Manufacturing equipment manufacturing parameter adjustment control system and method

Through the combination of self-organized image network and DeepFM model, the parameters of manufacturing equipment are dynamically adjusted, and the efficiency and quality problems caused by the fixed parameters of manufacturing equipment in the existing technology are solved, intelligent adjustment is achieved, and production efficiency and energy utilization are improved.

CN114547785BActive Publication Date: 2024-11-22INVENTEC PUDONG TECH CORPOARTION +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202011335344.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-11-25
Publication Date
2024-11-22
Estimated Expiration
2040-11-25

AI Technical Summary

Technical Problem

The manufacturing parameters setting methods of existing manufacturing equipment require experience and fixed, and cannot be intelligently adjusted to adapt to changes in production conditions, resulting in poor efficiency, quality and energy utilization.

Method used

Adopting self-organized image network and DeepFM model is used to receive manufacturing equipment and product information, generate data image results grid diagrams, select key parameters, and use DeepFM model to perform nonlinear regression and dynamically adjust manufacturing parameters.

Benefits of technology

Intelligent adjustment of manufacturing equipment parameters has been achieved, and production efficiency, quality and energy utilization efficiency have been improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114547785B_ABST
    Figure CN114547785B_ABST
Patent Text Reader

Abstract

A manufacturing parameter adjustment control system and method for manufacturing equipment, wherein a self-organizing image network is constructed, and manufacturing parameters corresponding to all manufacturing parameter record data in the group and manufacturing parameters of manufacturing equipment information are input into the self-organizing image network to generate a data image result grid diagram, and the group of manufacturing parameter record data corresponding to the highest grid image number in the data image result grid diagram is selected as the manufacturing parameters of the manufacturing equipment information, and then a DeepFM model is constructed with at least one target parameter selected from the manufacturing parameters of the manufacturing equipment information as the output parameter and unselected manufacturing parameters and a group of detection parameters in the manufacturing parameters of the manufacturing equipment information as the input parameters, and the output parameters output by the trained and verified DeepFM model are subjected to nonlinear regression and matched with the input parameters to generate at least one target parameter, and the corresponding manufacturing parameters of the manufacturing equipment information are dynamically adjusted according to the at least one target parameter.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to an adjustment control system and a method thereof, and in particular to a manufacturing parameter adjustment control system and a method thereof, which first calculates the manufacturing parameters of manufacturing equipment information by a self-organizing image network to provide manufacturing equipment for manufacturing use, and then dynamically calculates at least one target parameter by a DeepFM model to dynamically adjust the manufacturing parameters of the corresponding manufacturing equipment information. Background Art

[0002] Currently, in the manufacturing process, the manufacturing parameters used by the manufacturing equipment are usually manually set by experienced engineers when the production is started, or the set manufacturing parameters are stored in the manufacturing equipment in advance, and the manufacturing parameter record data is read and used when the manufacturing equipment is to start production.

[0003] The above-mentioned method of setting the manufacturing parameters of the manufacturing equipment requires the technician to have certain experience or technical level. In addition, since the manufacturing parameters of the manufacturing equipment are set to fixed values, the manufacturing equipment cannot comprehensively utilize the changing production status information to achieve more efficient, high-quality and energy-saving manufacturing production.

[0004] In summary, it can be seen that the prior art has long had the problem that the manufacturing parameters of manufacturing equipment cannot be adjusted intelligently, so it is necessary to propose improved technical means to solve this problem. Summary of the invention

[0005] In view of the problem that the manufacturing parameters of manufacturing equipment in the prior art cannot be adjusted intelligently, the present invention discloses a manufacturing parameter adjustment control system and method for manufacturing equipment, wherein:

[0006] The manufacturing equipment manufacturing parameter adjustment control system disclosed in the present invention comprises: a parameter database, a receiving module, a query module, a neural network-like calculation module, a parameter selection module and a transmission module.

[0007] The parameter database is used to store storage time, manufacturing equipment information, production product information and a corresponding set of manufacturing parameter record data; the receiving module is used to receive the manufacturing equipment information and the production product information, and receive a set of detection parameters from the manufacturing equipment, wherein the set of detection parameters is obtained by detection by a sensor set in the manufacturing equipment; the query module is used to query the set of manufacturing parameter record data that meets the preset quantity according to the manufacturing equipment information and the production product information received by the receiving module; the neural network calculation module multiplies the manufacturing parameter setting quantity of the manufacturing equipment information by the manufacturing parameter setting quantity of the manufacturing equipment information to construct a self-organizing image network (Self-Organizing Image Network A method for preparing a DeepFM model is disclosed in the present invention. The method comprises the steps of: a first manufacturing parameter map (SOM) and a second manufacturing parameter map (SOM) for selecting the manufacturing parameter record data of the group of manufacturing parameter record data obtained by the query and the manufacturing parameters corresponding to the manufacturing parameters of the manufacturing equipment information into a self-organizing mapping network to generate a data mapping result grid map; a DeepFM model is constructed by selecting at least one target parameter from the manufacturing parameters of the manufacturing equipment information as an output parameter and the manufacturing parameters not selected from the manufacturing parameters of the manufacturing equipment information and the group of detection parameters as input parameters; the DeepFM model is then divided into a training parameter set and a test parameter set according to a preset ratio; the DeepFM model is trained by the training parameter set; the trained DeepFM model is then verified by the test parameter set; the output parameters output by the trained and verified DeepFM model are subjected to nonlinear regression and matched with the input parameters to generate at least one target parameter; a parameter selection module is used to select the group of manufacturing parameter record data corresponding to the highest number of grid maps in the data mapping result grid map as the manufacturing parameters of the manufacturing equipment information; and a transmission module is used to transmit the manufacturing parameters of the manufacturing equipment information to the manufacturing equipment so as to use the manufacturing parameters of the manufacturing equipment information to produce products; and at least one target parameter is transmitted to the manufacturing equipment so as to dynamically adjust the corresponding manufacturing parameters of the manufacturing equipment information according to the at least one target parameter.

[0008] The manufacturing parameter adjustment control method of manufacturing equipment disclosed in the present invention comprises the following steps:

[0009] First, the storage time, manufacturing equipment information, production product information and a corresponding set of manufacturing parameter record data are stored; then, the manufacturing equipment information and the production product information are received; then, the group of manufacturing parameter record data that meets the preset quantity is queried according to the manufacturing equipment information and the production product information; then, the manufacturing parameter setting quantity of the manufacturing equipment information is multiplied by the manufacturing parameter setting quantity of the manufacturing equipment information to establish a self-organizing image network, and the manufacturing parameters corresponding to all the queried groups of manufacturing parameter record data and the manufacturing parameters of the manufacturing equipment information are input into the self-organizing image network to generate a data image result grid map; then, the group of manufacturing parameter record data corresponding to the highest grid image number in the data image result grid map is selected as the manufacturing parameters of the manufacturing equipment information; then, the manufacturing parameters of the manufacturing equipment information are transmitted to the manufacturing equipment to use the manufacturing parameters of the manufacturing equipment information to produce the product. ; Then, a set of detection parameters is received from the manufacturing equipment, wherein the set of detection parameters is obtained by detection by a sensor set in the manufacturing equipment; Then, at least one target parameter is selected from the manufacturing parameters of the manufacturing equipment information as an output parameter and the unselected manufacturing parameters in the manufacturing parameters of the manufacturing equipment information and the set of detection parameters are used as input parameters to build a DeepFM model, and then the queried set of manufacturing parameter record data is divided into a training parameter set and a test parameter set according to a preset ratio, the training parameter set is used to train the DeepFM model, and then the trained DeepFM model is verified by the test parameter set, and the output parameters output by the trained and verified DeepFM model are subjected to nonlinear regression and matched with the input parameters to generate at least one target parameter; Finally, the at least one target parameter is transmitted to the manufacturing equipment to dynamically adjust the corresponding manufacturing parameters of the manufacturing equipment information according to the at least one target parameter.

[0010] The system and method disclosed in the present invention are as described above, and the difference between them and the prior art lies in that a group of manufacturing parameter record data that meets a preset number is queried according to the manufacturing equipment information and the production product information, a self-organizing image network is established according to the manufacturing parameters of the manufacturing equipment information to input all the manufacturing parameters corresponding to the group of manufacturing parameter record data and the manufacturing parameters of the manufacturing equipment information into the self-organizing image network to generate a data image result grid diagram, the group of manufacturing parameter record data corresponding to the highest grid image number in the data image result grid diagram is selected as the manufacturing parameters of the manufacturing equipment information, and then a DeepFM model is established with at least one target parameter selected from the manufacturing parameters of the manufacturing equipment information as the output parameter and the unselected manufacturing parameters and a group of detection parameters in the manufacturing parameters of the manufacturing equipment information as the input parameters, the output parameters output by the trained and verified DeepFM model are subjected to nonlinear regression and combined with the input parameters to generate at least one target parameter, so that the corresponding manufacturing parameters of the manufacturing equipment information can be dynamically adjusted according to the at least one target parameter.

[0011] Through the above-mentioned technical means, the present invention can achieve the technical effect of providing manufacturing parameters of manufacturing equipment with intelligent adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A system block diagram of the manufacturing parameter adjustment control system of the manufacturing equipment of the present invention is shown.

[0013] Figure 2 A schematic diagram of manufacturing parameter recording data for manufacturing parameter adjustment control of the manufacturing equipment of the present invention is shown.

[0014] Figure 3 A grid diagram showing the data imaging results of the manufacturing parameter adjustment control of the manufacturing equipment of the present invention.

[0015] Figure 4 A schematic diagram of manufacturing parameters for adjusting and controlling manufacturing parameters of the manufacturing equipment of the present invention is shown.

[0016] Figure 5 A schematic diagram of the DeepFM model for adjusting and controlling manufacturing parameters of the manufacturing equipment of the present invention is shown.

[0017] Fig. 6A as well as Figure 6B A method flow chart showing the method for adjusting and controlling manufacturing parameters of manufacturing equipment according to the present invention.

[0018] Description of reference numerals:

[0019] 10. Manufacturing Equipment

[0020] 20 Parameter calculation device

[0021] 21 Parameter database

[0022] 22. Receiver Module

[0023] 23 Query Module

[0024] 24 types of neural network computing modules

[0025] 25 Parameter selection module

[0026] 26 Transmission Module

[0027] 31 Manufacturing parameter record data

[0028] 32 Data Mapping Result Grid

[0029] 33 Manufacturing parameters

[0030] 40 DeepFM Model DETAILED DESCRIPTION

[0031] The following will describe the implementation methods of the present invention in detail with reference to drawings and examples, so that the implementation process of how the present invention applies technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly.

[0032] The following first describes the manufacturing equipment manufacturing parameter adjustment control system disclosed in the present invention, and please refer to Figure 1 As shown, Figure 1 A system block diagram of the manufacturing parameter adjustment control system of the manufacturing equipment of the present invention is shown.

[0033] The manufacturing equipment manufacturing parameter adjustment control system disclosed in the present invention includes: a parameter database 21, a receiving module 22, a query module 23, a neural network computing module 24, a parameter selection module 25 and a transmission module 26. The aforementioned parameter database 21, receiving module 22, query module 23, neural network computing module 24, parameter selection module 25 and transmission module 26 are executed in a parameter calculation device 20.

[0034] The manufacturing equipment 10 is a device that provides product manufacturing. The manufacturing equipment 10 and the parameter calculation device 20 establish a connection through a wired transmission method or a wireless transmission method. The aforementioned wired transmission method is, for example: cable network, optical fiber network, etc., and the aforementioned wireless transmission method is, for example: Wi-Fi, mobile communication network (for example: 3G, 4G, 5G, etc.), etc. This is only for illustration and does not limit the scope of application of the present invention.

[0035] The parameter database 21 is used to store storage time, manufacturing equipment information, production product information and a corresponding set of manufacturing parameter record data. Specifically, the manufacturing equipment information is, for example, the equipment number of the corresponding manufacturing equipment, and the production product information is, for example, the name of the production product. The manufacturing parameter record data 31 is, for example: Front Pressure, Rear Pressure, Front Print Speed, Rear Print Speed, Front Print Limit, Rear Print Limit, ForwardX Offset, Reverse X Offset, Forward Y Offset, Reverse Y Offset, Forward ThetaOffset, Reverse Theta Offset, Separation Speed, Separation Distance, Print Gap, Clean Rate1, Clean Rate2, Paste While Clean, Paste Dispense Rate and Alternative Dispense Rate. This is only an example for explanation, and the scope of application of the present invention is not limited thereto. For a schematic diagram of the manufacturing parameter record data 31, please refer to Figure 2 As shown, Figure 2 A schematic diagram of manufacturing parameter recording data for manufacturing parameter adjustment control of the manufacturing equipment of the present invention is shown. In addition, the manufacturing parameter recording data may also be the following manufacturing parameters: Actual Separation Speed, Actual Front Pressure, Actual Front Print Speed, Actual Humidity, ActualTemperature, Actual Rear Pressure, Actual Cycle Time, State, Squeegee, ProductName and DateTime, which are only used as examples and are not intended to limit the scope of application of the present invention.

[0036] The receiving module 22 receives manufacturing equipment information and production product information input by the user through the user operation interface (such as keyboard, mouse, touch screen, etc., which is only used as an example and does not limit the scope of application of the present invention) provided by the parameter calculation device 20.

[0037] When the receiving module 22 receives the manufacturing equipment information and the production product information, the query module 23 can query the group of manufacturing parameter record data that meets the preset quantity according to the manufacturing equipment information and the production product information received by the receiving module 22. The preset quantity is, for example, 10,000, 15,000, 20,000, etc. This is only for illustration and does not limit the scope of application of the present invention.

[0038] Next, the neural network computing module 24 can multiply the number of manufacturing parameter settings of the manufacturing equipment information by the number of manufacturing parameter settings of the manufacturing equipment information to build a self-organizing image network, and input the manufacturing parameters corresponding to the manufacturing parameters of all the queried manufacturing parameter record data and the manufacturing equipment information into the self-organizing image network to generate a data imaging result grid diagram.

[0039] Specifically, assuming that the number of manufacturing parameter settings of the manufacturing equipment information is 20, the neural network computing module 24 can build a 20X20 self-organizing image network, and then input all the manufacturing parameter record data of the group to be queried into the self-organizing image network to generate a data image result grid diagram 32. For a schematic diagram of the data image result grid diagram 32, please refer to Figure 3 As shown, Figure 3 A grid diagram of the data imaging result of the manufacturing parameter adjustment control of the manufacturing equipment of the present invention is shown. The equipment parameter group mapped to a grid may be 0, 1 or more. The frequency of use of the group of manufacturing parameter record data is represented by counting the number of grids mapped to the group of manufacturing parameter record data. The frequency of use is then linearly mapped to the corresponding grids with different grayscales. The depth of the grid grayscale represents the frequency of use of the corresponding group of manufacturing parameter record data. The darker the grid grayscale, the more frequently used or most valued manufacturing parameter record data is.

[0040] When the neural network calculation module 24 generates the data image result grid map, the parameter selection module 25 can select the group of manufacturing parameter record data corresponding to the highest grid image number in the data image result grid map as the manufacturing parameters 33 of the manufacturing equipment information. In addition, the parameter selection module 25 can also select the group of manufacturing parameter record data corresponding to the first N highest grid image numbers in the data image result grid map to average the individual manufacturing parameters to generate the manufacturing parameters 33 of the manufacturing equipment information, where N is a positive integer greater than or equal to 2. The selection of N can be set accordingly according to actual needs. Please refer to Figure 4 As shown, Figure 4 A schematic diagram of manufacturing parameters for adjusting and controlling manufacturing parameters of the manufacturing equipment of the present invention is shown, Figure 4 The figure in the figure is a schematic diagram of the group of manufacturing parameter record data corresponding to the top three highest grid image numbers in the data image result grid diagram selected by the parameter selection module 25. This is only an example and does not limit the scope of application of the present invention.

[0041] When the parameter selection module 25 selects the manufacturing parameters of the manufacturing equipment information, the transmission module 26 can transmit the manufacturing parameters of the manufacturing equipment information to the manufacturing equipment 10, and the manufacturing equipment 10 can manufacture the product according to the manufacturing parameters of the manufacturing equipment information.

[0042] When the manufacturing equipment 10 manufactures products according to the manufacturing parameters of the manufacturing equipment information, the manufacturing equipment 10 further detects the production process of the manufacturing equipment 10 through sensors arranged on the manufacturing equipment 10 or external sensors. The detection of the production process of the manufacturing equipment 10 includes the detection of the manufacturing equipment 10 and / or the detection of the environment in which the manufacturing equipment 10 is located. This is only for example and does not limit the scope of application of the present invention. The manufacturing equipment 10 can receive a set of detection parameters through the sensor.

[0043] When the manufacturing equipment 10 receives the set of detection parameters through the sensor, the manufacturing equipment 10 may transmit the set of detection parameters to the receiving module 22 , and the receiving module 22 may receive the set of detection parameters from the manufacturing equipment 10 .

[0044] At the same time, the neural network calculation module 24 will select at least one target parameter from the manufacturing parameters of the manufacturing equipment information as the output parameter and the unselected manufacturing parameters from the manufacturing parameters of the manufacturing equipment information and the group of detection parameters as the input parameters to build the DeepFM model 40, and then divide the queried group of manufacturing parameter record data into a training parameter set and a test parameter set according to a preset ratio, train the DeepFM model 40 with the training parameter set, and then verify the trained DeepFM model 40 with the test parameter set, and perform nonlinear regression on the output parameters output by the trained and verified DeepFM model 40 and cooperate with the input parameters to generate at least one target parameter.

[0045] It is worth noting that the DeepFM model 40 constructed by the present invention removes the last layer of the original DeepFM model and adds a Concat layer. The FM part in the DeepFM model 40 realizes two-dimensional feature combination, and the Deep part realizes n-dimensional feature combination (i.e., high-order feature extraction), where n is a positive integer greater than or equal to 3. The Concat part realizes the fusion of the output results of the FM part and the Deep part. The final output dimension of the Concat layer is equal to the number of target parameters, and then nonlinear regression is performed to obtain the final output parameters. Please refer to the DeepFM model 40 constructed by the present invention. Figure 5 As shown, Figure 5 A schematic diagram of the DeepFM model for adjusting and controlling manufacturing parameters of the manufacturing equipment of the present invention is shown.

[0046] The data for model construction in DeepFM model 40 includes setting the learning rate to 0.01 and using exponential descent, setting the number of epochs to 600, setting the batch size to 16, setting the regularization coefficient (regression rate) to 0.001, setting the Deep layer network size to [300,100,50], setting the Concat layer network size to [30,3], setting the embedding layer network size to

[200] , setting the gradient optimization method to use the AdaDelta gradient descent method, and setting the loss function to use the Huber loss function.

[0047] Specifically, assuming that the target parameters selected by the neural network-like computing module 24 are “RearPressure”, “Front Pressure” and “Paste dispense Rate” respectively, the group of manufacturing parameter record data to be queried (for example, 20,000 groups of manufacturing parameter record data) are divided into a training parameter set of “14,000 groups of manufacturing parameter record data” (i.e., the preset ratio of the training parameter set is 70%) and a test parameter set of “6,000 groups of manufacturing parameter record data” (i.e., the preset ratio of the test parameter set is 30%) according to a preset ratio.

[0048] The neural network-like computing module 24 trains the DeepFM model 40 with a training parameter set, and then verifies the trained DeepFM model 40 with a test parameter set to ensure that the trained DeepFM model 40 is not overfitted. The output parameters of the trained and verified DeepFM model 40 are subjected to nonlinear regression and combined with the input parameters to generate at least one target parameter.

[0049] When the neural network-like computing module 24 generates at least one target parameter, the transmitting module 26 can transmit the at least one target parameter generated by the neural network-like computing module 24 to the manufacturing equipment 10 .

[0050] When the manufacturing equipment 10 receives at least one target parameter from the transmission module 26, the manufacturing equipment 10 can dynamically adjust the manufacturing parameters of the corresponding manufacturing equipment information according to the at least one target parameter to produce the product. It is worth noting that the transmission module 26 is deployed through Tensorflow-Serving to transmit at least one target parameter to the manufacturing equipment 10.

[0051] Next, the operation method of the present invention will be described below, and please refer to Fig. 6A as well as Figure 6B As shown, Fig. 6A as well as Figure 6B A method flow chart showing the method for adjusting and controlling manufacturing parameters of manufacturing equipment according to the present invention.

[0052] First, the storage time, manufacturing equipment information, production product information and a corresponding set of manufacturing parameter record data are stored (step 101); then, the manufacturing equipment information and the production product information are received (step 102); then, the group of manufacturing parameter record data that meets the preset number is queried according to the manufacturing equipment information and the production product information (step 103); then, the number of manufacturing parameter settings of the manufacturing equipment information is multiplied by the number of manufacturing parameter settings of the manufacturing equipment information to build a self-organizing image network, and the manufacturing parameters corresponding to all the queried groups of manufacturing parameter record data and the manufacturing parameters of the manufacturing equipment information are input into the self-organizing image network to generate a data image result grid diagram (step 104); then, the group of manufacturing parameter record data corresponding to the highest grid image number in the data image result grid diagram is selected as the manufacturing parameters of the manufacturing equipment information (step 105); then, the manufacturing parameters of the manufacturing equipment information are transmitted to the manufacturing equipment to perform product manufacturing according to the manufacturing parameters of the manufacturing equipment information. Manufacturing (step 106); then, receiving a set of detection parameters from the manufacturing equipment, wherein the set of detection parameters is obtained by detection by a sensor set in the manufacturing equipment (step 107); then, selecting at least one target parameter from the manufacturing parameters of the manufacturing equipment information as an output parameter and constructing a DeepFM model with the unselected manufacturing parameters from the manufacturing parameters of the manufacturing equipment information and the set of detection parameters as input parameters, and then dividing the queried set of manufacturing parameter record data into a training parameter set and a test parameter set according to a preset ratio, training the DeepFM model with the training parameter set, and then verifying the trained DeepFM model with the test parameter set, performing nonlinear regression on the output parameters output by the trained and verified DeepFM model and matching the input parameters to generate at least one target parameter (step 108); finally, transmitting the at least one target parameter to the manufacturing equipment to dynamically adjust the corresponding manufacturing parameters of the manufacturing equipment information according to the at least one target parameter (step 109).

[0053] In summary, it can be seen that the difference between the present invention and the prior art lies in that a group of manufacturing parameter record data that meets a preset number is queried according to the manufacturing equipment information and the production product information, a self-organizing image network is established according to the manufacturing parameters of the manufacturing equipment information to input all the manufacturing parameters corresponding to the group of manufacturing parameter record data and the manufacturing parameters of the manufacturing equipment information into the self-organizing image network to generate a data image result grid diagram, the group of manufacturing parameter record data corresponding to the highest grid image number in the data image result grid diagram is selected as the manufacturing parameters of the manufacturing equipment information, and then a DeepFM model is established with at least one target parameter selected from the manufacturing parameters of the manufacturing equipment information as the output parameter and unselected manufacturing parameters and a group of detection parameters in the manufacturing parameters of the manufacturing equipment information as the input parameters, the output parameters output by the trained and verified DeepFM model are subjected to nonlinear regression and combined with the input parameters to generate at least one target parameter, so that the corresponding manufacturing parameters of the manufacturing equipment information can be dynamically adjusted according to the at least one target parameter.

[0054] This technical means can be used to solve the problem that the manufacturing parameters of the manufacturing equipment in the prior art cannot be adjusted intelligently, thereby achieving the technical effect of providing the manufacturing parameters of the manufacturing equipment with intelligent adjustment.

[0055] Although the embodiments disclosed in the present invention are as above, the contents described are not intended to directly limit the scope of patent protection of the present invention. Any person skilled in the art may make some changes in the form and details of implementation without departing from the spirit and scope disclosed in the present invention. The scope of patent protection of the present invention shall still be subject to the scope defined in the attached claims.

Claims

1. A manufacturing equipment manufacturing parameter adjustment control system, comprising: A parameter database for storing storage time, manufacturing equipment information, production product information and a corresponding set of manufacturing parameter record data; A receiving module, used for receiving the manufacturing equipment information and the production product information, and receiving a set of detection parameters from the manufacturing equipment, wherein the set of detection parameters is obtained by detection by a sensor set in the manufacturing equipment; A query module, used for querying the set of manufacturing parameter record data that meets a preset quantity according to the manufacturing equipment information and the production product information received by the receiving module; A neural network-like computing module, multiplying the number of manufacturing parameter settings of the manufacturing equipment information by the number of manufacturing parameter settings of the manufacturing equipment information to build a self-organizing image network, inputting the manufacturing parameters corresponding to the manufacturing parameters of the manufacturing equipment information in all the queried manufacturing parameter record data into the self-organizing image network to generate a data image result grid diagram; and constructing a DeepFM model by selecting at least one target parameter from the manufacturing parameters of the manufacturing equipment information as an output parameter and the unselected manufacturing parameters from the manufacturing parameters of the manufacturing equipment information and the group of detection parameters as input parameters, and then dividing the queried group of manufacturing parameter record data into a training parameter set and a test parameter set according to a preset ratio, training the DeepFM model with the training parameter set, and then verifying the trained DeepFM model with the test parameter set, performing nonlinear regression on the output parameters output by the trained and verified DeepFM model and matching the input parameters to generate the at least one target parameter; A parameter selection module, for selecting the group of manufacturing parameter record data corresponding to the highest number of grid images in the data image result grid map as the manufacturing parameters of the manufacturing equipment information; and The transmission module is used to transmit the manufacturing parameters of the manufacturing equipment information to the manufacturing equipment so as to use the manufacturing parameters of the manufacturing equipment information to produce products; and transmit the at least one target parameter to the manufacturing equipment so as to dynamically adjust the corresponding manufacturing parameters of the manufacturing equipment information according to the at least one target parameter.

2. The manufacturing parameter adjustment and control system for manufacturing equipment according to claim 1, wherein the parameter selection module further comprises selecting the group of manufacturing parameter record data corresponding to the top N highest grid image numbers in the data image result grid diagram to average the individual manufacturing parameters to generate the manufacturing parameters of the manufacturing equipment information, wherein N is a positive integer greater than or equal to 2.

3. The manufacturing parameter adjustment and control system of manufacturing equipment according to claim 1, wherein the query module also includes periodically querying the group of manufacturing parameter record data that meets the preset quantity, and the neural network calculation module also includes periodically retraining the DeepFM model.

4. The manufacturing parameter adjustment control system of the manufacturing equipment according to claim 1, wherein the data for model construction in the DeepFM model includes setting the learning rate to 0.01 and using exponential descent, setting the number of repeated operations to 600, setting the batch size to 16, setting the regularization coefficient to 0.001, setting the Deep layer network size to [300, 100, 50], setting the Concat layer network size to [30, 3], setting the embedding layer network size to [200], setting the gradient optimization method to use the AdaDelta gradient descent method, and setting the loss function to use the Huberloss function.

5. The manufacturing equipment manufacturing parameter adjustment control system according to claim 1, wherein the transmission module is deployed through Tensorflow-Serving to transmit the at least one target parameter to the manufacturing equipment to dynamically adjust the manufacturing parameters corresponding to the manufacturing equipment information according to the at least one target parameter.

6. A method for adjusting and controlling manufacturing parameters of a manufacturing device, comprising the following steps: Store storage time, manufacturing equipment information, production product information and a corresponding set of manufacturing parameter record data; Receive manufacturing equipment information and production product information; According to the manufacturing equipment information and the production product information, query the set of manufacturing parameter record data that meets the preset quantity; Multiplying the number of manufacturing parameter settings of the manufacturing equipment information by the number of manufacturing parameter settings of the manufacturing equipment information to build a self-organizing mapping network, and inputting the manufacturing parameters corresponding to the manufacturing parameters of all the queried manufacturing parameter record data and the manufacturing parameters of the manufacturing equipment information into the self-organizing mapping network to generate a data mapping result grid diagram; Selecting the group of manufacturing parameter record data corresponding to the highest number of grid images in the data image result grid map as the manufacturing parameters of the manufacturing equipment information; Transmitting the manufacturing parameters of the manufacturing equipment information to the manufacturing equipment so as to manufacture the product according to the manufacturing parameters of the manufacturing equipment information; receiving a set of detection parameters from the manufacturing equipment, wherein the set of detection parameters is obtained by detection by a sensor disposed on the manufacturing equipment; A DeepFM model is constructed by selecting at least one target parameter from the manufacturing parameters of the manufacturing equipment information as an output parameter and the unselected manufacturing parameters from the manufacturing parameters of the manufacturing equipment information and the set of detection parameters as input parameters, and then the queried set of manufacturing parameter record data is divided into a training parameter set and a test parameter set according to a preset ratio, the DeepFM model is trained with the training parameter set, and then the trained DeepFM model is verified with the test parameter set, and the output parameter output by the trained and verified DeepFM model is subjected to nonlinear regression and matched with the input parameters to generate the at least one target parameter; and The at least one target parameter is transmitted to the manufacturing equipment to dynamically adjust the manufacturing parameters of the corresponding manufacturing equipment information according to the at least one target parameter.

7. The manufacturing parameter adjustment control method for manufacturing equipment according to claim 6, wherein the manufacturing parameter adjustment control method for manufacturing equipment further comprises the step of selecting the group of manufacturing parameter record data corresponding to the top N highest grid image numbers in the data image result grid diagram to average the individual manufacturing parameters to generate the manufacturing parameters of the manufacturing equipment information, wherein N is a positive integer greater than or equal to 2.

8. The manufacturing parameter adjustment control method for manufacturing equipment according to claim 6, wherein the manufacturing parameter adjustment control method for manufacturing equipment further comprises the step of periodically querying the set of manufacturing parameter record data that meets a preset quantity to periodically retrain the DeepFM model.

9. The manufacturing parameter adjustment and control method for manufacturing equipment according to claim 6, wherein the data for model construction in the DeepFM model includes setting the learning rate to 0.01 and using exponential descent, setting the number of repeated operations to 600, setting the batch size to 16, setting the regularization coefficient to 0.001, setting the Deep layer network size to [300, 100, 50], setting the Concat layer network size to [30, 3], setting the embedding layer network size to [200], setting the gradient optimization method to use the AdaDelta gradient descent method, and setting the loss function to use the Huberloss function.

10. The manufacturing parameter adjustment control method for manufacturing equipment according to claim 6, wherein the step of transmitting the at least one target parameter to the manufacturing equipment to dynamically adjust the manufacturing parameters of the corresponding manufacturing equipment information according to the at least one target parameter is to deploy the service through Tensorflow-Serving to transmit the at least one target parameter to the manufacturing equipment to dynamically adjust the manufacturing parameters of the corresponding manufacturing equipment information according to the at least one target parameter.