Intelligent control system and method for material mixer

By adopting an intelligent control system in the solder paste mixer and automatically adjusting the stirring temperature using image analysis and deep learning technology, the problem that temperature control in the existing technology cannot respond to changes in nonlinear systems is solved, and the precise control of the solder paste status is achieved and Stable improvement in quality.

CN118865268BActive Publication Date: 2024-11-29QINGDAO LINGJUN INTELLIGENT CONSTR NEW MATERIAL TECH CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411339334.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-25
Publication Date
2024-11-29
Estimated Expiration
2044-09-25

AI Technical Summary

Technical Problem

The temperature control method of existing solder paste mixers relies on the PD control algorithm, and cannot effectively identify and respond to nonlinear system changes, resulting in unstable solder paste quality.

Method used

An intelligent control system of the mixer machine is adopted to obtain the solder paste stirring state image through the camera, calculate the time interval, extract and optimize the stirring state characteristics of the solder paste, calculate the semantic offset coefficient and change rate, and automatically adjust the stirring temperature.

Benefits of technology

Accurate control of solder paste status is achieved, mass fluctuations and instability caused by untimely or inaccurate temperature adjustment are reduced, and the degree of automation and intelligence of stirring temperature control is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118865268B_ABST
    Figure CN118865268B_ABST
Patent Text Reader

Abstract

The present application relates to an intelligent control system and method for a material mixer, and relates to the field of control systems. The method comprises: collecting a first solder paste stirring state image of the solder paste to be stirred at a first time point and a second solder paste stirring state image at a second time point by a camera, and calculating the time interval between the second time point and the first time point, and using image analysis and processing technology based on deep learning to extract features, select optimization and calculate semantic offsets for the solder paste stirring state images at two time points, thereby automatically determining whether the stirring temperature at the next time point is increased based on the comparison between the state semantic change rate between the solder paste state semantic offset coefficient and the time interval and a predetermined threshold. The solder paste stirring state image can be collected in real time, and the precise control of the solder paste state can be achieved, reducing the quality fluctuation and instability caused by untimely or inaccurate temperature adjustment, thereby improving the automation and intelligence level of stirring temperature control.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of control systems, and in particular, to an intelligent control system and method for a mixer. Background Art

[0002] Solder paste is a mixture containing metal powder and binder, and its viscosity and fluidity are affected by temperature. The uniformity of solder paste is critical to ensure the consistency of the soldering process and the performance of the final product. In electronic assembly, the rheology and viscosity of solder paste directly affect its printing quality on PCB. Uneven solder paste may cause soldering defects such as voids, bridging or other deficiencies, which will affect the electrical connection and mechanical stability of electronic components. Therefore, controlling the stirring temperature can ensure that the solder paste reaches the optimal state suitable for printing and soldering, which is a key step in achieving high-reliability electronic products.

[0003] Chinese patent CN117348643B proposes a temperature control method, device, terminal and storage medium for a solder paste mixer, which obtains material parameters of the solder paste to be mixed, and then determines the heating stage control data, constant temperature stage control data and cooling stage control data in the temperature control process of the solder paste mixer based on the material parameters, and finally controls the heating stage, constant temperature stage and cooling stage of the solder paste mixer respectively based on the heating stage control data, constant temperature stage control data and cooling stage control data.

[0004] In the above existing schemes, the PD control algorithm is used to control the temperature rise of the solder paste mixer. However, the PD control algorithm is usually designed based on a linear system model, which makes it unable to identify and respond to nonlinear changes in the solder paste state when facing nonlinear systems or parameter changes, making it difficult to adjust the temperature in time for compensation, thereby failing to provide the best control effect. In addition, since the PD controller relies on fixed manual parameter settings, which are optimized under specific environments. When environmental conditions change, such as temperature fluctuations or changes in operating conditions, the PD controller cannot better adapt to the dynamic timing changes of the stirring state, resulting in fluctuations and instability in the quality of the solder paste.

[0005] Therefore, an intelligent control solution for the mixer is desired. Summary of the invention

[0006] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0007] In a first aspect, the present application provides an intelligent control system for a mixer, the system comprising:

[0008] A solder paste stirring state image acquisition module, used to acquire a first solder paste stirring state image of the solder paste to be stirred at a first time point and a second solder paste stirring state image at a second time point collected by a camera;

[0009] A time interval calculation module, used to calculate the time interval between the second time point and the first time point;

[0010] A solder paste stirring state feature extraction module, used for inputting the second solder paste stirring state image and the first solder paste stirring state image into a stirring state feature extractor to obtain a first solder paste stirring state feature map and a second solder paste stirring state feature map;

[0011] A stirring state local feature extraction module, used for performing feature dispersion on the first solder paste stirring state feature map and the second solder paste stirring state feature map to obtain a set of first solder paste stirring state local feature vectors and a set of second solder paste stirring state local feature vectors;

[0012] A solder paste stirring state local feature optimization module, used for inputting the set of the first solder paste stirring state local feature vectors and the set of the second solder paste stirring state local feature vectors into a feature sequence selection optimization module based on a feature energy distribution spectrum to obtain a selected set of the first solder paste stirring state local feature vectors and a selected set of the second solder paste stirring state local feature vectors;

[0013] A solder paste state semantic shift calculation module, used for inputting the selected set of local feature vectors of the first solder paste stirring state and the selected set of local feature vectors of the second solder paste stirring state into an inter-sequence matching network based on energy-intensive interactive distribution to obtain a solder paste state semantic shift coefficient;

[0014] A solder paste state semantic change rate calculation module, used for dividing the solder paste state semantic offset coefficient by the time interval to obtain the solder paste state semantic change rate;

[0015] The stirring temperature control module is used to determine whether the stirring temperature at a next time point is increased based on a comparison between the solder paste state semantic change rate and a predetermined threshold.

[0016] Optionally, the solder paste stirring state feature extraction module is used to: input the first solder paste stirring state image and the second solder paste stirring state image into a stirring state feature extractor based on a void convolutional neural network model to obtain the first solder paste stirring state feature map and the second solder paste stirring state feature map.

[0017] Optionally, the solder paste stirring state local feature optimization module includes: a first solder paste stirring state local feature energy distribution spectrum calculation unit, used to calculate the feature energy distribution spectrum vectors of each first solder paste stirring state local feature vector in the set of the first solder paste stirring state local feature vectors to obtain a set of first solder paste stirring state local feature energy distribution spectrum vectors; a position mean vector calculation unit, used to calculate the position mean vector of the set of the first solder paste stirring state local feature energy distribution spectrum vectors as the first solder paste stirring state energy spectrum distribution center vector; a first solder paste stirring state energy distribution spectrum span factor calculation unit; A calculation unit is used to calculate the energy distribution spectrum span factor between the first solder paste stirring state energy spectrum distribution center vector and each first solder paste stirring state local characteristic energy distribution spectrum vector in the set of the first solder paste stirring state local characteristic energy distribution spectrum vector to obtain a set of first solder paste stirring state energy distribution spectrum span factors; a span factor and preset threshold comparison unit is used to determine the set of the selected first solder paste stirring state local characteristic vectors based on the comparison between each first solder paste stirring state energy distribution spectrum span factor in the set of the first solder paste stirring state energy distribution spectrum span factor and the preset threshold.

[0018] Optionally, the first solder paste stirring state local characteristic energy distribution spectrum calculation unit includes: a first solder paste stirring state local characteristic distribution energy synergy subunit, used to respectively calculate the characteristic distribution energy synergy representation vector between each first solder paste stirring state local feature vector and other each first solder paste stirring state local feature vector in the set of the first solder paste stirring state local feature vector to obtain a set of multiple first solder paste stirring state local characteristic distribution energy synergy representation vectors; a first solder paste stirring state characteristic distribution energy synergy factor calculation subunit, used to calculate the characteristic distribution energy synergy factor vector of the set of each first solder paste stirring state local characteristic distribution energy synergy representation vector in the set of the multiple first solder paste stirring state local characteristic distribution energy synergy representation vectors to obtain a set of the first solder paste stirring state local characteristic energy distribution spectrum vectors.

[0019] Optionally, the first solder paste stirring state local feature distribution energy coordination subunit is used to: extract a predetermined first solder paste stirring state local feature vector from the set of the first solder paste stirring state local feature vectors; perform element-by-element maximum value extraction on the predetermined first solder paste stirring state local feature vector and each other first solder paste stirring state local feature vector, so as to obtain a set of first solder paste stirring state local feature distribution energy coordination representation vectors corresponding to the predetermined first solder paste stirring state local feature vector.

[0020] Optionally, the first solder paste stirring state characteristic distribution energy synergy factor calculation subunit is used to: respectively extract the maximum value of each first solder paste stirring state local characteristic distribution energy synergy representation vector in the set of the first solder paste stirring state local characteristic distribution energy synergy representation vector to obtain a set of first solder paste stirring state local characteristic maximum values; respectively calculate the mean and variance of each first solder paste stirring state local characteristic distribution energy synergy representation vector to obtain a set of first solder paste stirring state local characteristic mean values ​​and a set of first solder paste stirring state local characteristic variances; add the set of the first solder paste stirring state local characteristic variances and the preset hyperparameters by position to obtain a set of first energy distribution coefficients of the first solder paste stirring state local characteristics; calculate the first solder paste stirring state local characteristic maximum value and the first solder paste stirring state local characteristic maximum value and the first corresponding local characteristic variance of each group in the set of the first solder paste stirring state local characteristic maximum value and the first The square of the difference of the mean of the local feature of the solder paste stirring state is obtained to obtain a set of local difference values ​​of the first solder paste stirring state; the set of variances of the first local feature of the solder paste stirring state is multiplied by constant two by position to obtain a set of variances of the modulated first local feature of the solder paste stirring state; after adding each group of corresponding local difference values ​​of the first solder paste stirring state and the variance of the modulated first local feature of the solder paste stirring state in the set of local difference values ​​of the first solder paste stirring state and the set of variances of the modulated first local feature of the solder paste stirring state, the sum is added to the preset hyperparameter to obtain a set of second energy distribution coefficients of the local feature of the first solder paste stirring state; the set of first energy distribution coefficients of the local feature of the first solder paste stirring state is divided by position with the set of second energy distribution coefficients of the local feature of the first solder paste stirring state to obtain the energy distribution spectrum vector of the local feature of the first solder paste stirring state composed of multiple feature distribution energy synergy factors.

[0021] Optionally, the first solder paste stirring state energy distribution spectrum span factor calculation unit is used to: calculate the positional difference between the first solder paste stirring state energy spectrum distribution center vector and the first solder paste stirring state local characteristic energy distribution spectrum vector to obtain the first solder paste stirring state differential eigenvector; calculate the covariance matrix between the first solder paste stirring state energy spectrum distribution center vector and the first solder paste stirring state local characteristic energy distribution spectrum vector, and calculate the inverse of the covariance matrix to obtain the first solder paste stirring state inverse covariance matrix; calculate the transposed vector of the first solder paste stirring state differential eigenvector and the product of the first solder paste stirring state inverse covariance matrix and the first solder paste stirring state differential eigenvector to obtain the first solder paste stirring state distribution value; calculate the square root of the first solder paste stirring state distribution value to obtain the first solder paste stirring state energy distribution spectrum span factor.

[0022] Optionally, the solder paste state semantic offset calculation module includes: a solder paste stirring state local feature energy synergistic response value calculation unit, which is used to calculate the energy synergistic response value between any pair of selected first solder paste stirring state local feature vectors and selected second solder paste stirring state local feature vectors in the set of selected first solder paste stirring state local feature vectors and the set of selected second solder paste stirring state local feature vectors to obtain a solder paste stirring state local feature synergistic energy fine-grained global distribution matrix; a hole convolution coding unit, which is used to perform hole convolution coding on the solder paste stirring state local feature synergistic energy fine-grained global distribution matrix to obtain a solder paste stirring state local feature synergistic energy fine-grained global distribution feature matrix; and an inter-sequence matching degree measurement network unit, which is used to input the solder paste stirring state local feature synergistic energy fine-grained global distribution feature matrix into an inter-sequence matching degree measurement network to obtain the solder paste state semantic offset coefficient.

[0023] Optionally, the solder paste stirring state local characteristic energy synergistic response value calculation unit is used to: calculate the position-by-position division between the selected first solder paste stirring state local characteristic vector and the selected second solder paste stirring state local characteristic vector to obtain the selected solder paste stirring state local response characteristic vector; extract the maximum value of the selected solder paste stirring state local response characteristic vector to obtain the selected solder paste stirring state local response characteristic maximum value; respectively calculate the mean and variance of the selected solder paste stirring state local response characteristic vector to obtain the selected solder paste stirring state local response characteristic mean and the selected solder paste stirring state local response characteristic variance; multiply the value obtained by adding the selected solder paste stirring state local response characteristic variance and the offset term by four to obtain the selected solder paste stirring state local characteristic first energy synergistic response value; calculate the The square of the difference between the maximum value of the local response characteristic of the selected solder paste stirring state and the mean value of the local response characteristic of the selected solder paste stirring state is obtained to obtain the difference value of the local response characteristic of the selected solder paste stirring state; the modulated local response characteristic variance of the selected solder paste stirring state obtained by multiplying the variance of the local response characteristic of the selected solder paste stirring state by two is added to the value obtained by multiplying the bias term by two and the difference value of the local response characteristic of the selected solder paste stirring state to obtain the second energy synergistic response value of the local characteristic of the selected solder paste stirring state; the first energy synergistic response value of the local characteristic of the selected solder paste stirring state is divided by the second energy synergistic response value of the local characteristic of the selected solder paste stirring state to obtain the energy synergistic response value between the first local feature vector of the selected solder paste stirring state and the second local feature vector of the selected solder paste stirring state.

[0024] In a second aspect, the present application provides an intelligent control method for a mixer, the method comprising:

[0025] Acquire a first solder paste stirring state image of the solder paste to be stirred at a first time point and a second solder paste stirring state image at a second time point collected by a camera;

[0026] Calculating the time interval between the second time point and the first time point;

[0027] Inputting the second solder paste stirring state image and the first solder paste stirring state image into a stirring state feature extractor to obtain a first solder paste stirring state feature map and a second solder paste stirring state feature map;

[0028] Performing feature dispersion on the first solder paste stirring state feature map and the second solder paste stirring state feature map to obtain a set of first solder paste stirring state local feature vectors and a set of second solder paste stirring state local feature vectors;

[0029] Inputting the set of the first solder paste stirring state local feature vectors and the set of the second solder paste stirring state local feature vectors into a feature sequence selection optimization module based on a feature energy distribution spectrum to obtain a selected set of the first solder paste stirring state local feature vectors and a selected set of the second solder paste stirring state local feature vectors;

[0030] Inputting the selected set of local feature vectors of the first solder paste stirring state and the selected set of local feature vectors of the second solder paste stirring state into an inter-sequence matching network based on energy-intensive interaction distribution to obtain a solder paste state semantic shift coefficient;

[0031] Dividing the solder paste state semantic shift coefficient by the time interval to obtain a solder paste state semantic change rate;

[0032] Based on the comparison between the semantic change rate of the solder paste state and a predetermined threshold, it is determined whether the stirring temperature at the next time point is increased.

[0033] The above technical solution is adopted, by collecting the first solder paste stirring state image of the solder paste to be stirred at the first time point and the second solder paste stirring state image at the second time point by a camera, and calculating the time interval between the second time point and the first time point, and using the image analysis and processing technology based on deep learning to extract features, select optimization and calculate semantic offset of the solder paste stirring state images at the two time points, so as to automatically determine whether the stirring temperature at the next time point is increased based on the comparison between the state semantic change rate between the solder paste state semantic offset coefficient and the time interval and the predetermined threshold. In this way, the solder paste stirring state image can be collected in real time, thereby realizing the precise control of the solder paste state, reducing the quality fluctuation and instability caused by untimely or inaccurate temperature adjustment, thereby improving the automation and intelligent level of stirring temperature control.

[0034] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale. In the drawings:

[0036] Figure 1 It is a block diagram of an intelligent control system for a mixing machine according to an exemplary embodiment.

[0037] Figure 2 The present invention is a flow chart of an intelligent control method for a mixing machine according to an exemplary embodiment.

[0038] Figure 3 It is a block diagram of an electronic device according to an exemplary embodiment.

[0039] Figure 4 It is an application scenario diagram of an intelligent control system for a mixer according to an exemplary embodiment. DETAILED DESCRIPTION

[0040] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.

[0041] It should be understood that the various steps described in the method implementation of the present application can be performed in different orders and / or performed in parallel. In addition, the method implementation may include additional steps and / or omit the steps shown. The scope of the present application is not limited in this respect.

[0042] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0043] It should be noted that the concepts such as "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0044] It should be noted that the modifications of "one" and "plurality" mentioned in the present application are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0045] The names of the messages or information exchanged between multiple devices in the embodiments of the present application are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0046] The specific implementation of the present application is described in detail below with reference to the accompanying drawings.

[0047] Figure 1 FIG. 1 is a block diagram of an intelligent control system for a mixing machine according to an exemplary embodiment. Figure 1 As shown, the system 100 includes:

[0048] A solder paste stirring state image acquisition module 101, used to acquire a first solder paste stirring state image of the solder paste to be stirred at a first time point and a second solder paste stirring state image at a second time point collected by a camera;

[0049] A time interval calculation module 102, configured to calculate a time interval between the second time point and the first time point;

[0050] A solder paste stirring state feature extraction module 103, used for inputting the second solder paste stirring state image and the first solder paste stirring state image into a stirring state feature extractor to obtain a first solder paste stirring state feature map and a second solder paste stirring state feature map;

[0051] A stirring state local feature extraction module 104, used for performing feature dispersion on the first solder paste stirring state feature map and the second solder paste stirring state feature map to obtain a set of first solder paste stirring state local feature vectors and a set of second solder paste stirring state local feature vectors;

[0052] A solder paste stirring state local feature optimization module 105, used for inputting the set of the first solder paste stirring state local feature vectors and the set of the second solder paste stirring state local feature vectors into a feature sequence selection optimization module based on a feature energy distribution spectrum to obtain a selected set of the first solder paste stirring state local feature vectors and a selected set of the second solder paste stirring state local feature vectors;

[0053] A solder paste state semantic shift calculation module 106, configured to input the selected set of local feature vectors of the first solder paste stirring state and the selected set of local feature vectors of the second solder paste stirring state into an inter-sequence matching network based on energy-intensive interactive distribution to obtain a solder paste state semantic shift coefficient;

[0054] A solder paste state semantic change rate calculation module 107, configured to divide the solder paste state semantic offset coefficient by the time interval to obtain a solder paste state semantic change rate;

[0055] The stirring temperature control module 108 is used to determine whether the stirring temperature at the next time point should be increased based on the comparison between the solder paste state semantic change rate and a predetermined threshold.

[0056] In view of the above technical problems, the technical concept of the present application is to collect the first solder paste stirring state image of the solder paste to be stirred at the first time point and the second solder paste stirring state image at the second time point by a camera, and calculate the time interval between the second time point and the first time point, and use the image analysis and processing technology based on deep learning to extract features, select optimization and calculate semantic offset of the solder paste stirring state images at the two time points, so as to automatically determine whether the stirring temperature at the next time point is increased based on the comparison between the state semantic change rate between the solder paste state semantic offset coefficient and the time interval and the predetermined threshold. In this way, the solder paste stirring state image can be collected in real time to monitor the stirring process uninterruptedly, and the dynamic time sequence change of the solder paste state can be accurately captured by using deep learning technology, so as to realize the precise control of the solder paste state, reduce the quality fluctuation and instability caused by untimely or inaccurate temperature adjustment, and thus improve the automation and intelligence level of stirring temperature control.

[0057] Specifically, in the technical solution of the present application, firstly, a first solder paste stirring state image of the solder paste to be stirred at a first time point and a second solder paste stirring state image at a second time point captured by a camera are acquired.

[0058] Next, considering that the time interval is one of the bases for adjusting the stirring parameters (such as temperature), and the time interval also has an important influence on the change of the solder paste state. Based on this, in order for the system to dynamically adjust the stirring temperature according to the change of the time interval and the stirring state, in the technical solution of the present application, the time interval between the second time point and the first time point is calculated.

[0059] Then, in order to further capture and extract the characteristic information of the stirring state contained in the solder paste stirring state images at two time points, in the technical solution of the present application, the second solder paste stirring state image and the first solder paste stirring state image are input into the stirring state feature extractor based on the void convolutional neural network model to obtain the first solder paste stirring state feature map and the second solder paste stirring state feature map. That is, the void convolutional neural network can expand the receptive field without increasing the number of parameters by introducing the void convolution operation, so as to better capture the implicit stirring state features in each solder paste stirring state image. In particular, the stirring state feature extractor based on the void convolutional neural network model here is essentially a void convolutional neural network model.

[0060] In one embodiment of the present application, the solder paste stirring state feature extraction module 103 is used to: input the first solder paste stirring state image and the second solder paste stirring state image into a stirring state feature extractor based on a void convolutional neural network model to obtain the first solder paste stirring state feature map and the second solder paste stirring state feature map.

[0061] Next, considering that the feature map directly extracted by using the hole convolutional neural network may not fully reflect the complex features of the solder paste state. Based on this, in order to better capture the key solder paste stirring state information in the local area of ​​the image, in the technical solution of the present application, the first solder paste stirring state feature map and the second solder paste stirring state feature map are feature scattered to obtain a set of first solder paste stirring state local feature vectors and a set of second solder paste stirring state local feature vectors. In this way, through feature scattered, the local features in the solder paste stirring state feature map can be decomposed to obtain richer and more detailed local key feature expression information.

[0062] In one embodiment of the present application, the solder paste stirring state local feature optimization module 105 includes: a first solder paste stirring state local feature energy distribution spectrum calculation unit, used to calculate the feature energy distribution spectrum vectors of each first solder paste stirring state local feature vector in the set of the first solder paste stirring state local feature vectors to obtain a set of first solder paste stirring state local feature energy distribution spectrum vectors; a position mean vector calculation unit, used to calculate the position mean vector of the set of the first solder paste stirring state local feature energy distribution spectrum vectors as the first solder paste stirring state energy spectrum distribution center vector; the first solder paste stirring state energy distribution A spectral span factor calculation unit, used to calculate the energy distribution spectrum span factor between the first solder paste stirring state energy spectrum distribution center vector and each first solder paste stirring state local characteristic energy distribution spectrum vector in the set of the first solder paste stirring state local characteristic energy distribution spectrum vector to obtain a set of first solder paste stirring state energy distribution spectrum span factors; a span factor and preset threshold comparison unit, used to determine the set of selected first solder paste stirring state local characteristic vectors based on the comparison between each first solder paste stirring state energy distribution spectrum span factor in the set of the first solder paste stirring state energy distribution spectrum span factor and the preset threshold.

[0063] Then, considering that the set of the first solder paste stirring state local feature vectors and the set of the second solder paste stirring state local feature vectors have different energy distributions and importances in each set of the solder paste stirring state local features. In order to optimize and select the energy distribution between different features relatively, to retain these key feature vectors and remove redundant and noise features. In the technical solution of the present application, a feature sequence selection optimization module based on a feature energy distribution spectrum is further used to perform feature selection and energy enhancement on the set of the first solder paste stirring state local feature vectors and the set of the second solder paste stirring state local feature vectors to obtain the selected set of the first solder paste stirring state local feature vectors and the selected set of the second solder paste stirring state local feature vectors. Here, the set of the first solder paste stirring state local feature vectors is taken as an example. Specifically, the characteristic energy distribution spectrum vector of each first solder paste stirring state local feature vector is first calculated to map it to the energy distribution spectrum space to obtain the set of the first solder paste stirring state local feature energy distribution spectrum vectors. That is, by mapping to the energy distribution spectrum space, the amount of information carried by each first solder paste stirring state local feature can be quantified, thereby evaluating the importance of each feature vector. Next, the positional mean vector of the characteristic energy distribution spectrum vector sequence is calculated to obtain the center vector of the energy spectrum distribution of the first solder paste stirring state to represent the center vector of the overall energy distribution characteristics of the entire characteristic sequence, which is used to evaluate the degree of deviation of each characteristic vector from the overall distribution center. Then, the difference between the center vector of the energy spectrum distribution of the first solder paste stirring state and each characteristic energy distribution spectrum vector is calculated to obtain the energy distribution spectrum span factor. In particular, the energy distribution spectrum span factor is calculated based on the differential characteristics and covariance matrix between each characteristic vector and the center vector, reflecting the degree of discreteness of the characteristic vector. Finally, the energy distribution spectrum span factor is compared with the preset threshold, and the qualified characteristic first solder paste stirring state local features are screened out to obtain a set of the first solder paste stirring state local feature vectors that finally contain key information and representativeness.

[0064] In one embodiment of the present application, the first solder paste stirring state local characteristic energy distribution spectrum calculation unit includes: a first solder paste stirring state local characteristic distribution energy synergy subunit, which is used to respectively calculate the characteristic distribution energy synergy representation vector between each first solder paste stirring state local characteristic vector and other each first solder paste stirring state local characteristic vector in the set of the first solder paste stirring state local characteristic vector to obtain a set of multiple first solder paste stirring state local characteristic distribution energy synergy representation vectors; a first solder paste stirring state characteristic distribution energy synergy factor calculation subunit, which is used to calculate the characteristic distribution energy synergy factor vector of the set of each first solder paste stirring state local characteristic distribution energy synergy representation vector in the set of the multiple first solder paste stirring state local characteristic distribution energy synergy representation vectors to obtain a set of the first solder paste stirring state local characteristic energy distribution spectrum vectors.

[0065] Further, in one embodiment of the present application, the first solder paste stirring state local feature distribution energy coordination subunit is used to: extract a predetermined first solder paste stirring state local feature vector from the set of the first solder paste stirring state local feature vectors; perform element-by-element maximum value extraction on the predetermined first solder paste stirring state local feature vector and each other first solder paste stirring state local feature vector, so as to obtain a set of first solder paste stirring state local feature distribution energy coordination representation vectors corresponding to the predetermined first solder paste stirring state local feature vector.

[0066] Furthermore, in one embodiment of the present application, the first solder paste stirring state characteristic distribution energy synergy factor calculation subunit is used to: respectively extract the maximum value of each first solder paste stirring state local characteristic distribution energy synergy representation vector in the set of the first solder paste stirring state local characteristic distribution energy synergy representation vector to obtain a set of first solder paste stirring state local characteristic maximum values; respectively calculate the mean and variance of each first solder paste stirring state local characteristic distribution energy synergy representation vector to obtain a set of first solder paste stirring state local characteristic mean values ​​and a set of first solder paste stirring state local characteristic variances; add the set of the first solder paste stirring state local characteristic variances and the preset hyperparameters by position to obtain a set of first energy distribution coefficients of the first solder paste stirring state local characteristics; calculate the first solder paste stirring state local characteristic maximum values ​​and the first solder paste stirring state local characteristic mean values ​​of each group corresponding to each group; The square of the difference between the maximum value of the characteristic and the mean value of the local characteristic of the first solder paste stirring state is obtained to obtain a set of local difference values ​​of the first solder paste stirring state; the set of local characteristic variances of the first solder paste stirring state is multiplied by constant two by position to obtain a set of modulated local characteristic variances of the first solder paste stirring state; after adding each group of corresponding local difference values ​​of the first solder paste stirring state and the set of local characteristic variances of the modulated first solder paste stirring state in the set of local difference values ​​of the first solder paste stirring state and the set of local characteristic variances of the modulated first solder paste stirring state, the sum is added to the preset hyperparameter to obtain a set of second energy distribution coefficients of local characteristics of the first solder paste stirring state; the set of first energy distribution coefficients of local characteristics of the first solder paste stirring state is divided by position by the set of second energy distribution coefficients of local characteristics of the first solder paste stirring state to obtain the first solder paste stirring state local characteristic energy distribution spectrum vector composed of multiple characteristic distribution energy synergy factors.

[0067] Furthermore, in one embodiment of the present application, the first solder paste stirring state energy distribution spectrum span factor calculation unit is used to: calculate the positional difference between the first solder paste stirring state local characteristic energy distribution spectrum vector and the first solder paste stirring state energy spectrum distribution center vector to obtain the first solder paste stirring state differential characteristic vector; calculate the covariance matrix between the first solder paste stirring state energy spectrum distribution center vector and the first solder paste stirring state local characteristic energy distribution spectrum vector, and calculate the inverse of the covariance matrix to obtain the first solder paste stirring state inverse covariance matrix; calculate the transposed vector of the first solder paste stirring state differential characteristic vector and the product of the first solder paste stirring state inverse covariance matrix and the first solder paste stirring state differential characteristic vector to obtain the first solder paste stirring state distribution value; calculate the square root of the first solder paste stirring state distribution value to obtain the first solder paste stirring state energy distribution spectrum span factor.

[0068] Specifically, the set of local feature vectors of the first solder paste stirring state is input into a feature sequence selection optimization module based on a feature energy distribution spectrum, and is processed using the following selection optimization formula to obtain the set of local feature vectors of the first solder paste stirring state after the selection; wherein the selection optimization formula is: ; ; ; ; ; ; ;in, and respectively represent the first solder paste stirring state local feature vector set and The first solder paste stirring state local feature vector, It means taking the maximum value between two vectors element by element. For the and The first solder paste stirring state local feature distribution energy synergy representation vector between the first solder paste stirring state local feature vectors, To extract the maximum value of a vector, and They are The mean and variance of To preset hyperparameters, is the first solder paste stirring state local characteristic energy distribution spectrum vector set The first solder paste stirring state local characteristic energy distribution spectrum vector The characteristic distribution energy synergy factor, For the The first solder paste stirring state local characteristic energy distribution spectrum vector The characteristic distribution energy synergy factor, represents the set of local characteristic energy distribution spectrum vectors of the first solder paste stirring state, is the first solder paste stirring state local characteristic energy distribution spectrum vector set The local characteristic energy distribution spectrum vector of the first solder paste stirring state, is the number of vectors in the set of the local characteristic energy distribution spectrum vectors of the first solder paste stirring state, is the center vector of energy spectrum distribution in the first solder paste stirring state, is the transpose of a vector, It is The covariance matrix between the local characteristic energy distribution spectrum vector of the first solder paste stirring state and the center vector of the energy spectrum distribution of the first solder paste stirring state, For the The energy distribution spectrum span factor of the first solder paste stirring state corresponding to the local characteristic energy distribution spectrum vector of the first solder paste stirring state, is the preset threshold, is the first local feature vector of the first solder paste stirring state after the selection. The local feature vector of the first solder paste stirring state after selection, is the set of the selected local feature vectors of the first solder paste stirring state. Similarly, the encoding method of the set of the local feature vectors of the second solder paste stirring state is as shown in the above formula.

[0069] Further, the set of local feature vectors of the first solder paste stirring state selected and the set of local feature vectors of the second solder paste stirring state selected respectively represent the important local feature information of the solder paste stirring state at the first time point and the second time point, and in order to understand the semantic changes of the solder paste state in the time evolution process more carefully, so as to better control the stirring temperature, in the technical solution of the present application, the set of local feature vectors of the first solder paste stirring state selected and the set of local feature vectors of the second solder paste stirring state selected are input into the sequence matching network based on energy-intensive interactive distribution to obtain the semantic offset coefficient of the solder paste state. In particular, the sequence matching network based on energy-intensive interactive distribution analyzes the semantic interactive matching between the local features of the solder paste stirring state between two time points in a fine-grained manner to understand the semantic offset relationship between the two. In detail, the energy synergistic response value between any pair of vectors is first calculated to reflect the correlation and synergistic relationship between the two feature vectors in energy distribution. Here, the energy synergistic response value captures the local fine-grained semantic association of the solder paste stirring state between any two feature vectors, forming a global distribution matrix of the synergistic energy fine-grained local features of the solder paste stirring state. Then, the global distribution matrix is ​​subjected to dilated convolutional coding to capture and extract deeper semantic relevance and interaction patterns. Finally, the dilated convolutional coded features are input into the inter-sequence matching metric network to model the complex temporal correlation and semantic offset relationship between the two feature sequences, thereby outputting the matching score between the two sequences. This score can more accurately reflect the degree of semantic offset between the solder paste state feature vector sequences between two time points, thus providing an important basis for the decision-making of the mixer temperature adjustment.

[0070] In one embodiment of the present application, the solder paste state semantic offset calculation module 106 includes: a solder paste stirring state local feature energy synergistic response value calculation unit, which is used to calculate the energy synergistic response value between any pair of selected first solder paste stirring state local feature vectors and selected second solder paste stirring state local feature vectors in the set of selected first solder paste stirring state local feature vectors and the set of selected second solder paste stirring state local feature vectors to obtain a solder paste stirring state local feature synergistic energy fine-grained global distribution matrix; a hole convolution coding unit, which is used to perform hole convolution coding on the solder paste stirring state local feature synergistic energy fine-grained global distribution matrix to obtain a solder paste stirring state local feature synergistic energy fine-grained global distribution feature matrix; and an inter-sequence matching degree measurement network unit, which is used to input the solder paste stirring state local feature synergistic energy fine-grained global distribution feature matrix into the inter-sequence matching degree measurement network to obtain the solder paste state semantic offset coefficient.

[0071] Furthermore, in one embodiment of the present application, the solder paste stirring state local characteristic energy synergistic response value calculation unit is used to: calculate the position-by-position division between the selected first solder paste stirring state local characteristic vector and the selected second solder paste stirring state local characteristic vector to obtain the selected solder paste stirring state local response characteristic vector; extract the maximum value of the selected solder paste stirring state local response characteristic vector to obtain the selected solder paste stirring state local response characteristic maximum value; respectively calculate the mean and variance of the selected solder paste stirring state local response characteristic vector to obtain the selected solder paste stirring state local response characteristic mean and the selected solder paste stirring state local response characteristic variance; multiply the value obtained by adding the selected solder paste stirring state local response characteristic variance and the offset term by four to obtain the selected solder paste stirring state local characteristic first energy synergistic response value; calculate the square of the difference between the maximum value of the selected local response characteristic of the solder paste stirring state and the mean value of the selected local response characteristic of the solder paste stirring state to obtain the difference value of the selected local response characteristic of the solder paste stirring state; add the modulated local response characteristic variance of the selected solder paste stirring state obtained by multiplying the variance of the selected local response characteristic of the solder paste stirring state by two, the value obtained by multiplying the bias term by two and the difference value of the selected local response characteristic of the solder paste stirring state to obtain the second energy synergistic response value of the selected local characteristic of the solder paste stirring state; divide the first energy synergistic response value of the selected local characteristic of the solder paste stirring state by the second energy synergistic response value of the selected local characteristic of the solder paste stirring state to obtain the energy synergistic response value between the selected first local characteristic feature vector of the solder paste stirring state and the selected second local characteristic feature vector of the solder paste stirring state.

[0072] Specifically, the set of the selected first solder paste stirring state local feature vectors and the set of the selected second solder paste stirring state local feature vectors are input into an inter-sequence matching network based on energy-intensive interactive distribution, and processed with the following inter-sequence matching formula to obtain the solder paste state semantic shift coefficient; wherein the inter-sequence matching formula is: ; ; ; ; ; ;in, and The first and second solder paste stirring state local feature vectors are respectively represented by the set of the selected first solder paste stirring state local feature vectors and the set of the selected second solder paste stirring state local feature vectors. The first solder paste stirring state local feature vector and the The local feature vector of the second solder paste stirring state after selection, It means to calculate the energy synergy response value between two vectors. is the fine-grained global distribution matrix of the local characteristics of the solder paste stirring state and the coordinated energy The eigenvalues ​​at the positions, To extract the maximum value of a vector, For the The first solder paste stirring state local feature vector and the The selected solder paste stirring state local response feature vector between the selected second solder paste stirring state local feature vectors, and They are The mean and variance of is the bias term, is the global distribution matrix of the local characteristics and energy fine-grainedness of the solder paste stirring state, , , , They are respectively the local characteristics of the solder paste stirring state, the synergistic energy, and the fine-grained global distribution matrix , , , The eigenvalues ​​at the positions, is the dilated convolutional coding, is the local feature synergistic energy fine-grained global distribution feature matrix of the solder paste stirring state, is the matching degree measurement operation between sequences, is the solder paste state semantic shift coefficient.

[0073] Next, the solder paste state semantic shift coefficient is divided by the time interval to obtain the solder paste state semantic change rate. That is, the solder paste state semantic change rate can more intuitively reflect the dynamic change trend of the solder paste state in the time evolution process, which helps to understand the real-time change characteristics of the solder paste state, so as to more accurately predict the change of the solder paste state at the next moment, so as to make a more appropriate temperature adjustment.

[0074] Then, based on the comparison between the semantic change rate of the solder paste state and the predetermined threshold, it is determined whether the stirring temperature at the next time point increases. That is, the semantic change rate of the solder paste state calculated by the solder paste state semantic offset coefficient and the time interval is used to automatically determine whether the stirring temperature at the next time point increases. In this way, the solder paste stirring state image can be collected in real time to monitor the stirring process uninterruptedly, and the dynamic time series changes of the solder paste state can be accurately captured by using deep learning technology, thereby achieving precise control of the solder paste state, reducing quality fluctuations and instability caused by untimely or inaccurate temperature adjustment, thereby improving the degree of automation of stirring temperature control.

[0075] Preferably, considering that the set of selected first solder paste stirring state local feature vectors and the set of selected second solder paste stirring state local feature vectors respectively represent the image semantic features of the first solder paste stirring state image at the first time point and the second solder paste stirring state image at the second time point based on selective optimization of feature energy distribution, when calculating the solder paste state semantic shift coefficient of the sequence matching network based on energy-intensive interactive distribution to map it to the common image semantic feature shift metric space, there will also be an image semantic feature aggregation mapping shift caused by inconsistent image semantic feature distribution energy selectivity, so as to further improve the comprehensibility of the common mapping of image semantic features of the set of selected first solder paste stirring state local feature vectors and the set of selected second solder paste stirring state local feature vectors, thereby improving the calculation accuracy of the solder paste state semantic shift coefficient.

[0076] Therefore, when the set of selected first solder paste stirring state local feature vectors and the set of selected second solder paste stirring state local feature vectors are input into an inter-sequence matching network based on energy-intensive interactive distribution to obtain a solder paste state semantic shift coefficient, the present application jointly optimizes the set of selected first solder paste stirring state local feature vectors and the set of selected second solder paste stirring state local feature vectors, including the steps of:

[0077] Cascading each feature vector in the selected set of local feature vectors of the first solder paste stirring state and the selected set of local feature vectors of the second solder paste stirring state into a first-second solder paste stirring state local cascade feature vector;

[0078] Subtract the zero norm of the first-second solder paste stirring state local cascade feature vector from the length of the first-second solder paste stirring state local cascade feature vector to obtain a first-second solder paste stirring state local cascade isolated representation value;

[0079] Calculate the logarithm of the square of the first-second solder paste stirring state local cascade isolated representation value and the sum of the first-second solder paste stirring state local cascade isolated representation value with base 2 to obtain the first-second solder paste stirring state local cascade information order value;

[0080] Calculate a power function with each eigenvalue of the first-second solder paste stirring state local cascade eigenvector as the base, the difference of the first-second solder paste stirring state local cascade isolated representation value minus one as the exponent, and perform a point multiplication with the first-second solder paste stirring state local cascade information order value to obtain the first-second solder paste stirring state local cascade leading vector;

[0081] After performing a dot multiplication on the difference between the first and second solder paste stirring state local cascade feature vectors and the first and second solder paste stirring state local cascade isolated representation values ​​minus one, the dot multiplication is then performed on the inverse of the first and second solder paste stirring state local cascade isolated representation values ​​to obtain a first and second solder paste stirring state local cascade field constraint vector;

[0082] Calculate an exponential function with a natural constant as the base and each eigenvalue of the first-second solder paste stirring state local cascade field constraint vector as the exponent to obtain a first-second solder paste stirring state local cascade field bias vector;

[0083] Performing point addition of the first-second solder paste stirring state local cascade pilot vector and the first-second solder paste stirring state local cascade field bias vector to obtain an optimized first-second solder paste stirring state local cascade feature vector;

[0084] The optimized first-second solder paste stirring state local cascade feature vector is split into a set of optimized selected first solder paste stirring state local feature vectors and a set of optimized selected second solder paste stirring state local feature vectors.

[0085] The optimization process of the local cascade feature vector of the first-second solder paste stirring state is expressed as: ; ; To calculate a power function with each eigenvalue of the local cascade eigenvector of the first-second solder paste stirring state as the base and the difference of the local cascade isolated representation value of the first-second solder paste stirring state minus one as the exponent, is the local cascade feature vector of the first-second solder paste stirring state, is the zero norm of the vector, is the length of the local cascade feature vector of the first-second solder paste stirring state, It is the local cascade isolated representation value of the first-second solder paste stirring state. It is an exponential function that calculates the exponential function of each eigenvalue of a vector with a natural constant as the base. is the optimized local cascade feature vector of the first-second solder paste stirring state, It is the point multiplication by position. It is added by location point.

[0086] Therefore, for the high-dimensional feature manifold of the set of local feature vectors of the selected first solder paste stirring state and the set of local feature vectors of the selected second solder paste stirring state, the eigenvalues ​​of the feature set are used as the vector field representation of the aggregation dimension, and the overlapping values ​​of the vector field of the first-second solder paste stirring state local cascade feature vectors at the isolated zero position are used as the order information to fix the local position of the eigenvalues ​​of the feature set, and a bias for the reversibility of the feature regression distribution field of the first-second solder paste stirring state local cascade feature vectors is added as a reward to achieve the mapping target tracking of the regression distribution of the first-second solder paste stirring state local cascade feature vectors for the eigenvalue position, so that the feature sets of the set of local feature vectors of the selected first solder paste stirring state and the set of local feature vectors of the selected second solder paste stirring state perceive the mapping migration to the aggregate distribution, thereby improving the calculation accuracy of the solder paste state semantic offset coefficient by improving the comprehensibility of the joint mapping of the image semantic features of the set of local feature vectors of the selected first solder paste stirring state and the set of local feature vectors of the selected second solder paste stirring state. In this way, the solder paste stirring state image can be collected in real time to continuously monitor the stirring process, and the deep learning technology can be used to accurately capture the dynamic timing changes of the solder paste state, thereby achieving precise control of the solder paste state and reducing quality fluctuations and instability caused by untimely or inaccurate temperature adjustment, thereby improving the degree of automation of stirring temperature control.

[0087] In summary, the above scheme is adopted, by collecting the first solder paste stirring state image of the solder paste to be stirred at the first time point and the second solder paste stirring state image at the second time point by the camera, and calculating the time interval between the second time point and the first time point, and using the image analysis and processing technology based on deep learning to extract features, select optimization and calculate semantic offset of the solder paste stirring state images at the two time points, so as to automatically determine whether the stirring temperature at the next time point is increased based on the comparison between the state semantic change rate between the solder paste state semantic offset coefficient and the time interval and the predetermined threshold. In this way, the solder paste stirring state image can be collected in real time to monitor the stirring process uninterruptedly, and the dynamic time sequence change of the solder paste state can be accurately captured by using deep learning technology, so as to realize the precise control of the solder paste state, reduce the quality fluctuation and instability caused by untimely or inaccurate temperature adjustment, thereby improving the automation and intelligence level of stirring temperature control.

[0088] Figure 2 is a flow chart of an intelligent control method for a mixing machine according to an exemplary embodiment. Figure 2 As shown, the method includes:

[0089] Step S201: acquiring a first solder paste stirring state image of the solder paste to be stirred at a first time point and a second solder paste stirring state image at a second time point collected by a camera;

[0090] Step S202: Calculate the time interval between the second time point and the first time point;

[0091] Step S203: inputting the second solder paste stirring state image and the first solder paste stirring state image into a stirring state feature extractor to obtain a first solder paste stirring state feature map and a second solder paste stirring state feature map;

[0092] Step S204: performing feature dispersion on the first solder paste stirring state feature map and the second solder paste stirring state feature map to obtain a set of first solder paste stirring state local feature vectors and a set of second solder paste stirring state local feature vectors;

[0093] Step S205: inputting the set of the first solder paste stirring state local feature vectors and the set of the second solder paste stirring state local feature vectors into a feature sequence selection optimization module based on a feature energy distribution spectrum to obtain a selected set of the first solder paste stirring state local feature vectors and a selected set of the second solder paste stirring state local feature vectors;

[0094] Step S206: inputting the selected set of local feature vectors of the first solder paste stirring state and the selected set of local feature vectors of the second solder paste stirring state into an inter-sequence matching network based on energy-intensive interactive distribution to obtain a solder paste state semantic shift coefficient;

[0095] Step S207: Dividing the solder paste state semantic shift coefficient by the time interval to obtain a solder paste state semantic change rate;

[0096] Step S208: Based on the comparison between the solder paste state semantic change rate and a predetermined threshold, determining whether the stirring temperature at the next time point is increased.

[0097] Reference below Figure 3 , which shows a schematic diagram of the structure of an electronic device 600 suitable for implementing the embodiment of the present application. The terminal device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0098] like Figure 3 As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0099] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0100] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present application are executed.

[0101] It should be noted that the computer-readable medium mentioned above in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0102] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0103] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0104] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0105] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0106] The modules involved in the embodiments described in this application can be implemented by software or hardware. The name of the module does not limit the module itself in some cases. For example, the test parameter acquisition module can also be described as a "module for acquiring device test parameters corresponding to the target device".

[0107] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0108] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0109] Figure 4 : is an application scenario diagram of an intelligent control system for a mixing machine according to an exemplary embodiment. Figure 4 As shown, in this application scenario, first, a first solder paste stirring state image (for example, Figure 4 C1) and a second solder paste stirring state image at a second time point (e.g., Figure 4 Then, the obtained first solder paste stirring state image and second solder paste stirring state image are input to a server (for example, Figure 4 In S) shown in , the server is capable of processing the first solder paste stirring state image and the second solder paste stirring state image based on the intelligent control algorithm of the mixer to determine whether the stirring temperature at the next time point is increased.

[0110] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

[0111] In addition, although each operation is described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or to be performed in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the application. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0112] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely exemplary forms of implementation. With respect to the apparatus in the above-mentioned embodiments, the specific manner in which each module performs the operation has been described in detail in the embodiments related to the method, and will not be described in detail here.

Claims

1. An intelligent control system for a mixing machine, characterized in that: include: A solder paste stirring state image acquisition module, used to acquire a first solder paste stirring state image of the solder paste to be stirred at a first time point and a second solder paste stirring state image at a second time point collected by a camera; A time interval calculation module, used to calculate the time interval between the second time point and the first time point; A solder paste stirring state feature extraction module, used for inputting the second solder paste stirring state image and the first solder paste stirring state image into a stirring state feature extractor to obtain a first solder paste stirring state feature map and a second solder paste stirring state feature map; A stirring state local feature extraction module, used for performing feature dispersion on the first solder paste stirring state feature map and the second solder paste stirring state feature map to obtain a set of first solder paste stirring state local feature vectors and a set of second solder paste stirring state local feature vectors; A solder paste stirring state local feature optimization module, used for inputting the set of the first solder paste stirring state local feature vectors and the set of the second solder paste stirring state local feature vectors into a feature sequence selection optimization module based on a feature energy distribution spectrum to obtain a selected set of the first solder paste stirring state local feature vectors and a selected set of the second solder paste stirring state local feature vectors; A solder paste state semantic shift calculation module, used for inputting the selected set of local feature vectors of the first solder paste stirring state and the selected set of local feature vectors of the second solder paste stirring state into an inter-sequence matching network based on energy-intensive interactive distribution to obtain a solder paste state semantic shift coefficient; A solder paste state semantic change rate calculation module, used for dividing the solder paste state semantic offset coefficient by the time interval to obtain the solder paste state semantic change rate; The stirring temperature control module is used to determine whether the stirring temperature at a next time point is increased based on a comparison between the solder paste state semantic change rate and a predetermined threshold.

2. The intelligent control system of the material mixer according to claim 1 is characterized in that: The solder paste stirring state local feature optimization module includes: A first solder paste stirring state local characteristic energy distribution spectrum calculation unit, used to calculate the characteristic energy distribution spectrum vector of each first solder paste stirring state local characteristic vector in the set of the first solder paste stirring state local characteristic vectors to obtain a set of first solder paste stirring state local characteristic energy distribution spectrum vectors; A position mean vector calculation unit, used for calculating the position mean vector of the set of local characteristic energy distribution spectrum vectors of the first solder paste stirring state as the center vector of the energy spectrum distribution of the first solder paste stirring state; A first solder paste stirring state energy distribution spectrum span factor calculation unit, used to calculate the energy distribution spectrum span factor between the first solder paste stirring state energy spectrum distribution center vector and each first solder paste stirring state local characteristic energy distribution spectrum vector in the set of the first solder paste stirring state local characteristic energy distribution spectrum vector to obtain a set of first solder paste stirring state energy distribution spectrum span factors; A span factor and preset threshold comparison unit is used to determine the set of selected first solder paste stirring state local feature vectors based on the comparison between each first solder paste stirring state energy distribution spectrum span factor in the set of the first solder paste stirring state energy distribution spectrum span factors and the preset threshold.

3. The intelligent control system of the material mixer according to claim 2 is characterized in that: The first solder paste stirring state local characteristic energy distribution spectrum calculation unit includes: A first solder paste stirring state local feature distribution energy synergy subunit is used to respectively calculate the feature distribution energy synergy representation vector between each first solder paste stirring state local feature vector and each other first solder paste stirring state local feature vector in the set of the first solder paste stirring state local feature vector to obtain a set of multiple first solder paste stirring state local feature distribution energy synergy representation vectors; The first solder paste stirring state characteristic distribution energy synergy factor calculation subunit is used to calculate the characteristic distribution energy synergy factor vector of the set of each first solder paste stirring state local characteristic distribution energy synergy representation vector in the set of the multiple first solder paste stirring state local characteristic distribution energy synergy representation vectors to obtain the set of the first solder paste stirring state local characteristic energy distribution spectrum vectors.

4. The intelligent control system for a material mixer according to claim 3 is characterized in that: The first solder paste stirring state local characteristic distribution energy coordination subunit is used for: extracting a predetermined first solder paste stirring state local feature vector from the set of the first solder paste stirring state local feature vectors; The predetermined first solder paste stirring state local feature vector and each other first solder paste stirring state local feature vector are respectively subjected to element-by-element maximum value extraction to obtain a set of first solder paste stirring state local feature distribution energy synergistic representation vectors corresponding to the predetermined first solder paste stirring state local feature vector.

5. The intelligent control system for a material mixer according to claim 4 is characterized in that: The first solder paste stirring state characteristic distribution energy synergy factor calculation subunit is used to: Respectively extracting the maximum value of each first solder paste stirring state local feature distribution energy synergistic representation vector in the set of the first solder paste stirring state local feature distribution energy synergistic representation vector to obtain a set of first solder paste stirring state local feature maximum values; Respectively calculating the mean and variance of each first solder paste stirring state local feature distribution energy synergy representation vector to obtain a set of first solder paste stirring state local feature means and a set of first solder paste stirring state local feature variances; Adding the set of the first solder paste stirring state local feature variances and the preset hyperparameters by position to obtain a set of first energy distribution coefficients of the first solder paste stirring state local feature; Calculate the square of the difference between the maximum value of the local characteristic of the first solder paste stirring state and the mean value of the local characteristic of the first solder paste stirring state corresponding to each group in the set of the maximum value of the local characteristic of the first solder paste stirring state and the set of the mean value of the local characteristic of the first solder paste stirring state to obtain a set of local difference values ​​of the first solder paste stirring state; Multiplying the set of the first solder paste stirring state local feature variances by constant 2 by position to obtain a set of modulated first solder paste stirring state local feature variances; After adding each group of corresponding local difference values ​​of the first solder paste stirring state and the local feature variance of the modulated first solder paste stirring state in the set of local difference values ​​of the first solder paste stirring state and the set of local feature variance of the modulated first solder paste stirring state, the sum is added to the preset hyperparameter to obtain a set of second energy distribution coefficients of the local feature of the first solder paste stirring state; The set of first energy distribution coefficients of the first solder paste stirring state local characteristics and the set of second energy distribution coefficients of the first solder paste stirring state local characteristics are divided by position to obtain the first solder paste stirring state local characteristic energy distribution spectrum vector composed of multiple characteristic distribution energy synergy factors.

6. The intelligent control system for a material mixer according to claim 5, characterized in that: The first solder paste stirring state energy distribution spectrum span factor calculation unit is used to: Calculating the position difference between the first solder paste stirring state energy spectrum distribution center vector and the first solder paste stirring state local characteristic energy distribution spectrum vector to obtain a first solder paste stirring state differential characteristic vector; Calculate the covariance matrix between the center vector of the energy spectrum distribution of the first solder paste stirring state and the local characteristic energy distribution spectrum vector of the first solder paste stirring state, and calculate the inverse of the covariance matrix to obtain the first solder paste stirring state inverse covariance matrix; Calculating the transposed vector of the first solder paste stirring state differential eigenvector and the product of the first solder paste stirring state inverse covariance matrix and the first solder paste stirring state differential eigenvector to obtain a first solder paste stirring state distribution value; The square root of the first solder paste stirring state distribution value is calculated to obtain the first solder paste stirring state energy distribution spectrum span factor.

7. The intelligent control system for a material mixer according to claim 6, characterized in that: The solder paste state semantic offset calculation module includes: A solder paste stirring state local characteristic energy synergistic response value calculation unit, used to calculate the energy synergistic response value between any pair of the selected first solder paste stirring state local characteristic vector set and the selected second solder paste stirring state local characteristic vector set in order to obtain a solder paste stirring state local characteristic synergistic energy fine-grained global distribution matrix; A hole convolution coding unit, used for performing hole convolution coding on the solder paste stirring state local feature collaborative energy fine-grained global distribution matrix to obtain the solder paste stirring state local feature collaborative energy fine-grained global distribution feature matrix; The inter-sequence matching degree measurement network unit is used to input the solder paste stirring state local feature collaborative energy fine-grained global distribution feature matrix into the inter-sequence matching degree measurement network to obtain the solder paste state semantic offset coefficient.

8. The intelligent control system for a material mixer according to claim 7, characterized in that: The solder paste stirring state local characteristic energy synergistic response value calculation unit is used to: Calculating the position-by-position division between the selected first solder paste stirring state local feature vector and the selected second solder paste stirring state local feature vector to obtain a selected solder paste stirring state local response feature vector; Extracting the maximum value of the local response characteristic vector of the selected solder paste stirring state to obtain the maximum value of the local response characteristic of the selected solder paste stirring state; Respectively calculating the mean and variance of the selected local response feature vector of the solder paste stirring state to obtain the selected local response feature mean of the solder paste stirring state and the selected local response feature variance of the solder paste stirring state; The value obtained by adding the selected solder paste stirring state local response characteristic variance and the bias term is multiplied by four to obtain the selected solder paste stirring state local characteristic first energy synergistic response value; Calculating the square of the difference between the maximum value of the selected solder paste stirring state local response characteristic and the mean value of the selected solder paste stirring state local response characteristic to obtain a selected solder paste stirring state local response characteristic difference value; The second energy synergistic response value of the selected solder paste stirring state local feature is obtained by adding the modulated selected solder paste stirring state local feature variance obtained by multiplying the selected solder paste stirring state local feature variance by two, the value obtained by multiplying the bias term by two, and the selected solder paste stirring state local feature difference value; The first energy synergistic response value of the selected local characteristic of the solder paste stirring state is divided by the second energy synergistic response value of the selected local characteristic of the solder paste stirring state to obtain the energy synergistic response value between the selected first local characteristic vector of the solder paste stirring state and the selected second local characteristic vector of the solder paste stirring state.

9. An intelligent control method for a mixing machine, characterized in that: include: Acquire a first solder paste stirring state image of the solder paste to be stirred at a first time point and a second solder paste stirring state image at a second time point collected by a camera; Calculating the time interval between the second time point and the first time point; Inputting the second solder paste stirring state image and the first solder paste stirring state image into a stirring state feature extractor to obtain a first solder paste stirring state feature map and a second solder paste stirring state feature map; Performing feature dispersion on the first solder paste stirring state feature map and the second solder paste stirring state feature map to obtain a set of first solder paste stirring state local feature vectors and a set of second solder paste stirring state local feature vectors; Inputting the set of the first solder paste stirring state local feature vectors and the set of the second solder paste stirring state local feature vectors into a feature sequence selection optimization module based on a feature energy distribution spectrum to obtain a selected set of the first solder paste stirring state local feature vectors and a selected set of the second solder paste stirring state local feature vectors; Inputting the selected set of local feature vectors of the first solder paste stirring state and the selected set of local feature vectors of the second solder paste stirring state into an inter-sequence matching network based on energy-intensive interaction distribution to obtain a solder paste state semantic shift coefficient; Dividing the solder paste state semantic shift coefficient by the time interval to obtain a solder paste state semantic change rate; Based on the comparison between the solder paste state semantic change rate and a predetermined threshold, it is determined whether the stirring temperature at the next time point is increased.

Citation Information

Patent Citations

  • Temperature control method, device, terminal and storage medium for solder paste mixer

    CN117348643B

  • Control method for mixer truck, processor and control device

    CN113733354A

  • Method and device for adjusting size of discharge port of mixing plant based on deep learning

    CN115592819A