Smart manufacturing method and system based on centralized service platform industrial internet of things

Abstract

The present invention discloses a smart manufacturing method based on a centralized service platform industrial Internet of Things, which includes: a user platform inputs parameter configuration information, and a service platform breaks it into a plurality of configuration data groups according to a process; a management platform stores and processes the received configuration data group, and the stored configuration data group is taken as a reference data group; a target platform takes its sensing information as a check data group at a set time interval; the management platform receives and processes the check data group, and sends the reference data group and the check data group to the service platform; the service platform receives and compares the reference data group and the check data group, and if the comparison result exceeds a set threshold range, generates a stop command and sends it to the target platform to control the line equipment to stop operation. The present invention further discloses a system for realizing the smart manufacturing method based on the centralized service platform industrial Internet of Things. The present invention is applicable to various smart manufacturing lines, and can be quickly controlled to stop the line equipment when a production abnormality occurs.

Description

[Technical field]

[0001] The present specification relates to the field of smart manufacturing technology, and in particular to a smart manufacturing method and system based on a centralized service platform industrial Internet of Things. [Background technology]

[0002] In recent years, the industrial Internet of Things technology, which combines information technology and operation technology, has been developing rapidly and is expected to be applied to the smart manufacturing industry. At present, when the industrial Internet of Things technology is applied to the smart manufacturing industry, it is usually connected and integrated with different types of data collection devices, management and control systems, etc., to increase diversity and scale. When it is applied, the data collection device collects real-time status information and production and manufacturing data of the on-site equipment, and real-time data of the required equipment, production progress, etc. is provided to the user, solving problems such as automatic data collection, processing, statistics, and analysis, and further improving production and manufacturing efficiency, and optimizing resource allocation and management efficiency. However, the conventional industrial Internet of Things technology applied to smart manufacturing is usually developed for a single production project, and although it is interchangeable with a certain type of management and control system or a specific management and control system adopted by a certain user, it lacks universality and cannot take effective processing measures in a timely manner when production abnormalities occur, which seriously affects its popularization and application. For example, blank processing involves multiple types of processes, but conventional industrial Internet of Things technologies for smart blank processing only manage and control certain processes and cannot be applied to other processes.

[0003] Therefore, it is desirable to provide a smart manufacturing method based on a centralized service platform industrial Internet of Things that can better monitor the progress of blank processing by managing and controlling multiple types of processes for processing blanks, and take timely countermeasures when an abnormality occurs in the process. Summary of the Invention

[0004] One or more embodiments of the present specification provide a smart manufacturing method based on industrial Internet of Things with a centralized service platform, including a user platform, a service platform, a management platform, a sensing network platform and a target platform that sequentially interact with each other, in which the user platform is configured as a terminal device that interacts with a user, receives user input information, generates commands, and sends them to the service platform, and presents the information sent from the service platform to the user; the service platform is configured as a first server that receives commands sent from the user platform, processes them, and then sends them to the management platform, and obtains information required by the user from the management platform and sends it to the user platform; the management platform is configured as a second server that receives commands sent from the service platform, controls the target platform to operate according to the commands, and displays the information sent from the target platform to the user; the sensing network platform is configured as a communication network and gateway for interaction between the management platform and the target platform, the target platform is configured as a line equipment for manufacturing and a line sensor for collecting data, receives commands from the management platform to operate, and transmits sensing information to the management platform via the sensing network platform, the service platform adopts a centralized layout, the centralized layout means that the platform receives data in an integrated manner, processes data in an integrated manner, and transmits data in an integrated manner, both the management platform and the sensing network platform adopt a back-sub-platform layout, the back-sub-platform layout means that both the management platform and the sensing network platform are provided with an integrated platform and a plurality of sub-platforms,The transmission of control information and parameter configuration information of the target platform is from the sub-platform to the integrated platform, and the transmission of sensing information is from the integrated platform to the sub-platform. The method includes the following steps: when configuring parameters of the target platform, the user inputs the parameter configuration information of the target platform through the user platform; the service platform receives the parameter configuration information of the target platform transmitted from the user platform, and decomposes it into a plurality of sets of configuration data according to a process and transmits it to the management platform; the management platform stores and processes the received configuration data and transmits it to the sensing network platform, and the stored configuration data is taken as a reference data set; the sensing network platform stores and processes the received configuration data and transmits it to the target platform; the target platform performs parameter configuration of the target platform according to the parameter configuration information of the target platform; During operation of the line equipment, the target platform transmits its sensing information as a check data group to the management platform via the sensing network platform at a set time interval; the management platform receives and processes the check data group transmitted from the target platform, and transmits a reference data group and a check data group corresponding to the target platform that transmitted the check data group to the service platform; the service platform receives and compares the reference data group and the check data group; if all data in the check data group are within a set threshold range as a result of comparison with the reference data group, the data is cleared and no further processing is performed; if any data in the check data group exceeds the set threshold range as a result of comparison with the reference data group, an operation stop command is generated and transmitted to the management platform to be fed back to the user platform; and the management platform transmits the command to a corresponding target platform via the sensing network platform to control the operation of the line equipment to be stopped.Centralized service platform Provide smart manufacturing methods based on industrial Internet of Things.

[0005] One or more embodiments of the present specification provide a system for a smart manufacturing method based on a centralized service platform industrial Internet of Things, the system including a user platform, a service platform, a management platform, a sensing network platform and a target platform which sequentially interact with each other, the user platform is configured as a terminal device for interacting with a user, receives user input information, generates commands and sends them to the service platform, and presents the information sent from the service platform to the user, the service platform is configured as a first server, receives commands sent from the user platform, processes them and then sends them to the management platform, obtains information required by the user from the management platform and sends it to the user platform, the management platform is configured as a second server, receives commands sent from the service platform, and controls the target platform to operate according to the commands, and displays the information sent from the target platform to the user. the sensing network platform is configured as a communication network and gateway for interaction between the management platform and the target platform, the target platform is configured as a line equipment for performing manufacturing and a line sensor for performing data collection, receives commands from the management platform to operate, and transmits sensing information to the management platform via the sensing network platform, the service platform adopts a centralized layout, the centralized layout means that the platform receives data in an integrated manner, processes data in an integrated manner, and transmits data in an integrated manner, both the management platform and the sensing network platform adopt a back-sub-platform type layout, the back-sub-platform type layout means that both the management platform and the sensing network platform are provided with an integrated platform and a plurality of sub-platforms,This means that the transmission of control information and parameter configuration information of the target platform is from the sub-platform to the integrated platform, and the transmission of sensing information is from the integrated platform to the sub-platform. During parameter configuration of the target platform, the user inputs the parameter configuration information of the target platform through the user platform, the service platform receives the parameter configuration information of the target platform transmitted from the user platform, and decomposes it into a plurality of sets of configuration data according to a process and transmits it to the management platform, the management platform stores and processes the received configuration data sets and transmits them to the sensing network platform, the stored configuration data sets are regarded as reference data sets, the sensing network platform stores and processes the received configuration data sets and transmits them to the target platform, the target platform performs parameter configuration of the target platform according to the parameter configuration information of the target platform, and the license of the target platform is acquired. When the line equipment is in operation, the target platform transmits its sensing information as a check data group to the management platform via the sensing network platform at a set time interval; the management platform receives and processes the check data group transmitted from the target platform, and transmits a reference data group and a check data group corresponding to the target platform that transmitted the check data group to the service platform; the service platform receives and compares the reference data group and the check data group; if all data in the check data group are within a set threshold range as a result of comparison with the reference data group, the data is cleared and no further processing is performed; if any data in the check data group exceeds the set threshold range as a result of comparison with the reference data group, an operation stop command is generated and transmitted to the management platform to be fed back to the user platform; and the management platform transmits the command to a corresponding target platform via the sensing network platform to control the operation of the line equipment to be stopped.Provide a system of smart manufacturing methods based on a centralized service platform industrial Internet of Things. [Brief description of the drawings]

[0006] The present specification will be further illustrated in the form of exemplary embodiments, which will be described in detail with reference to the drawings, in which the exemplary embodiments are not limiting and in which like reference numerals indicate like structures. [Figure 1] FIG. 1 illustrates an example module diagram of a smart manufacturing system based on a centralized service platform industrial Internet of Things in accordance with some embodiments of the present disclosure. [Diagram 2] 4 is a flowchart of parameter configuration of the target platform in one embodiment of the present invention; [Diagram 3] 4 is a flow chart of checking sensing information in one embodiment of the present invention; [Figure 4] 1 is an example flowchart of a smart manufacturing method based on a centralized service platform industrial Internet of Things, according to some embodiments herein. [Diagram 5] FIG. 1 is an exemplary schematic diagram of a centralized service platform industrial Internet of Things-based smart manufacturing method applied to blank casting according to some embodiments herein. [Figure 6] FIG. 1 is an exemplary schematic diagram of a smart manufacturing method based on a centralized service platform industrial Internet of Things according to some embodiments of the present specification being applied to blank forging. [Figure 7] FIG. 1 is an exemplary schematic diagram of a smart manufacturing method based on a centralized service platform industrial Internet of Things applied to blank pressing according to some embodiments of the present disclosure. [Figure 8] 1 illustrates an example flow chart of a method for smart manufacturing of blanks based on blank performance according to some embodiments herein. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] In order to more clearly describe the technical solutions of the embodiments of this specification, the following briefly introduces drawings that need to be used in the description of the embodiments. Obviously, the drawings in the following description are only some examples or embodiments of this specification, and those skilled in the art can apply this specification to other similar scenes according to these drawings without paying creative labor. Unless otherwise clear from the context or otherwise described, the same numbers in the drawings represent the same structures or operations.

[0008] Flowcharts are used herein to describe operations performed in systems according to embodiments of the present invention. It should be understood that preceding or subsequent operations are not necessarily performed in precise order. Instead, steps may be processed in reverse order or simultaneously. Additionally, other operations may be added to these processes, or operations of one or more steps may be deleted from these processes.

[0009] 1 is an exemplary block diagram of a smart manufacturing system based on a centralized service platform industrial Internet of Things according to some embodiments of the present disclosure. As shown in FIG. 1, the system 100 includes a user platform, a service platform, a management platform, a sensing network platform, and a target platform that sequentially interact with each other, and the user platform, the service platform, the management platform, the sensing network platform, and the target platform are sequentially connected to each other to realize the interaction.

[0010] The user platform is configured as a terminal device for interacting with a user, receiving user input information, generating commands, sending the commands to the service platform, and presenting the information sent from the service platform to the user.

[0011] The service platform is configured as a first server, which receives and processes commands sent from the user platform, then sends them to the management platform, and obtains information required by the user from the management platform and sends it to the user platform. The service platform is further used to determine whether there is an abnormality in the process based on the post-processing check data set, the post-processing check data set including at least a standard degree score of the process execution by the line equipment, and if there is an abnormality in the process, sends a stop command to the management platform, and the management platform controls the line equipment to stop processing the blanks.

[0012] The management platform is configured as a second server, receives commands sent from the service platform, controls the target platform to operate according to the commands, and receives and stores the sensing information sent from the target platform. The management platform is further used to identify a process, obtain a check data group of the corresponding process, which is data obtained to check whether the process is normally performed, and process the check data group according to an anomaly judgment model to obtain a processed check data group.

[0013] The sensing network platform is configured as a communication network and a gateway through which the management platform and the target platform interact.

[0014] The target platform is configured as a line equipment for performing manufacturing and a line sensor for performing data collection, and receives commands from the management platform to operate and transmits sensing information to the management platform via the sensing network platform. The line equipment may include, but is not limited to, casting equipment, pouring equipment, pressurizing equipment, etc. The line sensor may include, but is not limited to, a temperature sensor, a pressure sensor, a hardness sensor, etc.

[0015] In the specific implementation of this embodiment, the user platform adopts smart electronic devices such as desktop computers, tablet computers, notebook computers, mobile phones, etc., which realize data processing and data communication, but are not limited thereto. The service platform of this embodiment adopts a centralized layout, which means that the platform receives data in an integrated manner, processes data in an integrated manner, and transmits data in an integrated manner. The management platform and the sensing network platform of this embodiment both adopt a back-to-back sub-platform layout, which means that the management platform and the sensing network platform both have an integrated platform and a number of sub-platforms, and the transmission of control information and parameter configuration information of the target platform is from the sub-platform to the integrated platform, and the transmission of sensing information is from the integrated platform to the sub-platform. In an embodiment, the integrated platform of the management platform is configured as a second main server and its sub-platform is configured as a second sub-server, data reception and processing by the integrated platform of the management platform is realized based on the second main server and data reception and processing by the sub-platform of the management platform is realized based on the second sub-server, the integrated platform of the sensing network platform is configured as a gateway main server and its sub-platform is configured as a gateway sub-server, data reception and processing by the integrated platform of the sensing network platform is realized based on the gateway main server and data reception and processing by the sub-platform of the sensing network platform is realized based on the gateway sub-server.The data processing process mentioned in this embodiment can be processed by the processors of the terminal device and the server, and accordingly, the server is provided with a database for storing data, and the database may be specifically stored in a memory device of the server, such as a hard disk or the like. The parameter configuration information of the target platform includes line equipment operation data, line equipment operation data, manufacturing process data, and product data such as blank samples, semi-finished products, and finished products corresponding to each stage. The sensing information acquired by the target platform includes line equipment operation data, line equipment operation data, manufacturing process data, and data collected by sensors.

[0016] In the specific implementation of this embodiment, based on the different line equipment and line sensors applied to different processes, the target platform is decomposed into multiple target platforms, and each target platform is provided with corresponding line equipment and line sensors.

[0017] The smart manufacturing method based on the centralized service platform industrial Internet of Things includes the steps of sequentially transmitting control information and parameter configuration information of a target platform by a user platform, a service platform, a management platform, a sensing network platform and a target platform, and sequentially transmitting sensing information by a target platform, a sensing network platform, a management platform, a service platform and a user platform, wherein, when transmitting a command, the receiving and processing of the command by each server is specifically processed into a data packet format that is easily identified by a pre-defined next-stage receiving target.

[0018] It should be understood that the system shown in FIG. 1 and its modules can be implemented in a variety of ways.

[0019] It should be noted that the above description of the centralized service platform industrial Internet of Things based smart manufacturing system and its modules is for convenience of description only, and does not limit the present specification to the scope of the embodiments given. It can be understood that after understanding the principle of the system, a person skilled in the art can arbitrarily combine each module or configure a subsystem and connect it with other modules without departing from the principle. In some embodiments, the user platform, service platform, management platform, sensing network platform and target platform shown in FIG. 1 may be different modules in one system, or one module may realize the functions of two or more modules. For example, each module may share one storage module, or each module may have its own storage module. Any such modifications are within the scope of protection of the present specification.

[0020] FIG. 2 is a flow chart of parameter configuration of the target platform in one embodiment of the present invention.

[0021] As shown in FIG. 2, the flow 200 of the smart manufacturing method further includes: when configuring parameters of the target platform, the user inputs parameter configuration information of the target platform through the user platform; the service platform receives the parameter configuration information of the target platform sent from the user platform, decomposes it into multiple sets of configuration data according to a process, and sends it to the management platform; the management platform stores and processes the received configuration data set and sends it to the sensing network platform, and uses the stored configuration data set as a reference data set; the sensing network platform stores and processes the received configuration data set and sends it to the target platform; and the target platform performs parameter configuration of the target platform according to the parameter configuration information of the target platform. In a specific implementation of this embodiment, when the user platform sends parameter configuration information to the target platform, each sub-platform in the management platform correspondingly stores and processes a set of configuration data, the integrated platform in the management platform compiles and stores and processes the configuration data sets processed by all the sub-platforms in the management platform, and transmits multiple sets of configuration data sets to the sub-platforms in the sensing network platform in a one-to-one correspondence, each sub-platform in the sensing network platform stores and processes the received configuration data sets, and the integrated platform in the sensing network platform compiles and stores and processes the configuration data sets processed by all the sub-platforms in the sensing network platform, and transmits multiple sets of configuration data sets to the target platform in a one-to-one correspondence.

[0022] FIG. 3 is a flow chart of checking sensing information in one embodiment of the present invention.

[0023] As shown in Fig. 3, the flow 300 of the smart manufacturing method further includes: when the line equipment of the target platform is in operation, the target platform transmits its sensing information as a check data group to the management platform through the sensing network platform at a set time interval; the management platform receives and processes the check data group transmitted from the target platform, and transmits a reference data group and a check data group corresponding to the target platform that transmitted the check data group to the service platform; the service platform receives and compares the reference data group and the check data group; if all data in the check data group are within a set threshold range as a result of comparison with the reference data group, the check data is cleared and no further processing is performed; if any data in the check data group exceeds the set threshold range as a result of comparison with the reference data group, a stop command is generated and sent to the management platform to feed back to the user platform; and the management platform transmits the command to the corresponding target platform through the sensing network platform to control the stop of the line equipment. Wherein, the set time interval for the target platform to obtain the sensing information and the set threshold range for parameter comparison are preset according to the needs of the user.

[0024] When this embodiment is applied, during the operation of the line equipment, the operating parameters and the products corresponding to each process are checked in real time, so that the impact of process deviations on the production of products can be quickly avoided and resources can be saved.

[0025] In some embodiments, when the service platform compares the reference data group with the check data group, if there is data in the check data group that exceeds a set threshold range as a result of comparison with the reference data group, the service platform also generates a sensing information acquisition command autonomously and sends it to the management platform before generating a shutdown command, the management platform receives the command sent from the service platform, and controls the corresponding target platform to send current sensing information according to the command. The target platform feeds back the current sensing information as a verification data group to the management platform via the sensing network platform, the management platform receives and processes the verification data group fed back from the target platform and then sends it to the service platform, the service platform receives the verification data group and compares it with the reference data group, if all data in the verification data group is within the set threshold range as a result of comparison with the reference data group, the data in the verification data group is cleared and no further processing is performed, and if there is still data in the verification data group that exceeds the set threshold range as a result of comparison with the reference data group, the service platform generates a shutdown command. Among these, the service platform spontaneously generates a command to obtain sensory information when it is confirmed that the check data group contains data that exceeds the set threshold range as a result of comparison with the reference data group, and the time required to send the command to the target platform is less than the time from the time it is confirmed that the data exceeds the set threshold range to the time when the target platform next spontaneously transmits the sensory information.

[0026] When this embodiment is applied, verification is performed again after checking, so that erroneous operation caused by deviation in data transmission can be avoided.

[0027] In some embodiments, after the service platform generates a shutdown command, the service platform also autonomously generates a sensing information acquisition command for a cascade process of the current process and sends it to the management platform, and the management platform receives the command sent from the service platform, and controls the target platform for the cascade process of the currently corresponding target platform according to the command to send current sensing information, and the cascade process is the previous process or the next process of the current process. The target platform for the cascade process feeds back current sensing information as a check data group to the management platform via the sensing network platform, the management platform receives and processes the check data group fed back from the target platform for the cascade process, and then transmits a reference data group and a check data group corresponding to the target platform for the cascade process that transmitted the check data group to the service platform, the service platform receives the check data group and the reference data group and compares them, and if all data in the check data group are within a set threshold range as a result of comparing with the reference data group, the data in the check data group is cleared and no further processing is performed, and if there is data in the check data group that exceeds a set threshold range as a result of comparing with the reference data group, the service platform generates an operation stop command and transmits it to the management platform to feed it back to the user platform, and the management platform transmits it to a corresponding target platform for the cascade process via the sensing network platform to control the operation of the cascade process line equipment to be stopped. The smart manufacturing process involves blank production, component production, full machine assembly, product inspection, etc., and specific processing involves casting, forging, punching, etc., and the blank material needs to go through a series of consecutive processes until the finished product is obtained. In this embodiment, when a problem is detected in a certain process, the cascade process is immediately inspected, so that the quality of the product manufactured in the cascade process can be ensured.

[0028] In some embodiments, when the cascade process is a process of the next stage of the current process, the service platform also autonomously generates a sensing information acquisition command for the cascade process and sends it to the management platform before generating an operation stop command; the management platform receives the command sent from the service platform and controls the corresponding target platform for the cascade process to send current sensing information according to the command; the target platform for the cascade process feeds back the current sensing information as a verification data group to the management platform via the sensing network platform; the management platform receives and processes the verification data group fed back from the target platform for the cascade process and sends it to the service platform; the service platform receives the verification data group and compares it with a reference data group; if all data in the verification data group is within a set threshold range as a result of comparing with the reference data group, the data in the verification data group is cleared and no further processing is performed; if there is still data in the verification data group that exceeds the set threshold range as a result of comparing with the reference data group, the service platform generates an operation stop command to control the operation of the line equipment for the cascade process to be stopped. For products that are processed sequentially through processes, the product operated in the next process is a further processed product of the product manufactured in the previous process, and if a problem occurs in the process preceding the current process, there is a possibility that a problem will also occur in the processed product. In this embodiment, if a problem occurs in the current process, a re-verification is performed when initially checking that there are no problems in the next cascade process, thereby ensuring the quality of the processed product.

[0029] In some embodiments, after the service platform breaks down the parameter configuration information into a plurality of configuration data groups according to the process, the service platform also establishes a product model of the corresponding process according to the data in each configuration data group and sends it to the user platform; the user confirms that there is no error in the product model through the user platform, and then sends a confirmation command to the service platform; the service platform receives and processes the confirmation command and then sends the confirmed configuration data group to the management platform. Specifically, the service platform of this embodiment establishes a product model of the corresponding process according to the data in each configuration data group, and may be realized based on conventional modeling software such as Solidworks, UG, 3DS Max, etc. In this embodiment, by establishing a product model and having the user confirm it, the user can correct the input product parameters in a timely manner even if there is a deviation, and can avoid the accurate operation of the system being affected by the reference data error during subsequent checking and verification.

[0030] In some embodiments, the service platform pre-stores pre-stored information of the general local design of the product, and before the service platform decomposes the parameter configuration information of the target platform into a plurality of configuration data groups according to the process, the service platform selects general local design information in the parameter configuration information of the target platform and compares it with the pre-stored information of the general local design of the product, and if all the comparison results are within a set design deviation threshold range, perform a decomposition process, and if any of the comparison results exceed the set design deviation threshold range, send it to the user platform; if the user confirms that the input information is correct through the user platform, a confirmation command is sent to the service platform, and the service platform performs a decomposition process; if the user changes the input information through the user platform, the service platform performs a re-verification until it is confirmed by the user platform, and then the service platform performs a decomposition process. Thus, when the embodiment is applied, it is possible to provide a comparison with the general design data of the product, provide an inspection function for the user during early data registration, and improve the performance of the smart system.

[0031] In some embodiments, when the target platform transmits its sensing information as a check data group to the management platform via the sensing network platform at a set time interval, the sensing information is transmitted alternately by different target platforms, thus the embodiment can reduce the working load of the first server, the second main server and the gateway main server at the same time, and effectively improve the working efficiency.

[0032] In some embodiments, there are multiple target platforms corresponding to each process, and when the line equipment of any target platform is stopped, the service platform checks the production status information of the target platform of the same process as the target platform, and adjusts the production quantity of the target platform of the same process as the target platform according to the production needs. In the smart manufacturing process, it is often the case that a production plan is made according to the quantity of products required by the customer, and this embodiment can ensure that the production quantity reaches the expected requirements through collaboration processing. In the specific implementation of this embodiment, when the problematic line equipment is adjusted and confirmed to be able to continue to participate in production, the processing quantity of the target platform corresponding to each process can be readjusted to ensure efficient production.

[0033] FIG. 4 is an example flowchart of a smart manufacturing method based on a centralized service platform industrial Internet of Things according to some embodiments of the present disclosure.

[0034] In some embodiments, the smart manufacturing method may be a method of machining a blank, where the method of machining a blank may include a plurality of processes, and the process of machining the blank may include at least casting, forging, and / or pressing, etc.

[0035] In some embodiments, the system 100 executes the flow 400 when the line equipment of the target platform operates a blank processing process. The line equipment may include at least a forging equipment, a pressing equipment, and / or a punch press, etc. For more details of the target platform and the line equipment, please refer to FIG. 1 and its related description. As shown in FIG. 4, the flow 400 includes the following steps 410 to 440.

[0036] In step 410, the management platform identifies a process and obtains a set of check data for the corresponding process.

[0037] In some embodiments, the target platform may be decomposed into multiple types according to the process, and the management platform may identify the process according to the type of the target platform. For example, the type of the target platform A is a casting target platform, and the management platform may identify the process acquired from the target platform A as a blank casting process, and the sensory information received from the target platform A may be the check data group of blank casting. The casting target platform refers to the target platform that casts the blank. For more details on the decomposition of the target platform, please refer to FIG. 2 and its related description. For more details on the management platform, please refer to FIG. 1 and its related description.

[0038] The check data group may be various data acquired to check whether the process is normally performed. In some embodiments, the check data group may be sensory information. For example, the process may be blank casting, and the blank casting step may include at least metal smelting. The check data group may include operation data and operational data of the smelting equipment, process data of metal smelting, and temperature information of the metal acquired by a temperature sensor, etc. For more details on the sensory information, please refer to FIG. 1 and its related description.

[0039] In step 420, the management platform processes the set of check data according to the anomaly judgment model to obtain a set of processed check data.

[0040] In some embodiments, an anomaly judgment model is installed in the management platform, and the anomaly judgment model can process the set of check data to obtain a set of processed check data. In some embodiments, the anomaly judgment model may be various machine learning models, including, but not limited to, random forest rules, logistic regression, support vector machines, etc.

[0041] In some embodiments, there may be multiple anomaly judgment models, and different anomaly judgment models may be installed in different sub-platforms of the management platform to process different types of check data groups.

[0042] In some embodiments, the management platform may input the reference data group and the check data group into the anomaly judgment model, and the model may output a standard score of the check data group. The reference data group may be various data indicating that the process is running normally. For example, the reference data group may include, but is not limited to, operation data and operation data of normal operation of the line equipment, standard process data of blank processing, data of normal operation of the line equipment acquired by a sensor, etc. The type of reference data may include, but is not limited to, a numerical range, an image of a standard process, etc. For more details on the reference data group, please refer to FIG. 2 and its related description. For more details on the anomaly judgment model, please refer to FIG. 5, FIG. 6, and FIG. 7 and their related description.

[0043] In step 430, the service platform determines whether there is an abnormality in the process based on the post-processing check data group.

[0044] The processed check data group includes at least a standard score of the process performed by the line equipment. The standard score can be used to indicate the standard degree of the process performed by the line equipment. For example, a higher score indicates a higher standard degree, and a lower score indicates a lower standard degree, and if the score is below a set threshold range, it can be determined that there is an abnormality in the process. The set threshold range may be a range of standard scores when the line equipment is operating normally. In some embodiments, the set threshold range may be set by a user via a user platform and sent to the service platform. In some embodiments, the set threshold ranges corresponding to different processes may be different, but can be set according to experience.

[0045] In some embodiments, the service platform may compare the obtained normality score with a set threshold range, and if the normality score is not within the set threshold range, an abnormality in the corresponding process is indicated.

[0046] Step 440: if it is determined that the process is abnormal, the service platform sends a stop command to the management platform, and the management platform controls the line equipment to stop processing the blanks.

[0047] In some embodiments, if it is determined that the process is abnormal, the service platform generates a blanking stop command and sends it to the management platform to feed back to the user platform. The management platform receives the stop command sent from the service platform and controls the corresponding target platform to stop operation.

[0048] FIG. 5 is an exemplary schematic diagram of a centralized service platform industrial Internet of Things based smart manufacturing method applied to blank casting according to some embodiments herein.

[0049] In some embodiments, when the blank is cast by the line equipment, the abnormality judgment model may be a first model, and the check data group may include temperature information. As shown in Fig. 5, a schematic flow 500 includes the following steps 510 to 520.

[0050] In step 510, the management platform inputs the temperature information into a first model, which outputs a first score.

[0051] The casting step may include at least melting a metal and pouring the melted metal into a mold to obtain a casting. The mold may refer to a metal mold into which molten metal is poured to form a casting during casting. The temperature information may be information about a temperature generated during casting of the blank. In some embodiments, the temperature information may be divided into melting temperature information and pouring temperature information according to the casting step.

[0052] The melting temperature information may refer to temperature information during melting of the metal. For example, the melting temperature information may include temperature information of the metal being melted, acquired at a first set time interval during the melting process.

[0053] The first set time interval may refer to a time interval for acquiring the melting temperature information that is set in advance. The first set time interval can be set based on experience.

[0054] The pouring temperature information may refer to temperature information during a process of pouring a molten metal into a mold to obtain a casting. For example, the pouring temperature information includes temperature information of the casting obtained at a second set time interval after pouring.

[0055] The second set time interval may refer to a preset time interval for acquiring pouring temperature information. The second set time interval can be set according to experience.

[0056] Since temperature affects the hardness of metal, castings at different temperatures will have different distortions due to forging. In some embodiments, to avoid the casting being significantly deformed during forging and resulting in waste, the temperature information of the casting may include a temperature distribution at multiple locations on the casting, such as temperature values ​​at the top, middle, and bottom of the casting. When the temperature values ​​at the multiple locations on the casting are all at a temperature suitable for forging, the casting is forged.

[0057] In some embodiments, temperature information may be obtained in a variety of possible ways.

[0058] The first score can be used to indicate the standard of performance of the casting process by the casting facility, in some embodiments, the first score can be expressed as a numerical value, with a higher numerical value indicating a more standard of performance of the casting process and vice versa.

[0059] In some embodiments, the first score may be determined using a first model, which in some embodiments may include a trained machine learning model, which may include a variety of models and results, such as a deep learning model (DNN), a recurrent neural network (RNN), etc.

[0060] In some embodiments, the input of the first model includes temperature information, and the output is a first score. For example, the input temperature information may be the melting temperature value and the pouring temperature value at each time point, and the first model extracts the temperature values ​​at each time point of different temperature information, respectively, to obtain the change characteristics of the melting temperature value and the change characteristics of the pouring temperature value, and outputs a first score of the blank casting. The input of the first model may further include other temperature information, and other possible ways may be used for outputting and determining the first score.

[0061] In some embodiments, the method for obtaining the first model includes obtaining at least one first training sample, the first training sample including scored sample temperature information, and an initial first model, and iteratively updating parameters of the initial first model based on the at least one first training sample to obtain a first model. For example, a plurality of labeled training samples may be input into the initial first model, a loss function may be constructed according to the label and the prediction result of the initial first model, and the parameters of the initial first model may be iteratively updated based on the loss function, and the training of the model is completed when the loss function of the initial first model satisfies a preset condition, where the preset condition may be that the loss function converges, the number of iterations reaches a threshold, etc. The training method of the initial first model may be various well-known methods, such as gradient descent.

[0062] Step 520: if the first score exceeds a first set threshold range, the service platform determines that there is an abnormality in the casting process, and controls the line equipment to stop casting blanks.

[0063] The first set threshold range may refer to a preset range of the first score, and when the first score is within the range, it is unlikely that an abnormality will occur in the casting process, and it can be considered that there is no abnormality in the casting process.

[0064] In some embodiments, the first predetermined threshold range can be set based on experience. For example, experience shows that when the first score is less than 3, the probability of an anomaly occurring in the casting process is close to 100%. Therefore, the first predetermined threshold range may be determined as a range greater than 3.

[0065] Some embodiments herein can continuously monitor the temperature of the casting blank and use a first model to determine if there is an anomaly in the casting process, ensuring that the casting of the blank can proceed in a safer and more orderly manner.

[0066] FIG. 6 is an exemplary schematic diagram of a smart manufacturing method based on a centralized service platform industrial Internet of Things according to some embodiments herein being applied to blank forging.

[0067] In some embodiments, when the blank is forged by the line equipment, the abnormality judgment model may be a second model, and the check data group may include pre-pressure images and post-pressure images of the blank during forging. As shown in Fig. 6, a schematic flow 600 includes the following steps 610 to 620.

[0068] In step 610, the management platform inputs the pre-compression image, the post-compression image and the first set of reference data into a second model, and the second model outputs a second score.

[0069] A pre-pressure image may refer to an image of the blank before pressure is applied, such as an image of a casting, an image of the blank before it is pressed, etc. A pre-pressure image can be used to show the configuration of the blank before it is pressed.

[0070] An after-press image may refer to an image of the blank after it has been pressed, for example, an image of the blank after each press. The after-press image can be used to show the appearance of the blank after it has been pressed.

[0071] In some embodiments, pre-pressure and post-pressure images of the blank may be captured by various image capture devices.

[0072] The first set of reference data may refer to standard data for determining whether the blank forging is standard. In some embodiments, the first set of reference data includes a standard pre-press image and a standard post-press image.

[0073] The standard pre-press image may be a pre-set standard shape of the blank before pressing. For example, the standard pre-press image may be an image of a product model before forging. In some embodiments, the standard pre-press image includes a standard shape of the blank before forging, such as the size of the casting, the flatness of the casting, etc.

[0074] The standard post-press image may be a preset standard shape of the blank after pressing. For example, the standard post-press image may be an image of a product model after forging. In some embodiments, the standard post-press image includes a standard shape after forging for the blank. For example, the size of the forging, the flatness of the forging, etc.

[0075] The second score can be used to indicate the standard degree of the forging process performed by the forging equipment. The indication of the second score is similar to that of the first score, and for more details of the second score, please refer to FIG. 5 and its related description.

[0076] In some embodiments, a second model may be used to determine the second score. In some embodiments, the second model may include a trained machine learning model, which may include a variety of models and results, such as a deep neural network (DNN), a convolutional neural network (CNN), etc.

[0077] In some embodiments, the input of the second model may be an input of an image pair, and the image pair may include an image before forging and a standard pre-pressing image, and an image after forging and a standard post-pressing image, and the output may be a second score of the blank forging. For example, image a is an image of casting A, image d is an image of forging A, image a1 is an image of a product model before forging (i.e., an image of a standard casting), and image b1 is an image of a product model after forging (i.e., an image of a standard forging). Among them, forging A can be obtained by forging casting A. Thus, the input of the second model may be {(a, a1), (d, b1)}, and the second model may extract features of the input images, respectively, and then match the features of a and a1, and the features of d and b1, respectively, and obtain a second score based on the matching result.

[0078] In some embodiments, the check data set includes an image sequence of multiple pressurizations of the blank. The standard pre-pressure image may be a standard image before the blank is pressed. The standard post-pressure image may be a standard image after the final pressurization of the blank.

[0079] The images of multiple presses may be from the forging process of the same blank, and the images of multiple presses may be sorted according to the order of forging to obtain an image sequence of multiple presses. For example, a casting A is pressed three times to obtain a forging A, and an image a is obtained before pressing the casting A, an image b is obtained after the first pressing of the casting A, and then images c and d are obtained after the second and third pressing in the same manner as image b. In this way, an image sequence of the forging A pressed multiple times: (a, b, c, d) can be obtained.

[0080] Since the intermediate form of the blank formed during forging is not uniform, a standard image before the blank is pressed may be a standard pre-pressure image, and a standard image after the blank is pressed for the final time may be a standard post-pressure image. For example, the standard pre-pressure image may be a standard image of a casting. The standard post-pressure image may be a standard image of a forging.

[0081] In some embodiments, the second model may be a spatio-temporal network model (CNN+LSTM). In some embodiments, the input of the second model may include an image sequence of multiple pressings, a standard pre-pressing image, and a standard post-pressing image, and the output may be a second score of the forging process. For example, the image sequence of multiple pressings of the forging A may be (a, b, c, d), the standard pre-pressing image may be a1, and the standard post-pressing image may be b1, and the input of the second model may be {(a, a1), ((a, b, c, d), b1)}, and the second model may obtain a feature e of the forging A based on the image sequence of multiple pressings, and then match the feature between a and a1 and the feature between e and b1, and obtain a second score based on the matching result.

[0082] Some embodiments herein obtain characteristics of the forging based on image sequences of multiple pressings, so that the characteristics of the forging include forging process information, thereby improving the accuracy of the second score.

[0083] In some embodiments, the method for obtaining the second model includes obtaining at least one second training sample, the second training sample including a scored second image sample group, the second image sample group including at least a sample pre-pressure image, a sample post-pressure image, a standard pre-pressure image, and a standard post-pressure image, and an initial second model; and iteratively updating parameters of the initial second model based on the at least one second training sample to obtain a second model. For example, a plurality of labeled training samples may be inputted into the initial second model, a loss function may be constructed according to the labels and the prediction result of the initial second model, and the parameters of the initial second model may be iteratively updated based on the loss function, and the training of the model is completed when the loss function of the initial second model satisfies a preset condition, where the preset condition may be that the loss function converges, the number of iterations reaches a threshold, etc. The training method of the initial second model may be various well-known methods, such as gradient descent.

[0084] Step 620: if the second score exceeds a second set threshold range, the service platform determines that there is an abnormality in the forging process, and controls the line equipment to stop forging the blank.

[0085] The second set threshold range may refer to a preset range of the second score, and if the second score is within the range, it is unlikely that an abnormality will occur in the forging process, and it can be considered that there is no abnormality in the forging process.

[0086] In some embodiments, the second set threshold range is obtained in a similar manner to the first set threshold range, and more details about the second set threshold range can be found in FIG. 5 and its related description.

[0087] Some embodiments herein monitor the blank forging and use the second model to judge whether there is an abnormality in the forging process, so that the status of the blank forging can be obtained in a timely manner and the abnormal situation can be dealt with in a timely manner, thereby avoiding the expansion of losses caused by not dealing with the abnormal situation in a timely manner.

[0088] FIG. 7 is an exemplary schematic diagram of a smart manufacturing method based on a centralized service platform industrial Internet of Things according to some embodiments of the present disclosure being applied to blank pressing.

[0089] In some embodiments, when the blank is pressed by the line equipment, the abnormality judgment model may be a third model, and the check data set may include a pre-press image and a post-press image of the blank. As shown in Fig. 7, a schematic flow 700 includes the following steps 710 to 720.

[0090] In step 710, the management platform inputs the before-press image, the after-press image, and the second set of reference data into a third model, and the third model outputs a third score.

[0091] A pre-press image may refer to an image of the blank before it is pressed, such as an image of a forging, an image of the blank before each press, etc. A pre-press image can be used to show the form of the blank before it is pressed.

[0092] The after-press image may be an after-press image of the blank, for example an image of the blank after each press, which can be used to show the form of the blank after it has been pressed.

[0093] In some embodiments, the acquisition method of the pre-press image and the post-press image is similar to the acquisition method of the pre-press image and the post-press image, for more details on the acquisition of the pre-press image and the post-press image, please refer to FIG. 6 and its related description.

[0094] The second set of reference data may refer to standard data for determining whether the pressing of the blank is standard. In some embodiments, the second set of reference data includes a standard before-press image and a standard after-press image.

[0095] The standard pre-press image may be a pre-set standard configuration of the pre-press blank. For example, the standard pre-press image may be an image of a pre-press product model. In some embodiments, the standard pre-press image includes a pre-press standard configuration for the blank, for example, the size of the forging, the thickness of the forging, etc.

[0096] The standard post-press image may be a preset standard form of the blank after pressing. For example, the standard post-press image may be an image of a product model after pressing. In some embodiments, the standard post-press image includes a standard form after pressing for the blank. For example, the size of the pressed product, the thickness of the pressed product, etc.

[0097] The third score can be used to indicate the standard degree of the execution of the pressing process by the pressing equipment. The indication by the third score is similar to that of the first score, and more details of the third score can be found in FIG. 5 and its related description.

[0098] In some embodiments, a third model may be used to determine the third score. The type of the third model and the method of determining the third score by the third model are similar to those of the second model. For more details about the third model, please refer to FIG. 6 and its related description.

[0099] In some embodiments, the check data set includes an image sequence of multiple presses on the blank. The standard pre-press image may be a standard image before the blank is pressed. The standard post-press image may be a standard image after the final press on the blank. The standard image includes a standard configuration of the blank.

[0100] The images of multiple pressings may be from the pressing process of the same blank, and the images of multiple pressings can be sorted according to the order of pressing to obtain an image sequence of multiple pressings. The pressing process is similar to the forging process, and more details of the image sequence of multiple pressings can be found in FIG. 6 and its related description.

[0101] For reasons similar to those for forging the blank, a standard image before the blank is pressed may be a standard pre-press image, and a standard image after the blank is pressed for the final time may be a standard post-press image. For example, the standard pre-press image may be a standard image of the forging. The standard post-press image may be a standard image of the pressed product.

[0102] In some embodiments, the input of the third model may include an image sequence of multiple presses, a standard pre-press image, and a standard post-press image, and the output may be a third score for the press. The third model derives a third score based on an image sequence of multiple presses, a standard pre-press image, and a standard post-press image in a manner similar to the second model deriving a second score based on an image sequence of multiple presses, a standard pre-press image, and a standard post-press image; for more details on the third model, see FIG. 6 and the associated description.

[0103] Some embodiments herein obtain characteristics of a pressed product based on image sequences of multiple pressings, thereby allowing the characteristics of the pressed product to include information about the pressing process, thereby improving the accuracy of the third score.

[0104] In some embodiments, the method for obtaining the third model includes: obtaining at least one third training sample, the third training sample includes a group of scored third image samples, the group of third image samples includes at least a sample pre-press image, a sample post-press image, a standard pre-press image and a standard post-press image; and an initial third model; and iteratively updating parameters of the initial third model according to the at least one third training sample to obtain a third model. The method for training the third model is similar to the method for training the second model, and for more details of the third model, please refer to FIG. 6 and its related description.

[0105] Step 720: if the third score exceeds a third set threshold range, the service platform determines that there is an abnormality in the pressing process, and controls the line equipment to stop pressing the blanks.

[0106] The third set threshold range may refer to a preset range of the third score, and when the third score is within the range, it is unlikely that an abnormality will occur in the pressing process, and it can be considered that there is no abnormality in the pressing process.

[0107] In some embodiments, the third set threshold range is obtained in a similar manner to the first set threshold range, and for more details about the third set threshold range, please refer to FIG. 5 and its related description.

[0108] Some embodiments herein monitor the pressing of the blank, and use the third model to judge whether there is an abnormality in the pressing process, so that the status of the pressing of the blank can be obtained in a timely manner, and the abnormal situation can be dealt with in a timely manner, thereby avoiding losses caused by not dealing with the abnormal situation in a timely manner.

[0109] 8 is an exemplary flow chart of a method for smart manufacturing of blanks based on blank performance according to some embodiments of the present disclosure. As shown in FIG. 8, flow 800 includes the following steps 810-830.

[0110] In step 810, the management platform may predict the performance of the blank after each process based on a set of check data from a plurality of processes for processing the blank.

[0111] The performance of the blank may include, but is not limited to, the hardness, strength, and the like of the blank.

[0112] In some embodiments, the management platform may input the set of check data into a performance prediction model, and the performance prediction model may output the performance of the blank. For example, the management platform may input the set of check data of the pressing of the blank into a performance prediction model, and the model may output a predicted hardness of the blank after pressing.

[0113] In some embodiments, the performance prediction model can be obtained by training the initial performance prediction model with a fourth training sample. The fourth training sample includes a sample check data group. The sample check data group is assigned with corresponding blank performance. The fourth training sample can be obtained by extracting blank processing historical data. The training method of the performance prediction model is similar to that of the first model. For more details on the training of the performance prediction model, please refer to FIG. 4 and its related description.

[0114] In some embodiments, the management platform may predict the performance of the blank after each step by fitting the set of check data to historical statistical data.

[0115] The past statistical data may be data obtained after statistical processing of past data of blank processing. The past statistical data may include a check data set of past blank processing, and the performance of blanks obtained by processing the blanks by the line equipment according to the check data set.

[0116] In some embodiments, the management platform may classify the historical statistical data, obtain the check data group and historical statistical data of the same type as the check data group, fit the relationship between the check data group and the historical statistical data using the least squares method, and then calculate the blank performance of the check data group from the blank performance corresponding to the historical statistical data.

[0117] In some embodiments, the management platform may adjust the fitted blank performance according to the actual performance of the blank, and store the adjusted data. By recording the actual blank performance and the predicted blank performance, a more suitable fitting effect can be achieved.

[0118] In some embodiments herein, the predicted blank performance is predicted more accurately by fitting a set of check data to past statistical data to predict the blank performance.

[0119] Step 820 involves the service platform determining whether the performance of the blank meets a preset condition based on the set of reference data.

[0120] In some embodiments, the reference data set includes standard data for the process. For example, the reference data set includes the performance that the blank should achieve after each process. For more details on the reference data set, see FIG. 4 and the associated description.

[0121] The preset conditions may refer to conditions that the performance of the blank after processing should meet. In some embodiments, the service platform may determine the standard value range of each performance of the blank after the process according to the data of the reference data set. In some embodiments, the service platform determines whether the performance of the blank after each process is unacceptable according to the reference data set, and if unacceptable, it indicates that there is an abnormality in the processing process.

[0122] Step 830 stops machining the blank if it is determined that the performance of the blank does not meet the preset conditions. For more details on stopping machining, please refer to FIG. 4 and its related description.

[0123] In some embodiments, the service platform may determine whether there is an abnormality risk in the blank processing process based on the score of each process, and if so, perform actual detection for the performance with an unacceptable score to determine whether there is really an abnormality risk, and if so, send a stop command to the production equipment with an unacceptable performance.

[0124] The abnormality risk may refer to the risk of an abnormality occurring during the blanking process. The abnormality risk may be indicated as high or low.

[0125] In some embodiments, the service platform may determine whether there is an abnormality risk in the blanking process based on the first score, the second score and the third score, for example, the service platform determines whether the first score, the second score and the third score are all within corresponding set threshold ranges, and if so, determines that there is no risk in the blanking process, and if not, performs actual detection for unacceptable performance.

[0126] The actual detection may be detection of the operating status of the target platform. For example, a detection device may be installed in the target platform, and the detection device can be used to detect the target platform with an abnormality risk. If the service platform determines that there is an abnormality risk in the blanking process, the service platform will automatically send an instruction to obtain a detection check data group to the management platform. The management platform obtains the detection check data group from the detection device according to the instruction, and the service platform obtains data from the management platform to determine whether there is really an abnormality risk in the blanking process by the target platform. If the actual detection result still indicates that there is an abnormality risk in the target platform, it is determined that the abnormality risk is real, and the management platform controls the target platform to stop blanking. The manner in which the service platform determines whether the detection check data group is abnormal is similar to the manner in which the check data group is abnormal. For more details on the determination of whether the detection check data group is abnormal, please refer to FIG. 4 and its related description.

[0127] In some embodiments, the service platform may fuse the scores of each process, compare the fused score with a threshold, and determine whether there is an anomaly risk based on the comparison result, where the fusion includes weight fusion based on each score. For example, the service platform may adopt at least an arithmetic average method and a weighted average method to perform a fusion process of the first score, the second score, and the third score to obtain a fused score. In some embodiments, the service platform may determine the reliability of each score, and determine the weight of each score at the time of fusion based on the reliability. In some embodiments, the reliability may be determined according to the accuracy of the anomaly judgment model at the time of training. For example, the weight may be the accuracy rate of the anomaly judgment model, and the accuracy rate may be the ratio of the number of correctly predicted training samples to the total number of training samples. For further example, the weight may be the F value of the anomaly judgment model, and the F value is a composite value of the accuracy rate and the recall rate. The F value may be obtained by Equation (1). JPEG0007659624000001.jpg15170

[0128] Wherein, F1 is the F-measure, the precision rate is the ratio of the number of correctly predicted positive samples to the total number of predicted positive samples, and the recall rate is the ratio of the number of correctly predicted positive samples to the total number of actual positive samples.

[0129] Some embodiments in this specification can reduce the number of false positives and improve the reliability of the system by performing detection again on a target platform that is at risk of an anomaly.

[0130] Since the ultimate purpose of blank processing is to make the blank usable, some embodiments in this specification determine whether the process is abnormal based on the performance of the blank, so that it can more directly determine whether the processed blank can be used normally, and the prediction result is more accurate.

[0131] Although the basic concept has been described above, it is obvious to those skilled in the art that the detailed disclosure above is merely an example and does not constitute a limitation to the present specification. Although not explicitly described herein, various changes, improvements and modifications may be made to the present specification by those skilled in the art. Since such changes, improvements and modifications are proposed herein, such changes, improvements and modifications are still within the spirit and scope of the exemplary embodiments of the present specification.

[0132] Moreover, the specification uses certain terms to describe the embodiments of the specification. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a feature, structure, or characteristic associated with at least one embodiment of the specification. Thus, it should be emphasized and noted that "one embodiment," "an embodiment," or "an alternative embodiment" referenced two or more times in different locations in the specification do not necessarily refer to the same embodiment. Also, some features, structures, or characteristics in one or more embodiments of the specification may be combined as appropriate.

[0133] Similarly, it should be noted that in the above description of the embodiments of the present specification, multiple features may be grouped together in one embodiment, drawing, or description thereof in order to simplify the presentation of the present specification and to facilitate understanding of one or more embodiments of the present invention. However, such presentation does not imply that the subject matter of the present specification requires more features than are recited in the claims. In fact, an embodiment may have fewer features than all of the features in a single embodiment presented above.

[0134] Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments herein. Other variations may be within the scope of the present specification. Thus, by way of example, and not of limitation, alternative configurations of the embodiments herein are contemplated as being consistent with the teachings of the present specification. Accordingly, the embodiments herein are not limited to the embodiments expressly introduced and described herein.

Claims

1. A smart manufacturing method for managing and controlling multiple processes based on a centralized service platform industrial Internet of Things, the method including a user platform, a service platform, a management platform, a sensing network platform and a target platform that sequentially interact with each other, comprising: The user platform is configured as a terminal device that interacts with a user, receives user input information, generates commands, and transmits the commands to the service platform, and presents the information transmitted from the service platform to the user; The service platform is configured as a first server, which receives and processes commands sent from the user platform, and then sends the commands to the management platform; and obtains information required by the user from the management platform and sends the information to the user platform; A management platform is configured as a second server, which receives commands sent from the service platform, controls the target platform to operate according to the commands, and receives and stores sensory information sent from the target platform; a sensing network platform configured as a communication network and a gateway through which the management platform and the target platform interact; The target platform is configured as a line equipment for performing manufacturing and a line sensor for performing data collection, and receives commands from the management platform to operate and transmits sensing information to the management platform via the sensing network platform; The service platform adopts a centralized layout, which means that the service platform receives data in an integrated manner, processes data in an integrated manner, and transmits data in an integrated manner; the management platform and the sensing network platform both adopt a back-to-back sub-platform layout, which means that both the management platform and the sensing network platform are provided with an integrated platform and a number of sub-platforms, and control information and parameter configuration information of a target platform are transmitted from the sub-platform to the integrated platform, and sensing information is transmitted from the integrated platform to the sub-platforms; The method comprises: During parameter configuration of the target platform, the user inputs parameter configuration information of the target platform through the user platform, the service platform receives the parameter configuration information of the target platform sent from the user platform, decomposes it into multiple sets of configuration data according to multiple types of processes, and sends it to the management platform, the management platform stores and processes the received configuration data and sends it to the sensing network platform, the stored configuration data set is used as a reference data set, the sensing network platform stores and processes the received configuration data and sends it to the target platform, and the target platform performs parameter configuration of the target platform according to the parameter configuration information of the target platform; During operation of the line equipment of the target platform, the target platform identifies a process, and transmits its sensing information as a check data group to the management platform via the sensing network platform at a set time interval; the management platform receives and processes the check data group transmitted from the target platform, and transmits a reference data group and a check data group corresponding to the target platform that transmitted the check data group to the service platform; the service platform receives and compares the reference data group and the check data group; if all data in the check data group are within a set threshold range as a result of comparison with the reference data group, the data is cleared and no further processing is performed; if any data in the check data group exceeds the set threshold range as a result of comparison with the reference data group, a stop command is generated and transmitted to the management platform to be fed back to the user platform; and the management platform transmits the command to a corresponding target platform via the sensing network platform to control the stop of operation of the line equipment; The service platform pre-stores pre-stored information of general local design of a product. Before the service platform decomposes the parameter configuration information of the target platform into a plurality of configuration data groups according to the process, the service platform selects general local design information in the parameter configuration information of the target platform and compares it with the pre-stored information of the general local design of the product. If all the comparison results are within a set design deviation threshold range, a decomposition process is performed. If any of the comparison results exceed the set design deviation threshold range, the comparison results are sent to the user platform. If the user confirms through the user platform that there is no error in the input information, a confirmation command is sent to the service platform, and the service platform performs the decomposition process. If the user changes the input information through the user platform, the service platform performs the comparison again until it is confirmed by the user platform, and then the service platform performs the decomposition process. The smart manufacturing method is a method for processing a blank, the process of processing the blank including at least casting, forging and / or pressing, and during operation of a line facility of a target platform, The management platform identifies the process and obtains a set of check data for the corresponding process, the set of check data being data obtained to check whether the process is normally performed; The management platform processes the set of check data according to an anomaly judgment model to obtain a set of processed check data; The service platform judges whether there is an abnormality in the process based on the set of post-processing check data, and the set of post-processing check data includes at least a standard score of the execution of the process by the line equipment; If an abnormality is found, the service platform sends a stop command to the management platform, and the management platform controls the line equipment to stop processing the blanks; The standardized scores include a first score, a second score, and a third score, combining the first score, the second score, and the third score to determine a combined score; Combining the first score, the second score, and the third score to determine a combined score includes: determining confidence levels corresponding to the first score, the second score, and the third score, respectively, according to the accuracy of the anomaly judgment model during training; determining weights corresponding to the first score, the second score, and the third score, respectively, based on the reliability corresponding to the first score, the second score, and the third score, respectively, the weights being an F-value of the anomaly judgment model, the F-value being a composite value of a precision rate and a recall rate; and determining whether or not there is an abnormality based on the result of comparing the fused score with a threshold.

2. When the user platform sends parameter configuration information to the target platform, each sub-platform in the management platform stores and processes a set of configuration data correspondingly, and an integrated platform in the management platform stores and processes the configuration data processed by all the sub-platforms in the management platform, and sends a plurality of sets of configuration data to the sub-platforms in the sensing network platform in a one-to-one correspondence; The smart manufacturing method based on the centralized service platform industrial Internet of Things as claimed in claim 1, characterized in that each sub-platform in the sensing network platform stores and processes the received configuration data groups, and an integrated platform in the sensing network platform stores and processes the configuration data groups processed by all sub-platforms in the sensing network platform, and sends multiple sets of configuration data groups to the target platform in a one-to-one correspondence.

3. When the service platform compares the reference data group with the check data group, if the check data group contains data that exceeds a set threshold range as a result of comparison with the reference data group, the service platform also generates a sensing information acquisition command spontaneously before generating a shutdown command and sends it to the management platform; the management platform receives the command sent from the service platform, and controls the corresponding target platform to send current sensing information according to the command; 2. The smart manufacturing method based on industrial Internet of Things with a centralized service platform of claim 1, wherein the target platform feeds back current sensing information as a verification data group to the management platform via the sensing network platform, the management platform receives the verification data group fed back from the target platform, processes it, and then sends it to the service platform, the service platform receives the verification data group and compares it with a reference data group, and if all data in the verification data group are within a set threshold range as a result of comparing with the reference data group, the data in the verification data group is cleared and no further processing is performed, and if there is still data in the verification data group that exceeds the set threshold range as a result of comparing with the reference data group, the service platform generates an operation shutdown command.

4. After the service platform generates a stop command, the service platform also generates a sensing information acquisition command for a cascade process of a current process and sends it to the management platform, the management platform receives the command sent from the service platform, and controls a target platform for a cascade process of the currently corresponding target platform according to the command to send current sensing information, the cascade process being a previous process or a next process of the current process; 4. The smart manufacturing method based on industrial Internet of Things with a centralized service platform according to claim 3, wherein the target platform for the cascade process feeds back current sensing information as a check data group to the management platform through the sensing network platform, the management platform receives and processes the check data group fed back from the target platform for the cascade process, and then transmits a reference data group and a check data group corresponding to the target platform for the cascade process that transmitted the check data group to the service platform, the service platform receives the check data group and the reference data group and compares them, and if all data in the check data group are within a set threshold range as a result of comparing with the reference data group, clears the data in the check data group and does not perform further processing, and if any data in the check data group exceeds the set threshold range as a result of comparing with the reference data group, generates an operation stop command and transmits it to the management platform to feed it back to the user platform, and the management platform transmits it to a corresponding target platform for the cascade process via the sensing network platform to control the operation of the cascade process line equipment to be stopped.

5. When the cascade process is a next-stage process of a current process, before generating a stop command, the service platform also generates a sensing information acquisition command for the cascade process and sends it to the management platform, and the management platform receives the command sent from the service platform and controls the corresponding target platform for the cascade process to send current sensing information according to the command; 5. The smart manufacturing method based on industrial Internet of Things with a centralized service platform of claim 4, wherein the target platform for the cascade process feeds back current sensing information as a verification data group to the management platform through the sensing network platform, the management platform receives the verification data group fed back from the target platform for the cascade process, processes the verification data group, and then transmits the verification data group to the service platform, the service platform receives the verification data group and compares it with a reference data group, and if all data in the verification data group are within a set threshold range as a result of comparing with the reference data group, the data in the verification data group is cleared and no further processing is performed, and if there is still data in the verification data group that exceeds the set threshold range as a result of comparing with the reference data group, the service platform generates an operation stop command to control the operation of equipment in the cascade process line to stop.

6. 2. The smart manufacturing method based on industrial Internet of Things with a centralized service platform according to claim 1, wherein after the service platform decomposes parameter configuration information into a plurality of sets of configuration data groups according to processes, the service platform also establishes a product model of the corresponding process according to the data in each set of configuration data groups and sends it to the user platform; the user confirms that there is no error in the product model through the user platform, and then sends a confirmation command to the service platform; the service platform receives and processes the confirmation command, and then sends the confirmed configuration data group to the management platform.

7. When the blank is cast by the line equipment, the abnormality judgment model is a first model, and the check data group includes temperature information, The management platform inputs the temperature information into the first model, and the first model outputs the first score, the temperature information including melting temperature information and pouring temperature information, the melting temperature information including temperature information of the metal to be melted, which is obtained at a first set time interval during the melting process, and the pouring temperature information including temperature information of the casting, which is obtained at a second set time interval after pouring; 2. The smart manufacturing method based on the centralized service platform industrial Internet of Things of claim 1, wherein if the first score exceeds a first set threshold range, the service platform determines that there is an abnormality in the casting process, and controls the line equipment to stop casting blanks.

8. When the blank is forged by the line equipment, the abnormality judgment model is a second model, and the check data group includes pre-pressure images and post-pressure images of the blank forging, The management platform inputs the pre-pressure image, the post-pressure image, and a first set of reference data into the second model, and the second model outputs a second score, the first set of reference data including a standard pre-pressure image and a standard post-pressure image, the standard pre-pressure image including a standard pre-forging shape for a blank, and the standard post-pressure image including a standard post-forging shape for a blank; 2. The smart manufacturing method based on the centralized service platform industrial Internet of Things as claimed in claim 1, characterized in that if the second score exceeds a second set threshold range, the service platform determines that there is an abnormality in the forging process, and controls the line equipment to stop forging blanks.

9. 9. The smart manufacturing method based on the centralized service platform industrial Internet of Things of claim 8, wherein the check data set includes an image sequence of multiple pressurizations on a blank, the standard pre-pressurization image is a standard image before the blank is pressed, the standard post-pressurization image is a standard image after the final pressurization on the blank, and the standard image includes a standard form of the blank.

10. When the blank is pressed by the line equipment, the abnormality judgment model is a third model, and the check data group includes pre-press images and post-press images of the blank, The management platform inputs the pre-press image, the post-press image, and a second set of reference data into the third model, and the third model outputs the third score, and the second set of reference data includes a standard pre-press image and a standard post-press image, the standard pre-press image includes a standard pre-press form for a blank, and the standard post-press image includes a standard post-press form for a blank; 2. The smart manufacturing method based on the centralized service platform industrial Internet of Things of claim 1, wherein if the third score exceeds a third set threshold range, the service platform determines that there is an abnormality in the pressing process, and controls the line equipment to stop pressing the blank.

11. 11. The smart manufacturing method based on the centralized service platform industrial Internet of Things of claim 10, wherein the check data set includes an image sequence of multiple presses on a blank, the standard pre-press image is a standard image before the blank is pressed, and the standard post-press image is a standard image after the final press on the blank, and the standard image includes a standard form of the blank.

12. The management platform predicts the performance of the blank after each process based on a set of check data of multiple processes for processing the blank; The service platform judges whether the performance of the blank meets a preset condition based on a set of reference data, the set of reference data including standard data of the process; If not, stopping the processing of the blank. The smart manufacturing method based on the centralized service platform industrial Internet of Things according to claim 1 .

13. The smart manufacturing method based on the centralized service platform industrial Internet of Things as claimed in claim 12, characterized in that the management platform predicts the performance of the blank after each process by fitting the group of checking data to past statistical data.

14. A system for implementing a smart manufacturing method for managing and controlling multiple processes based on the Industrial Internet of Things, comprising a user platform, a service platform, a management platform, a sensing network platform and a target platform that sequentially interact with each other, The user platform is configured as a terminal device that interacts with a user, receives user input information, generates commands, and transmits the commands to the service platform, and presents the information transmitted from the service platform to the user; The service platform is configured as a first server, which receives and processes commands sent from the user platform, and then sends the commands to the management platform; and obtains information required by the user from the management platform and sends the information to the user platform; A management platform is configured as a second server, which receives commands sent from the service platform, controls the target platform to operate according to the commands, and receives and stores sensory information sent from the target platform; a sensing network platform configured as a communication network and a gateway through which the management platform and the target platform interact; The target platform is configured as a line equipment for performing manufacturing and a line sensor for performing data collection, and receives commands from the management platform to operate and transmits sensing information to the management platform via the sensing network platform; The service platform adopts a centralized layout, which means that the service platform receives data in an integrated manner, processes data in an integrated manner, and transmits data in an integrated manner; the management platform and the sensing network platform both adopt a back-to-back sub-platform layout, which means that both the management platform and the sensing network platform are provided with an integrated platform and a number of sub-platforms, and control information and parameter configuration information of a target platform are transmitted from the sub-platform to the integrated platform, and sensing information is transmitted from the integrated platform to the sub-platforms; During parameter configuration of the target platform, the user inputs parameter configuration information of the target platform through the user platform, the service platform receives the parameter configuration information of the target platform sent from the user platform, decomposes it into multiple sets of configuration data according to multiple types of processes, and sends it to the management platform, the management platform stores and processes the received configuration data and sends it to the sensing network platform, the stored configuration data group is used as a reference data group, the sensing network platform stores and processes the received configuration data and sends it to the target platform, and the target platform performs parameter configuration of the target platform according to the parameter configuration information of the target platform; When the line equipment of the target platform is in operation, the target platform identifies a process and transmits its sensing information as a check data group to the management platform via the sensing network platform at a set time interval; the management platform receives and processes the check data group transmitted from the target platform, and transmits a reference data group and a check data group corresponding to the target platform that transmitted the check data group to the service platform; the service platform receives and compares the reference data group and the check data group; if all data in the check data group are within a set threshold range as a result of comparison with the reference data group, the data is cleared and no further processing is performed; if there is data in the check data group that exceeds the set threshold range as a result of comparison with the reference data group, an operation stop command is generated and transmitted to the management platform to be fed back to the user platform; and the management platform transmits the command to a corresponding target platform via the sensing network platform to control the operation of the line equipment to be stopped; The service platform further pre-stores pre-stored information of the general local design of the product; before the service platform decomposes the parameter configuration information of the target platform into multiple sets of configuration data groups according to the process, it selects general local design information in the parameter configuration information of the target platform and compares it with the pre-stored information of the general local design of the product; if all the comparison results are within a set design deviation threshold range, it performs a decomposition process; if any of the comparison results exceeds the set design deviation threshold range, it is sent to the user platform; if the user confirms through the user platform that there is no error in the input information, it sends a confirmation command to the service platform, and the service platform performs a decomposition process; if the user changes the input information through the user platform, the service platform checks again until it is confirmed by the user platform, and then the service platform performs a decomposition process; The smart manufacturing method is a method for processing a blank, the process of processing the blank including at least casting, forging and / or pressing, and during operation of a line facility of a target platform, The management platform identifies the process and obtains a set of check data for the corresponding process, the set of check data being data obtained to check whether the process is normally performed; The management platform processes the set of check data according to an anomaly judgment model to obtain a set of processed check data; The service platform judges whether there is an abnormality in the process based on the set of post-processing check data, and the set of post-processing check data includes at least a standard score of the execution of the process by the line equipment; If an abnormality is found, the service platform sends a stop command to the management platform, and the management platform controls the line equipment to stop processing the blanks; The standardized scores include a first score, a second score, and a third score, combining the first score, the second score, and the third score to determine a combined score; Combining the first score, the second score, and the third score to determine a combined score includes: determining confidence levels corresponding to the first score, the second score, and the third score, respectively, according to the accuracy of the anomaly judgment model during training; determining weights corresponding to the first score, the second score, and the third score, respectively, based on the reliability corresponding to the first score, the second score, and the third score, respectively, the weights being an F-value of the anomaly judgment model, the F-value being a composite value of a precision rate and a recall rate; and determining whether or not there is an abnormality based on the result of comparing the fused score with a threshold.

Images