Uniform control method and device for light emitting color of LED lamp bead and LED lamp bead

Abstract

The invention relates to the technical field of light emitting of LED lamp beads, and discloses a uniform control method and device for the light emitting color of the LED lamp beads and the LED lamp beads, and the method comprises the steps that LED wafers are placed in a triangular annular mode, and the LED lamp beads are prepared through centrifugal treatment of double-layer packaging glue; acquiring an initial optical parameter matrix after applying rated working parameters, and establishing a standard data model; monitoring the LED lamp beads in real time to obtain a monitoring data set; calculating a multi-dimensional deviation vector by using a spectral similarity algorithm, an Euclidean distance algorithm and a ratio algorithm; a comprehensive deviation evaluation value is obtained through weighted summation; and generating a correction amount based on the evaluation value to carry out closed-loop control until a control termination condition is reached. According to the method, accurate control over the light emitting colors of the LED lamp beads is achieved, and the uniformity and stability of the light emitting colors of the LED lamp beads are improved.

Description

Technical Field

[0001] The present invention relates to the field of LED lamp bead luminescence technology, and in particular to a method and device for uniformly controlling the luminescence color of an LED lamp bead, and an LED lamp bead. Background Art

[0002] The uniformity of light emission and color stability of LED lamp beads have become key factors affecting product quality. At present, in the production process of LED lamp beads, due to the influence of packaging technology, material characteristics and environmental factors, there are common problems such as uneven light color, obvious color spots, and spectral drift, which seriously affects the application quality of LED products in the field of high-end display and lighting.

[0003] Traditional LED lamp bead packaging technology mainly adopts a single-layer packaging structure, which makes it difficult to effectively control the distribution uniformity of phosphors, and lacks a real-time monitoring and precise control mechanism for the luminous color. Existing color control methods mostly use a single parameter as the control basis, and fail to fully consider the synergistic relationship between spectral characteristics, chromaticity parameters and luminous flux, resulting in insufficient control accuracy and stability, and unable to meet the technical requirements of high-quality LED products. Traditional solutions are often limited to static optimization and lack dynamic compensation capabilities. Especially during long-term use, due to the influence of factors such as temperature changes and device aging, the luminous characteristics of LED lamp beads will drift. Existing technologies are difficult to achieve real-time precise control, which seriously restricts the application scope and service life of LED products. Summary of the invention

[0004] The present invention provides a method and device for uniformly controlling the luminous color of an LED lamp bead, and an LED lamp bead. The present invention improves the uniformity and stability of the luminous color of the LED lamp bead.

[0005] In a first aspect, the present invention provides a method for uniformly controlling the color of light emitted by an LED lamp bead, the method comprising: The LED chips are placed on the LED bracket in a triangular ring shape, the LED chips are connected by wires, and the first packaging glue and the second packaging glue are injected and centrifuged in sequence to obtain LED lamp beads with a double-layer packaging structure; Applying rated operating parameters to the LED lamp beads and collecting an initial optical parameter matrix; A standard data model is established based on the initial optical parameter matrix, and multi-parameter real-time monitoring of the LED lamp beads is performed to obtain a monitoring data set; Inputting the monitoring data set into a data processing unit, calculating the spectral deviation coefficient by a spectral similarity algorithm, calculating the chromaticity deviation coefficient by a Euclidean distance algorithm, and calculating the luminous flux deviation coefficient by a ratio algorithm to obtain a multidimensional deviation vector; Performing a weighted sum operation on the multi-dimensional deviation vector to obtain a comprehensive deviation evaluation value; Based on the comprehensive deviation evaluation value, a current correction amount and a voltage correction amount are generated, and the LED lamp bead is closed-loop controlled until the comprehensive deviation evaluation value is lower than a set threshold value, and a control termination signal is obtained.

[0006] In a second aspect, the present invention provides a device for uniformly controlling the color of light emitted by an LED lamp bead, the device comprising: The packaging module is used to place the LED chip in a triangular ring on the LED bracket, connect the LED chip with wires, inject the first packaging glue and the second packaging glue in sequence and perform centrifugal treatment to obtain an LED lamp bead with a double-layer packaging structure; A collection module, used for applying rated working parameters to the LED lamp beads and collecting an initial optical parameter matrix; A monitoring module, used to establish a standard data model based on the initial optical parameter matrix, perform multi-parameter real-time monitoring on the LED lamp beads, and obtain a monitoring data set; A calculation module, used for inputting the monitoring data set into a data processing unit, calculating the spectral deviation coefficient by a spectral similarity algorithm, calculating the chromaticity deviation coefficient by a Euclidean distance algorithm, calculating the luminous flux deviation coefficient by a ratio algorithm, and obtaining a multidimensional deviation vector; A summing module, used for performing a weighted summing operation on the multi-dimensional deviation vector to obtain a comprehensive deviation evaluation value; The control module is used to generate a current correction amount and a voltage correction amount based on the comprehensive deviation evaluation value, and perform closed-loop control on the LED lamp bead until the comprehensive deviation evaluation value is lower than a set threshold value, thereby obtaining a control termination signal.

[0007] A third aspect of the present invention provides an LED lamp bead, which, when in use, is used to implement the above-mentioned method for uniformly controlling the light emitting color of the LED lamp bead.

[0008] In the technical solution provided by the present invention, a triangular ring wafer arrangement and a double-layer packaging structure are adopted to significantly improve the uniformity and luminous efficiency of light, and the color spot problem of traditional LED lamp beads is effectively solved by accurately controlling the ratio and distribution of phosphor and diffusion powder. A multi-dimensional parameter real-time monitoring system including spectrum, chromaticity and luminous flux is established. Through high-precision sensors and synchronous acquisition technology, all-round dynamic monitoring of the optical characteristics of LED lamp beads is realized, and the monitoring accuracy is improved to 0.1nm. By integrating the bidirectional threshold recurrent neural network and PID control algorithm, adaptive adjustment of the luminous characteristics of LED lamp beads is realized, and the control accuracy reaches ±0.1%, which greatly improves the uniformity and stability of the luminous color. Through multi-dimensional deviation vector analysis and comprehensive evaluation mechanism, a complete closed-loop control system is established, which can compensate for the performance drift caused by environmental changes and device aging in real time, and extend the service life of LED lamp beads. The high-precision centrifugal packaging process and automatic control technology are adopted to significantly improve production efficiency and product consistency and reduce production costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0010] Figure 1 It is a schematic diagram of the steps of a method for uniformly controlling the light emission color of an LED lamp bead according to an embodiment of the present invention; Figure 2 Schematic diagram of the structure of the device for uniformly controlling the light color of LED lamp beads in an embodiment of the present invention. DETAILED DESCRIPTION

[0011] The embodiments of the present invention provide a method, device and LED lamp bead for uniformly controlling the luminous color of an LED lamp bead. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0012] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 , an embodiment of a method for uniformly controlling the light emission color of an LED lamp bead in an embodiment of the present invention includes: Step S1, placing the LED chip in a triangular ring shape on the LED bracket, connecting the LED chip with wires, injecting the first packaging glue and the second packaging glue in sequence and performing centrifugal treatment to obtain an LED lamp bead with a double-layer packaging structure; It is understandable that the execution subject of the present invention can be a device for controlling the uniform color of LED lamp beads, or a terminal or a server, which is not limited here. The embodiment of the present invention is described by taking the server as the execution subject as an example.

[0013] Specifically, the LED bracket is surface treated to ensure that the subsequent coating can be firmly attached. An aluminum oxide reflective layer is coated on the inner wall of the LED bracket, and a high-temperature sintering process is used to tightly combine the reflective layer with the bracket structure to improve the reflective performance of the bracket. The treated LED chip is placed on the bracket structure to ensure that the LED chip forms an angle of 60° with the horizontal direction. This design helps to achieve a good optical layout in the triangular ring array. Through a precise positioning system, the chips are evenly arranged in a triangular pattern to form a chip array structure. The chip array structure is gold wire bonded. The LED chip is connected to the conductive pad of the bracket structure through an automatic wire bonding system to ensure the reliability of the electrical connection to obtain a good conduction structure. The phosphor with a particle size of 10 microns is mixed with epoxy resin in a mass ratio of 4:6, and a high-speed stirring device is used for sufficient dispersion treatment to ensure that the phosphor is evenly distributed in the resin and improve the optical properties of the encapsulation glue. The treated first encapsulation glue is injected into the conduction structure, and the injection amount is strictly controlled by a weight sensor to ensure that the injection amount error is controlled within the range of ±0.1mg, so as to obtain a uniform and suitable thickness of the first encapsulation layer. After completing the first layer of packaging, place it in a centrifuge at a speed of 3000 rpm for centrifugal treatment for 300 seconds, so that the phosphor can be evenly distributed around the LED chip to form an ideal coating structure. The diffusion powder and epoxy resin are mixed at a mass ratio of 1.2:98.8, and high-speed stirring equipment is also used to ensure that the two are fully dispersed to obtain a uniform second packaging glue. When the second packaging glue is injected into the coating structure, the injection amount and injection angle are adjusted by the CNC system to ensure that the second packaging glue formed has a concave structure with a curvature radius of 1.5 times the diameter of the packaging surface, which enhances the light scattering effect and effectively improves the uniformity of the LED lamp bead. After completing these steps, the final LED lamp bead has a double-layer packaging structure.

[0014] Step S2, applying rated operating parameters to the LED lamp beads and collecting the initial optical parameter matrix; Specifically, the environmental parameters of the LED lamp beads are controlled. Under standard environmental conditions, that is, the temperature is 25°C and the relative humidity is 60%, a preheating treatment is performed to ensure that the LED lamp beads reach a stable working state. At this stage, the purpose of the preheating treatment is to eliminate the instability of optical properties caused by temperature fluctuations or humidity changes, and to ensure the reliability and consistency of subsequent test results. The rated working parameters are applied to the LED lamp beads in a stable working state, with the voltage set to 3.0V and the current set to 350mA. These parameters are powered by a high-precision DC power supply to ensure that the LED lamp beads operate normally under the specified electrical conditions and maintain their stable power supply state. After the LED lamp beads reach a stable power supply state, a spectrum analyzer with a resolution of 0.1nm is used to align the light-emitting surface of the LED lamp beads and perform scanning and acquisition in the wavelength range of 380-780nm. The spectrum analyzer can obtain the spectral intensity distribution data of the LED lamp beads at different wavelengths, reflecting the spectral characteristics of the lamp beads. At the same time, the chromaticity parameters of the light-emitting surface of the LED lamp beads are measured. The colorimeter is used to measure at a distance of 100 mm from the luminous surface, and the CIE chromaticity coordinate values ​​are collected to obtain the chromaticity distribution data. The LED lamp bead is placed at the center of the integrating sphere, and the luminous flux value is collected with the help of a luminous flux sensor to obtain the luminous flux data. The spectral intensity distribution data is divided into wavelength intervals, and the discrete wavelength points are numerically fitted by an interpolation algorithm to obtain a continuous spectral curve. The chromaticity distribution data and the luminous flux data are fused, and the normalized parameter values ​​are obtained through standardization processing to form standardized data. The continuous spectral curve is combined with the standardized data by matrix synthesis operation, and a three-dimensional data structure is generated by a data reconstruction algorithm, and finally the initial optical parameter matrix is ​​obtained.

[0015] Step S3, establishing a standard data model based on the initial optical parameter matrix, performing multi-parameter real-time monitoring of LED lamp beads, and obtaining a monitoring data set; Specifically, the initial optical parameter matrix is ​​parameterized. The matrix decomposition algorithm is used to convert the spectrum data, chromaticity data and luminous flux data into a feature matrix, extract the standard optical characteristics of the LED lamp beads, and reduce the complexity of the data. For example, the feature matrix contains key indicators such as color temperature and color rendering index, which accurately reflect the optical characteristics of the LED lamp beads under different working conditions. A three-dimensional parameter space is constructed based on the standard optical characteristics to visualize the changing relationship between the spectrum, chromaticity and luminous flux. The spectrum curve model, chromaticity distribution model and luminous flux change model are fitted by the least squares method to form a standard mathematical model to describe the performance of LED lamp beads under ideal conditions and provide a prediction basis for various situations encountered by the lamp beads in practical applications. The constructed standard mathematical model is input into the Kalman filter, and a dynamic prediction model is established through the state prediction algorithm. The model can be updated in real time, and the prediction value is continuously adjusted according to the real-time collected data to improve the monitoring and control of the lamp bead performance. For example, if the spectrum data is found to deviate from the expectation, the system can quickly feedback and adjust the current or voltage to restore it to its normal state. The parameter threshold is set based on the standard data model. Through the interval control algorithm, the spectral fluctuation range, chromaticity offset range and luminous flux variation range are determined to form a clear parameter control range. The setting of the control range directly affects the luminous effect and stability of the LED lamp beads. Reasonable threshold setting can effectively prevent performance degradation caused by temperature changes, aging and other factors, and ensure that the lamp beads always maintain efficient luminous effects under different working conditions. In order to achieve efficient real-time monitoring, a multi-channel data acquisition system with a sampling frequency of 1000Hz is used to synchronously capture spectral, chromaticity and luminous flux data. High-frequency data acquisition can timely capture instantaneous changes in the lamp beads during use, ensuring that the system can respond quickly when performance changes. The real-time sampling data is input into the standard data model, and the deviation between the current state and the predicted state is calculated by the state estimation algorithm. The quantification of the deviation enables the system to identify whether the performance of the LED lamp beads is abnormal. If the deviation exceeds the set range, an alarm is issued or automatically adjusted to ensure the normal operation of the lamp beads. In the abnormality detection link, the Mahalanobis distance algorithm is used to determine whether the collected data falls within the set parameter control range. In this way, potential abnormal data can be quickly identified and the data is marked for validity. The data marked as valid is reorganized in time series. Through the data encapsulation algorithm, the spectral data, chromaticity data and luminous flux data are integrated into a unified format to form a complete monitoring data set.

[0016] Step S4, inputting the monitoring data set into the data processing unit, calculating the spectral deviation coefficient by the spectral similarity algorithm, calculating the chromaticity deviation coefficient by the Euclidean distance algorithm, calculating the luminous flux deviation coefficient by the ratio algorithm, and obtaining a multidimensional deviation vector; Specifically, the real-time spectral data in the monitoring data set is Fourier transformed, the spectral signal is converted from the time domain to the frequency domain, the spectral frequency components are extracted, and the spectral frequency domain characteristics are obtained to reveal the frequency components of the luminous characteristics of the lamp beads, which is helpful for analyzing their optical properties. The cosine similarity between the spectral frequency domain characteristics and the spectral data in the standard data model is calculated. Through this algorithm, the similarity between the current spectrum and the standard spectrum is judged, and the spectral deviation is quantified. Through normalization processing, the calculation results are adjusted to the range of 0 to 1, eliminating the influence of different dimensions, and obtaining the spectral deviation coefficient.

[0017] At the same time, the real-time chromaticity data is converted into three-dimensional chromaticity space coordinates. Through the coordinate mapping algorithm, the chromaticity space distribution points are generated to form a chromaticity space vector, which accurately reflects the chromaticity performance of the lamp beads. The Euclidean distance between the chromaticity space vector and the chromaticity data in the standard data model is calculated, and this distance value is mapped to the interval of 0 to 1 through standardization processing to obtain the chromaticity deviation coefficient. The real-time luminous flux data is reconstructed according to the time series. Through the sliding window algorithm, the luminous flux time series curve is generated to obtain the luminous flux sequence, which helps to identify the law of luminous flux change over time. The luminous flux sequence is ratioed with the luminous flux value in the standard data model, and the ratio result is converted into a linear relationship through logarithmic transformation to more clearly show the degree of luminous flux deviation and obtain the luminous flux deviation coefficient. A three-dimensional feature space is constructed based on the spectral deviation coefficient, the chromaticity deviation coefficient and the luminous flux deviation coefficient. Based on these three deviation coefficients, orthogonal processing is performed to generate a standard feature basis. By constructing a feature basis matrix, a unified reference framework is provided for subsequent data analysis. The spectral deviation coefficient, chromaticity deviation coefficient and luminous flux deviation coefficient are projected on the characteristic basis matrix. Through this matrix operation, a multi-dimensional deviation vector is generated, which comprehensively reflects the performance deviation of LED lamp beads in the three dimensions of spectrum, chromaticity and luminous flux.

[0018] Step S5, performing a weighted sum operation on the multi-dimensional deviation vector to obtain a comprehensive deviation evaluation value; Specifically, the principal component analysis is performed on the multidimensional deviation vector, and the main characteristic components and secondary characteristic components are extracted by the singular value decomposition algorithm to obtain the characteristic component sequence. The most representative features in multiple dimensions such as spectrum, chromaticity and luminous flux are identified. Through singular value decomposition, high-dimensional data is effectively reduced to lower dimensions while retaining as much original information as possible. The characteristic component sequence is orthogonally transformed, and the standard orthogonal basis vectors are constructed using the Schmidt orthogonalization algorithm to form an orthogonal basis matrix. The construction of the orthogonal basis matrix helps to eliminate the correlation between features and improve the stability and accuracy of subsequent calculations. Each column of the orthogonal basis matrix represents an independent characteristic direction, so that the changes in the luminous characteristics of the lamp beads can be more accurately captured during data processing. The orthogonal basis matrix is ​​reduced in dimension according to the contribution rate of the main and secondary features. The method of truncating singular values ​​is used to retain the main characteristic dimensions and generate a reduced dimension feature matrix. Through the dimensionality reduction process, the complexity of the calculation can be effectively reduced, while avoiding the risk of overfitting, ensuring that only the features that have the greatest impact on performance are retained in feature selection. Based on the reduced dimension feature matrix, a weight distribution model is constructed. The initial weight values ​​of the spectral deviation coefficient, chromaticity deviation coefficient and luminous flux deviation coefficient are calculated by the coefficient of variation method. An initial relative importance index is assigned to each feature to reflect its role in the overall performance evaluation. The coefficient of variation can effectively measure the degree of fluctuation of each feature and help determine which feature occupies a more important position in the overall performance. The initial weight value is analyzed hierarchically. The rationality of the weight distribution is verified by the consistency test algorithm to obtain the modified weight coefficient to ensure that the weight relationship between different features is reasonable and avoid errors caused by subjective setting of the weight ratio. After the consistency test, if it is found that the weight of some features deviates significantly from the expectation, the modified weight coefficient is adjusted to make it more in line with the actual situation. The modified weight coefficient is linearly combined with the preset weight ratio (such as 0.4:0.4:0.2) to generate the target weight coefficient. Based on the generated target weight coefficient, the multi-dimensional deviation vector is weighted and fused. The weighted deviation value is generated by matrix multiplication operation, which can comprehensively consider the influence of features of different dimensions and form a comprehensive evaluation index. The normalized deviation value is nonlinearly mapped and compressed to the range of 0 to 1 using the sigmoid function to improve the stability of the data, making the final comprehensive deviation evaluation value easier to understand and use. The comprehensive deviation evaluation value calculated through the above steps can fully reflect the luminous performance of the LED lamp bead. Through this evaluation value, the control system monitors and adjusts the working status of the lamp bead in real time to ensure that its luminous color remains within a uniform range.

[0019] Step S6: Based on the comprehensive deviation evaluation value, generate a current correction amount and a voltage correction amount, and perform closed-loop control on the LED lamp beads until the comprehensive deviation evaluation value is lower than the set threshold, and a control termination signal is obtained.

[0020] Specifically, the comprehensive deviation evaluation value is input into the parameter prediction model, which adopts a bidirectional threshold recurrent neural network. The network consists of an input layer, a hidden layer and a fully connected layer, wherein the hidden layer includes a forward threshold recurrent unit and a reverse threshold recurrent unit. After the input layer receives the comprehensive deviation evaluation value, the forward threshold recurrent unit extracts the forward time series features, while the reverse threshold recurrent unit extracts the reverse time series features. After being processed by these two units, the feature information is fused into the fully connected layer to obtain the initial compensation parameters. The initial compensation parameters are processed by the self-attention mechanism. The attention weight matrix is ​​obtained by calculating the dot product operation of the query matrix, the key matrix and the value matrix, and after softmax normalization. The weight matrix helps to emphasize the more important features in the initial compensation parameters, thereby improving the effectiveness and accuracy of subsequent calculations. Based on the attention weight matrix, the initial compensation parameters are weighted, and feature enhancement is performed through the multi-head attention mechanism. In this process, each attention head independently calculates its attention score and extracts features to obtain an enhanced feature vector. The enhanced eigenvector is input into the PID controller, and the parameters are adjusted using the proportional coefficient of 0.8, the integral coefficient of 0.3 and the differential coefficient of 0.1 to obtain the PID compensation parameters. The adjustment mechanism of the PID controller can make adaptive adjustments based on the current deviation and historical data, so that the control process can respond to the deviation changes more quickly and accurately, and realize the effective control of the LED lamp beads. Through adjustment, the appropriate current correction and voltage correction can be generated to ensure that the lamp beads emit light evenly under different working conditions. The current and voltage corrections are input into a high-precision digital-to-analog converter, usually a 16-bit DAC, to achieve signal conversion. This process also includes PWM modulation to output the drive signal and obtain the corrected working parameters. The corrected working parameters are monitored and adjusted in real time through a closed-loop control system. By comparing the corrected working parameters with the set threshold, the comprehensive deviation evaluation value is monitored in real time to determine whether the control achieves the expected effect. If the comprehensive deviation evaluation value is lower than the set threshold, a control termination signal is issued. At the same time, the comparison result will be fed back to the input layer of the bidirectional threshold recurrent neural network to ensure that the network can self-adjust according to the latest data and further optimize the control process. The closed-loop control mechanism ensures that the LED lamp beads always emit uniform light color under different working conditions, improving their overall performance and user experience.

[0021] In the embodiment of the present invention, a triangular ring wafer arrangement and a double-layer packaging structure are adopted to significantly improve the uniformity and luminous efficiency of light. By accurately controlling the ratio and distribution of phosphor and diffusion powder, the color spot problem of traditional LED lamp beads is effectively solved. A multi-dimensional parameter real-time monitoring system including spectrum, chromaticity and luminous flux is established. Through high-precision sensors and synchronous acquisition technology, all-round dynamic monitoring of the optical characteristics of LED lamp beads is realized, and the monitoring accuracy is improved to 0.1nm. By integrating the bidirectional threshold recurrent neural network and PID control algorithm, adaptive adjustment of the luminous characteristics of LED lamp beads is realized, and the control accuracy reaches ±0.1%, which greatly improves the uniformity and stability of the luminous color. Through multi-dimensional deviation vector analysis and comprehensive evaluation mechanism, a complete closed-loop control system is established, which can compensate for the performance drift caused by environmental changes and device aging in real time, and extend the service life of LED lamp beads. The high-precision centrifugal packaging process and automatic control technology are adopted to significantly improve production efficiency and product consistency and reduce production costs.

[0022] In a specific embodiment, the process of executing step S1 may specifically include the following steps: The LED bracket is subjected to surface treatment, an aluminum oxide reflective layer is coated on the inner wall of the LED bracket, and the reflective layer is combined with the bracket through a high-temperature sintering process to obtain a bracket structure; The LED chips are placed on the support structure so that the LED chips form a 60° angle with the horizontal direction, and arranged in a triangular ring array through a positioning system to obtain a chip array structure; Gold wire bonding is performed on the chip array structure, and the LED chip and the conductive pad of the bracket structure are connected by an automatic wire bonding system to obtain a conductive structure; A phosphor with a particle size of 10 microns is mixed with an epoxy resin in a mass ratio of 4:6, and dispersed by a high-speed stirring device to obtain a first packaging glue, and the first packaging glue is injected into the conductive structure, and the injection amount is controlled by a weight sensor so that the injection amount error is controlled within the range of ±0.1mg to obtain a first packaging layer; The first packaging layer is placed in a centrifuge at a speed of 3000 rpm, and the phosphor is evenly distributed around the LED chip by centrifugation for 300 seconds to obtain a coating structure, and the diffusion powder and epoxy resin are mixed at a mass ratio of 1.2:98.8, and dispersed by a high-speed stirring device to obtain a second packaging glue; The second packaging glue is injected into the coating structure, and the injection amount and injection angle are adjusted by the numerical control system so that the second packaging glue forms a concave structure with a curvature radius of 1.5 times the diameter of the packaging surface, thereby obtaining an LED lamp bead with a double-layer packaging structure.

[0023] Specifically, the surface of the LED bracket is treated, and an aluminum oxide reflective layer is coated on the inner wall of the LED bracket. Aluminum oxide, as an excellent reflective material, can effectively enhance the light efficiency of the LED. The treatment of its inner wall usually involves a high-temperature sintering process. In this process, the aluminum oxide reflective layer is combined with the inner wall of the bracket under a high temperature environment to form a solid bracket structure with good reflective performance. Assume that the thickness of the bracket is The thickness of the aluminum oxide layer is , during the sintering process, the bonding strength between the reflective layer and the bracket is described by the following formula: ; in, is the bonding strength, is the reflectivity of aluminum oxide, is the reflectivity of the support material. This bonding strength directly affects the overall performance of the LED lamp bead. The LED chip is placed on the support structure to ensure that the LED chip forms an angle of 60° with the horizontal direction. This design helps to improve the efficiency of light divergence and improve the uniformity of light. In this process, the positioning system is used to ensure that the chips are arranged in a triangular ring array to form a chip array structure. This layout can effectively disperse the LED light source in space and improve the overall brightness. Gold wire bonding is performed on the chip array structure. Through the automatic wire bonding system, the LED chip is connected to the conductive pad of the support structure to form a conductive structure. In this process, the accuracy and consistency of the wire bonding are crucial to ensure the flow of current. Through precise control, the reliability of the LED can be greatly improved. The phosphor with a particle size of 10 microns is mixed with epoxy resin in a mass ratio of 4:6, and then dispersed by a high-speed stirring device to ensure that the phosphor is evenly distributed in the colloid to form a high-performance first encapsulation glue. The first encapsulation glue is injected into the conductive structure, and the injection amount is controlled by a weight sensor to ensure that the error is controlled within the range of ±0.1mg to obtain the first encapsulation layer. Place the first packaging layer in a centrifuge with a speed of 3000 rpm. After 300 seconds of centrifugation, the phosphor is evenly distributed around the LED chip to form a coating structure. The uniform distribution can ensure that the LED can provide stable light output when working. Mix the diffusion powder and epoxy resin in a mass ratio of 1.2:98.8, and also disperse them through a high-speed stirring equipment to obtain the second packaging glue to improve the diffusion of light and enhance the uniformity of light. When injecting the second packaging glue into the coating structure, the CNC system is used to adjust the injection amount and injection angle to ensure that the second packaging glue forms a concave structure with a curvature radius of 1.5 times the diameter of the packaging surface. The set curvature radius Diameter of package surface The relationship is expressed by the following formula: ; The concave design can enhance the focusing effect of light, thereby improving the overall luminous efficiency and lighting effect.

[0024] In a specific embodiment, the process of executing step S2 may specifically include the following steps: The environmental parameters of the LED lamp beads are controlled, and preheating treatment is performed in a standard environment with a temperature of 25°C and a relative humidity of 60% to obtain LED lamp beads in a stable working state; Apply the rated working parameters of 3.0V voltage and 350mA current to the LED lamp beads in stable working state, and control the power supply through a high-precision DC power supply to obtain a stable power supply state; A spectrum analyzer with a resolution of 0.1nm is aimed at the light-emitting surface of the LED lamp bead, and scanning and collecting data in the wavelength range of 380-780nm is performed to obtain the spectral intensity distribution data; The chromaticity parameters of the light-emitting surface of the LED lamp bead are measured, and the CIE chromaticity coordinate values ​​are collected by a colorimeter at a distance of 100 mm from the light-emitting surface to obtain the chromaticity distribution data; Place the LED lamp bead at the center of the integrating sphere, collect the luminous flux value through the luminous flux sensor, obtain the luminous flux data, divide the spectral intensity distribution data into wavelength intervals, and numerically fit the discrete wavelength points through the interpolation algorithm to obtain a continuous spectrum curve; The chromaticity distribution data and the luminous flux data are fused, and the normalized parameter value is obtained through standardization processing to obtain standardized data. The continuous spectral curve and the standardized data are subjected to matrix synthesis operation, and a three-dimensional data structure is generated through a data reconstruction algorithm to obtain an initial optical parameter matrix.

[0025] Specifically, the environmental parameters of the LED lamp beads are controlled. Preheating treatment is carried out in a standard environment with a temperature of 25°C and a relative humidity of 60% to eliminate the fluctuation of photoelectric performance caused by environmental factors and ensure that the LED lamp beads can perform at their best in a stable environment. The preheating stage is a thermal equilibrium process, and its temperature and humidity Described by the following formula: ; in, It is the environmental effect. and are the influence coefficients of temperature and humidity, and It is the reference temperature and humidity of the environment. By adjusting these parameters, the LED lamp beads can reach a stable working state. After the LED lamp beads reach a stable working state, the rated working parameters are applied. A voltage of 3.0V and a current of 350mA are provided, and the power supply is controlled by a high-precision DC power supply. This power supply can ensure the accuracy of current and voltage, thereby avoiding performance fluctuations caused by unstable power supply. The stability of the power supply state is crucial to the light output and color stability of the LED lamp beads. A spectrum analyzer with a resolution of 0.1nm is used to align the light-emitting surface of the LED lamp bead, and scan and collect in the wavelength range of 380-780nm to obtain spectral intensity distribution data. Spectral intensity distribution It is expressed as: ; in, is the spectral output of the luminescent source, is the response function of the spectrum analyzer. While acquiring the spectral data, the chromaticity parameters of the light-emitting surface of the LED lamp bead are measured. The CIE chromaticity coordinate values ​​are collected by a colorimeter at a distance of 100mm from the light-emitting surface to obtain the chromaticity distribution data. In this way, the color performance of the LED lamp bead under specific conditions can be obtained, and the understanding of its performance can be enhanced. The LED lamp bead is placed at the center of the integrating sphere, and the luminous flux value is collected by a luminous flux sensor to obtain the luminous flux data to ensure that the light output capacity of the LED can be accurately measured. At the same time, in order to analyze the spectral intensity distribution data, it is divided into wavelength intervals, and the discrete wavelength points are numerically fitted by an interpolation algorithm to obtain a continuous spectral curve. The mathematical expression of this process is expressed by the following formula: ; in, is a continuous curve of spectral intensity, is at discrete wavelengths The spectral intensity under is the weight of each wavelength. By fusing the chromaticity distribution data with the luminous flux data, a more comprehensive optical property is obtained. The data of different dimensions are unified through standardization processing to obtain the normalized parameter value. On this basis, the continuous spectrum curve is combined with the standardized data through matrix synthesis operation, and the three-dimensional data structure is generated by the data reconstruction algorithm to obtain the initial optical parameter matrix.

[0026] In a specific embodiment, the process of executing step S3 may specifically include the following steps: The initial optical parameter matrix is ​​decomposed, and the spectrum data, chromaticity data and luminous flux data are converted into a feature matrix through a matrix decomposition algorithm to obtain the standard optical characteristics of the LED lamp beads; A three-dimensional parameter space is constructed based on standard optical characteristics, and the standard mathematical model of LED lamp beads is obtained by fitting the spectrum curve model, chromaticity distribution model and luminous flux change model through the least squares method. The standard mathematical model is input into the Kalman filter, and a dynamic prediction model of spectrum, chromaticity and luminous flux is established through a state prediction algorithm to obtain a standard data model; The parameter threshold is set based on the standard data model, and the spectral fluctuation range, chromaticity shift range and luminous flux variation range are determined by the interval control algorithm to obtain the parameter control range; Monitor LED lamp beads in real time, and synchronously collect spectrum, chromaticity and luminous flux data through a multi-channel data acquisition system with a sampling frequency of 1000Hz to obtain real-time sampling data; Input the real-time sampling data into the standard data model, calculate the deviation between the current state and the predicted state through the state estimation algorithm, and obtain the state deviation data; Anomaly detection is performed based on state deviation data, and the Mahalanobis distance algorithm is used to determine whether the data falls within the parameter control range to obtain the data validity mark; The data marked as valid are reorganized in time sequence, and the spectral data, chromaticity data and luminous flux data are integrated into a unified format through a data encapsulation algorithm to obtain a monitoring data set.

[0027] Specifically, the initial optical parameter matrix is ​​decomposed, and the spectrum data, chromaticity data and luminous flux data are converted into a feature matrix through a matrix decomposition algorithm to extract the standard optical characteristics of the LED lamp beads. Using the singular value decomposition technology, the initial optical parameter matrix is ​​assumed to be , then its decomposition is expressed as: ; in, is the left singular vector matrix, is a diagonal matrix containing singular values, is the right singular vector matrix. Through this decomposition, the characteristic matrix is ​​extracted , which is used for subsequent model construction and analysis. A three-dimensional parameter space is constructed based on standard optical characteristics, and the spectral curve model, chromaticity distribution model and luminous flux change model are fitted using the least squares method. , expressed as: ; in, is the observation data, is the fitting function, is the independent variable. Through this method, the standard mathematical model of LED lamp beads can be obtained, reflecting the changes of its optical properties under different conditions. The standard mathematical model is input into the Kalman filter, and the dynamic prediction model of spectrum, chromaticity and luminous flux is established through the state prediction algorithm to obtain the standard data model. In this process, the state transfer equation of the Kalman filter is expressed as: ; in, is the current state, is the state transition matrix, is the control input matrix, is the control input, It is process noise. By continuously updating the state estimation, the optical property changes of LED lamp beads during operation can be accurately predicted. Based on the standard data model, the parameter threshold is set, and the spectral fluctuation range, chromaticity shift range and luminous flux change range are determined by the interval control algorithm. The standard deviation of each parameter is obtained through statistical analysis. and mean , used to set the control interval, for example: ; in, Is a constant used to determine the strictness of control. The control interval is established to ensure that the LED lamp beads are always in a controllable state during operation to avoid excessive fluctuations. The LED lamp beads are monitored in real time, and a multi-channel data acquisition system with a sampling frequency of 1000Hz is used to synchronously collect spectrum, chromaticity and luminous flux data to obtain real-time sampling data to ensure that during the operation of the LED lamp beads, various parameter changes can be responded to in a timely manner to maintain performance stability. The real-time sampling data is input into the standard data model, and the deviation between the current state and the predicted state is calculated through the state estimation algorithm to obtain the state deviation data. State deviation It is expressed as: ; By analyzing this deviation, we can identify whether there is an abnormal situation. Based on the state deviation data, we perform anomaly detection and use the Mahalanobis distance algorithm to determine whether the data falls within the set parameter control range. The calculation formula is: ; in, is the current state vector, is the mean vector, is the covariance matrix. By judging whether the distance exceeds the set threshold, the data validity mark is obtained. The data marked as valid are reorganized in time sequence, and the spectral data, chromaticity data and luminous flux data are integrated into a unified format through the data packaging algorithm to obtain the monitoring data set.

[0028] Among them, the real-time sampling data is input into the standard data model, the deviation between the current state and the predicted state is calculated by the state estimation algorithm, and the state deviation data is obtained; anomaly detection is performed based on the state deviation data, and the Mahalanobis distance algorithm is used to determine whether the data falls within the parameter control interval to obtain a data validity mark, including the following steps: the real-time sampling data is separated into three groups of characteristic data: spectral data, chromaticity data and luminous flux data, and the current state vector is obtained; data smoothing is performed on the current state vector, and random fluctuations are eliminated by the sliding average method to obtain smoothed state data; the smoothed state data is input into the standard data model, and the predicted value of the next moment is calculated according to historical data to obtain a predicted state vector; the current state vector is smoothed. The difference between the quantity and the predicted state vector is calculated to obtain a state deviation matrix; the state deviation matrix is ​​standardized and converted into a standard score through a normalization operation to obtain a standardized deviation value; the Mahalanobis distance is calculated based on the standardized deviation value to obtain a distance evaluation value; the distance evaluation value is compared with a preset parameter control interval to obtain an out-of-bounds judgment result; a marking rule is set based on the out-of-bounds judgment result, and data with a distance evaluation value exceeding the control interval is marked as abnormal to obtain an initial marking sequence; a time series association analysis is performed on the initial marking sequence to determine the duration of the abnormality and obtain a time series association mark; the time series association mark is converted into a binary sequence to generate 0-1 marking data to obtain a data validity mark.

[0029] In a specific embodiment, the process of executing step S4 may specifically include the following steps: The real-time spectral data in the monitoring data set is Fourier transformed, and the spectral frequency components are extracted through the spectrum analysis algorithm to obtain the spectral frequency domain characteristics; The cosine similarity between the spectral frequency domain features and the spectral data in the standard data model is calculated, and the spectral similarity value between 0 and 1 is obtained by normalization, and the spectral deviation coefficient is obtained; The real-time chromaticity data in the monitoring data set is converted into three-dimensional chromaticity space coordinates, and the chromaticity space distribution points are generated through the coordinate mapping algorithm to obtain the chromaticity space vector; The Euclidean distance between the chromaticity space vector and the chromaticity data in the standard data model is calculated, and the distance value is mapped to the range of 0-1 through standardization to obtain the chromaticity deviation coefficient; The real-time luminous flux data in the monitoring data set is reconstructed according to the time series, and the luminous flux time series curve is generated by the sliding window algorithm to obtain the luminous flux sequence. The luminous flux sequence is then ratio-calculated with the luminous flux value in the standard data model, and the ratio result is converted into a linear relationship by logarithmic transformation to obtain the luminous flux deviation coefficient. A three-dimensional feature space is constructed based on the spectral deviation coefficient, the chromaticity deviation coefficient and the luminous flux deviation coefficient, and a standard feature basis is generated through orthogonalization to obtain a feature basis matrix. The spectral deviation coefficient, chromaticity deviation coefficient and luminous flux deviation coefficient are projected and transformed on the characteristic basis matrix, and a multi-dimensional deviation vector is generated through matrix operation.

[0030] Specifically, the real-time spectral data in the monitoring data set is subjected to Fourier transform. The spectral frequency components are extracted through the spectrum analysis algorithm to obtain the spectral frequency domain characteristics. The basic formula of Fourier transform is: ; in, represents the frequency domain signal, is the time domain signal, is the frequency, is an imaginary unit. By performing Fourier transform on real-time spectral data, the intensity and phase information of each frequency component in the spectrum are identified, and the spectral frequency domain features are obtained. These features can provide important information about the luminous characteristics of LED lamp beads. The extracted spectral frequency domain features are calculated by cosine similarity with the spectral data in the standard data model to obtain the spectral deviation coefficient. The formula for cosine similarity is: ; in, and Represent two spectral frequency domain eigenvectors, is the norm of the vector. Through normalization, the cosine similarity value is limited to between 0 and 1, and the spectral deviation coefficient is obtained, which effectively quantifies the difference between the current spectrum and the standard spectrum, and helps the system determine whether the luminous performance of the LED lamp beads meets expectations. When processing chromaticity data, the real-time chromaticity data is converted into three-dimensional chromaticity space coordinates, which usually relies on the CIE chromaticity coordinate system. The chromaticity space distribution points are generated through the coordinate mapping algorithm to obtain the chromaticity space vector. The Euclidean distance between the chromaticity space vector and the chromaticity data in the standard data model is calculated to obtain the chromaticity deviation coefficient. The formula for the Euclidean distance is: ; in, Represents distance, and is the corresponding coordinate value in the chromaticity space, is the number of dimensions. The distance value obtained is mapped to the range of 0 to 1 through standardization to generate the chromaticity deviation coefficient. The real-time luminous flux data in the monitoring data set is reconstructed according to the time series, and the luminous flux time series curve is generated using the sliding window algorithm to obtain the luminous flux sequence. The luminous flux sequence is ratioed with the luminous flux value in the standard data model, and the ratio result is converted into a linear relationship through logarithmic transformation to obtain the luminous flux deviation coefficient. The ratio operation is expressed by the following formula: ; in, is the ratio, is the measured luminous flux value, is the standard luminous flux value. The logarithmic transformation is expressed as: ; Through the above steps, the spectral deviation coefficient, chromaticity deviation coefficient and luminous flux deviation coefficient are calculated, and these coefficients together construct a three-dimensional feature space. In order to better utilize these deviation coefficients, orthogonalization is performed to generate a standard characteristic basis and obtain a characteristic basis matrix. The characteristic basis matrix is ​​a linear space containing the relationship between each deviation coefficient, expressed as: ; In this matrix, each row represents a deviation coefficient. The spectral deviation coefficient, chromaticity deviation coefficient and luminous flux deviation coefficient are projected on the characteristic basis matrix, and a multi-dimensional deviation vector is generated through matrix operation.

[0031] In a specific embodiment, the process of executing step S5 may specifically include the following steps: Perform principal component analysis on the multidimensional deviation vector, extract the main characteristic components and secondary characteristic components through the singular value decomposition algorithm, and obtain the characteristic component sequence; The characteristic component sequence is orthogonally transformed, and the standard orthogonal basis vector is constructed by the Schmidt orthogonalization algorithm to obtain the orthogonal basis matrix. The orthogonal basis matrix is ​​reduced in dimension according to the primary and secondary characteristic contribution rates, and the main characteristic dimensions are retained by the truncated singular value method to obtain the reduced dimension characteristic matrix. A weight distribution model is constructed based on the dimension-reduced feature matrix, and the initial weight values ​​of the spectral deviation coefficient, chromaticity deviation coefficient and luminous flux deviation coefficient are calculated by the coefficient of variation method. Perform hierarchical analysis on the initial weight values, verify the rationality of weight allocation through consistency check algorithm, obtain revised weight coefficients, and linearly combine the revised weight coefficients with the preset weight ratio of 0.4:0.4:0.2 to generate the target weight coefficients through weighted average algorithm; The multidimensional deviation vector is weighted and fused based on the target weight coefficient, and the weighted deviation value is generated through matrix multiplication operation to obtain the normalized deviation value. The normalized deviation value is nonlinearly mapped and the deviation value is compressed to the range of 0-1 through the sigmoid function to obtain the comprehensive deviation evaluation value.

[0032] Specifically, the principal component analysis is performed on the multidimensional deviation vector, and the main characteristic components and secondary characteristic components are extracted by the singular value decomposition algorithm to obtain the characteristic component sequence. The basic formula of singular value decomposition is: ; in, represents the data matrix, is a left singular matrix, is a diagonal matrix where the diagonal elements are singular values, is the transpose of the right singular matrix. Through singular value decomposition, the original data is decomposed into different characteristic components, the main variation direction in the data is found, the main characteristic components are extracted, and the secondary characteristic components are screened out to form a characteristic component sequence. The characteristic component sequence is orthogonally transformed to ensure the independence of each characteristic component, and the Schmidt orthogonalization algorithm is used. Through Schmidt orthogonalization, the standard orthogonal basis vector is constructed to obtain the orthogonal basis matrix. The characteristic component sequence is expressed as: ; in, Indicates Orthogonal basis vectors. The orthogonal basis matrix is ​​subjected to dimensionality reduction processing, and is screened according to the contribution rate of primary and secondary features, and the main feature dimensions are retained by truncating singular values ​​to obtain a reduced-dimensional feature matrix. The dimensionality reduction process is represented by the following relationship: ; in, represents the data matrix after dimensionality reduction, is the selected orthogonal basis vector matrix, is the corresponding singular value matrix. Based on the dimension-reduced feature matrix, a weight distribution model is constructed. The initial weight values ​​of the spectral deviation coefficient, chromaticity deviation coefficient, and luminous flux deviation coefficient are calculated by the coefficient of variation method. The formula for the coefficient of variation is: ; in, represents the coefficient of variation, is the standard deviation, is the mean. By calculating the coefficient of variation of each deviation coefficient, the corresponding initial weight value is obtained to reflect the relative importance of each deviation. A hierarchical analysis is performed on the initial weight value, and the rationality of the weight allocation is verified by the consistency test algorithm. When performing the consistency test, the consistency ratio (CR) is used to determine whether the weight allocation is appropriate. The formula is: ; in, is a consistency indicator, is a random consistency indicator. If , then the weight distribution is reasonable, otherwise the weight distribution needs to be re-evaluated. After obtaining the modified weight coefficient, it is linearly combined with the preset weight ratio (such as 0.4:0.4:0.2) to generate the target weight coefficient through the weighted average algorithm. It can be expressed as: ; in, is the target weight coefficient, , , is the weight value of each corrected deviation coefficient. Based on the target weight coefficient, the multi-dimensional deviation vector is weighted and fused. This step involves matrix multiplication to generate weighted deviation values, which are expressed as: ; in, is the weighted deviation value, is the target weight coefficient matrix, is a multidimensional deviation vector. The weighted deviation value is normalized and nonlinearly mapped, and the deviation value is compressed to the range of 0-1 through the sigmoid function. The formula is: ; in, is the output of the sigmoid function, is the normalized deviation value of the input. Through this process, the comprehensive deviation evaluation value is obtained, which can effectively reflect the performance and stability of LED lamp beads in all aspects.

[0033] Among them, a weight allocation model is constructed based on the reduced dimension feature matrix, and the initial weight values ​​of the spectral deviation coefficient, chromaticity deviation coefficient and luminous flux deviation coefficient are calculated by the coefficient of variation method; the initial weight values ​​are subjected to hierarchical analysis, and the rationality of the weight allocation is verified by the consistency test algorithm to obtain the modified weight coefficient, and the modified weight coefficient is linearly combined with the preset weight ratio of 0.4:0.4:0.2, and the target weight coefficient is generated by the weighted average algorithm, including the following steps: statistical analysis is performed on the reduced dimension feature matrix, and the coefficient of variation matrix is ​​obtained by calculating the mean and standard deviation of the spectral data, chromaticity data and luminous flux data; the coefficient of variation matrix is ​​input into the feature normalization module, and the coefficient of variation is normalized by the maximum and minimum value normalization method to obtain the standardized coefficient of variation; a judgment matrix is ​​constructed based on the standardized coefficient of variation, and the relative importance of the spectral, chromaticity and luminous flux parameters is calculated by the paired comparison method to obtain the feature importance matrix; the feature importance matrix is ​​subjected to eigenvalue decomposition, and the power iteration is used to calculate the relative importance of the spectral, chromaticity and luminous flux parameters. The maximum eigenvalue and its corresponding eigenvector are solved by the method to obtain the initial weight value; the initial weight value is input into the hierarchical analysis model, and the consistency ratio is obtained by calculating the ratio of the consistency index CR and the random consistency index RI; the weight is corrected based on the consistency ratio, and the weight distribution is adjusted by the iterative optimization algorithm until the consistency ratio is less than 0.1 to obtain the corrected weight coefficient; the corrected weight coefficient and the preset weight ratio 0.4:0.4:0.2 are linearly interpolated, and the interpolation coefficient α=0.6 is set by the convex combination algorithm to obtain the combined weight vector; the combined weight vector is input into the weight optimization module, and the optimal weight distribution is solved by the Lagrange multiplier method to obtain the balanced weight coefficient; the balanced weight coefficient is normalized, and the weight value is mapped to the (0, 1) interval by the softmax function and the sum is guaranteed to be 1 to obtain the normalized weight coefficient; a weighting function is constructed based on the normalized weight coefficient, and the multidimensional features are fused by the linear weighted combination algorithm to obtain the target weight coefficient.

[0034] In a specific embodiment, the process of executing step S6 may specifically include the following steps: The comprehensive deviation evaluation value is input into the parameter prediction model, which is a bidirectional threshold recurrent neural network. The bidirectional threshold recurrent neural network includes an input layer, a hidden layer and a fully connected layer. The hidden layer includes a forward threshold recurrent unit and a reverse threshold recurrent unit. The comprehensive deviation evaluation value is input into the input layer of the parameter prediction model, the forward time series features are extracted through the forward threshold recurrent unit, the reverse time series features are extracted through the reverse threshold recurrent unit, and the initial compensation parameters are obtained through fusion in the fully connected layer; The initial compensation parameters are processed by the self-attention mechanism, and the attention weight matrix is ​​obtained by calculating the dot product operation of the query matrix, the key matrix and the value matrix, and then normalized by softmax. The initial compensation parameters are weighted based on the attention weight matrix, and the features are enhanced through the multi-head attention mechanism. Each attention head independently calculates the attention score and extracts features to obtain an enhanced feature vector. The enhanced characteristic vector is input into the PID controller, and the parameters are adjusted by using the proportional coefficient 0.8, the integral coefficient 0.3, and the differential coefficient 0.1 to obtain the PID compensation parameters; Adaptive adjustment is performed according to the PID compensation parameters to achieve the coordinated optimization of deep learning and PID control, and the current correction and voltage correction are obtained. The current correction and voltage correction are input into a high-precision digital-to-analog converter, and the signal is converted through a 16-bit DAC. The drive signal is output through PWM modulation to obtain the corrected working parameters. The corrected working parameters are closed-loop controlled by real-time monitoring of the comparison result between the comprehensive deviation evaluation value and the set threshold, and the comparison result is fed back to the input layer of the bidirectional threshold recurrent neural network to obtain a control termination signal.

[0035] Specifically, the comprehensive deviation evaluation value is input into the parameter prediction model, which is a bidirectional threshold recurrent neural network. The network structure includes an input layer, a hidden layer, and a fully connected layer. Among them, the hidden layer is divided into a forward threshold recurrent unit and a reverse threshold recurrent unit. The former extracts forward time series features, and the latter extracts reverse time series features. This structure can effectively capture the contextual information in the sequence data and enhance the expression ability of the model. After the comprehensive deviation evaluation value is input into the input layer of the parameter prediction model, the forward threshold recurrent unit processes the input time series data, and the generated output is expressed as: ; in, represents the forward hidden state, is the current input, is the weight matrix of the forward unit, is the weight matrix associated with the hidden state at the previous time step, is the bias term, is the activation function, using sigmoid or tanh function. Similarly, the output of the reverse threshold cycle unit is expressed as: ; in, represents the reverse hidden state, , and are the weight and bias of the reverse unit respectively. The forward and reverse hidden states are fused in the fully connected layer to form the initial compensation parameters, which are expressed as: ; Among them, concat means concatenating the forward and reverse hidden states. is the weight matrix of the fully connected layer, is the bias term, and the final result is That is the initial compensation parameter. The initial compensation parameter is processed by the self-attention mechanism, and the dot product operation of the query matrix, key matrix and value matrix is ​​calculated to extract features and enhance important information. The query, key and value matrices are defined as follows: ; in, , and are the weight matrices for query, key, and value respectively. The formula for calculating the attention score is: ; in, represents the attention output, is the dimension of the key, which is used for scaling to avoid vanishing gradients due to excessive dot products. After softmax normalization, the attention weight matrix is ​​obtained, and the initial compensation parameters are weighted to obtain the enhanced feature vector. The enhanced feature vector is input into the PID controller for adjustment. The output of the PID controller is calculated according to the following formula: ; in, is the control output, is the current error, , and They are proportional coefficient, integral coefficient and differential coefficient respectively. The proportional coefficient is set to 0.8, the integral coefficient is set to 0.3, and the differential coefficient is set to 0.1. The control output is dynamically adjusted through the feedback error. According to the compensation parameters output by the PID controller, the current correction and voltage correction are adaptively adjusted. Combining the coordinated optimization of deep learning and PID control can ensure the rapid response and stability of the system. On this basis, the current correction and voltage correction are input into a high-precision digital-to-analog converter (DAC), and the signal is converted through a 16-bit DAC, which is expressed as: ; in, is the output voltage, is the numeric input value, is the resolution of the DAC (here 16 bits), is the reference voltage. After the signal conversion, it is modulated by PWM and the drive signal is output to obtain the corrected working parameters. The corrected working parameters are closed-loop controlled. The real-time monitoring comprehensive deviation evaluation value is compared with the set threshold. If the deviation is within a reasonable range, the current state is maintained. Otherwise, the result is fed back to the input layer of the bidirectional threshold recurrent neural network for readjustment to obtain the control termination signal. The feedback mechanism is expressed by the formula: ; in, represents the comprehensive deviation evaluation value, is the set threshold. When the deviation is within the set range, the feedback is 1, indicating that the system is stable and the control process is over; otherwise, the system enters the adjustment state. The closed-loop control strategy ensures that the performance of the LED lamp beads is continuously optimized and can effectively cope with different working conditions.

[0036] The above describes the method for uniformly controlling the light color of the LED lamp beads in the embodiment of the present invention. The following describes the device for uniformly controlling the light color of the LED lamp beads in the embodiment of the present invention. Figure 2 In one embodiment of the present invention, a device for uniformly controlling the light emission color of an LED lamp bead comprises: The packaging module is used to place the LED chip in a triangular ring on the LED bracket, connect the LED chip with wires, inject the first packaging glue and the second packaging glue in sequence and perform centrifugal treatment to obtain an LED lamp bead with a double-layer packaging structure; The acquisition module is used to apply rated working parameters to the LED lamp beads and collect the initial optical parameter matrix; The monitoring module is used to establish a standard data model based on the initial optical parameter matrix, perform multi-parameter real-time monitoring of LED lamp beads, and obtain a monitoring data set; A calculation module is used to input the monitoring data set into the data processing unit, calculate the spectral deviation coefficient by the spectral similarity algorithm, calculate the chromaticity deviation coefficient by the Euclidean distance algorithm, calculate the luminous flux deviation coefficient by the ratio algorithm, and obtain a multi-dimensional deviation vector; A summation module is used to perform a weighted summation operation on the multi-dimensional deviation vector to obtain a comprehensive deviation evaluation value; The control module is used to generate current correction and voltage correction based on the comprehensive deviation evaluation value, and perform closed-loop control on the LED lamp beads until the comprehensive deviation evaluation value is lower than the set threshold and a control termination signal is obtained.

[0037] Through the cooperation of the above components, the triangular ring wafer placement and double-layer packaging structure are adopted to significantly improve the uniformity and luminous efficiency of light. By accurately controlling the ratio and distribution of phosphor and diffusion powder, the color spot problem of traditional LED lamp beads is effectively solved. A multi-dimensional parameter real-time monitoring system including spectrum, chromaticity and luminous flux is established. Through high-precision sensors and synchronous acquisition technology, all-round dynamic monitoring of the optical characteristics of LED lamp beads is realized, and the monitoring accuracy is improved to 0.1nm. The integration of bidirectional threshold recurrent neural network and PID control algorithm realizes adaptive adjustment of the luminous characteristics of LED lamp beads, and the control accuracy reaches ±0.1%, which greatly improves the uniformity and stability of luminous color. Through multi-dimensional deviation vector analysis and comprehensive evaluation mechanism, a complete closed-loop control system is established, which can compensate for the performance drift caused by environmental changes and device aging in real time, and extend the service life of LED lamp beads. The use of high-precision centrifugal packaging process and automatic control technology significantly improves production efficiency and product consistency, and reduces production costs.

[0038] An embodiment of the present invention further provides an LED lamp bead, which, when used, is used to implement the method for uniformly controlling the light emission color of the LED lamp bead as claimed in the claim.

[0039] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided by the present invention and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM.

[0040] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0041] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the whole or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0042] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for uniformly controlling the light color of an LED lamp bead, characterized in that: The method comprises: The LED chips are placed on the LED bracket in a triangular ring shape, the LED chips are connected by wires, and the first packaging glue and the second packaging glue are injected and centrifuged in sequence to obtain LED lamp beads with a double-layer packaging structure; Applying rated operating parameters to the LED lamp beads and collecting an initial optical parameter matrix; A standard data model is established based on the initial optical parameter matrix, and multi-parameter real-time monitoring of the LED lamp beads is performed to obtain a monitoring data set; Inputting the monitoring data set into a data processing unit, calculating the spectral deviation coefficient by a spectral similarity algorithm, calculating the chromaticity deviation coefficient by a Euclidean distance algorithm, and calculating the luminous flux deviation coefficient by a ratio algorithm to obtain a multidimensional deviation vector; Performing a weighted sum operation on the multi-dimensional deviation vector to obtain a comprehensive deviation evaluation value; Based on the comprehensive deviation evaluation value, a current correction amount and a voltage correction amount are generated, and the LED lamp bead is closed-loop controlled until the comprehensive deviation evaluation value is lower than a set threshold value, and a control termination signal is obtained.

2. The method for uniformly controlling the light emission color of an LED lamp bead according to claim 1, characterized in that: The LED chips are placed on the LED bracket in a triangular ring manner, the LED chips are connected by wires, and the first packaging glue and the second packaging glue are injected and centrifuged in sequence to obtain the LED lamp beads with a double-layer packaging structure, including: Performing surface treatment on the LED bracket, coating an aluminum oxide reflective layer on the inner wall of the LED bracket, and combining the reflective layer with the bracket through a high-temperature sintering process to obtain a bracket structure; The LED chips are placed on the support structure so that the LED chips form an angle of 60° with the horizontal direction, and arranged in a triangular ring array by a positioning system to obtain a chip array structure; Performing gold wire bonding on the chip array structure, connecting the LED chip and the conductive pad of the support structure through an automatic wire bonding system to obtain a conductive structure; A phosphor with a particle size of 10 microns is mixed with an epoxy resin in a mass ratio of 4:6, and dispersed by a high-speed stirring device to obtain a first packaging glue, and the first packaging glue is injected into the conductive structure, and the injection amount is controlled by a weight sensor so that the injection amount error is controlled within the range of ±0.1 mg to obtain a first packaging layer; The first packaging layer is placed in a centrifuge at a speed of 3000 rpm, and the phosphor is evenly distributed around the LED chip by centrifugation for 300 seconds to obtain a coating structure, and the diffusion powder and the epoxy resin are mixed at a mass ratio of 1.2:98.8, and dispersed by a high-speed stirring device to obtain a second packaging glue; The second packaging glue is injected into the coating structure, and the injection amount and injection angle are adjusted by the numerical control system so that the second packaging glue forms a concave structure with a curvature radius of 1.5 times the diameter of the packaging surface, thereby obtaining an LED lamp bead with a double-layer packaging structure.

3. The method for uniformly controlling the light emission color of an LED lamp bead according to claim 2, characterized in that: The step of applying rated operating parameters to the LED lamp beads and collecting an initial optical parameter matrix includes: The LED lamp beads are subjected to environmental parameter control and preheated in a standard environment with a temperature of 25° C. and a relative humidity of 60% to obtain LED lamp beads in a stable working state; Apply the rated working parameters of 3.0V voltage and 350mA current to the LED lamp beads in stable working state, and control the power supply through a high-precision DC power supply to obtain a stable power supply state; A spectrum analyzer with a resolution of 0.1 nm is aimed at the light-emitting surface of the LED lamp bead, and scanning and collecting data within the wavelength range of 380-780 nm to obtain spectral intensity distribution data; The chromaticity parameters of the light-emitting surface of the LED lamp bead are measured, and the CIE chromaticity coordinate values ​​are collected by a colorimeter at a distance of 100 mm from the light-emitting surface to obtain chromaticity distribution data; The LED lamp bead is placed at the center of an integrating sphere, and the luminous flux value is collected by a luminous flux sensor to obtain luminous flux data, and the spectral intensity distribution data is divided into wavelength intervals, and discrete wavelength points are numerically fitted by an interpolation algorithm to obtain a continuous spectrum curve; The chromaticity distribution data and the luminous flux data are fused, a normalized parameter value is obtained through standardization processing, and standardized data is obtained. A matrix synthesis operation is performed on the continuous spectral curve and the standardized data, and a three-dimensional data structure is generated through a data reconstruction algorithm to obtain an initial optical parameter matrix.

4. The method for uniformly controlling the light emission color of an LED lamp bead according to claim 3, characterized in that: The standard data model is established based on the initial optical parameter matrix, and multi-parameter real-time monitoring of the LED lamp beads is performed to obtain a monitoring data set, including: Performing parameter decomposition on the initial optical parameter matrix, converting the spectrum data, chromaticity data and luminous flux data into a feature matrix through a matrix decomposition algorithm, and obtaining the standard optical characteristics of the LED lamp beads; A three-dimensional parameter space is constructed based on the standard optical characteristics, and a spectral curve model, a chromaticity distribution model and a luminous flux variation model are fitted by the least squares method to obtain a standard mathematical model of the LED lamp bead; The standard mathematical model is input into a Kalman filter, and a dynamic prediction model of spectrum, chromaticity and luminous flux is established through a state prediction algorithm to obtain a standard data model; The parameter threshold is set based on the standard data model, and the spectral fluctuation range, chromaticity shift range and luminous flux variation range are determined by the interval control algorithm to obtain the parameter control interval; The LED lamp beads are monitored in real time, and spectrum, chromaticity and luminous flux data are synchronously collected through a multi-channel data acquisition system with a sampling frequency of 1000 Hz to obtain real-time sampling data; Inputting the real-time sampling data into the standard data model, calculating the deviation between the current state and the predicted state through a state estimation algorithm, and obtaining state deviation data; Perform anomaly detection based on the state deviation data, determine whether the data falls within the parameter control interval through a Mahalanobis distance algorithm, and obtain a data validity mark; The data marked as valid are reorganized in time sequence, and the spectral data, chromaticity data and luminous flux data are integrated into a unified format through a data encapsulation algorithm to obtain a monitoring data set.

5. The method for uniformly controlling the light emission color of an LED lamp bead according to claim 4, characterized in that: The monitoring data set is input into a data processing unit, a spectral deviation coefficient is calculated by a spectral similarity algorithm, a chromaticity deviation coefficient is calculated by a Euclidean distance algorithm, and a luminous flux deviation coefficient is calculated by a ratio algorithm to obtain a multidimensional deviation vector, including: Performing Fourier transformation on the real-time spectral data in the monitoring data set, extracting spectral frequency components through a spectrum analysis algorithm, and obtaining spectral frequency domain features; The cosine similarity calculation is performed on the spectral frequency domain feature and the spectral data in the standard data model, and a spectral similarity value in the numerical range of 0-1 is obtained by normalization processing to obtain a spectral deviation coefficient; Converting the real-time chromaticity data in the monitoring data set into three-dimensional chromaticity space coordinates, generating chromaticity space distribution points through a coordinate mapping algorithm, and obtaining a chromaticity space vector; Calculating the Euclidean distance between the chromaticity space vector and the chromaticity data in the standard data model, mapping the distance value to a 0-1 interval through standardization processing, and obtaining a chromaticity deviation coefficient; The real-time luminous flux data in the monitoring data set is reconstructed according to a time series, a luminous flux time series curve is generated by a sliding window algorithm to obtain a luminous flux sequence, and a ratio operation is performed on the luminous flux sequence and the luminous flux value in the standard data model, and the ratio result is converted into a linear relationship by logarithmic transformation to obtain a luminous flux deviation coefficient; Constructing a three-dimensional feature space based on the spectral deviation coefficient, the chromaticity deviation coefficient and the luminous flux deviation coefficient, generating a standard feature basis through orthogonalization processing, and obtaining a feature basis matrix; The spectral deviation coefficient, the chromaticity deviation coefficient and the luminous flux deviation coefficient are projected onto the characteristic basis matrix, and a multi-dimensional deviation vector is generated through matrix operation.

6. The method for uniformly controlling the light emission color of an LED lamp bead according to claim 5, characterized in that: The weighted sum operation is performed on the multi-dimensional deviation vector to obtain a comprehensive deviation evaluation value, including: Performing principal component analysis on the multidimensional deviation vector, extracting main characteristic components and secondary characteristic components by singular value decomposition algorithm, and obtaining a characteristic component sequence; The characteristic component sequence is orthogonally transformed, and a standard orthogonal basis vector is constructed by a Schmidt orthogonalization algorithm to obtain an orthogonal basis matrix, and the orthogonal basis matrix is ​​dimensionality reduced according to the primary and secondary characteristic contribution rates, and the main characteristic dimensions are retained by a truncated singular value method to obtain a reduced-dimensional characteristic matrix; A weight distribution model is constructed based on the dimension reduction feature matrix, and initial weight values ​​of the spectral deviation coefficient, the chromaticity deviation coefficient and the luminous flux deviation coefficient are calculated by a coefficient of variation method; Performing a hierarchical analysis on the initial weight value, verifying the rationality of the weight distribution through a consistency check algorithm, obtaining a revised weight coefficient, and linearly combining the revised weight coefficient with a preset weight ratio of 0.4:0.4:0.2, and generating a target weight coefficient through a weighted average algorithm; The multidimensional deviation vector is weightedly fused based on the target weight coefficient, and a weighted deviation value is generated through matrix multiplication to obtain a normalized deviation value. The normalized deviation value is nonlinearly mapped, and the deviation value is compressed to the range of 0-1 through the sigmoid function to obtain a comprehensive deviation evaluation value.

7. The method for uniformly controlling the light emission color of an LED lamp bead according to claim 6, characterized in that: The method generates a current correction amount and a voltage correction amount based on the comprehensive deviation evaluation value, performs closed-loop control on the LED lamp bead, and obtains a control termination signal until the comprehensive deviation evaluation value is lower than a set threshold value, including: Inputting the comprehensive deviation evaluation value into a parameter prediction model, wherein the parameter prediction model is a bidirectional threshold recurrent neural network, wherein the bidirectional threshold recurrent neural network comprises an input layer, a hidden layer and a fully connected layer, wherein the hidden layer comprises a forward threshold recurrent unit and a reverse threshold recurrent unit; Input the comprehensive deviation evaluation value into the input layer of the parameter prediction model, extract the forward time series feature through the forward threshold recurrent unit, extract the reverse time series feature through the reverse threshold recurrent unit, and obtain the initial compensation parameter through the full connection layer fusion; The initial compensation parameters are processed by a self-attention mechanism, and an attention weight matrix is ​​obtained by calculating the dot product operation of the query matrix, the key matrix and the value matrix, and performing a softmax normalization process; The initial compensation parameters are weighted based on the attention weight matrix, and feature enhancement is performed through a multi-head attention mechanism, where each attention head independently calculates an attention score and performs feature extraction to obtain an enhanced feature vector; The enhanced characteristic vector is input into the PID controller, and the parameters are adjusted by using a proportional coefficient of 0.8, an integral coefficient of 0.3, and a differential coefficient of 0.1 to obtain a PID compensation parameter; Adaptive adjustment is performed according to the PID compensation parameters to achieve collaborative optimization of deep learning and PID control, and current correction and voltage correction are obtained. The current correction and voltage correction are input into a high-precision digital-to-analog converter, and signal conversion is performed through a 16-bit DAC. The drive signal is output through PWM modulation to obtain the corrected working parameters; The corrected working parameters are closed-loop controlled, and the comparison result between the comprehensive deviation evaluation value and the set threshold is monitored in real time, and the comparison result is fed back to the input layer of the bidirectional threshold recurrent neural network to obtain a control termination signal.

8. A device for uniformly controlling the light color of an LED lamp bead, characterized in that: The device is used to perform a method for uniformly controlling the light emission color of an LED lamp bead according to any one of claims 1 to 7, the device comprising: The packaging module is used to place the LED chip in a triangular ring on the LED bracket, connect the LED chip with wires, inject the first packaging glue and the second packaging glue in sequence and perform centrifugal treatment to obtain an LED lamp bead with a double-layer packaging structure; A collection module, used for applying rated working parameters to the LED lamp beads and collecting an initial optical parameter matrix; A monitoring module, used to establish a standard data model based on the initial optical parameter matrix, perform multi-parameter real-time monitoring on the LED lamp beads, and obtain a monitoring data set; A calculation module, used for inputting the monitoring data set into a data processing unit, calculating the spectral deviation coefficient by a spectral similarity algorithm, calculating the chromaticity deviation coefficient by a Euclidean distance algorithm, calculating the luminous flux deviation coefficient by a ratio algorithm, and obtaining a multidimensional deviation vector; A summing module, used for performing a weighted summing operation on the multi-dimensional deviation vector to obtain a comprehensive deviation evaluation value; The control module is used to generate a current correction amount and a voltage correction amount based on the comprehensive deviation evaluation value, and perform closed-loop control on the LED lamp bead until the comprehensive deviation evaluation value is lower than a set threshold value, thereby obtaining a control termination signal.

9. An LED lamp bead, characterized in that: When used, the LED lamp bead is used to implement the method for uniformly controlling the luminous color of the LED lamp bead according to any one of claims 1 to 7.

Images