Method for determining cause of abnormal temperature of bonding wire annealing equipment, electronic equipment and medium

Abstract

The present invention provides a method for determining the cause of temperature anomaly in bonding wire annealing equipment, an electronic device, and a medium, and relates to the technical field of determining the cause of temperature anomaly in bonding wire annealing equipment. The method comprises: obtaining the air pressure at the corresponding position of each temperature sensor each time the temperature is detected within a preset sliding time window to obtain an air pressure matrix HA; obtaining a number of gas parameters, a number of pipeline parameters, and a number of environmental parameters corresponding to the gas annealing device to obtain a key parameter characteristic vector QA corresponding to the annealing device; inputting QA and HA into a preset bonding wire temperature prediction model to obtain a predicted temperature matrix HB corresponding to HA; performing a parity difference between HB and A to obtain a temperature difference matrix ΔH; analyzing ΔH to determine the specific cause of the bonding wire annealing anomaly; the present invention can realize accurate diagnosis of temperature anomalies, reduce the increase in maintenance costs and production stagnation caused by blind investigation, and ensure the stability of bonding wire annealing quality.

Description

Technical Field

[0001] The present invention relates to the technical field of determining the cause of abnormal temperature of bonding wire annealing equipment, and in particular to a method for determining the cause of abnormal temperature of bonding wire annealing equipment, electronic equipment and a medium. Background Art

[0002] In semiconductor packaging, bond wire performance directly impacts device reliability, and gas annealing is a critical process step. During the annealing process, the bond wire is conveyed through the gas annealing device using a conveyor. Temperature sensors monitor temperature changes at various locations to ensure annealing quality. However, temperature anomalies frequently occur during annealing, and existing technologies have significant shortcomings in locating the cause of these anomalies. They rely solely on single-point temperature data, ignoring the coupled influence of multiple factors such as gas flow, pipeline pressure, and environmental parameters. They also lack a correlation model between measurement data and device status parameters, making it difficult to distinguish between initial temperature control inaccuracy and sensor failure. For example, sensor errors can be misinterpreted as a heating system failure, while initial temperature anomalies caused by gas flow fluctuations can also lead to batch quality issues if not located in a timely manner. Existing diagnostic methods suffer from insufficient multi-dimensional parameter integration and low anomaly identification accuracy, making them unable to meet the requirements of high-precision annealing processes. Therefore, a method for determining the cause of temperature anomalies that integrates gas pressure changes, gas parameters, pipeline conditions, and environmental factors is urgently needed to achieve accurate diagnosis and ensure consistent annealing quality. Summary of the Invention

[0003] In view of the above technical problems, the technical solution adopted by the present invention is:

[0004] According to a first aspect of the present application, a method for determining the cause of temperature anomaly in a bonding wire annealing device is provided. The bonding wire annealing device includes a gas annealing device and a conveying device. The conveying device is used to convey the bonding wire through the gas annealing device for gas annealing. The gas annealing device is provided with a plurality of sequentially arranged temperature sensors, and the temperature sensors are used to detect the temperature of the bonding wire.

[0005] The method comprises the following steps:

[0006] Q100, if the cause of the abnormal annealing of the bonding wire is the abnormal initial temperature or the abnormal temperature sensor, then the air pressure at the corresponding position of each temperature sensor each time the temperature is detected within the preset sliding time window is obtained to obtain the air pressure matrix HA; HA includes several rows and several columns, each row includes the air pressure at the position corresponding to the same temperature sensor detected at different detection times, and each column includes the air pressure at the position corresponding to different temperature sensors detected at the same detection time.

[0007] Q200, obtaining several gas parameters, several pipeline parameters and several environmental parameters corresponding to the gas annealing device, and obtaining a key parameter feature vector QA corresponding to the gas annealing device.

[0008] Q300, input QA and HA into the preset bonding wire temperature prediction model to obtain the predicted temperature matrix HB corresponding to HA; wherein HB has the same dimension as HA, and each element in HB represents the predicted temperature of the bonding wire at the corresponding temperature sensor position at the corresponding detection moment.

[0009] Q400, perform a parity difference between HB and A to obtain a temperature difference matrix ΔH; wherein A is an actual temperature matrix obtained by each temperature sensor collecting the actual temperature of the bonding wire within a preset sliding time window; A includes several rows and several columns, each row includes the temperatures detected by the same temperature sensor at different detection times, and each column includes the temperatures detected by different temperature sensors at the same detection time.

[0010] Q500, analyze ΔH to determine the specific cause of abnormal bonding wire annealing.

[0011] According to another aspect of the present application, a non-transitory computer-readable storage medium is also provided, in which at least one instruction or at least one program is stored. The at least one instruction or at least one program is loaded and executed by a processor to implement the above-mentioned method for determining the cause of temperature abnormality of the bonding wire annealing equipment.

[0012] According to another aspect of the present application, an electronic device is provided, including a processor and the above-mentioned non-transitory computer-readable storage medium.

[0013] The present invention has at least the following beneficial effects:

[0014] The present invention provides a method for determining the cause of temperature anomalies in bonding wire annealing equipment. The method obtains the air pressure matrix at the corresponding position of each temperature sensor within a preset sliding time window and combines the key parameter characteristic vector composed of gas parameters, pipeline parameters and environmental parameters to incorporate multi-dimensional information such as air pressure changes, equipment operating status and environmental factors during the annealing process into the analysis system. This changes the limitation of traditional methods that only rely on single-point temperature data and comprehensively reflects the coupling effect of complex physical fields in the annealing device. A preset bonding wire temperature prediction model is used to establish an association mapping between detection data and equipment status parameters, generate a predicted temperature matrix and compare it with the actual temperature matrix in the same position. Based on the analysis of the difference matrix, the method can accurately identify initial temperature control anomalies and temperature sensor anomalies, avoid misjudgment and accurately locate the root cause of the anomaly. Through systematic analysis, the temperature deviation characteristics at different positions and at different times are quantified, and the abnormal link is quickly locked in combination with the temporal and spatial distribution laws of air pressure and key parameters. This overcomes the defect of insufficient multi-dimensional parameter fusion, realizes accurate diagnosis of temperature anomalies, reduces the increase in maintenance costs and production stagnation caused by blind investigation, and ensures the stability of bonding wire annealing quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 A flow chart of a method for determining the cause of abnormal temperature in a bonding wire annealing device provided in an embodiment of the present invention;

[0017] Figure 2 A schematic structural diagram of a gas annealing device provided in an embodiment of the present invention;

[0018] Explanation of symbols:

[0019] 100. Gas annealing device, 110. Temperature sensor, 200. Bonding wire. DETAILED DESCRIPTION

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0021] It should be noted that, based on this disclosure, those skilled in the art will appreciate that an aspect described herein can be implemented independently of any other aspect, and that two or more of these aspects can be combined in various ways. For example, any number of the aspects described herein can be used to implement an apparatus and / or practice a method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement such an apparatus and / or practice such a method.

[0022] The following will refer to Figure 1 The flowchart of the method for determining the cause of abnormal temperature of the bonding wire annealing equipment is shown, and a method for determining the cause of abnormal temperature of the bonding wire annealing equipment is introduced.

[0023] In this embodiment, Figure 2 As shown, the bonding wire annealing equipment includes a gas annealing device 100 and a conveying device, wherein the conveying device is used to convey the bonding wire 200 through the gas annealing device for gas annealing. The gas annealing device 100 is provided with a plurality of temperature sensors 110 arranged in sequence, and the temperature sensors 110 are used to detect the temperature of the bonding wire 200.

[0024] In this embodiment, after the bonding wire 200 is heated in the heating furnace, the conveying device moves the heated bonding wire from the gas annealing device 100 at a uniform speed so as to slowly cool it down through the inert gas in the gas annealing device 100; a plurality of temperature sensors 110 arranged in a row are provided on the inner wall of the gas annealing device 100, and the sampling frequency of the temperature sensor 110 is set according to the moving speed of the bonding wire 200, so that when the target position on the bonding wire 200 passes through each temperature sensor 110, the temperature sensor 110 collects the temperature of the target position; the temperature sensor can be an infrared temperature sensor or a thermocouple temperature sensor, which can be selected according to actual needs.

[0025] It should be noted that those skilled in the art can use existing heating furnaces and conveying devices to heat and convey the bonding wires according to actual needs, which will not be elaborated here.

[0026] The method for determining the cause of abnormal temperature of the bonding wire annealing equipment may include the following steps:

[0027] Q100, if the cause of the abnormal annealing of the bonding wire is the abnormal initial temperature or the abnormal temperature sensor, then the air pressure at the corresponding position of each temperature sensor each time the temperature is detected within the preset sliding time window is obtained to obtain the air pressure matrix HA; HA includes several rows and several columns, each row includes the air pressure at the position corresponding to the same temperature sensor detected at different detection times, and each column includes the air pressure at the position corresponding to different temperature sensors detected at the same detection time.

[0028] If the initial cause of the annealing anomaly is determined to be an abnormal initial temperature, such as abnormal heating of the bonding wire in the furnace or an abnormal temperature sensor, the air pressure data at each temperature sensor location within the preset sliding time window is collected. A pressure matrix HA is constructed based on the dimensions sensor location × detection time. Each row corresponds to the sensor location, reflecting the spatial distribution, and each column corresponds to the detection time, reflecting the time series.

[0029] The air pressure parameter is introduced as the environmental feature of the sensor location. The temporal correlation of the air pressure data is retained through a sliding time window, which avoids the randomness of single-point data and provides dynamic air pressure change characteristics for subsequent model prediction.

[0030] Q200, obtaining several gas parameters, several pipeline parameters and several environmental parameters corresponding to the gas annealing device, and obtaining a key parameter feature vector QA corresponding to the gas annealing device.

[0031] In this embodiment, an inert gas is introduced into the gas annealing device. There are several types of inert gases, and several gas parameters corresponding to the inert gas can be obtained, such as flow rate, composition, temperature, etc.; pipeline parameters include inner diameter, roughness, blockage rate, material, etc.; environmental parameters include room temperature, humidity, air pressure, etc. After collecting the above parameters, a corresponding key parameter feature vector QA can be generated. When generating QA, parameters with specific numerical values ​​can be directly used as corresponding elements in QA. If the parameters are type data, the corresponding elements in QA can be generated through secondary encoding.

[0032] QA includes key parameters such as gas heat dissipation efficiency, pipeline transmission characteristics, and environmental heat dissipation conditions, solving the one-sided problem of traditional methods that rely solely on temperature data.

[0033] Q300, input QA and HA into the preset bonding wire temperature prediction model to obtain the predicted temperature matrix HB corresponding to HA; wherein HB has the same dimension as HA, and each element in HB represents the predicted temperature of the bonding wire at the corresponding temperature sensor position at the corresponding detection moment.

[0034] In this embodiment, an integrated learning model, such as XGBoost, or a lightweight neural network, such as a one-dimensional CNN-LSTM, can be used as a preset bonding wire temperature prediction model to balance accuracy and real-time performance to meet the online monitoring requirements of the bonding wire production line.

[0035] It can be understood that during the bonding wire annealing process, when several gas parameters, several pipeline parameters and several environmental parameters remain constant, the temperature change at the same temperature sensor position will cause the gas pressure to change. Therefore, by obtaining the characteristic vectors corresponding to the above parameters and combining them with HA, the predicted temperature at each temperature sensor can be reversely predicted.

[0036] The preset bonding wire temperature prediction model is a trained model, and the initial model can be trained using a large amount of known historical data. The known historical data include corresponding gas parameters, pipeline parameters, environmental parameters, and the temperature and air pressure at the same position of the bonding wire at different sensor positions. It should be noted that those skilled in the art can use existing model training methods to train the initial model according to actual needs, which will not be elaborated here.

[0037] Input QA and HA into the preset temperature prediction model, and output the predicted temperature matrix HB with the same dimension as HA, where each element represents the theoretical temperature at the corresponding position and time.

[0038] By learning the mapping relationship between pressure, gas, pipeline, and environmental parameters and temperature, the model constructs a mathematical representation of the device state and temperature field, breaking through the limitations of existing technologies that separate temperature data from device parameter analysis. HB, the ideal temperature after eliminating sensor anomalies or initial temperature anomalies, provides a comparison benchmark for actual temperature deviation analysis, significantly improving the scientific nature of anomaly identification.

[0039] Q400, perform a parity difference between HB and A to obtain a temperature difference matrix ΔH; wherein A is an actual temperature matrix obtained by each temperature sensor collecting the actual temperature of the bonding wire within a preset sliding time window; A includes several rows and several columns, each row includes the temperatures detected by the same temperature sensor at different detection times, and each column includes the temperatures detected by different temperature sensors at the same detection time.

[0040] The actual temperature matrix A (i.e., sensor measured data) is subtracted from the predicted matrix HB to obtain ΔH = A - HB. Each element of ΔH represents the deviation between the measured and theoretical temperatures at each sensor location and at each moment. A positive value indicates that the measured temperature is higher than the theoretical value, possibly indicating sensor failure or local overheating. A negative value indicates that the measured temperature is lower than the theoretical value, possibly indicating insufficient gas flow or sensor failure. Preserving this information in the spatial and temporal dimensions in matrix form avoids the crude diagnostic approach of traditional methods that only analyze average temperatures or single extreme values.

[0041] Q500, analyze ΔH to determine the specific cause of abnormal bonding wire annealing.

[0042] Based on the spatiotemporal distribution characteristics of ΔH, we can distinguish between initial temperature anomalies, such as equipment-side problems, and sensor anomalies, such as detection-side problems, solving the problem of confusion and misjudgment of the two types of anomalies in existing technologies.

[0043] Furthermore, step Q500 may include the following steps:

[0044] Q510, get ΔH = (ΔH1, ΔH2,…, ΔH i ,…,ΔH n ), i=1, 2, …, n; where ΔH i is the temperature difference sequence corresponding to the i-th temperature sensor, n is the number of temperature sensors; ΔH i It includes the temperature difference between the predicted temperature and the actual temperature of the i-th temperature sensor at different detection times.

[0045] Q520, obtain the average temperature difference corresponding to each temperature difference sequence in ΔH, to obtain the average temperature difference list YA=(YA1, YA2, ..., YA i ,…,YA n ); among them, YA iΔH i The corresponding average temperature difference.

[0046] Q530, traverse YA, if YA i >ψ, the i-th temperature sensor is determined as an abnormal temperature sensor; wherein ψ is a preset average temperature difference threshold.

[0047] In this embodiment, ψ can be obtained by analyzing a large amount of historical data. For example, the value range of ψ is -5°C to 5°C.

[0048] In the above steps, random noise is filtered by averaging, focusing on persistent deviations, avoiding manual point-by-point troubleshooting and improving diagnostic efficiency. If multiple sensors are abnormal, such as if adjacent sensors all exceed the threshold, it indicates a common problem in the detection system, such as poor sensor contact caused by vibration at the installation location.

[0049] Q540: Determine the specific cause of abnormal bonding wire annealing based on the number and location of abnormal temperature sensors.

[0050] Furthermore, step Q540 may include the following steps:

[0051] Q541, if it is determined that the number of abnormal temperature sensors is 0, it is determined that the cause of the abnormal annealing of the bonding wire is the abnormal initial temperature.

[0052] If the number of abnormal sensors is 0, it means that the predicted temperature is consistent with the temperature actually measured by the sensor. It can be determined that the initial temperature is abnormal. For example, a failure of the heating module of the heating furnace causes the initial temperature of the bonding wire to be abnormal after it comes out of the heating furnace.

[0053] Q542, if it is determined that the number of abnormal temperature sensors is greater than 0, the detected temperatures corresponding to the abnormal temperature sensors in A are deleted to obtain a corrected actual temperature matrix WA corresponding to A.

[0054] Delete abnormal sensor data and generate the correction matrix WA to further verify whether it is a simple sensor problem.

[0055] Q543: Based on WA, determine whether the cause of abnormal bonding wire annealing is an abnormal temperature sensor.

[0056] By first eliminating sensor anomalies and then analyzing the logic of the remaining data, we can avoid misjudging device-side problems as sensor failures. For example, when gas flow fluctuations cause global temperature anomalies, the sensor is not faulty but the average temperature is normal. The risk of misjudgment is also reduced. For example, when a single sensor is abnormal, if the remaining temperature field conforms to the theoretical distribution after deleting its data, it can be diagnosed as an individual sensor failure rather than a device-side problem.

[0057] Furthermore, step Q543 may include the following steps:

[0058] Q10, get the average temperature corresponding to each row in WA.

[0059] Q20, use a preset fitting algorithm to fit the average temperature corresponding to each row in WA and the position of the temperature sensor corresponding to each row to obtain the functional relationship RG between the temperature and sensor position corresponding to WA; the independent variable of RG is the sensor position, and the dependent variable is the temperature.

[0060] In this embodiment, the preset fitting algorithm may be a polynomial regression fitting algorithm and a nonlinear least squares fitting algorithm. It should be noted that those skilled in the art can use the polynomial regression fitting algorithm and the nonlinear least squares fitting algorithm according to actual needs to fit the average temperature corresponding to each row in WA and the position of the temperature sensor corresponding to each row to obtain the functional relationship RG between the temperature corresponding to WA and the sensor position, which will not be elaborated here.

[0061] Q30, determining the corrected temperature corresponding to each deleted detected temperature according to RG and the position of the temperature sensor corresponding to the deleted detected temperature, and obtaining a corrected temperature matrix WB corresponding to WA.

[0062] Through this step, the reasonable value corresponding to the abnormal temperature sensor can be supplemented.

[0063] Q40: Based on the WB, determine whether the cause of abnormal bonding wire annealing is an abnormal temperature sensor.

[0064] Fitting algorithms extract the spatial distribution characteristics of normal temperature fields, such as uniform or gradient temperature rise, to avoid distortion of the overall temperature field analysis caused by local sensor anomalies. Anomalous sensor data is properly interpolated to provide a complete data foundation for subsequent comparison with the standard temperature matrix.

[0065] Furthermore, step Q40 may include the following steps:

[0066] Q41, obtain the standard temperature matrix HK corresponding to the current type of bonding wire; HK includes several rows and several columns, each row includes the standard temperature corresponding to the same temperature sensor at different detection times, and each column includes the standard temperature corresponding to different temperature sensors at each detection time.

[0067] Obtain the bonding wire standard temperature matrix HK, that is, the ideal temperature spatiotemporal distribution based on process specifications.

[0068] Q42, obtain the similarity ω between WB and HK.

[0069] Furthermore, ω can be obtained by the following steps:

[0070] Q421, use the same feature extraction method to extract features from WB and HK respectively to obtain the feature vector XL1 corresponding to WB and the feature vector XL2 corresponding to HK.

[0071] Q422, the similarity between XL1 and XL2 is determined as ω.

[0072] Perform feature extraction on WB and HK, such as principal component analysis and convolution features, and calculate cosine similarity ω.

[0073] Q43, if ω>ω', the cause of the abnormal annealing of the bonding wire is determined to be the abnormal temperature sensor; otherwise, the cause of the abnormal annealing of the bonding wire is determined to be the abnormal initial temperature and the abnormal temperature sensor; where ω' is a preset temperature matrix similarity threshold.

[0074] If ω>ω', such as ω'=0.9, it is judged as a simple sensor abnormality, that is, the corrected temperature field meets the standard; otherwise, it is judged as a mixed abnormality of the device side and the sensor side, such as initial temperature abnormality and partial sensor failure.

[0075] Through similarity calculation, the corrected temperature field is directly compared with the ideal state to avoid subjective judgment and improve the credibility of the diagnosis results; mixed anomaly recognition solves the problem that the existing technology cannot distinguish between single anomalies and compound anomalies, such as the abnormality of the heating module of the heating furnace leading to local temperature anomalies, and the aging of individual sensors amplifying deviations.

[0076] Furthermore, the distances between any two adjacent temperature sensors are equal.

[0077] Adjacent sensors are distributed equidistantly to ensure the homogenization of the spatial coordinates of the temperature field, which facilitates fitting algorithm modeling and abnormal position positioning. For example, equidistant spacing can simplify gradient calculation.

[0078] In this embodiment, by obtaining the air pressure matrix corresponding to each temperature sensor position within a preset sliding time window and combining it with the key parameter feature vector composed of gas parameters, pipeline parameters, and environmental parameters, multi-dimensional information such as air pressure changes during the annealing process, equipment operating status, and environmental factors is incorporated into the analysis system. This overcomes the limitation of traditional methods that rely solely on single-point temperature data and comprehensively reflects the coupling effect of the complex physical field within the annealing device. A preset bonding wire temperature prediction model is used to establish an association mapping between detection data and equipment status parameters, generate a predicted temperature matrix, and compare it with the actual temperature matrix. Based on the analysis of the difference matrix, initial temperature control anomalies and temperature sensor anomalies can be accurately identified, avoiding misjudgment and accurately locating the root cause of the anomaly. Through systematic analysis, the temperature deviation characteristics at different locations and times are quantified. Combined with the spatiotemporal distribution of air pressure and key parameters, the abnormal link is quickly identified. This overcomes the defect of insufficient multi-dimensional parameter fusion, achieves accurate diagnosis of temperature anomalies, reduces the increased maintenance costs and production stagnation caused by blind investigation, and ensures the stability of bonding wire annealing quality.

[0079] In an exemplary embodiment, before step Q100, the cause of abnormal annealing of the bonding wire can be determined by the following method:

[0080] S100 , obtaining a temperature sequence obtained by each temperature sensor collecting the temperature of the bonding wire within a preset sliding time window.

[0081] In this embodiment, the end time point of the preset sliding time window can be a dynamic current time point, and the length of the sliding time window can be set according to actual needs, for example: the length of the sliding time window is 20 seconds; the step size can also be set according to actual needs, for example: the step size of the sliding time window is 10 seconds.

[0082] Several temperature sensors are placed along the wire feed direction within the gas annealing unit. Each sensor collects wire temperature at a fixed sampling frequency, such as 10 Hz. Temperature data from each sensor is dynamically captured within a preset sliding time window to form a temperature sequence. For example, each temperature sequence contains 100 temperature points.

[0083] S200: Obtain the average temperature and temperature fluctuation rate corresponding to each temperature sequence.

[0084] In this embodiment, two key indicators are calculated for each temperature series: the average temperature and the temperature fluctuation rate. The temperature fluctuation rate is obtained by calculating the variance of the corresponding temperature series. The average temperature can reflect the steady-state temperature level of the corresponding temperature sensor area, and the temperature fluctuation rate reflects the fluctuation amplitude of the temperature in the time dimension.

[0085] S300, if |η i，1 -T i|>ΔT or η i，2 >η', the ith temperature sequence is determined as an abnormal temperature sequence, and the abnormal temperature sequence list B=(B1,B2,…,B j ,…,B m ), j = 1, 2, …, m; B j is the jth abnormal temperature sequence determined, m is the number of abnormal temperature sequences determined; η i，1 and η i，2 are the average temperature and temperature fluctuation rate corresponding to the i-th temperature sequence; T i is the standard temperature corresponding to the i-th temperature sensor, ΔT is the preset temperature difference threshold, η' is the preset temperature fluctuation rate threshold; i=1, 2, ..., n; n is the number of temperature sensors.

[0086] In this embodiment, under normal steady-state conditions, the temperature at the same position on the bonding wire will not change significantly when passing through each temperature sensor in the gas annealing device. That is, the temperature values ​​in the temperature sequence corresponding to each temperature sensor should be in a relatively stable state and within a stable temperature range. For example, under normal conditions, the temperature values ​​in the temperature sequence collected by the first temperature sensor in the gas annealing device are all 200°C, with an upper and lower deviation of no more than 5°C.

[0087] Based on this, if |η i，1 -T i |>ΔT, indicating that most of the temperature values ​​in the temperature sequence collected by the i-th temperature sensor within the preset sliding time window have undergone significant changes, which is an abnormal state. The i-th temperature sequence is determined to be an abnormal temperature sequence; if η i，2 >η', indicating that the temperature values ​​in the temperature sequence collected by the i-th temperature sensor within the preset sliding time window fluctuate greatly, which is also an abnormal state. The i-th temperature sequence is determined to be an abnormal temperature sequence, and B is obtained.

[0088] S400, if m=0, determining that the annealing of the bonding wire within the preset sliding time window meets the preset annealing condition; otherwise, determining that the annealing of the bonding wire within the preset sliding time window does not meet the preset annealing condition, and entering S500.

[0089] In this embodiment, if B is empty, it means that the temperature mean and fluctuation rate of all sensors meet the standards and the annealing is qualified; if B is not empty, the annealing is unqualified, and further analysis of the abnormal area of ​​the bonding wire and the cause of the abnormality is required.

[0090] S500 , according to B, determining an abnormal area corresponding to the bonding wire during the bonding wire annealing process and a cause of the abnormality.

[0091] Based on abnormal list B, combined with temperature data and bonding wire feeding parameters, the specific abnormal area of ​​the bonding wire during annealing, such as a certain section of wire, is located, and the cause of the abnormality is analyzed.

[0092] In this embodiment, multiple sensors are used to cover the entire gas annealing process, avoiding single-point monitoring that misses local anomalies. Simultaneously, both the temperature mean and fluctuation are monitored. For example, if a sensor's mean meets the standard but the fluctuation is extremely high, such as a ±15°C fluctuation, it can still be identified as an anomaly, thus avoiding potential hazards such as gas flow fluctuations that are masked by instantaneous compliance. From data collection to anomaly alarms and then to positioning analysis, a complete monitoring chain is formed, providing direction for subsequent repairs.

[0093] Furthermore, step S500 may include the following steps:

[0094] S510, obtain B j =(B j，1 , B j，2 ,…,B j，p ,…,B j，q ), p = 1, 2, ..., q; where B j，p is the pth temperature in the jth abnormal temperature sequence, q is the number of temperatures in the abnormal temperature sequence; B j，r The collection time is earlier than B j，r+1 The collection time; r=1, 2,…, q-1.

[0095] In this embodiment, B j The temperatures in the table are arranged in the order of the time of collection, among which B j，1 is the earliest collected temperature, B j，q is the most recently collected temperature.

[0096] S520, traverse B j , if |B j，p -QT j |>ΔT, then B j，p The corresponding position on the bonding wire is determined as the abnormal position to obtain B j Corresponding abnormal location list C j =(C j，1 , C j，2 ,…,C j，u ,…,C j，f（j） ), u = 1, 2, ..., f (j); where C j，u B j The corresponding u-th abnormal position, f(j) is B j The number of corresponding anomaly locations.

[0097] In this embodiment, under normal circumstances, when the same position on the bonding wire passes through different temperature sensor positions, it corresponds to a standard temperature;j For each temperature point in the data, if its deviation from the corresponding standard temperature exceeds the preset temperature difference threshold ΔT, such as ΔT = 5°C, then its physical position on the bonding wire is calculated based on the acquisition time of the temperature point and the bonding wire feeding speed. For example, if the acquisition time is 3 seconds, the corresponding position is 3 cm, and the position is marked as an abnormal position to form an abnormal position list C. j .

[0098] S530, obtain the temperature matrix A=(A1, A2, ..., A) corresponding to all temperature sequences. i ,…,A n ); where A i is the temperature sequence corresponding to the i-th temperature sensor; A i =(A i，1 , A i，2 ,…,A i，p ,…,A i，q );A i，p is the pth temperature in the temperature sequence corresponding to the i temperature sensors; each temperature sensor collects the temperature at each preset position on the bonding wire.

[0099] The temperature sequences of all temperature sensors are integrated to obtain a global temperature matrix A. The temperature matrix A records the temperature data of each preset position of the bonding wire, such as the temperature data of each sensor at every 0.1 cm. For example, at a position of 2 cm, the temperature at sensor 1 is 300°C, and at sensor 2 is 280°C.

[0100] S540, according to C j and A, determine the corresponding abnormal area and abnormal cause during the bonding wire annealing process.

[0101] Based on the abnormal location list C j And temperature matrix A, further analyze the abnormal area, such as the 5cm-8cm segment of the bonding wire, and the abnormal cause, such as initial temperature abnormality, temperature sensor abnormality or material abnormality.

[0102] In this embodiment, the abstract temperature anomaly is mapped to the specific position of the bonding wire through time-position mapping, so as to process the specific position; abnormal position list C j Provide specific objects for subsequent analysis to avoid analysis difficulties caused by data dispersion.

[0103] Furthermore, step S540 may include the following steps:

[0104] S541, perform deduplication processing on all abnormal locations to obtain an abnormal location list D = (D1, D2, ..., D x ,…,D y ), x=1, 2,…, y; where Dx is the xth abnormal position determined, and y is the number of abnormal positions determined.

[0105] Merge repeated abnormal positions in different abnormal sequences. For example, if sensor 1 marks 5.1 cm and sensor 2 also marks 5.1 cm, merge the same positions to obtain a unique abnormal position list D.

[0106] According to the sampling frequency of the temperature sensor, the bonding wire feeding speed and the time point when the abnormal position reaches each sensor, the temperature data of the abnormal position at each sensor is extracted from the global temperature matrix A to form the full-process temperature sequence of the position.

[0107] S542: Determine the areas on the bonding wire corresponding to all abnormal positions in D as abnormal areas.

[0108] The coverage of all abnormal positions in D on the bonding wire is determined as the abnormal area, such as the 5.1 cm-6.3 cm segment.

[0109] The above steps have at least the following beneficial effects:

[0110] Reduce redundant interference: Deduplication processing prevents the same location from being marked multiple times, focusing on core anomalies and improving analysis efficiency;

[0111] Regional positioning: Integrate discrete abnormal locations into continuous areas to facilitate targeted process adjustments or equipment maintenance.

[0112] Furthermore, after step S542, the method may further include the following steps:

[0113] S543: Based on the sampling frequency of the temperature sensor, the feeding speed of the bonding wire, and the time point when each abnormal position reaches each temperature sensor, the temperature sequence corresponding to each abnormal position is determined from A, and an abnormal temperature sequence list E = (E1, E2, ..., E x ,…,E y ); where E x is the abnormal temperature sequence corresponding to the x-th abnormal position.

[0114] S544: Generate an abnormal temperature curve corresponding to each abnormal temperature sequence in E to obtain an abnormal temperature curve list F corresponding to E = (F1, F2, ..., F x ,…,F y ); where F x For E x Corresponding abnormal temperature curve.

[0115] In this embodiment, the temperature sequence of each abnormal position is converted into a temperature-time curve, with time on the horizontal axis and temperature on the vertical axis, intuitively showing the temperature change trend of this position during the annealing process.

[0116] S545. Obtain the similarity between each abnormal temperature curve in F and the standard temperature curve corresponding to the bonding wire, so as to obtain a similarity list γ = (γ1, γ2,..., γ x ,..., γ y ); where γ x is the similarity between F x and the standard temperature curve corresponding to the bonding wire.

[0117] By comparing the abnormal curve with the standard temperature curve, that is, the temperature-time curve when the bonding wire is normally annealed, the matching degree between the abnormal temperature curve and the standard temperature curve corresponding to the bonding wire can be calculated by the dynamic time warping (DTW) algorithm, and the matching degree is determined as the similarity.

[0118] S555. If γ x < γ' and |TF x，max - TR| < ΔT, then determine D x as the abnormal position with material abnormality; otherwise, determine D x as the abnormal position with temperature abnormality; where TF x，max is the highest temperature corresponding to F x [[ID= and TR is the standard temperature after the bonding wire is heated by the heating furnace. [[ID=

[0119] In this embodiment, if γ x < γ', for example: γ' = 0.7, it means that there is a large difference between F x and the standard temperature curve corresponding to the bonding wire, and |TF[[ID= x，max - TR| < ΔT means that the highest temperature is close to the standard value, that is, the temperature at which the bonding wire is heated in the heating furnace meets the preset conditions. Therefore, D x can be determined as the abnormal position with material abnormality; otherwise, determine D<0000 x as the abnormal position with temperature abnormality, for example: the temperature sensor fails or the heating temperature of the heating furnace does not meet the preset conditions.

[0120] S556. If NUM1 / y > μ, then determine that the reason for the abnormal annealing of the bonding wire is material abnormality; otherwise, determine that the reason for the abnormal annealing of the bonding wire is initial temperature abnormality or temperature sensor abnormality; NUM1 is the number of abnormal positions with material abnormality, and μ is the preset weight, μ > 0.6.

[0121] Count the number of material abnormal positions NUM1. If NUM1 / y>μ, such as μ=0.8, that is, more than 80% of the abnormal positions are material problems, then the main cause is material abnormality; otherwise, it is due to initial temperature abnormality or temperature sensor abnormality.

[0122] The above steps have at least the following beneficial effects:

[0123] Identifying the root cause of anomalies: By analyzing curve similarity and maximum temperature, the cause of anomalies can be narrowed down from substandard temperature to material or equipment issues. For example, if the curves at multiple locations in a batch of bonding wire have low similarity but the maximum temperature is normal, poor material consistency can be inferred, such as high impurity content leading to abnormal thermal conductivity.

[0124] Quantitative decision-making basis: The threshold of μ=0.8 is set based on industrial experience to ensure that most anomalies are only judged as material problems when they are caused by the material, avoiding misjudgments due to anomalies in individual locations.

[0125] Guide precise repairs: If the material is determined to be abnormal, the raw material supplier can be traced; if the equipment is abnormal, the sensor or heating module can be repaired specifically to shorten the troubleshooting cycle.

[0126] Furthermore, η i，2 A i The corresponding variance.

[0127] In this embodiment, the variance directly reflects the degree to which the temperature value deviates from the mean and is more sensitive to capturing fluctuation energy than the standard deviation. The mathematical definition of the variance is simple and suitable for real-time calculation. For example, each time a new temperature point is added to the sliding window, the variance can be quickly updated, meeting the real-time requirements of industrial scenarios.

[0128] Furthermore, the distances between any two adjacent temperature sensors are equal.

[0129] The equidistant layout ensures consistent temperature monitoring density across all sections of the gas annealing unit, avoiding local monitoring blind spots caused by uneven sensor spacing. The equidistant arrangement linearly corresponds the bond wire positions to the sensor numbers, eliminating the need for complex coordinate transformations and simplifying the calculation of abnormal positions.

[0130] Furthermore, the temperature sensor is an infrared temperature sensor.

[0131] Infrared temperature sensors eliminate the need for contact with the wire, thus avoiding wire deformation or conveying speed fluctuations caused by mechanical contact. Infrared temperature sensors can operate stably without contacting high-temperature areas and have a longer lifespan than contact sensors. Infrared temperature measurement has a short response time and is suitable for dynamic temperature monitoring in continuous bonding wire conveying scenarios, such as real-time capture of temperature fluctuations within 0.1 seconds.

[0132] In this embodiment, by setting a number of temperature sensors arranged in sequence in the gas annealing device, the temperature sequence of each sensor within a preset sliding time window is obtained, and abnormal temperature sequences are identified based on the dual criteria of average temperature and temperature fluctuation rate, which effectively solves the problems of insufficient comprehensiveness of temperature monitoring, single abnormality judgment criteria and lack of abnormality location and traceability in the existing technology. Specifically, the multi-sensor layout combined with the sliding time window can capture the dynamic temperature changes of different areas of the bonding wire during the continuous annealing process in real time, avoiding the omission of local abnormalities by single-point detection; through the dual threshold judgment of the difference between the average temperature and the standard temperature and the temperature fluctuation rate, it can not only monitor whether the temperature average meets the process requirements, but also identify drastic temperature fluctuations in a short period of time, thereby improving the accuracy and comprehensiveness of abnormality identification; based on the abnormal temperature sequence list, the abnormal area and cause of the bonding wire are determined, and possible abnormal factors are associated, providing clear guidance for process adjustment and equipment maintenance, reducing reliance on manual experience, shortening the fault handling cycle, thereby significantly improving the consistency of bonding wire annealing quality and production efficiency, and reducing material performance defects and yield losses caused by annealing abnormalities.

[0133] Furthermore, although the steps of the method of the present disclosure are described in a particular order in the accompanying drawings, this does not require or imply that the steps must be performed in this particular order, or that all steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0134] An embodiment of the present invention also provides a non-transitory computer-readable storage medium, which can be set in an electronic device to store at least one instruction or at least one program related to implementing a method in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement the method provided in the above embodiment.

[0135] The program product may utilize any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0136] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0137] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0138] The program code for performing the operations of the present application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0139] An embodiment of the present invention further provides an electronic device including a processor and the aforementioned non-transitory computer-readable storage medium.

[0140] The electronic device is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0141] The electronic device is implemented as a general-purpose computing device. Components of the electronic device may include, but are not limited to, the aforementioned at least one processor, the aforementioned at least one memory, and a bus connecting different system components (including the memory and the processor).

[0142] The memory stores program codes, which can be executed by the processor, so that the processor performs the steps of various embodiments described in this specification.

[0143] The memory may include readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory, and may further include read-only memory (ROM).

[0144] The memory may also include a program / utility having a set (at least one) of program modules, such program modules including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0145] The bus may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

[0146] The electronic device may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface. Furthermore, the electronic device may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter. The network adapter communicates with other modules of the electronic device via a bus. It should be understood that, although not shown in the figures, other hardware and / or software modules may be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0147] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

[0148] An embodiment of the present invention further provides a computer program product comprising program code. When the program product is run on an electronic device, the program code is used to enable the electronic device to execute the steps of the method according to various exemplary embodiments of the present invention described above in this specification.

[0149] Although some specific embodiments of the present invention have been described in detail by way of examples, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It should also be understood by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the present invention.

Claims

1. A method for determining the cause of abnormal temperature of a bonding wire annealing equipment, characterized in that: The bonding wire annealing equipment includes a gas annealing device and a conveying device, wherein the conveying device is used to convey the bonding wire through the gas annealing device for gas annealing, and the gas annealing device is provided with a plurality of sequentially arranged temperature sensors, and the temperature sensors are used to detect the temperature of the bonding wire; The method comprises the following steps: Q100, if the cause of the abnormal annealing of the bonding wire is an abnormal initial temperature or an abnormal temperature sensor, obtain the air pressure at the corresponding position of each temperature sensor at each temperature detection within a preset sliding time window to obtain an air pressure matrix HA; HA includes several rows and several columns, each row includes the air pressure at the position corresponding to the same temperature sensor detected at different detection times, and each column includes the air pressure at the positions corresponding to different temperature sensors detected at the same detection time; Q200, obtaining several gas parameters, several pipeline parameters and several environmental parameters corresponding to the gas annealing device, and obtaining a key parameter characteristic vector QA corresponding to the gas annealing device; Q300 inputs QA and HA into a preset bond wire temperature prediction model to obtain a predicted temperature matrix HB corresponding to HA. HB has the same dimensions as HA, and each element in HB represents the predicted bond wire temperature at the corresponding temperature sensor position at the corresponding detection moment. Q400, perform a parity difference between HB and A to obtain a temperature difference matrix ΔH; wherein A is an actual temperature matrix obtained by each temperature sensor collecting the actual temperature of the bonding wire within a preset sliding time window; A includes a plurality of rows and a plurality of columns, each row includes temperatures detected by the same temperature sensor at different detection times, and each column includes temperatures detected by different temperature sensors at the same detection time; Q500, analyze ΔH to determine the specific cause of abnormal bonding wire annealing; Step Q500 includes the following steps: Q510, get ΔH = (ΔH1, ΔH2,…, ΔH i ,…,ΔH n ), i=1, 2, …, n; where ΔH i is the temperature difference sequence corresponding to the i-th temperature sensor, n is the number of temperature sensors; ΔH i Including the temperature difference between the predicted temperature and the actual temperature of the i-th temperature sensor at different detection moments; Q520, obtain the average temperature difference corresponding to each temperature difference sequence in ΔH, to obtain the average temperature difference list YA=(YA1, YA2, ..., YA i ,…,YA n ); among them, YA i ΔH i The corresponding average temperature difference; Q530, traverse YA, if YA i >ψ, the i-th temperature sensor is determined as an abnormal temperature sensor; where ψ is the preset average temperature difference threshold; Q540, determine the specific cause of abnormal bonding wire annealing based on the number and location of abnormal temperature sensors; Step Q540 includes the following steps: Q541, if it is determined that the number of abnormal temperature sensors is 0, it is determined that the cause of the abnormal annealing of the bonding wire is the abnormal initial temperature; Q542, if it is determined that the number of abnormal temperature sensors is greater than 0, the detected temperatures corresponding to the abnormal temperature sensors in A are deleted to obtain a corrected actual temperature matrix WA corresponding to A; Q543: Based on WA, determine whether the cause of abnormal bonding wire annealing is an abnormal temperature sensor.

2. The method for determining the cause of abnormal temperature of bonding wire annealing equipment according to claim 1, characterized in that: Step Q543 includes the following steps: Q10, get the average temperature corresponding to each row in WA; Q20, use a preset fitting algorithm to fit the average temperature corresponding to each row in WA and the position of the temperature sensor corresponding to each row to obtain the functional relationship RG between the temperature and the sensor position corresponding to WA; the independent variable of RG is the sensor position, and the dependent variable is the temperature; Q30, determining the corrected temperature corresponding to each deleted detected temperature based on RG and the position of the temperature sensor corresponding to the deleted detected temperature, and obtaining a corrected temperature matrix WB corresponding to WA; Q40: Based on the WB, determine whether the cause of abnormal bonding wire annealing is an abnormal temperature sensor.

3. The method for determining the cause of abnormal temperature of bonding wire annealing equipment according to claim 2, characterized in that: Step Q40 includes the following steps: Q41, obtain the standard temperature matrix HK corresponding to the current type of bonding wire; HK includes several rows and several columns, each row includes the standard temperature corresponding to the same temperature sensor at different detection times, and each column includes the standard temperature corresponding to different temperature sensors at each detection time; Q42, obtain the similarity ω between WB and HK; Q43, if ω>ω', the cause of the abnormal annealing of the bonding wire is determined to be the abnormal temperature sensor; otherwise, the cause of the abnormal annealing of the bonding wire is determined to be the abnormal initial temperature and the abnormal temperature sensor; where ω' is a preset temperature matrix similarity threshold.

4. The method for determining the cause of abnormal temperature of bonding wire annealing equipment according to claim 3, characterized in that: ω is obtained by the following steps: Q421, use the same feature extraction method to extract features from WB and HK respectively to obtain the feature vector XL1 corresponding to WB and the feature vector XL2 corresponding to HK; Q422, the similarity between XL1 and XL2 is determined as ω.

5. The method for determining the cause of abnormal temperature of bonding wire annealing equipment according to claim 2, characterized in that: The preset fitting algorithms include: a polynomial regression fitting algorithm and a nonlinear least squares fitting algorithm.

6. The method for determining the cause of abnormal temperature of bonding wire annealing equipment according to claim 1, characterized in that: The distance between any two adjacent temperature sensors is equal.

7. A non-transitory computer-readable storage medium, wherein at least one instruction or at least one program is stored in the storage medium, characterized in that: The at least one instruction or the at least one program segment is loaded and executed by the processor to implement the method for determining the cause of abnormal temperature of bonding wire annealing equipment according to any one of claims 1 to 6.

8. An electronic device, characterized in that: The method comprises a processor and the non-transitory computer-readable storage medium of claim 7.

Images