Internet of Things cooperative intelligent manufacturing method, system and medium

By setting up equipment status and product status acquisition network on the manufacturing production line, forming a product status prediction model and building a manufacturer collaborative network, the problem of lack of collaborative cooperation in the existing technology is solved, and collaborative manufacturing and product status among manufacturers is realized Forecasting improves manufacturing efficiency.

CN119090439APending Publication Date: 2024-12-06ZHEJIANG WANLI UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411180035.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The lack of collaborative cooperation of existing manufacturing methods has caused manufacturers to be unable to obtain collaborative help from other manufacturers, affecting product manufacturing efficiency.

Method used

By laying a collaborative network for equipment status acquisition and a wireless network for product status acquisition on the production line of the target product, a collaborative network for manufacturing the manufacturer is formed, and a collaborative network for manufacturing equipment and raw material status parameters are obtained, and processing is adjusted to meet preset status conditions. Achieve collaborative manufacturing of products.

Benefits of technology

When the manufacturer is unable to continue manufacturing the product, the subsequent manufacturing of the target product is completed through collaborative manufacturing and predict the product status to improve manufacturing efficiency and collaborative processing capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119090439A_ABST
    Figure CN119090439A_ABST
Patent Text Reader

Abstract

The invention relates to an Internet of Things collaborative intelligent manufacturing method and system and a medium, and the method comprises the steps: laying an equipment state collection collaborative network and a product state collection collaborative wireless network on a manufacturer production line, pre-forming a product state prediction model for a target product, and forming a manufacturer collaborative network; obtaining an equipment state parameter actual value set and a raw material state numerical parameter actual value set when a product production line of a manufacturer starts to manufacture a target product; and according to the obtained actual manufacturing capability parameters of the manufacturer, determining whether to request to complete product collaborative manufacturing processing for the target product in the manufacturer collaborative network, and inputting the obtained actual value set of the equipment state parameters and the actual value set of the numerical parameters of the raw material state into a product state prediction model for adjustment processing. Therefore, follow-up manufacturing of the target product is completed through cooperation of collaborative manufacturing, and the state condition of the target product is obtained through prediction.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of intelligent manufacturing, and in particular to an Internet of Things collaborative intelligent manufacturing method, system and medium. Background Art

[0002] In the existing manufacturing industry, the Internet of Things and intelligent manufacturing technologies have been widely used in manufacturers' product manufacturing processes to efficiently process and manufacture more products.

[0003] However, the existing manufacturing methods have shortcomings: although different manufacturers have their own intelligent manufacturing capabilities, they lack coordination and cooperation with each other. Once a manufacturer is unable to continue processing the products on its own production line, it will not be able to obtain coordination and help from other manufacturers, which will be detrimental to the progress of the manufacturer's products and reduce product manufacturing efficiency. Summary of the invention

[0004] The first technical problem to be solved by the present invention is to provide an Internet of Things collaborative intelligent manufacturing method with collaborative manufacturing coordination function in view of the above-mentioned prior art.

[0005] The second technical problem to be solved by the present invention is to provide an Internet of Things collaborative intelligent manufacturing system for realizing the above-mentioned Internet of Things collaborative intelligent manufacturing method in response to the above-mentioned prior art.

[0006] The third technical problem to be solved by the present invention is to provide a readable storage medium for realizing the above-mentioned IoT collaborative intelligent manufacturing method in response to the above-mentioned prior art.

[0007] The technical solution adopted by the present invention to solve the first technical problem is: an Internet of Things collaborative intelligent manufacturing method, characterized in that it includes the following steps:

[0008] Arrange in advance on the product production line for manufacturing the target product an equipment status collection collaborative network for collecting a set of manufacturing equipment status parameters and a product status collection collaborative wireless network for collecting product status parameters corresponding to the products at different stages on the production line;

[0009] A product state prediction model for a target product is formed in advance; wherein the input of the product state prediction model is a set of pre-collected equipment state parameters and a set of pre-collected raw material state numerical parameter values ​​of raw materials required for manufacturing the product, the raw material state numerical parameter values ​​are the values ​​of the raw material state parameters after numerical processing, and the output of the product state prediction model is the product state parameter set;

[0010] Constructing a manufacturer collaborative network formed by a collaborative manufacturing dispatching center and multiple manufacturer processing centers, and allowing each manufacturer processing center in the manufacturer collaborative network to establish a communication connection with the collaborative manufacturing dispatching center;

[0011] Obtaining a set of actual values ​​of equipment state parameters corresponding to when the manufacturer's product production line starts manufacturing the target product and a set of actual values ​​of raw material state numerical parameters of the raw materials required to manufacture the target product;

[0012] Acquire actual manufacturing capacity parameters of the manufacturer that manufactures the target product, and complete product collaborative manufacturing processing for the target product within the established manufacturer collaborative network based on the actual manufacturing capacity parameters of the manufacturer;

[0013] Input the acquired actual value set of equipment state parameters and the actual value set of raw material state digitized parameters into the product state prediction model to predict the target product real-time prediction state of the target product;

[0014] The actual equipment status and raw material status are adjusted according to the real-time predicted status of the target product, until the real-time predicted status of the target product after adjustment meets the preset status conditions again, and the manufacturer is required to manufacture products according to the adjusted equipment status and raw material status corresponding to the preset status.

[0015] Improved, in the invention, the Internet of Things collaborative intelligent manufacturing method further includes:

[0016] Generate a product processing 3D model corresponding to the target product in advance according to the equipment state parameters and raw material state numerical parameter values ​​corresponding to the target product when manufacturing the target product; wherein the product processing 3D model includes the product 3D models corresponding to the product at different manufacturing stages;

[0017] Establishing the correlation between the product processing 3D model and the product status prediction model when the target product is at different manufacturing stages; and,

[0018] When the product status is output using the product status prediction model, the product processing 3D model corresponding to the corresponding manufacturing stage is also output simultaneously.

[0019] Further improvement, in the IoT collaborative intelligent manufacturing method, the process of forming the product state prediction model includes forming a product qualified state prediction model and a product unqualified state prediction model; wherein the process of forming the product qualified state prediction model includes the following steps:

[0020] Step a1, pre-acquire a set of equipment state parameters of the equipment state corresponding to the target product manufactured by the product production line; wherein the set of equipment state parameters includes a set of equipment state parameters under the qualified product state corresponding to the qualified target product manufactured by the product production line and a set of equipment state parameters under the unqualified product state corresponding to the unqualified target product manufactured by the product production line;

[0021] Step a2, performing numerical data screening processing on the data in the device state parameter set to obtain a numerical device state parameter set that can be represented by numerical values;

[0022] Step a3, according to the numerical device state parameter set as the numerical data screening standard, the device state parameter set in the qualified product state and the device state parameter set in the unqualified product state are screened respectively, and the numerical data set of the device state in the qualified product state and the numerical data set of the device state in the unqualified product state are obtained accordingly, and the numerical data set of the device state in the qualified product state is combined as the first numerical data set to be screened, and the numerical data set of the device state in the unqualified product state is combined as the second numerical data set to be screened;

[0023] Step a4, with the goal of screening the product manufacturing stage status data, respectively perform data screening processing on the first to-be-screened numerical data set and the second to-be-screened numerical data set to obtain the product manufacturing stage status numerical data set corresponding to the product qualified state and the product manufacturing stage status numerical data set corresponding to the product unqualified state;

[0024] Step a5, normalizing the data in the device state parameter set in the qualified product state and the device state parameter set in the unqualified product state, respectively, to obtain a first normalized data set and a second normalized data set;

[0025] Step a6, respectively calculating the correlation between each data in the first normalized data set and the product manufacturing stage status numerical data set in the set, and marking all the calculated correlations as a product qualified state data correlation sequence;

[0026] Step a7, respectively calculating the correlation between each data in the second normalized data set and the product manufacturing stage status numerical data set in the set, and marking all the calculated correlations as a product unqualified state data correlation sequence;

[0027] Step a8, selecting all the correlations in the product qualified state data correlation sequence and having correlation values ​​greater than a first preset correlation threshold, and taking all the device state parameters corresponding to the selected all correlations as a set of product qualified rate influencing factors affecting the qualified rate of the target product;

[0028] Step a9, performing training processing based on the product qualification rate influencing factor set and the product manufacturing stage state data corresponding to the product being in a qualified state, to obtain a product manufacturing stage state data prediction model corresponding to the prediction of manufacturing qualified products;

[0029] Step a10, performing training processing based on the product unqualified rate influencing factor set and the product manufacturing stage state data corresponding to the product being in an unqualified state, to obtain a product manufacturing stage state data prediction model corresponding to the prediction of manufacturing unqualified products;

[0030] Step a11, the obtained product manufacturing stage status data prediction model corresponding to when the manufacturing plant manufactures qualified products and the product manufacturing stage status data prediction model corresponding to when the manufacturing plant manufactures unqualified products are formed together into the product status prediction model.

[0031] Furthermore, in the IoT collaborative intelligent manufacturing method, the preset state condition is that the state parameters corresponding to the target product at each manufacturing stage match the preset state parameters.

[0032] Further improved, in the IoT collaborative intelligent manufacturing method, the collaborative manufacturing process of the target product by the manufacturer collaborative network includes the following steps:

[0033] Step b1, making a judgment based on the actual manufacturing capacity parameters of the manufacturer of the target product:

[0034] When the actual manufacturing capability parameter of the manufacturer is higher than the preset manufacturing capability parameter value, the product collaborative manufacturing process is not executed for the current target product manufacturing process; otherwise, the process proceeds to step b2; wherein the target product is a device formed by assembling multiple components;

[0035] Step b2, the manufacturer sends product collaborative manufacturing request information to the collaborative manufacturing scheduling center; wherein the product collaborative manufacturing request information includes product parameter information corresponding to each manufacturing stage of the target product and the remaining product unexecuted manufacturing stages;

[0036] Step b3, the collaborative manufacturing scheduling center schedules other manufacturers in the collaborative network of manufacturers according to the remaining unexecuted manufacturing stages of the target product, so as to determine the execution correspondence between each manufacturer and the unexecuted manufacturing stages of each product in the order of collaborative execution; wherein there is a one-to-one correspondence between the manufacturers participating in the collaborative manufacturing and the unexecuted manufacturing stages of the target product;

[0037] Step b4, the collaborative manufacturing scheduling center instructs each manufacturer to execute the unexecuted manufacturing stage work of the corresponding target product, and obtains the components corresponding to each unexecuted manufacturing stage to complete the collaborative manufacturing of the target product.

[0038] Furthermore, in the IoT collaborative intelligent manufacturing method, the collaborative manufacturing process of the target product by the manufacturer collaborative network further includes the following steps:

[0039] Step c1, each manufacturer participating in the collaboration pre-deploys an equipment status collection collaboration network for collecting a set of manufacturing equipment status parameters and a product status collection collaboration wireless network for collecting product status parameters corresponding to products at different stages on the production line;

[0040] Step c2, each manufacturer participating in the collaboration sends the product status parameters of the corresponding target product when the work at the manufacturing stage is not performed to the collaborative manufacturing scheduling center;

[0041] Step c3, the collaborative manufacturing scheduling center determines the status of the parts manufactured by the manufacturer based on the product status parameters sent by the manufacturer:

[0042] When the state of the parts manufactured by the manufacturer is qualified, the process proceeds to step c4; otherwise, the collaborative manufacturing scheduling center designates the manufacturer corresponding to the unqualified parts to readjust the equipment state parameters of the manufacturing equipment, and the process proceeds to step c6;

[0043] Step c4, the collaborative manufacturing scheduling center generates corresponding component 3D models according to the status parameters of each qualified product, and performs virtual assembly on the target product with all the generated component 3D models and all the component 3D models generated by the initial manufacturer of the target product to obtain the virtual assembled product 3D model;

[0044] Step c5, the collaborative manufacturing scheduling center performs assembly effect judgment processing on the 3D model of the product after virtual assembly:

[0045] When the virtualized assembled product 3D model meets the assembly requirements, it is determined that the collaborative manufacturing process of the target product by the manufacturer collaborative network is completed; otherwise, it is determined that the component 3D model does not meet the assembly requirements, and the collaborative manufacturing scheduling center specifies the manufacturer corresponding to the component 3D model that does not meet the assembly requirements to readjust the equipment status parameters of the manufacturing equipment, and then proceeds to step c6;

[0046] In step c6, the manufacturer sends the adjusted equipment status parameters to the collaborative manufacturing scheduling center and proceeds to step c3.

[0047] The technical solution adopted by the present invention to solve the second technical problem is: an Internet of Things collaborative intelligent manufacturing system, which implements the Internet of Things collaborative intelligent manufacturing method, characterized in that the Internet of Things collaborative intelligent manufacturing system includes:

[0048] Multiple manufacturer processing centers, each manufacturer's processing center belongs to a manufacturer with a product production line;

[0049] Multiple equipment status collection collaborative networks correspond one-to-one with the manufacturer's product production lines, collecting the manufacturing equipment status parameter sets on the product production lines;

[0050] Multiple product status collection collaborative wireless networks correspond to the manufacturer's product production lines one by one, collecting product status parameters corresponding to the products at different stages on the production line;

[0051] The collaborative manufacturing dispatching center is connected to the processing centers of each manufacturer in communication to form a collaborative network of manufacturers.

[0052] The technical solution adopted by the present invention to solve the third technical problem is: a readable storage medium, on which a computer program is stored, characterized in that when the computer program is executed by a processor, any one of the Internet of Things collaborative intelligent manufacturing methods is implemented.

[0053] Compared with the prior art, the advantages of the present invention are: the Internet of Things collaborative intelligent manufacturing method of the invention pre-deploys a collaborative network for equipment status collection and a collaborative wireless network for product status collection on the production line of the manufacturer, and pre-forms a product status prediction model for the target product, and forms a manufacturer collaborative network formed by a collaborative manufacturing scheduling center and multiple manufacturer processing centers, and then obtains the actual value set of equipment status parameters corresponding to when the manufacturer's product production line starts to manufacture the target product and the actual value set of raw material status numerical parameters of the raw materials required to manufacture the target product, and determines whether to request to complete the product collaborative manufacturing processing for the target product in the manufacturer collaborative network based on the acquired actual manufacturing capacity parameters of the manufacturer, and inputs the acquired actual value set of equipment status parameters and actual value set of raw material status numerical parameters into the product status prediction model for adjustment processing until the real-time predicted status of the target product is predicted, so that when the manufacturer is unable to continue to manufacture the product, it can request to complete the subsequent manufacturing of the target product through collaborative manufacturing cooperation, and can predict the status of the target product. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a schematic diagram of the process flow of the Internet of Things collaborative intelligent manufacturing method in an embodiment of the present invention;

[0055] Figure 2Schematic diagram of the Internet of Things collaborative intelligent manufacturing system in an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The present invention is further described in detail below with reference to the accompanying drawings.

[0057] This embodiment provides an IoT collaborative intelligent manufacturing method. Figure 1 As shown, the IoT collaborative intelligent manufacturing method of this embodiment includes the following steps 1 to 7:

[0058] Step 1: pre-deploy an equipment status collection collaborative network for collecting a set of manufacturing equipment status parameters and a product status collection collaborative wireless network for collecting product status parameters corresponding to products at different stages on the production line for manufacturing the target product;

[0059] Step 2, pre-form a product state prediction model for the target product; wherein the input of the product state prediction model is a pre-collected set of equipment state parameters and a pre-collected set of raw material state numerical parameter values ​​of the raw materials required for manufacturing the product, the raw material state numerical parameter values ​​are the values ​​of the raw material state parameters after numerical processing, and the output of the product state prediction model is a set of product state parameters; for example, the set of equipment state parameters here includes electrical parameters (such as working voltage, working current) and cutting parameters (such as cutting speed, cutting depth, feed speed, tool radius and tool back angle), etc.; the raw material state values ​​here include common parameters such as density, material gap, material strength, elastic modulus and material hardness;

[0060] Specifically, in step 2, the process of forming the aforementioned product status prediction model includes forming a product qualified state prediction model and a product unqualified state prediction model; wherein the process of forming the product qualified state prediction model includes the following steps a1 to a11:

[0061] Step a1, pre-acquire a set of equipment state parameters of the equipment state corresponding to the target product manufactured by the product production line; wherein the set of equipment state parameters includes a set of equipment state parameters under the qualified product state corresponding to the qualified target product manufactured by the product production line and a set of equipment state parameters under the unqualified product state corresponding to the unqualified target product manufactured by the product production line;

[0062] Step a2, performing numerical data screening processing on the data in the device state parameter set to obtain a numerical device state parameter set that can be represented by numerical values;

[0063] Step a3, according to the numerical device state parameter set as the numerical data screening standard, the device state parameter set in the qualified product state and the device state parameter set in the unqualified product state are screened respectively, and the numerical data set of the device state in the qualified product state and the numerical data set of the device state in the unqualified product state are obtained accordingly, and the numerical data set of the device state in the qualified product state is combined as the first numerical data set to be screened, and the numerical data set of the device state in the unqualified product state is combined as the second numerical data set to be screened;

[0064] Step a4, with the goal of screening the product manufacturing stage status data, respectively perform data screening processing on the first to-be-screened numerical data set and the second to-be-screened numerical data set to obtain the product manufacturing stage status numerical data set corresponding to the product qualified state and the product manufacturing stage status numerical data set corresponding to the product unqualified state;

[0065] Step a5, normalizing the data in the device state parameter set in the qualified product state and the device state parameter set in the unqualified product state, respectively, to obtain a first normalized data set and a second normalized data set;

[0066] For example, for a device state parameter set in a product qualified state, the device state parameter set in a product qualified state is marked as X, X={X i}, X i is the i-th device state parameter value in parameter set X;

[0067]

[0068] Among them, x i is the device status parameter value X i The normalized value after normalization, X min is the minimum value of all device status parameter values ​​in parameter set X, X max is the maximum value of all device status parameter values ​​in parameter set X;

[0069] For example, for a device state parameter set in a product unqualified state, the device state parameter set in a product unqualified state is marked as Y, where Y={Y j},Y j is the j-th device state parameter value in parameter set Y;

[0070]

[0071] Among them, y j is the device status parameter value Y j The normalized value after normalization, Y min is the minimum value of all device status parameter values ​​in parameter set Y,max is the maximum value of all device status parameter values ​​in parameter set Y;

[0072] For example, for the device status parameter set in the qualified state of the product, the above normalized value x i The implementation code of the calculation method is as follows:

[0073] maximums,minimums=training_data.max(axis=0),training_data.min(axis=0)

[0074] for i in range(feature_num):

[0075] data[:,i]=(data[:,i]-minimums[i]) / (maximums[i]-minimums[i]);

[0076] For example, for the device status parameter set under the product unqualified state, the above normalized value y j The implementation code of the calculation method is as follows:

[0077] maximums,minimums=training_data.max(axis=0),training_data.min(axis=0)

[0078] for i in range(feature_num):

[0079] data[:,j]=(data[:,j]-minimums[j]) / (maximums[j]-minimums[j]);

[0080] Step a6, respectively calculating the correlation between each data in the first normalized data set and the product manufacturing stage status numerical data set in the set, and marking all the calculated correlations as product qualified state data correlation sequence; the correlation calculation here can be processed according to the existing mature technology, which will not be repeated here;

[0081] For example, suppose the first normalized data set is labeled x, x = {x1, x2, x3, x4, x5}; the product manufacturing stage state numerical data set z, z = {z1, z2, z3, z4}

[0082] pip install mlxtend / / Install mlxtend library

[0083] from mlxtend.frequent_patterns import apriori

[0084] from mlxtend.frequent_patterns import association_rules

[0085] dataset=[['x1','x2','x3','x4','x5'],

[0086] ['z1','z2','z3','z4'],

[0087] from mlxtend.preprocessing import TransactionEncoder / / Convert the dataset to one-hot encoding

[0088] te = TransactionEncoder()

[0089] te_ary=te.fit(dataset).transform(dataset)

[0090] df=pd.DataFrame(te_ary,columns=te.columns_)

[0091] frequent_itemsets = apriori(df, min_support = 0.6, use_colnames = True) / / Calculate frequent item sets

[0092] rules=association_rules(frequent_itemsets,metric="confidence",min_threshold=0.7)

[0093] print(rules) / / Generate association rules

[0094] Step a7, respectively calculating the correlation between each data in the second normalized data set and the product manufacturing stage status numerical data set in the set, and marking all the calculated correlations as a product unqualified state data correlation sequence;

[0095] For example, suppose the second normalized data set is labeled y, y = {y1, y2, y3, y4, y5, y6}; the product manufacturing stage state numerical data set z, z = {z1, z2, z3, z4}

[0096] pip install mlxtend / / Install mlxtend library

[0097] from mlxtend.frequent_patterns import apriori

[0098] from mlxtend.frequent_patterns import association_rules

[0099] dataset=[['y1','y2','y3','y4','y5','y6'],

[0100] ['z1','z2','z3','z4'],

[0101] from mlxtend.preprocessing import TransactionEncoder / / Convert the dataset to one-hot encoding

[0102] te = TransactionEncoder()

[0103] te_ary=te.fit(dataset).transform(dataset)

[0104] df=pd.DataFrame(te_ary,columns=te.columns_)

[0105] frequent_itemsets = apriori(df, min_support = 0.6, use_colnames = True) / / Calculate frequent item sets

[0106] rules=association_rules(frequent_itemsets,metric="confidence",min_threshold=0.7)

[0107] print(rules) / / Generate association rules

[0108] Step a8, selecting all the correlations in the product qualified state data correlation sequence and having correlation values ​​greater than a first preset correlation threshold, and taking all the device state parameters corresponding to the selected all correlations as a set of product qualified rate influencing factors affecting the qualified rate of the target product;

[0109] In this embodiment, by calculating the correlation between each data in the normalized data set and the product manufacturing stage status numerical data set in the set, the manufacturing plant equipment status parameters that affect the qualification of the manufactured industrial products are mined, thereby ensuring a more comprehensive and accurate comprehensive analysis, and providing more comprehensive data support for the subsequent prediction model of the product manufacturing stage status data corresponding to the predicted manufacturing product;

[0110] Step a9, performing training processing based on the product qualification rate influencing factor set and the product manufacturing stage state data corresponding to the product being in a qualified state, to obtain a product manufacturing stage state data prediction model corresponding to the prediction of manufacturing qualified products;

[0111] Step a10, performing training processing based on the product unqualified rate influencing factor set and the product manufacturing stage state data corresponding to the product being in an unqualified state, to obtain a product manufacturing stage state data prediction model corresponding to the prediction of manufacturing unqualified products;

[0112] Step a11, the obtained product manufacturing stage state data prediction model corresponding to when the manufacturing plant manufactures qualified products and the obtained product manufacturing stage state data prediction model corresponding to when the manufacturing plant manufactures unqualified products form the product state prediction model together;

[0113] Step 3, constructing a manufacturer collaborative network formed by a collaborative manufacturing scheduling center and multiple manufacturer processing centers, and allowing each manufacturer processing center in the manufacturer collaborative network to establish a communication connection with the collaborative manufacturing scheduling center;

[0114] Step 4, obtaining a set of actual values ​​of equipment state parameters corresponding to when the manufacturer's product production line starts to manufacture the target product and a set of actual values ​​of raw material state numerical parameters of the raw materials required to manufacture the target product;

[0115] Step 5, obtaining actual manufacturing capacity parameters of the manufacturer that manufactures the target product, and completing product collaborative manufacturing processing for the target product within the established manufacturer collaborative network according to the actual manufacturing capacity parameters of the manufacturer;

[0116] Step 6, inputting the acquired actual value set of the equipment state parameter and the actual value set of the raw material state digitized parameter into the product state prediction model, and predicting the target product real-time prediction state of the target product;

[0117] Step 7, adjust the actual equipment state and raw material state according to the obtained real-time predicted state of the target product, until the adjusted real-time predicted state of the target product meets the preset state condition again, and order the manufacturer to manufacture the product according to the adjusted equipment state and raw material state corresponding to the preset state. The preset state condition here is that the state parameters corresponding to the target product at each manufacturing stage match the preset state parameters. In other words, the state parameter value corresponding to the target product at each manufacturing stage is equal to the corresponding preset state parameter value or is within the allowable error range.

[0118] Specifically in this embodiment, in the above step 5, the actual manufacturing capacity parameter of the manufacturer is calculated as follows:

[0119] Step 51, pre-screening the device state parameters corresponding to the manufacturer when manufacturing the qualified target product in the device state parameter set, to form a subset of the device state parameters when the manufacturer manufactures the qualified target product;

[0120] Step 52, taking the equipment state parameters that are in the equipment state parameter subset and are consistent with the influencing factors in the product qualification rate influencing factor set as target state parameters that characterize the manufacturing capability of the manufacturer; wherein the total number of target state parameters is M, M≥2;

[0121] Step 53: The manufacturer processes the target state parameters of the same type of equipment in the equipment state parameter subset to obtain the target state parameter offset variance of each target state parameter of the corresponding equipment, and uses the target state parameter offset variance as the target state parameter offset reference value of each target state parameter of the corresponding equipment; wherein the target state parameter offset reference value corresponding to the mth target state parameter is marked as σ m,0 ; 1≤m≤M;

[0122] In the process of forming the equipment status parameter set, a certain type of status data of the manufacturing equipment will continuously generate a large amount of equipment status parameter data along with the manufacturing process. These equipment status parameter data usually show certain common characteristics or abnormal characteristics. Here, these abnormal characteristics need to be processed;

[0123] Step 54, obtain all the target state parameters corresponding to the manufacturer when manufacturing the product, and calculate the real-time offset value of the target state parameters of the manufacturer in the current product manufacturing process; wherein the real-time offset value of the target state parameters of the manufacturer in the current product manufacturing process is marked as σ m (t); t>0;

[0124] Step 55, according to the offset reference value of each target state parameter and the real-time offset value of the target state parameter, the actual manufacturing capacity parameter of the manufacturer itself is calculated; wherein the actual manufacturing capacity parameter of the manufacturer itself is marked as δ(t):

[0125]

[0126] in, is a sequence of values.

[0127] In order to facilitate the observation of the status of products manufactured by the manufacturer on the production line, the IoT collaborative intelligent manufacturing method of this embodiment is characterized by further comprising:

[0128] Generate a product processing 3D model corresponding to the target product in advance according to the equipment state parameters and raw material state numerical parameter values ​​corresponding to the target product when manufacturing the target product; wherein the product processing 3D model includes the product 3D models corresponding to the product at different manufacturing stages;

[0129] Establishing the correlation between the product processing 3D model and the product status prediction model when the target product is at different manufacturing stages; and,

[0130] When the product status is output using the product status prediction model, the product processing 3D model corresponding to the corresponding manufacturing stage is also output simultaneously.

[0131] It should be noted that in the above step 5, the collaborative manufacturing process of the target product by the manufacturer collaborative network includes the following steps b1 to b4:

[0132] Step b1, making a judgment based on the actual manufacturing capacity parameters of the manufacturer of the target product:

[0133] When the actual manufacturing capability parameter of the manufacturer is higher than the preset manufacturing capability parameter value, the product collaborative manufacturing process is not executed for the current target product manufacturing process; otherwise, the process proceeds to step b2; wherein the target product is a device formed by assembling multiple components;

[0134] Step b2: the manufacturer sends product collaborative manufacturing request information to the collaborative manufacturing scheduling center; wherein the product collaborative manufacturing request information includes product parameter information corresponding to each manufacturing stage of the target product and the remaining product unexecuted manufacturing stages;

[0135] Step b3, the collaborative manufacturing scheduling center schedules other manufacturers in the collaborative network of manufacturers according to the remaining unexecuted manufacturing stages of the target product, so as to determine the execution correspondence between each manufacturer and the unexecuted manufacturing stages of each product in the order of collaborative execution; wherein there is a one-to-one correspondence between the manufacturers participating in the collaborative manufacturing and the unexecuted manufacturing stages of the target product;

[0136] Step b4, the collaborative manufacturing scheduling center instructs each manufacturer to execute the unexecuted manufacturing stage work of the corresponding target product, and obtains the components corresponding to each unexecuted manufacturing stage to complete the collaborative manufacturing of the target product.

[0137] Of course, in the actual collaborative manufacturing process, the collaborative manufacturing process of the target product by the collaborative network of manufacturers mentioned above also includes the following steps c1 to c6:

[0138] Step c1, each manufacturer participating in the collaboration pre-deploys an equipment status collection collaboration network for collecting a set of manufacturing equipment status parameters and a product status collection collaboration wireless network for collecting product status parameters corresponding to products at different stages on the production line;

[0139] Step c2, each manufacturer participating in the collaboration sends the product status parameters of the corresponding target product when the work at the manufacturing stage is not performed to the collaborative manufacturing scheduling center;

[0140] Step c3, the collaborative manufacturing scheduling center determines the status of the parts manufactured by the manufacturer based on the product status parameters sent by the manufacturer:

[0141] When the state of the parts manufactured by the manufacturer is qualified, the process proceeds to step c4; otherwise, the collaborative manufacturing scheduling center designates the manufacturer corresponding to the unqualified parts to readjust the equipment state parameters of the manufacturing equipment, and the process proceeds to step c6;

[0142] Step c4, the collaborative manufacturing scheduling center generates corresponding component 3D models according to the status parameters of each qualified product, and performs virtual assembly on the target product with all the generated component 3D models and all the component 3D models generated by the initial manufacturer of the target product to obtain the virtual assembled product 3D model;

[0143] Step c5, the collaborative manufacturing scheduling center performs assembly effect judgment processing on the 3D model of the product after virtual assembly:

[0144] When the virtualized assembled product 3D model meets the assembly requirements, it is determined that the collaborative manufacturing process of the target product by the manufacturer collaborative network is completed; otherwise, it is determined that the component 3D model does not meet the assembly requirements, and the collaborative manufacturing scheduling center specifies the manufacturer corresponding to the component 3D model that does not meet the assembly requirements to readjust the equipment status parameters of the manufacturing equipment, and then proceeds to step c6;

[0145] In step c6, the manufacturer sends the adjusted equipment status parameters to the collaborative manufacturing scheduling center and proceeds to step c3.

[0146] It should be noted that in the IoT collaborative intelligent manufacturing method of this embodiment, the product status prediction model for the target product is obtained by training based on a neural network. Specifically, the formation process of the product status prediction model is as follows:

[0147] Step e1, constructing an initial BP neural network; wherein the initial BP neural network includes two input layers, multiple intermediate layers and an output layer; one of the two input layers is a set of input device state parameters, and the other input layer is a set of input raw material state numerical parameters, and the number of intermediate layers is the same as the number of process steps required for the manufacturing plant to produce qualified products; the output layer is configured to output product manufacturing stage status data corresponding to the qualified state of the product manufactured by the manufacturer;

[0148] Step e2, dividing all data in the obtained product qualification rate influencing factor set into a training product qualification rate influencing factor set and a test product qualification rate influencing factor set equally according to the number of data of the same type;

[0149] Step e3, dividing the product manufacturing stage status data corresponding to the product being in a qualified state into a training product manufacturing stage status data subset and a test product manufacturing stage status data subset in equal amounts according to the same type of data;

[0150] Step e4, inputting the training product qualification rate influencing factor set as input data of one input layer, and the obtained training product manufacturing stage state data subset as input data of another input layer into the initial BP neural network, to obtain the initial product manufacturing stage state data prediction model;

[0151] Step e5, using the set of influencing factors of the test product qualification rate and the subset of the test product manufacturing stage status data to optimize and adjust the initial product manufacturing stage status data prediction model, to obtain the optimized product manufacturing stage status data prediction model, and use the optimized product manufacturing stage status data prediction model as the product manufacturing stage status data prediction model corresponding to the manufacturing plant when predicting the qualified products.

[0152] For example, in this embodiment, part of the implementation code of the product manufacturing stage status data prediction model obtained by training based on a neural network is as follows:

[0153] import pandas as pd

[0154] import numpy as np

[0155] import matplotlib.pyplot as plt

[0156] data = pd.read_csv('stock_data.csv') / / Read the data in the input device status parameter set

[0157] data['Date'] = pd.to_datetime(data['Date']) / / data preprocessing

[0158] data.set_index('Date',inplace=True)

[0159] data.sort_index(inplace=True)

[0160] features=data[['X1','X2','X3','X4']].values

[0161] labels = data['Z'].values

[0162] features=(features-np.mean(features,axis=0)) / np.std(features,axis=0)

[0163] labels=(labels-np.mean(labels)) / np.std(labels)

[0164] train_size=int(len(features)*0.8)

[0165] train_features=features[:train_size]

[0166] train_labels=labels[:train_size]

[0167] test_features=features[train_size:]

[0168] test_labels=labels[train_size:]

[0169] model = tf.keras.Sequential([

[0170] tf.keras.layers.Dense(64,activation='relu',input / / Build a neural network model

[0171] It should be noted that in order to ensure that the machining tools set on the production line of the manufacturer work normally and avoid the normal use of the tools affected by tool wear, the IoT collaborative intelligent manufacturing method of this embodiment also includes the manufacturer performing tool wear status monitoring operations on the tools on its product production line. For example, in this embodiment, the tool wear status monitoring operation here includes the following steps f1 to f10:

[0172] Step f1, pre-constructing a tool type sub-matching model that represents a material type tool when not performing processing; wherein a tool has a tool type sub-matching model that corresponds to its material type one by one, and of course, a processing tool has its own edge line curve;

[0173] Step f2, pre-setting a plurality of milling key points for the tool corresponding to the tool type sub-matching model, and constructing a three-dimensional tool model of the tool corresponding to the milling tool type sub-matching model in a preset rectangular coordinate system; wherein the tool and the three-dimensional tool model are in one-to-one correspondence;

[0174] Step f3, obtaining a three-dimensional coordinate set of the three-dimensional model of the tool and key point coordinates of each milling key point on the three-dimensional model of the tool, to form a milling key point coordinate set corresponding to the tool; wherein the milling key point coordinate set corresponds to the tool one by one;

[0175] Step f4, collecting vibration signal information and pressure signal information of each corresponding milling key point on the tool in advance during the process of the material type tool processing workpieces of different materials, and respectively forming a set of milling processing signal curves when the material type tool mills the corresponding material workpiece; wherein the milling processing signal curve set corresponds to the tool and the material workpiece milled by the tool, and the milling processing signal curve set includes a vibration signal curve set and a pressure signal curve set, the vibration signal curve set is formed by the vibration signal curves of all milling key points on the tool, and the pressure signal curve set is formed by the pressure signal curves of all milling key points on the tool;

[0176] Step f5, respectively determining the abnormal wear moments when the tool appears different wear states in the process of milling workpieces of different materials, and the tool vibration signal amplitude and tool pressure signal amplitude on the milling processing signal curve of each key milling point corresponding to each abnormal wear moment, and establishing a tool wear abnormal amplitude relationship list when the tool mills workpieces of different materials; wherein the tool wear abnormal amplitude relationship list includes a one-to-one correspondence between the tool wear state and the tool vibration signal amplitude and tool pressure signal amplitude of each key milling point;

[0177] Step f6, according to the abnormal wear amplitude relationship list of each tool, respectively calculate the tool wear state reference values ​​when the tool is in different wear states and milling workpieces of different materials;

[0178] Step f7, pre-constructing a set of milling waste characteristic parameters of milling waste obtained from milling workpieces of different materials when the tool is in different wear states; wherein the tool material, the workpiece material to be milled, the wear state of the tool, and the milling waste characteristic parameters of the milling waste obtained from milling the workpiece are all in one-to-one correspondence;

[0179] Step f8, based on the obtained reference value set of each tool wear state and the set of milling waste chip characteristic parameters, construct tool wear state judgment sub-models for milling workpieces of different materials with the tool of the material;

[0180] Step f9, determining the workpiece material in the actual milling process and the current tool material type in the actual milling process based on the tool type matching model, obtaining the current milling signal curve set of the tool in the milling process and the current milling waste chip characteristic parameters; wherein the tool in the actual milling process and the tool forming the corresponding tool type sub-matching model are tools of the same material and specification;

[0181] Step f10, input the obtained current tool material type, workpiece material, current milling processing signal curve set and current milling waste chip characteristic parameters into the tool wear state judgment sub-model, and output the current tool wear state.

[0182] This embodiment also provides an Internet of Things collaborative intelligent manufacturing system to implement the Internet of Things collaborative intelligent manufacturing method. Figure 2 As shown, the IoT collaborative intelligent manufacturing system includes:

[0183] Multiple manufacturer processing centers, each manufacturer's processing center belongs to a manufacturer with a product production line;

[0184] Multiple equipment status collection collaborative networks correspond one-to-one with the manufacturer's product production lines, collecting the manufacturing equipment status parameter sets on the product production lines;

[0185] Multiple product status collection collaborative wireless networks correspond to the manufacturer's product production lines one by one, collecting product status parameters corresponding to the products at different stages on the production line;

[0186] The collaborative manufacturing dispatching center is connected to the processing centers of each manufacturer in communication to form a collaborative network of manufacturers.

[0187] This embodiment also provides a readable storage medium. Specifically, the readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned Internet of Things collaborative intelligent manufacturing method is implemented.

[0188] Although the preferred embodiments of the present invention are described in detail above, it should be clearly understood that various modifications and variations are possible for those skilled in the art. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. The method for collaborative intelligent manufacturing using the Internet of Things is characterized by: The steps include: Arrange in advance on the product production line for manufacturing the target product an equipment status collection collaborative network for collecting a set of manufacturing equipment status parameters and a product status collection collaborative wireless network for collecting product status parameters corresponding to the products at different stages on the production line; A product state prediction model for a target product is formed in advance; wherein the input of the product state prediction model is a set of pre-collected equipment state parameters and a set of pre-collected raw material state numerical parameter values ​​of raw materials required for manufacturing the product, the raw material state numerical parameter values ​​are the values ​​of the raw material state parameters after numerical processing, and the output of the product state prediction model is the product state parameter set; Constructing a manufacturer collaborative network formed by a collaborative manufacturing dispatching center and multiple manufacturer processing centers, and allowing each manufacturer processing center in the manufacturer collaborative network to establish a communication connection with the collaborative manufacturing dispatching center; Obtaining a set of actual values ​​of equipment state parameters corresponding to when the manufacturer's product production line starts manufacturing the target product and a set of actual values ​​of raw material state numerical parameters of the raw materials required to manufacture the target product; Acquire actual manufacturing capacity parameters of the manufacturer that manufactures the target product, and complete product collaborative manufacturing processing for the target product within the established manufacturer collaborative network based on the actual manufacturing capacity parameters of the manufacturer; Input the acquired actual value set of equipment state parameters and the actual value set of raw material state digitized parameters into the product state prediction model to predict the target product real-time prediction state of the target product; The actual equipment status and raw material status are adjusted according to the real-time predicted status of the target product, until the real-time predicted status of the target product after adjustment meets the preset status conditions again, and the manufacturer is required to manufacture products according to the adjusted equipment status and raw material status corresponding to the preset status.

2. The IoT collaborative intelligent manufacturing method according to claim 1, characterized in that: Also includes: Generate a product processing 3D model corresponding to the target product in advance according to the equipment state parameters and raw material state numerical parameter values ​​corresponding to the target product when manufacturing the target product; wherein the product processing 3D model includes the product 3D models corresponding to the product at different manufacturing stages; Establishing the correlation between the product processing 3D model and the product status prediction model when the target product is at different manufacturing stages; and, When the product status is output using the product status prediction model, the product processing 3D model corresponding to the corresponding manufacturing stage is also output simultaneously.

3. The IoT collaborative intelligent manufacturing method according to claim 1, characterized in that: The process of forming the product status prediction model includes forming a product qualified state prediction model and a product unqualified state prediction model; wherein the process of forming the product qualified state prediction model includes the following steps: Step a1, pre-acquire a set of equipment state parameters of the equipment state corresponding to the target product manufactured by the product production line; wherein the set of equipment state parameters includes a set of equipment state parameters under the qualified product state corresponding to the qualified target product manufactured by the product production line and a set of equipment state parameters under the unqualified product state corresponding to the unqualified target product manufactured by the product production line; Step a2, performing numerical data screening processing on the data in the device state parameter set to obtain a numerical device state parameter set that can be represented by numerical values; Step a3, according to the numerical device state parameter set as the numerical data screening standard, the device state parameter set in the qualified product state and the device state parameter set in the unqualified product state are screened respectively, and the numerical data set of the device state in the qualified product state and the numerical data set of the device state in the unqualified product state are obtained accordingly, and the numerical data set of the device state in the qualified product state is combined as the first numerical data set to be screened, and the numerical data set of the device state in the unqualified product state is combined as the second numerical data set to be screened; Step a4, with the goal of screening the product manufacturing stage status data, respectively perform data screening processing on the first to-be-screened numerical data set and the second to-be-screened numerical data set to obtain the product manufacturing stage status numerical data set corresponding to the product qualified state and the product manufacturing stage status numerical data set corresponding to the product unqualified state; Step a5, normalizing the data in the device state parameter set in the qualified product state and the device state parameter set in the unqualified product state, respectively, to obtain a first normalized data set and a second normalized data set; Step a6, respectively calculating the correlation between each data in the first normalized data set and the product manufacturing stage status numerical data set in the set, and marking all the calculated correlations as a product qualified state data correlation sequence; Step a7, respectively calculating the correlation between each data in the second normalized data set and the product manufacturing stage status numerical data set in the set, and marking all the calculated correlations as a product unqualified state data correlation sequence; Step a8, selecting all the correlations in the product qualified state data correlation sequence and having correlation values ​​greater than a first preset correlation threshold, and taking all the device state parameters corresponding to the selected all correlations as a set of product qualified rate influencing factors affecting the qualified rate of the target product; Step a9, performing training processing based on the product qualification rate influencing factor set and the product manufacturing stage state data corresponding to the product being in a qualified state, to obtain a product manufacturing stage state data prediction model corresponding to the prediction of manufacturing qualified products; Step a10, performing training processing based on the product unqualified rate influencing factor set and the product manufacturing stage state data corresponding to the product being in an unqualified state, to obtain a product manufacturing stage state data prediction model corresponding to the prediction of manufacturing unqualified products; Step a11, the obtained product manufacturing stage status data prediction model corresponding to when the manufacturing plant manufactures qualified products and the product manufacturing stage status data prediction model corresponding to when the manufacturing plant manufactures unqualified products are formed together into the product status prediction model.

4. The IoT collaborative intelligent manufacturing method according to claim 3 is characterized in that: The preset state condition is that the state parameters corresponding to the target product at each manufacturing stage match the preset state parameters.

5. The IoT collaborative intelligent manufacturing method according to claim 1, characterized in that: The collaborative manufacturing process of the target product in the manufacturer collaborative network includes the following steps: Step b1, making a judgment based on the actual manufacturing capacity parameters of the manufacturer of the target product: When the actual manufacturing capability parameter of the manufacturer is higher than the preset manufacturing capability parameter value, the product collaborative manufacturing process is not executed for the current target product manufacturing process; otherwise, the process proceeds to step b2; wherein the target product is a device formed by assembling multiple components; Step b2, the manufacturer sends product collaborative manufacturing request information to the collaborative manufacturing scheduling center; wherein the product collaborative manufacturing request information includes product parameter information corresponding to each manufacturing stage of the target product and the remaining product unexecuted manufacturing stages; Step b3, the collaborative manufacturing scheduling center schedules other manufacturers in the collaborative network of manufacturers according to the remaining unexecuted manufacturing stages of the target product, so as to determine the execution correspondence between each manufacturer and the unexecuted manufacturing stages of each product in the order of collaborative execution; wherein there is a one-to-one correspondence between the manufacturers participating in the collaborative manufacturing and the unexecuted manufacturing stages of the target product; Step b4, the collaborative manufacturing scheduling center instructs each manufacturer to execute the unexecuted manufacturing stage work of the corresponding target product, and obtains the components corresponding to each unexecuted manufacturing stage to complete the collaborative manufacturing of the target product.

6. An Internet of Things collaborative intelligent manufacturing system, which implements the Internet of Things collaborative intelligent manufacturing method described in claim 1, characterized in that: The IoT collaborative intelligent manufacturing system includes: Multiple manufacturer processing centers, each manufacturer's processing center belongs to a manufacturer with a product production line; Multiple equipment status collection collaborative networks correspond one-to-one with the manufacturer's product production lines, collecting the manufacturing equipment status parameter sets on the product production lines; Multiple product status collection collaborative wireless networks correspond to the manufacturer's product production lines one by one, collecting product status parameters corresponding to the products at different stages on the production line; The collaborative manufacturing dispatching center is connected to the processing centers of each manufacturer in communication to form a collaborative network of manufacturers.

7. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the Internet of Things collaborative intelligent manufacturing method described in any one of claims 1 to 5 is implemented.