second-level detection device is used to perform contact detection on the enameled wire to be inspected having the suspected abnormal enameled wire mark according to the high-frequency defect sorting result to obtain the first quality detection result.

[0130] Further, the paint roller speed deviation coefficient, the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the curing longitudinal temperature deviation coefficient, the curing transverse temperature deviation coefficient and the enameled wire conveying speed deviation coefficient are traversed to perform paint film defect frequency matching, and obtain paint roller speed deviation high-frequency defects, evaporation longitudinal temperature deviation high-frequency defects, evaporation transverse temperature deviation high-frequency defects, curing longitudinal temperature deviation high-frequency defects, curing transverse temperature deviation high-frequency defects and enameled wire conveying speed deviation high-frequency defects, including:

[0131] Retrieve the first paint film quality detection record data in which the paint roller speed deviation coefficient is greater than or equal to the deviation coefficient threshold, and the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the curing longitudinal temperature deviation coefficient, the curing transverse temperature deviation coefficient and the enameled wire conveying speed deviation coefficient are all less than the deviation coefficient threshold;

[0132] The paint film defects whose paint film defect triggering frequency is greater than or equal to the defect triggering frequency threshold in the first paint film quality detection record data are counted and set as the paint transport roller speed deviation high-frequency defects.

[0133] Embodiment three:

[0134] See also Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an electronic device 200 provided by an embodiment of the present invention includes a memory 210, a processor 220, and a first computer program 211 stored in the memory 210 and executable on the processor 220. When the processor 220 executes the first computer program 211, an online detection device for paint film of enameled wire is implemented.

[0135] Embodiment 4:

[0136] See also Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 300 on which a second computer program 311 is stored. When the second computer program 311 is executed by a processor, an online detection device for paint film of an enameled wire is implemented.

[0137] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0138] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0139] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0140] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0141] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0142] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0143] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technology, the present invention is also intended to include these changes and variations.

Claims

1. An online detection device for enameled wire paint film, characterized in that: include: A parameter receiving unit, the parameter receiving unit is used to receive a paint film generation monitoring control parameter and a paint film generation desired control parameter of the enameled wire to be inspected; An abnormality prediction unit, the abnormality prediction unit is used to predict the abnormality probability of the paint film generation monitoring control parameter and the paint film generation expected control parameter through a primary detection network to obtain the paint film abnormality probability; An abnormality identification unit, the abnormality identification unit is used to identify the enameled wire to be inspected as a suspected abnormal enameled wire when the paint film abnormality probability is greater than or equal to the paint film abnormality probability threshold; A contact detection unit, the contact detection unit is used to perform contact detection on the enameled wire to be inspected having the suspected abnormal enameled wire mark through a secondary detection device to obtain a first quality detection result; A normal identification unit, wherein the normal identification unit is used to identify the enameled wire to be inspected as having no paint film abnormality when the paint film abnormality probability is less than the paint film abnormality probability threshold, and obtain a second quality inspection result; A result feedback unit, the result feedback unit is used to feed back the first quality detection result or the second quality detection result to a client; The execution steps of the abnormal prediction unit include: The paint roller speed monitoring value, evaporation longitudinal temperature monitoring curve, evaporation transverse temperature monitoring value, curing longitudinal temperature monitoring curve, curing transverse temperature monitoring value, and enameled wire conveying speed monitoring value are compared with the expected value of the paint roller speed, the expected evaporation longitudinal temperature curve, the expected evaporation transverse temperature value, the expected curing longitudinal temperature curve, the expected curing transverse temperature value, and the expected value of the enameled wire conveying speed to obtain the paint roller speed deviation coefficient, evaporation longitudinal temperature deviation coefficient, evaporation transverse temperature deviation coefficient, curing longitudinal temperature deviation coefficient, curing transverse temperature deviation coefficient, and enameled wire conveying speed deviation coefficient; Constructing a paint film generation control deviation matrix according to the paint conveying roller speed deviation coefficient, the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the curing longitudinal temperature deviation coefficient, the curing transverse temperature deviation coefficient and the enameled wire conveying speed deviation coefficient; Inputting the paint film generation control deviation matrix into the primary detection network, and outputting the paint film abnormality probability; Furthermore, the execution steps of the contact detection unit include: Traversing the paint roller speed deviation coefficient, the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the curing longitudinal temperature deviation coefficient, the curing transverse temperature deviation coefficient and the enameled wire conveying speed deviation coefficient to perform paint film defect frequency matching, and obtain paint roller speed deviation high-frequency defects, evaporation longitudinal temperature deviation high-frequency defects, evaporation transverse temperature deviation high-frequency defects, curing longitudinal temperature deviation high-frequency defects, curing transverse temperature deviation high-frequency defects and enameled wire conveying speed deviation high-frequency defects; According to the paint roller speed deviation coefficient, the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the curing longitudinal temperature deviation coefficient, the curing transverse temperature deviation coefficient and the enameled wire conveying speed deviation coefficient, the paint roller speed deviation high-frequency defect, the evaporation longitudinal temperature deviation high-frequency defect, the evaporation transverse temperature deviation high-frequency defect, the curing longitudinal temperature deviation high-frequency defect, the curing transverse temperature deviation high-frequency defect and the enameled wire conveying speed deviation high-frequency defect are sorted from large to small to obtain a high-frequency defect sorting result; The second-level detection device is used to perform contact detection on the enameled wire to be inspected having the suspected abnormal enameled wire mark according to the high-frequency defect sorting result to obtain the first quality detection result.

2. The device according to claim 1, characterized in that The execution steps of the parameter receiving unit include: Communicate with the sensor array and receive the paint conveying roller speed monitoring value, evaporation longitudinal temperature monitoring curve, evaporation transverse temperature monitoring value, curing longitudinal temperature monitoring curve, curing transverse temperature monitoring value, and enameled wire conveying speed monitoring value of the enameled wire to be inspected; Communicate with the paint film generation control end and receive the expected value of the paint conveying roller speed, the expected evaporation longitudinal temperature curve, the expected evaporation transverse temperature, the expected curing longitudinal temperature curve, the expected curing transverse temperature, and the expected value of the enameled wire conveying speed of the enameled wire to be inspected; Add the paint roller speed monitoring value, the evaporation longitudinal temperature monitoring curve, the evaporation transverse temperature monitoring value, the curing longitudinal temperature monitoring curve, the curing transverse temperature monitoring value, and the enameled wire conveying speed monitoring value into the paint film generation monitoring control parameters; The expected value of the paint roller rotation speed, the expected evaporation longitudinal temperature curve, the expected evaporation transverse temperature, the expected curing longitudinal temperature curve, the expected curing transverse temperature, and the expected value of the enameled wire conveying speed are added to the expected control parameters for paint film generation.

3. The device according to claim 2, characterized in that The execution step of the abnormal prediction unit also includes: Construct the coefficient of deviation evaluation function: ， in, Characterize the paint conveying roller speed deviation coefficient or the evaporation longitudinal temperature deviation coefficient or the evaporation transverse temperature deviation coefficient or the curing longitudinal temperature deviation coefficient or the curing transverse temperature deviation coefficient or the enameled wire conveying speed deviation coefficient, the i-th order monitoring value representing the paint conveying roller speed monitoring value, the evaporation longitudinal temperature monitoring curve, the evaporation transverse temperature monitoring value, the curing longitudinal temperature monitoring curve, the curing transverse temperature monitoring value, or the enameled wire conveying speed monitoring value, Characterizes the i-th order expected value of the expected value of the paint conveying roller speed, the expected curve of the evaporation longitudinal temperature, the expected value of the evaporation transverse temperature, the expected curve of the curing longitudinal temperature, the expected value of the curing transverse temperature, or the expected value of the enameled wire conveying speed, Q represents the number of characteristic values; According to the deviation coefficient evaluation function, the paint roller speed monitoring value, the evaporation longitudinal temperature monitoring curve, the evaporation transverse temperature monitoring value, the solidification longitudinal temperature monitoring curve, the solidification transverse temperature monitoring value, and the enameled wire conveying speed monitoring value are compared with the expected value of the paint roller speed, the expected evaporation longitudinal temperature curve, the expected evaporation transverse temperature value, the expected solidification longitudinal temperature curve, the expected solidification transverse temperature value, and the expected value of the enameled wire conveying speed to obtain the paint roller speed deviation coefficient, the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the solidification longitudinal temperature deviation coefficient, the solidification transverse temperature deviation coefficient, and the enameled wire conveying speed deviation coefficient.

4. The device according to claim 2, characterized in that The execution step of the abnormal prediction unit also includes: According to the model of the enameled wire to be inspected, the primary detection network is retrieved, the paint film generation control deviation matrix is ​​processed, and the paint film abnormality probability is obtained; The primary detection network construction step includes: Collecting paint film generation record data of a preset enameled wire model, wherein the paint film generation record data includes paint film generation record monitoring control parameters and paint film generation record expected control parameters; Constructing a paint film generation control record deviation matrix according to the paint film generation record monitoring control parameters and the paint film generation record expected control parameters; Taking the paint film generation control record deviation matrix as a constraint, collecting paint film quality detection record data, and counting the proportion of quality abnormality record data of the paint film quality detection record data, which is set as the paint film abnormality probability identification value; The paint film abnormality probability identification value is used as supervision data, and the paint film generation control record deviation matrix is ​​used as input data to train a BP neural network to obtain the primary detection network.

5. The device according to claim 2, characterized in that The execution step of the contact detection unit also includes: Retrieve the first paint film quality detection record data in which the paint roller speed deviation coefficient is greater than or equal to the deviation coefficient threshold, and the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the curing longitudinal temperature deviation coefficient, the curing transverse temperature deviation coefficient and the enameled wire conveying speed deviation coefficient are all less than the deviation coefficient threshold; The paint film defects whose paint film defect triggering frequency is greater than or equal to the defect triggering frequency threshold in the first paint film quality detection record data are counted and set as the paint transport roller speed deviation high-frequency defects.

6. An online detection system for enameled wire paint film, characterized in that: The implementation steps include: Receiving the paint film generation monitoring control parameters and the paint film generation expected control parameters of the enameled wire to be inspected; By means of a primary detection network, abnormal probability prediction is performed on the paint film generation monitoring control parameter and the paint film generation expected control parameter to obtain a paint film abnormal probability; When the paint film abnormality probability is greater than or equal to the paint film abnormality probability threshold, the enameled wire to be inspected is marked as a suspected abnormal enameled wire; Conducting contact detection on the enameled wire to be inspected having the suspected abnormal enameled wire mark by means of a secondary detection device to obtain a first quality detection result; When the paint film abnormality probability is less than the paint film abnormality probability threshold, the enameled wire to be inspected is marked as having no paint film abnormality to obtain a second quality inspection result; Feedback the first quality detection result or the second quality detection result to the client; Among them, through the primary detection network, the abnormal probability prediction of the paint film generation monitoring control parameters and the paint film generation expected control parameters is performed to obtain the paint film abnormal probability, including: The paint roller speed monitoring value, evaporation longitudinal temperature monitoring curve, evaporation transverse temperature monitoring value, curing longitudinal temperature monitoring curve, curing transverse temperature monitoring value, and enameled wire conveying speed monitoring value are compared with the expected value of the paint roller speed, the expected evaporation longitudinal temperature curve, the expected evaporation transverse temperature value, the expected curing longitudinal temperature curve, the expected curing transverse temperature value, and the expected value of the enameled wire conveying speed to obtain the paint roller speed deviation coefficient, evaporation longitudinal temperature deviation coefficient, evaporation transverse temperature deviation coefficient, curing longitudinal temperature deviation coefficient, curing transverse temperature deviation coefficient, and enameled wire conveying speed deviation coefficient; Constructing a paint film generation control deviation matrix according to the paint conveying roller speed deviation coefficient, the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the curing longitudinal temperature deviation coefficient, the curing transverse temperature deviation coefficient and the enameled wire conveying speed deviation coefficient; Inputting the paint film generation control deviation matrix into the primary detection network, and outputting the paint film abnormality probability; Further, the second-level detection device is used to perform contact detection on the enameled wire to be inspected having the suspected abnormal enameled wire mark to obtain a first quality detection result, including: Traversing the paint roller speed deviation coefficient, the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the curing longitudinal temperature deviation coefficient, the curing transverse temperature deviation coefficient and the enameled wire conveying speed deviation coefficient to perform paint film defect frequency matching, and obtain paint roller speed deviation high-frequency defects, evaporation longitudinal temperature deviation high-frequency defects, evaporation transverse temperature deviation high-frequency defects, curing longitudinal temperature deviation high-frequency defects, curing transverse temperature deviation high-frequency defects and enameled wire conveying speed deviation high-frequency defects; According to the paint roller speed deviation coefficient, the evaporation longitudinal temperature deviation coefficient, the evaporation transverse temperature deviation coefficient, the curing longitudinal temperature deviation coefficient, the curing transverse temperature deviation coefficient and the enameled wire conveying speed deviation coefficient, the paint roller speed deviation high-frequency defect, the evaporation longitudinal temperature deviation high-frequency defect, the evaporation transverse temperature deviation high-frequency defect, the curing longitudinal temperature deviation high-frequency defect, the curing transverse temperature deviation high-frequency defect and the enameled wire conveying speed deviation high-frequency defect are sorted from large to small to obtain a high-frequency defect sorting result; The second-level detection device is used to perform contact detection on the enameled wire to be inspected having the suspected abnormal enameled wire mark according to the high-frequency defect sorting result to obtain the first quality detection result.

7. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby realizing an enameled wire paint film online detection device as described in any one of claims 1-5.

8. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, and when the computer software program is executed by the processor, an online detection device for paint film of an enameled wire is implemented as described in any one of claims 1 to 5.

Images