Intelligent recommendation method and system for production process based on industrial Internet of Things information cloud sharing
Through the industrial IoT information cloud sharing platform, the distributed server and perception control platform are used to realize intelligent processing of production data in industrial IoT systems and automatic regulation of production line equipment, solving the problem of lack of intelligent recommendations in the existing technology , improves production efficiency and product quality.
Patent Information
- Application Number
- CN202411215452.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-02
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-09-02
AI Technical Summary
The existing technology lacks an intelligent and personalized production process recommendation mechanism in the field of industrial Internet of Things, and it is difficult to effectively use production data to optimize production processes and improve production efficiency and product quality.
Through the industrial IoT information cloud sharing platform, the communication connection between the distributed server and the industrial IoT system is used to obtain production data, determine whether it is necessary to adjust the operating parameters of the production line equipment, generate production process parameters and adjustment time, generate process adjustment instructions, and The perception control platform regulates production line equipment to realize intelligent and personalized production process recommendations.
It realizes personalized production process recommendation based on production data, helping production enterprises quickly select the optimal production process plan and improve production efficiency and product quality.
Smart Images

Figure CN118732629B_ABST
Abstract
Description
Technical Field
[0001] This specification relates to the field of industrial Internet of Things and intelligent manufacturing, and in particular to a method and system for intelligently recommending production processes through industrial Internet of Things information cloud sharing. Background Art
[0002] Industrial Internet of Things (IIoT) technology has been widely used in many fields such as manufacturing, smart cities, and energy management. With the widespread application of IIoT technology, the amount of data generated in each production link of the production line has increased dramatically. However, how to effectively use the data in the production process, optimize the production process, and improve production efficiency and product quality has become an important challenge facing the current manufacturing industry. At present, the selection of production processes mostly relies on manual experience or fixed processes, lacks an intelligent and personalized recommendation mechanism, and is difficult to meet complex and changing production needs.
[0003] Therefore, it is necessary to provide an intelligent production process recommendation method and system for industrial Internet of Things information cloud sharing, which can provide intelligent and personalized production process recommendations to improve production efficiency and product quality. Summary of the invention
[0004] One or more embodiments of the present specification provide a method for intelligently recommending production processes for industrial Internet of Things information cloud sharing, the method being executed by a cloud platform, the cloud platform comprising a distributed server; the cloud platform being communicated and connected with industrial Internet of Things management platforms of multiple industrial Internet of Things systems corresponding to multiple factories through the distributed server; the industrial Internet of Things system comprising an industrial Internet of Things user platform, an industrial Internet of Things service platform, an industrial Internet of Things management platform, an industrial Internet of Things sensor network platform and an industrial Internet of Things perception control platform; wherein the industrial Internet of Things perception control platform is configured as production line equipment and a data acquisition device deployed on the production line, and the industrial Internet of Things perception control platform realizes data interaction with the industrial Internet of Things management platform through the industrial Internet of Things sensor network platform, and the industrial Internet of Things management platform realizes data interaction with the cloud platform; the method comprising: based on the industrial Internet of Things management platform, acquiring and storing the production data of the production line; based on the production data, determining whether it is necessary to adjust the operating parameters of the production line equipment; in response to the need to adjust the operating parameters of the production line equipment: generating production process parameters and adjustment time based on the production data; and generating process adjustment instructions based on the production process parameters and the adjustment time and issuing them to the industrial Internet of Things management platform The process adjustment instruction is parsed through the industrial Internet of Things management platform, and the industrial Internet of Things management platform adjusts the operating parameters of the production line equipment through the control system of the industrial Internet of Things perception control platform based on the process adjustment instruction when the adjustment time is reached; wherein the production process parameters include at least one of a target screening parameter, a target conveying parameter, a target assembly parameter and a target quality inspection parameter, and the production line equipment includes at least one of a screening device, a conveying device, an assembly device and a quality inspection device; the control system of the industrial Internet of Things perception control platform based on the process adjustment instruction adjusts the operating parameters of the production line equipment including: adjusting the first working parameter of the screening device based on the process adjustment instruction so that the operating parameter of the screening device reaches the target screening parameter; adjusting the second working parameter of the conveying device based on the process adjustment instruction so that the operating parameter of the conveying device reaches the target conveying parameter; adjusting the first setting parameter of the assembly device based on the process adjustment instruction so that the operating parameter of the assembly device reaches the target assembly parameter; or adjusting the second setting parameter of the quality inspection device based on the process adjustment instruction so that the operating parameter of the quality inspection device reaches the target quality inspection parameter.
[0005] One of the embodiments of this specification provides an intelligent recommendation system for production processes shared by an industrial Internet of Things information cloud, the system comprising a cloud platform, the cloud platform comprising a distributed server, a data receiving module, a data processing module, an intelligent recommendation module and a user interaction module; the cloud platform is connected to a plurality of industrial Internet of Things systems corresponding to a plurality of factories through the distributed server; the industrial Internet of Things system comprises an industrial Internet of Things user platform, an industrial Internet of Things service platform, an industrial Internet of Things management platform, an industrial Internet of Things sensor network platform and an industrial Internet of Things perception control platform; wherein the industrial Internet of Things perception control platform is configured as a production line device and a data acquisition device deployed on the production line, and the industrial Internet of Things The perception control platform realizes data interaction with the industrial Internet of Things management platform through the industrial Internet of Things sensor network platform, and the industrial Internet of Things management platform realizes data interaction with the cloud platform; the data receiving module performs data docking with the industrial Internet of Things management platform of the industrial Internet of Things system through the distributed server to receive the corresponding production data of the industrial Internet of Things system, the data processing module processes the production data obtained by the data receiving module, the intelligent recommendation module performs intelligent recommendation of production process based on the processed production data, and the user interaction module displays the recommendation results for users to view and interact with; the cloud platform is further configured to: based on the industrial Internet of Things The industrial Internet of Things management platform obtains and stores the production data of the production line; based on the production data, determines whether it is necessary to adjust the operating parameters of the production line equipment; in response to the need to adjust the operating parameters of the production line equipment: based on the production data, generates production process parameters and adjustment time; and based on the production process parameters and the adjustment time, generates process adjustment instructions and sends them to the industrial Internet of Things management platform; the industrial Internet of Things management platform parses the process adjustment instructions, and the industrial Internet of Things management platform adjusts the operating parameters of the production line equipment through the control system of the industrial Internet of Things perception control platform based on the process adjustment instructions when the adjustment time arrives; wherein, The production process parameters include at least one of a target screening parameter, a target conveying parameter, a target assembly parameter and a target quality inspection parameter, and the production line equipment includes at least one of a screening device, a conveying device, an assembly device and a quality inspection device; in order to adjust the operating parameters of the production line equipment through the control system of the industrial Internet of Things perception control platform based on the process adjustment instruction, the cloud platform is further configured to: based on the process adjustment instruction, adjust the first working parameter of the screening device so that the operating parameter of the screening device reaches the target screening parameter; based on the process adjustment instruction, adjust the second working parameter of the conveying device so that the operating parameter of the conveying device reaches the target conveying parameter;Based on the process adjustment instruction, the first setting parameter of the assembly equipment is adjusted so that the operating parameter of the assembly equipment reaches the target assembly parameter; or based on the process adjustment instruction, the second setting parameter of the quality inspection equipment is adjusted so that the operating parameter of the quality inspection equipment reaches the target quality inspection parameter. ;
[0006] One or more embodiments of the present specification provide a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method for intelligently recommending production processes for industrial Internet of Things information cloud sharing as described in any embodiment of the present specification.
[0007] In the embodiments of this specification, through the communication connection between the industrial Internet of Things system and the cloud platform, a personalized production process recommendation plan can be generated based on the production data of the production line equipment, helping manufacturing companies to quickly select the optimal production process plan and improve production efficiency and product quality. BRIEF DESCRIPTION OF THE DRAWINGS
[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:
[0009] Figure 1 It is a structural schematic diagram of a production process intelligent recommendation system based on industrial Internet of Things information according to some embodiments of this specification;
[0010] Figure 2 is an exemplary flow chart of a production process intelligent recommendation method based on industrial Internet of Things information according to some embodiments of this specification;
[0011] Figure 3 is an exemplary schematic diagram of a fault prediction model according to some embodiments of this specification;
[0012] Figure 4 It is an exemplary schematic diagram of generating production process parameters according to some embodiments of this specification. DETAILED DESCRIPTION
[0013] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.
[0014] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.
[0015] Figure 1 It is a schematic diagram of the structure of the production process intelligent recommendation system based on industrial Internet of Things information according to some embodiments of this specification. It should be noted that the following embodiments are only used to explain this specification and do not constitute a limitation of this specification.
[0016] like Figure 1 As shown, in some embodiments, the production process intelligent recommendation system 100 for industrial Internet of Things information cloud sharing may include a cloud platform 110 and an industrial Internet of Things system 120.
[0017] In some embodiments, one or more platforms or devices in the production process intelligent recommendation system 100 shared by the industrial Internet of Things information cloud can exchange information and / or data through a network. In some embodiments, the network can be any one or more of a wired network or a wireless network.
[0018] The cloud platform 110 is a service providing platform based on cloud computing technology, which can provide various computing resources and services through the Internet. In some embodiments, the cloud platform 110 may include a distributed server 111, a data receiving module 112, a data processing module 113, an intelligent recommendation module 114, and a user interaction module 115. As an example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, etc., or any combination thereof.
[0019] In some embodiments, the cloud platform 110 can be communicatively connected with multiple industrial Internet of Things systems 120 corresponding to multiple factories through a distributed server 111.
[0020] The data receiving module 112 can collect production data from the industrial Internet of Things system 120. In some embodiments, the data receiving module 112 can connect data with the industrial Internet of Things management platform 123 of the industrial Internet of Things system 120 through the distributed server 111 to receive the production data of the corresponding industrial Internet of Things system. Multiple industrial Internet of Things systems 120 can upload their respective production data to the cloud platform after desensitizing. For example, production data may include but is not limited to product type, product characteristic parameters, product quality inspection data, and corresponding production processes and the quantity, layout, status, production parameters, etc. of various types of production line equipment corresponding to each process.
[0021] The data processing module 113 can process data and / or information obtained from other devices / components or components. The data processing module 113 may include a processor. The processor can process data and / or information obtained from other devices or system components. The processor can execute program instructions based on these data, information and / or processing results to perform one or more functions described in the embodiments of this specification. As an example only, the processor may include a central processing unit (CPU), an application specific integrated circuit (ASIC), etc. or any combination thereof. In some embodiments, the processor may include multiple modules, and different modules may be used to execute different program instructions respectively.
[0022] In some embodiments, the data processing module 113 can process the collected raw data (for example, the production data obtained by the data receiving module 112). For example, data cleaning, removing noise and outliers, etc. In some embodiments, the data processing module 113 can integrate the data, unify the production data from different sources into the same framework, and then perform standardization to obtain the processed production data. Data integration can ensure the consistency of data format and protocol, and provide a high-quality data source for subsequent analysis. In some embodiments, the data processing module 113 can also include a data storage center, and the data processing module 113 can classify and store the processed production data in the data storage center.
[0023] The intelligent recommendation module 114 can make intelligent recommendations for production processes based on the processed production data. In some embodiments, the intelligent recommendation module 114 can include a processor to process data and / or information obtained from other devices or system components (e.g., the data processing module 113 or a data storage center).
[0024] In some embodiments, the intelligent recommendation module 114 can build a production feature model based on historical data and industry knowledge base, and then use machine learning algorithms to train and optimize the model. In some embodiments, the intelligent recommendation module 114 can generate personalized production process recommendation solutions based on real-time production data and user needs. Among them, machine learning algorithms can include deep learning and reinforcement learning algorithms. In some embodiments, the recommendation solution can include at least one of optimization of the production process, adjustment of process parameters, and suggestions for equipment configuration.
[0025] The user interaction module 115 can display information (e.g., recommendation results) for users to view and interact with. Among them, the user who interacts with the user interaction module 115 is a cloud platform user. For example, the user interaction module 115 can provide an intuitive and easy-to-use user interface for cloud platform users to view intelligent recommendation results. In some embodiments, cloud platform users can make production adjustments based on the recommendation scheme displayed by the user interaction module 115 and provide real-time feedback on the adjustment effect. In some embodiments, cloud platform users can also rate and comment on the recommendation scheme through the user interaction module 115 to provide data support for subsequent recommendation optimization.
[0026] The Industrial Internet of Things refers to the application of intelligent computing, data analysis and network connection in industrial environments. The Industrial Internet of Things system 120 realizes real-time data collection, transmission and analysis through the interconnection between sensors, equipment, machines, systems and humans and machines, thereby realizing intelligent industrial operation management. Each factory can correspond to an Industrial Internet of Things system.
[0027] In some embodiments, the industrial Internet of Things system 120 may include an industrial Internet of Things user platform 121, an industrial Internet of Things service platform 122, an industrial Internet of Things management platform 123, an industrial Internet of Things sensor network platform 124 and an industrial Internet of Things perception control platform 125.
[0028] The IIoT user platform 121 is a platform that provides information or services to users of the IIoT system. The users of the IIoT system may be staff members of the factory corresponding to the IIoT system, i.e., factory users. In some embodiments, the factory users may be the person in charge or leadership of the factory. In some embodiments, the IIoT user platform 121 may be configured as a terminal device.
[0029] The industrial Internet of Things service platform 122 is a platform that connects the industrial Internet of Things user platform 121 and the industrial Internet of Things management platform 123, and realizes information transmission between the industrial Internet of Things user platform 121 and the industrial Internet of Things management platform 123.
[0030] In some embodiments, the production data of the IIoT system 120 can be transmitted to the distributed server 111 of the cloud platform 110 through the IIoT service platform 122. In some embodiments, the process adjustment instructions generated by the cloud platform 110 can be transmitted to the IIoT management platform 123 through the IIoT service platform 122 for analysis.
[0031] The industrial Internet of Things management platform 123 is responsible for the resource management, monitoring and maintenance of the entire industrial Internet of Things system, ensuring the stable operation of the system, and providing a platform for the perception management and control management functions for the Internet of Things operation system. For example, the industrial Internet of Things management platform 123 can manage the industrial Internet of Things system 120. In some embodiments, the industrial Internet of Things management platform 123 is a platform for communicating with the distributed server 111 of the cloud platform 110, and is a platform for realizing data interaction between the cloud platform 110 and the industrial Internet of Things system 120.
[0032] In some embodiments, the IIoT management platform 123 can communicate with the control system of the IIoT perception control platform 125 through the IIoT sensor network platform 124 to intelligently adjust the operating parameters of the production line equipment corresponding to the IIoT perception control platform 125. In some embodiments, the IIoT management platform 123 can parse the received process adjustment instructions, and adjust the operating parameters of the production line equipment through the control system of the IIoT perception control platform 125 based on the process adjustment instructions when the adjustment time arrives. For more information about adjusting operating parameters, please refer to Figure 2~Figure 4 and related instructions.
[0033] The IIoT sensor network platform 124 is a functional platform for comprehensive management of sensor communications. In some embodiments, the IIoT sensor network platform 124 can realize the functions of sensing information sensor communications and controlling information sensor communications. In some embodiments, the IIoT sensor network platform 124 can exchange data with the IIoT sensing control platform 125 and the IIoT management platform 123.
[0034] The IIoT sensing control platform 125 is configured as a production line device and a data acquisition device deployed on the production line to perform real-time sensing and dynamic control of production data. In some embodiments, the IIoT sensing control platform 125 realizes data interaction with the IIoT management platform 123 through the IIoT sensor network platform 124.
[0035] In some embodiments, the industrial Internet of Things perception control platform 125 can acquire and store production data of the production line through a data acquisition device.
[0036] In some embodiments, the industrial Internet of Things system 120 may also include a storage device to store production data in the production line and other data related to the production line, such as historical fault records, product parameter data, historical maintenance records, etc.
[0037] A production line refers to a series of continuous operations or equipment set up in the manufacturing and assembly process to improve production efficiency. For example, automobile manufacturing production lines, electronic product production lines, food processing production lines, etc.
[0038] Production line equipment refers to mechanical equipment and tools used to perform specific production tasks on the production line, and is equipment related to product production on the production line. Among them, production tasks may include material processing, assembly, testing, packaging, etc. In some embodiments, the production line equipment may be automated equipment. In some embodiments, the industrial Internet of Things perception control platform 125 may include corresponding production line equipment.
[0039] In some embodiments of this specification, the production process of over-temperature sensors is taken as an example to illustrate the intelligent recommendation method and system for production process shared by the industrial Internet of Things information cloud. In some embodiments, the production process of over-temperature sensors may include temperature controller screening, thermistor welding, pin crimping, assembly, glue injection, testing, etc. In some embodiments, for the production line of over-temperature sensors, the production line equipment may include at least one of screening equipment, assembly equipment, quality inspection equipment and conveying devices.
[0040] Screening equipment refers to equipment that performs all-round testing on materials or devices (eg, thermostats) to ensure that the quality and performance of the materials or devices meet standards. In some embodiments, the screening equipment may include a thermostat screening equipment.
[0041] Assembly equipment refers to equipment that can assemble parts according to design requirements. For example, the over-temperature sensor core can be obtained by assembling thermostats, thermistors, connectors, pins and other components according to design requirements. In some embodiments, the assembly equipment may include over-temperature sensor core assembly equipment. In some embodiments, the assembly method may include welding, crimping, etc., and accordingly, the over-temperature sensor core assembly equipment may include non-standard special machines, etc.
[0042] The quality inspection equipment can perform quality inspection on the inner core of the over-temperature sensor. In some embodiments, the quality inspection equipment can include one or more of a digital multimeter, a withstand voltage tester, a high temperature test chamber, an aging test chamber, an environmental simulation test equipment, an infrared thermal imager, an oscilloscope, and the like.
[0043] The conveying device can convey materials, such as thermostats, thermistors, etc. In some embodiments, the conveying device can include a conveyor belt.
[0044] In some embodiments, the production line equipment may also include equipment such as glue injection, finished product testing, and finished product packaging to perform the production process of the over-temperature sensor. For more information about the production line equipment, please refer to Figure 2 and related instructions.
[0045] In some embodiments, production line equipment may include a data acquisition device and a control system.
[0046] The data acquisition device is a device used to collect production data. The data acquisition device can be deployed on the production line.
[0047] In some embodiments, the data acquisition device may include an image acquisition device and a positioning tracking device. The image acquisition device is a camera deployed at multiple locations on the production line, which is used to capture image data in the production line. The positioning tracking device is an RFID (Radio Frequency Identification) reader / writer, which is used to track the flow of raw materials and semi-finished products in the production line and record product information.
[0048] In some embodiments, the data acquisition device may include sensors deployed at various locations on the production line. The sensors may collect multi-dimensional data of the production line environment and production line equipment. For example, the sensors may include vibration sensors, temperature sensors, pressure sensors, and humidity sensors deployed on the production line. For more information about vibration sensors, temperature sensors, and humidity sensors, see Figure 2~Figure 4 and related instructions.
[0049] The control system can be used to adjust the operating parameters of the production line. In some embodiments, the control system can be connected to the industrial Internet of Things management platform 123 to adjust the operating parameters of the production line equipment according to the instructions issued by the industrial Internet of Things management platform 123. For more information on how to adjust the operating parameters, please refer to Figure 2 and related instructions.
[0050] In some embodiments, the control system may include a programmable logic controller (PLC). A PLC is an electronic system that operates digital operations and is used to automatically control machinery or processes. It uses programmable memory to store and execute instructions such as logic operations, sequential control, timing, counting, and arithmetic operations to control mechanical equipment or processes. In some embodiments, the control system may include controllers corresponding to temperature controller screening equipment, assembly equipment, quality inspection equipment, and conveying devices, such as PLCs.
[0051] In the embodiments of this specification, through the communication connection between the industrial Internet of Things system and the cloud platform, a personalized production process recommendation plan can be generated based on the production data of the production line equipment, helping manufacturing companies to quickly select the optimal production process plan and improve production efficiency and product quality.
[0052] Figure 2is an exemplary flow chart of a production process intelligent recommendation method based on industrial Internet of Things information according to some embodiments of this specification. In some embodiments, process 200 can be executed by cloud platform 110. Figure 2 As shown, the process 200 may include the following steps. For the industrial Internet of Things system corresponding to any one of the multiple factories, the cloud platform 110 may perform the following steps.
[0053] Step 210: Acquire and store production data of the production line based on the industrial Internet of Things management platform.
[0054] Production data is data related to the production situation of a production line. In some embodiments, the production data may include at least one of product image data, product record parameters, production process data, equipment status data, raw material and semi-finished product data, and product quality inspection data.
[0055] Product image data refers to image data of products taken on a production line. In some embodiments, the product image data can be acquired by an image acquisition device.
[0056] Product record parameters refer to parameters directly related to the production process. In some embodiments, product record parameters may include at least one of material consumption, energy use, production tact, production batch, and product production rate. The production tact is the interval between the continuous production of two products. In some embodiments, product record parameters can be obtained by recording the production process through production line equipment (e.g., data acquisition device).
[0057] The production process data refers to the process parameters of the production stage. The production process of a product may include multiple production stages, and one production stage may correspond to one production task. In some embodiments, the production process data may include at least one of the temperature, pressure, speed, humidity and time of assembly and packaging. In some embodiments, the production process data may be acquired through a temperature sensor, a pressure sensor, a humidity sensor, etc. in a data acquisition device.
[0058] Equipment status data refers to status data related to production line equipment. In some embodiments, the equipment status data may include at least one of equipment type, equipment specifications, equipment operating time, and efficiency. Among them, the equipment specifications may include maximum operating power, maximum operating voltage, maximum operating current, maximum load, etc. In some embodiments, the equipment status data may be determined in advance based on the basic properties of the production line equipment, or may be obtained by monitoring the production line equipment during production (for example, through a voltage detector, a current detector).
[0059] Raw material and semi-finished product data refers to data related to raw materials and semi-finished products. In some embodiments, the raw material and semi-finished product data may include the inventory, conveying speed, current location of raw materials, and the conveying speed, current location of semi-finished products. In some embodiments, the raw material and semi-finished product data may be obtained through a positioning tracking device. In some embodiments, for the production line of over-temperature sensors, the raw materials and semi-finished products may include at least one of a thermostat, a thermistor, a pin, a connector, a welding material, a potting compound, and materials required for packaging.
[0060] Product quality inspection data is data obtained by testing the quality of a product. In some embodiments, the product quality inspection data may include at least one of product specifications, pass rate, defect type, and defect rate. For example, defect types may include thermostat consistency problems, welding problems, measurement accuracy problems, etc. In some embodiments, for a production line of an over-temperature sensor, product specifications may include basic performance parameters, electrical characteristics, environmental adaptability, physical characteristics, etc. In some embodiments, the product quality inspection data may be obtained through quality inspection equipment.
[0061] In some embodiments, the production line equipment of the Industrial Internet of Things perception control platform can obtain production data on the production line and transmit it to the Industrial Internet of Things management platform through the Industrial Internet of Things sensor network platform.
[0062] In some embodiments, the cloud platform (e.g., the data receiving module) can communicate with the industrial Internet of Things management platform of the industrial Internet of Things system through a distributed server to obtain production data of the production line. In some embodiments, the production data is transmitted from the industrial Internet of Things management platform to the distributed server of the cloud platform, and then obtained by the data receiving module.
[0063] Step 220: Based on the production data, determine whether it is necessary to adjust the operating parameters of the production line equipment.
[0064] Operating parameters refer to the relevant parameters of the production line equipment in executing the production process.
[0065] In some embodiments, the operating parameters may include at least one of screening parameters, delivery parameters, assembly parameters, and quality inspection parameters.
[0066] The screening parameters are parameters for the screening device to perform the screening process. In some embodiments, the screening parameters may include thermostat screening parameters, such as one or more of thermostat size, thermostat type, appearance defects, and thermostat screening speed. The thermostat screening speed is the number of thermostats screened per unit time. The unit time can be set according to actual needs.
[0067] The conveying parameters are the parameters of the conveying device for conveying materials. The materials may include thermostats, thermistors, connectors, pins, and materials required for packaging. In some embodiments, the conveying parameters may include one or more of the conveying beat, material conveying speed, etc. The conveying beat is the interval time between two consecutive conveying of material products. The material conveying speed is the length of the material passing through the conveying device per unit time.
[0068] The assembly parameters are parameters of the assembly equipment for performing the assembly process. In some embodiments, the assembly parameters may include one or more of welding parameters, connection methods, packaging parameters, etc. In some embodiments, the welding parameters may include welding power, speed, time, focal position, etc. In some embodiments, the connection method may include a connection between a thermostat and a thermistor, or a connection between two thermistors (if multiple thermistors are included). In some embodiments, the packaging parameters may include the speed, pressure, time, etc. of packaging the inner core of the over-temperature sensor.
[0069] The quality detection parameters are parameters that the quality detection equipment performs or detects. In some embodiments, the quality detection parameters may include one or more of accuracy parameters, measurement range parameters, environmental simulation parameters, response time parameters, etc. In some embodiments, the accuracy parameter refers to the deviation range between the measured value of the over-temperature sensor and the actual temperature value, expressed as a percentage or a specific temperature value. In some embodiments, the measurement range parameter is the temperature range that the over-temperature sensor can accurately measure. In some embodiments, the environmental simulation parameters may include parameters that simulate the test conditions in the actual use environment, such as temperature, humidity, etc. In some embodiments, the response time is the time required for the over-temperature sensor to sense the temperature change and output a stable signal.
[0070] In some embodiments, in response to the qualified rate of the product in the product quality inspection data in the production data being lower than the reference qualified threshold and / or the production rate being lower than the reference rate threshold, the cloud platform may determine that it is necessary to adjust the operating parameters of the production line equipment. The reference threshold is a threshold predicted by the cloud platform based on the production data of each industrial Internet of Things system of the same type for determining whether it is necessary to adjust the operating parameters of the production line equipment. The reference qualified threshold and the reference rate threshold can also be set or adjusted manually. If the qualified rate of the product is lower than the reference qualified threshold and / or the production rate is lower than the reference rate threshold, it means that there may be a reduction in production efficiency or quality at this time, so it is necessary to adjust the operating parameters to improve production efficiency or the quality of the products produced.
[0071] In some embodiments, if the qualified rate of the product is lower than the reference qualified threshold and / or the production rate is lower than the reference rate threshold for a number of times that reaches a reference number, the cloud platform may determine that the operating parameters of the production line equipment need to be adjusted. The reference number may be manually set or adjusted.
[0072] In some embodiments, the cloud platform may determine that operating parameters of production line equipment need to be adjusted based on instructions to change production requirements actively input by factory users to the industrial Internet of Things system.
[0073] In some embodiments, the cloud platform can determine whether it is necessary to adjust the operating parameters of the production line equipment by judging whether there are possible failures or hidden dangers in the production line equipment.
[0074] In some embodiments, a vibration sensor deployed on a production line may be configured to acquire vibration data. The vibration data is the vibration condition of the production line equipment detected by the vibration sensor. In some embodiments, the vibration data may include one or more of vibration frequency, amplitude, vibration velocity, vibration acceleration, etc.
[0075] In some embodiments, the cloud platform can determine the fault probability sequence through a fault prediction model based on the production data of the production line, historical fault records, vibration data, parameter data of currently produced products, historical maintenance records and reference data; based on the judgment result of whether the fault probability sequence meets the fault conditions, determine whether it is necessary to adjust the operating parameters of the production line equipment.
[0076] The historical fault record is the relevant data of the faults of the production line equipment at the historical time. In some embodiments, the historical fault record may include at least one of the fault occurrence time, fault type, and fault resolution time.
[0077] Product parameter data is data related to the characteristics and performance of the currently produced product. In some embodiments, the product parameter data may include at least one of the number of thermistors of each product, the connection method between components, product structure data, product use, etc. The product structure data may include size, shape, material distribution, etc. The connection method between components may include the connection method between thermostat and thermistor, the connection method between thermistor and thermistor, etc., for example, series or parallel connection.
[0078] The historical maintenance record is data related to the maintenance of the production line equipment at historical times. In some embodiments, the historical maintenance record may include at least one of the maintenance date and time, the maintenance type, and the maintenance operation record. The maintenance type may include preventive maintenance and fault repair. The maintenance operation record may include a record of one or more steps in the maintenance process.
[0079] Reference data is data related to the production line obtained by the cloud platform based on data analysis of multiple industrial Internet of Things systems of the same type. In some embodiments, the reference data may include reference production data and reference fault data. Reference production data is data obtained by the cloud platform after obtaining and analyzing production data of multiple industrial Internet of Things of the same type. Reference fault data is data obtained by the cloud platform after obtaining and analyzing fault data of multiple industrial Internet of Things of the same type.
[0080] In some embodiments, historical fault records, product parameter data, and historical maintenance records can be stored in a storage device of the industrial Internet of Things system, and the cloud platform can obtain them from the storage device through the communication connection between the distributed server and the industrial Internet of Things system.
[0081] The fault probability sequence is a sequence of possible faults and corresponding probabilities of different production line equipment in the future. For example, the fault probability sequence may include possible faults and corresponding probabilities of different production line equipment in the future period. The start and end time points of the future period can be set according to actual needs.
[0082] In some embodiments, the fault prediction model is a machine learning model. In some embodiments, the fault prediction model may be a long short-term memory neural network (LSTM) model. The fault prediction model may also be a machine learning model of other structures, such as a neural network model, a recurrent neural network model, etc.
[0083] In some embodiments, the input of the fault prediction model may include production data of the production line, historical fault records, vibration data, parameter data of currently produced products, historical maintenance records and reference data, and the output may include a failure probability sequence at a future time point.
[0084] In some embodiments, the cloud platform may obtain a plurality of first training samples with a first label to form a first training sample set, and obtain a fault prediction model through training with the first training sample set. The first training sample may be obtained from historical data. In some embodiments, the first training sample may include sample production data, sample fault records, sample vibration data, sample product parameter data, sample maintenance records, and sample reference data. The first label may be a fault that occurs after the time period corresponding to the first training sample. The first label may be determined by the system or by human annotation. For example, if fault B and fault C actually occur at a future time point corresponding to the historical data, then the labels of fault B and fault C may be 1, and the labels of other fault types may be 0.
[0085] In some embodiments, the cloud platform may input the first training sample set into the initial fault prediction model to perform multiple rounds of iterations. Each round of iteration includes: selecting one or more first training samples from the first training sample set, inputting one or more first training samples into the initial fault prediction model, and obtaining the model prediction output corresponding to the one or more first training samples; according to the model prediction output corresponding to the one or more first training samples, and the first label of the one or more first training samples, substitute into the formula of the predefined loss function to calculate the value of the loss function; according to the value of the loss function, reversely update the model parameters in the initial fault prediction model. When the iteration end condition is met, the iteration ends and a trained fault prediction model is obtained. Among them, the iteration end condition may be that the loss function converges, the number of iterations reaches a threshold, etc.
[0086] The fault condition is a preset condition for determining whether to adjust the operating parameters. In some embodiments, the fault condition may include a fault probability greater than a probability threshold. The probability threshold may be manually set or adjusted.
[0087] In some embodiments, if the probability corresponding to a certain fault in the fault probability sequence is greater than the probability threshold, the cloud platform may determine that the operating parameters of the production line equipment need to be adjusted. For example, when the probability of a certain fault in the fault probability sequence is greater than the probability threshold, the cloud platform may determine to adjust the operating parameters of the production line equipment corresponding to the fault. In some embodiments, the cloud platform may also set different probability thresholds for different production line equipment.
[0088] For faults with a probability lower than the probability threshold, the manifestation of these faults may not be particularly obvious or may not be detected, but they may occur later and still affect the production rate and pass rate. In some embodiments, the cloud platform can further determine whether it is necessary to adjust the operating parameters of the production line equipment by predicting the efficiency distribution data.
[0089] In some embodiments, in response to the failure probability sequence not meeting the failure condition, the cloud platform can predict the predicted efficiency distribution data of the production line after a preset time period based on the failure probability sequence; and determine whether it is necessary to adjust the operating parameters of the production line equipment based on the predicted efficiency distribution data corresponding to multiple predictions made continuously at a preset interval. The preset interval is the time interval between two consecutive predictions. For example, the preset interval can include 1min, 2min, 3min, 4min, etc.
[0090] The predicted efficiency distribution data is the change trend of the production efficiency of the production line and the corresponding probability. For example, the predicted efficiency distribution data can be expressed as (change trend type, change probability). The change trend type can include rising, unchanged and falling, and the corresponding change probabilities are rising probability, unchanged probability and falling probability.
[0091] The sum of the probability of increase, the probability of no change, and the probability of decrease is 100%. For example, the predicted efficiency distribution data can be expressed as (increase, 70%), (no change, 20%), (decrease, 10%). Among them, production efficiency can be measured by the number of qualified products produced by the production line in a period of time.
[0092] In some embodiments, the fault prediction model may include a prediction layer and a review layer. The cloud platform may predict the predicted efficiency distribution data of the production line after a preset time period through the review layer of the fault prediction model.
[0093] In some embodiments, Figure 3 As shown, the fault prediction model 310 may include a prediction layer 320 and a verification layer 330. The prediction layer 320 and the verification layer 330 may be obtained by separate training.
[0094] In some embodiments, the prediction layer may be a long short-term memory neural network (LSTM) model.
[0095] like Figure 3 As shown, in some embodiments, the input of the prediction layer 320 may include production data 321, historical fault records 322, vibration data 323, currently produced product parameter data 324, historical maintenance records 325 and reference data 326, and the output of the prediction layer 320 may include a fault probability sequence 340.
[0096] In some embodiments, the prediction layer can be obtained by training the first training sample set. For more information, please refer to the above related description.
[0097] In some embodiments, the review layer may be a recurrent neural network (RNN) model.
[0098] like Figure 3 As shown, in some embodiments, the input of the review layer 330 may include a fault probability sequence 340, production data 321, and environmental parameters 331, and the output of the review layer 330 may include predicted efficiency distribution data 350 of the production line after a preset time period. For more information about environmental parameters and predicted efficiency distribution data, see Figure 2 and related instructions.
[0099] In some embodiments, the verification layer 330 can obtain a plurality of second training samples with second labels to form a second training sample set, and can be trained by the second training sample set. In some embodiments, the verification layer 330 can be obtained by training similar to the training process of the prediction layer described above.
[0100] In some embodiments, the second training sample may include a sample failure probability sequence, sample production data, and sample environmental parameters. The second label may be the predicted efficiency distribution data corresponding to the second training sample. In some embodiments, the second label may be determined based on the difference between the actual recorded production efficiency of the second training sample in a later period of time and the historical production efficiency of the historical period corresponding to the second training sample. For example, if the production efficiency in the later period of time has increased compared with the historical production efficiency, and the increase is greater than the first threshold, the second label is (increase, 1), (unchanged, 0), (decline, 0); if the production efficiency in the later period of time has decreased compared with the historical production efficiency, and the decrease is greater than the second threshold, the second label is (increase, 0), (unchanged, 0), (decline, 1); if the production efficiency in the later period of time has decreased compared with the historical production efficiency but has not exceeded the second threshold, and the increase has not exceeded the first threshold, it can be considered unchanged. The first threshold and the second threshold can be preset and obtained.
[0101] In the embodiments of this specification, by determining the fault probability sequence through the fault prediction model, the self-learning ability of the machine learning model can be used to find regularities from a large amount of historical data, obtain the relationship between production data, historical fault records, vibration data, current production product parameter data, historical maintenance records, reference data and fault probability sequence, etc., thereby improving the accuracy and efficiency of determining the fault probability sequence. By determining the predicted efficiency distribution data through the review layer of the fault prediction model, the self-learning ability of the machine learning model can be used to find regularities from a large amount of historical data, obtain the relationship between production data, environmental parameters, fault probability sequence and predicted efficiency distribution data, etc., thereby improving the accuracy and efficiency of determining the predicted efficiency distribution data.
[0102] In some embodiments, the cloud platform may determine whether the predicted efficiency distribution data satisfies an adjustment condition. The adjustment condition may include that the probability of a decrease in the predicted efficiency distribution data is greater than the probability of an increase, and the probability of a decrease is greater than a decrease threshold. The decrease threshold is a threshold condition for determining the probability of a decrease.
[0103] In some embodiments, if the number of times the predicted efficiency distribution data obtained in response to multiple predictions meets the adjustment conditions is greater than a number threshold, the cloud platform may determine that the operating parameters need to be adjusted.
[0104] Among them, the number threshold can be determined based on the fault type with the highest probability in the fault probability sequence. For example, the fault type can be represented in a hierarchical manner, such as dividing the fault level into level one, level two, and level three based on the impact caused by the fault, representing severe impact, general impact, and slight impact, respectively. The cloud platform can pre-set the corresponding initial number thresholds for different fault levels. For example, the cloud platform can set a smaller initial number threshold for level one faults and a larger initial number threshold for level three faults.
[0105] In some embodiments, the cloud platform can determine the fault level corresponding to the most likely fault, and then determine an initial number threshold based on the fault level; determine a correction value based on the fault probability corresponding to the most likely fault; and, based on the correction value, correct the initial number threshold to determine the number threshold.
[0106] In some embodiments, the cloud platform may determine the correction value based on a preset correction table. The preset correction table may include a fault probability and a correction value corresponding to the fault probability. In some embodiments, the correction value is negatively correlated with the fault probability, and the correction value may be a negative number.
[0107] For example, if the fault with the highest probability in the fault probability sequence is a primary fault, the initial number threshold is 4, and the correction value determined in the preset correction table based on the fault probability is +1, then the number threshold can be determined to be 5. If the correction value determined in the preset correction table based on the fault probability is -1, then the number threshold is determined to be 3.
[0108] In some embodiments, the preset correction table can be set manually. For example, if the probability of failure is greater, the correction value is smaller, the number threshold is smaller, indicating that timely processing is more necessary; conversely, if the probability of failure is smaller, the correction value is larger, the number threshold is larger, indicating that more observation is needed.
[0109] In the embodiments of this specification, whether the operating parameters of the production line equipment need to be adjusted is judged based on the predicted efficiency distribution data and the drop threshold, taking into account the situation where the probability of failure is lower than the probability threshold, and a more accurate judgment can be made. The fault prediction model is used to predict the future trend of production efficiency changes and the corresponding probability, and through multiple continuous predictions and analysis of the predicted efficiency distribution data, it is judged whether the production line needs to be adjusted. Measures can be taken before the efficiency drops, thereby maintaining or even improving production efficiency. The predicted efficiency distribution data of a single prediction may be accidental, but multiple consecutive predictions can help distinguish between the true trend changes in production efficiency and short-term fluctuations, reduce the possibility of misjudgment, and determine whether it is really necessary to adjust the operating parameters to avoid unnecessary changes.
[0110] In some embodiments, the cloud platform may determine the preset interval and the drop threshold based on user input.
[0111] In some embodiments, the cloud platform may determine the preset interval and the drop threshold based on the current production rate and the historical failure frequency.
[0112] In some embodiments, the preset interval is negatively correlated with at least one of the current production rate and the historical fault frequency, and the descending threshold is negatively correlated with at least one of the current production rate and the historical fault frequency. For example, the faster the current production rate is or the higher the historical fault frequency is, the shorter the preset interval is; when the current production rate is high or the historical fault frequency is high, the descending threshold can be set low.
[0113] In some embodiments, the cloud platform can determine the preset interval and the drop threshold by looking up a preset table based on the current production rate and the historical fault frequency. The preset table can include the production rate, the fault frequency, and the preset interval and the drop threshold corresponding to the production rate and the fault frequency.
[0114] In the embodiments of the present specification, the preset interval and the drop threshold determined can be made more accurate through the current production rate and the historical failure frequency, so as to timely discover potential failure trends. When the current production rate increases, it means that the equipment load is greater and the possibility of potential failures will also increase. Shortening the preset interval can detect the equipment status more frequently, which helps to discover potential problems in time. On the contrary, when the production rate is low, extending the preset interval can reduce unnecessary computing resource consumption while still maintaining sufficient monitoring density. In addition, for equipment with a higher production rate or a higher historical failure frequency, setting a lower drop threshold can help identify trends that may lead to failures earlier, so that action can be taken in advance.
[0115] Step 230, in response to the need to adjust the operating parameters of the production line equipment, generate production process parameters and adjustment time based on the production data.
[0116] The production process parameters are target parameters that the operating parameters of the production line equipment need to meet. In some embodiments, the production process parameters may include at least one of a target screening parameter, a target conveying parameter, a target assembly parameter, and a target quality inspection parameter.
[0117] The adjustment time is the time set to adjust the operating parameters. When it is determined that the operating parameters need to be adjusted, in some cases, it may be necessary to adjust the operating parameters with a delay rather than in real time. In some embodiments, for the production change requirements actively input by the factory user to the industrial Internet of Things system, the adjustment time may be after the production process of the previous batch of products is completed.
[0118] In some embodiments, the adjustment time can be set to 0, indicating that the operating parameters are adjusted immediately.
[0119] In some embodiments, the cloud platform can generate production process parameters and adjustment time according to the production requirements input by factory users. For example, when the production demand for single-day orders increases, the conveying parameters, screening parameters, assembly parameters, quality inspection parameters, etc. can be increased based on the operating parameters used in the previous production as target conveying parameters, target screening parameters, target assembly parameters, target quality inspection parameters, etc. For example, the assembly stations and corresponding equipment for assembly input in the assembly parameters increase, and the welding stations in the welding parameters also increase accordingly.
[0120] In some embodiments, the cloud platform can determine the production process parameters based on the most common defect types in the production data. In some embodiments, the cloud platform can determine the production process parameters based on the most common defect types and a preset defect table. The preset defect table may include defect types and corresponding adjustment plans. The adjustment plan may include the category of operating parameters that need to be adjusted, the adjustment direction, and the target value that the operating parameters need to be adjusted to. In some embodiments, the preset defect table can be obtained based on historical data statistics.
[0121] In some embodiments, in response to the need to adjust the operating parameters of the production line equipment, the cloud platform can determine the possible failure of the production line based on the failure probability sequence; and determine the production process parameters based on the possible failure and production characteristics.
[0122] A possible fault is a fault whose probability in the fault probability sequence is greater than a probability threshold. In some embodiments, a possible fault may be a fault with the highest probability in the fault probability sequence.
[0123] Production characteristics refer to the characteristics related to the production process and production results of the production line. For more information about production characteristics, see Figure 4 and related instructions.
[0124] In some embodiments, the cloud platform may determine the cause of the failure based on possible failures and production characteristics, and determine the production process parameters based on the cause of the failure.
[0125] In some embodiments, the cause of the fault may include at least one of excessive operating load of the production line equipment or excessive mechanical wear. In some embodiments, the cause of the fault may also be "null", which indicates that the problem with the production line equipment is serious or the corresponding cause cannot be found. At this time, the cloud platform can issue a shutdown inspection instruction to the industrial Internet of Things management platform, and the industrial Internet of Things management platform will convey the recommended suggestions for shutdown inspection according to actual needs to eliminate safety hazards.
[0126] In some embodiments, the cloud platform can determine the cause of the failure in a variety of ways based on possible failures and production characteristics.
[0127] In some embodiments, the cloud platform can construct a fault feature vector based on possible faults, production characteristics, current operating parameters, and environmental parameters; based on the fault feature vector, a match is performed in a reference database to determine the cause of the fault. Among them, the environmental parameters may include temperature parameters and humidity parameters. The reference database includes multiple reference fault feature vectors and corresponding reference fault causes. The current operating parameters are the operating parameters of the production line equipment at the current time point.
[0128] In some embodiments, the cloud platform can construct at least one reference fault feature vector based on historical faults, historical production characteristics, historical operating parameters, and historical environmental parameters in historical data in the same manner as constructing a fault feature vector, and use the historical fault causes corresponding to the historical faults as the reference fault causes corresponding to the reference fault feature vector.
[0129] In some embodiments, the cloud platform may determine the reference fault cause corresponding to the reference fault feature vector in the reference database that is closest to the fault feature vector as the fault cause of the possible fault.
[0130] In some embodiments, the cloud platform can determine the production process parameters based on the cause of the failure and the current operating parameters. For example, if the cause of the failure is that the operating power of the production line equipment is too large, the cloud platform can reduce the operating power of the production line equipment based on the current operating parameters to determine the production process parameters. The adjustment range of the operating parameters can be related to the average probability of possible failures. The higher the average probability of possible failures, the larger the adjustment range can be.
[0131] In the embodiments of this specification, by determining the cause of the fault through the fault probability sequence to determine the production process parameters, more appropriate production process parameters can be obtained for the possible fault conditions of the production line equipment to avoid the occurrence of faults as much as possible. By predicting the probability of failure at a future time point, measures can be taken before the failure actually occurs, thereby effectively preventing the occurrence of the failure. In addition, by identifying the cause of the failure that may lead to a decrease in efficiency early and adjusting the operating parameters accordingly, the production line can maintain a high production rate and production quality level, avoiding unnecessary downtime in the production process or avoiding unnecessary overload and waste, thereby improving the overall production efficiency.
[0132] In some embodiments, the cloud platform may first generate at least one set of candidate production process parameters, and then select production process parameters from the at least one set of candidate production process parameters based on production data. For more information on how to determine production process parameters based on candidate production process parameters, see Figure 4 and related instructions.
[0133] Step 240: Generate a process adjustment instruction based on the production process parameters and the adjustment time.
[0134] The process adjustment instruction is an instruction used to control or adjust the operating parameters of the production line equipment. The process adjustment instruction may include production process parameters and adjustment time.
[0135] In some embodiments, the cloud platform can send the generated process adjustment instructions to the industrial Internet of Things management platform through a distributed server.
[0136] Step 250, the process adjustment instruction is parsed through the industrial Internet of Things management platform, and the operating parameters of the production line equipment are adjusted based on the process adjustment instruction when the adjustment time arrives.
[0137] The embodiments of this specification do not specifically limit the method of parsing instructions, and operations familiar to those skilled in the art may be used.
[0138] In some embodiments, the industrial Internet of Things management platform can adjust the first working parameters of the screening equipment based on the process adjustment instructions so that the operating parameters of the screening equipment reach the target screening parameters. The screening equipment (for example, the thermostat screening equipment) can screen the thermostat through visual detection in cooperation with the robotic arm. The first working parameters of the thermostat screening equipment may include the position accuracy and movement speed of the robotic arm, and the accuracy of the sensor set on the robotic arm. By adjusting the first working parameters, the screening parameters can be affected, thereby achieving the purpose of adjusting the thermostat size, thermostat type, appearance defects and thermostat screening speed of the thermostat screening equipment. For example, improving the position accuracy and movement speed of the robotic arm can increase the thermostat screening speed.
[0139] In some embodiments, the industrial Internet of Things management platform can adjust the second working parameter of the conveying device based on the process adjustment instruction so that the operating parameter of the conveying device reaches the target conveying parameter. The second working parameter of the conveying device may include the motor power of the conveying device, etc. By adjusting the motor power of the conveying device, the conveying parameters can be affected, thereby achieving the purpose of adjusting the conveying beat and material conveying speed of the conveying device. For example, increasing the motor power of the conveying device can increase the moving speed of the conveyor belt, thereby increasing the conveying beat and material conveying speed.
[0140] In some embodiments, the industrial Internet of Things management platform can adjust the first setting parameters of the assembly equipment based on the process adjustment instruction so that the operating parameters of the assembly equipment reach the target assembly parameters. The assembly equipment may include an over-temperature sensor assembly equipment, and the controller is a control system that controls the assembly equipment, which may be a PLC. The first setting parameters may include parameters related to welding parameters, connection methods, packaging parameters, etc. of a welder (e.g., a tin soldering machine), such as the power and speed of the welder. By adjusting the parameters of the controller of the over-temperature sensor assembly equipment to adjust the first setting parameters of the assembly equipment, the welding parameters, connection methods, and packaging parameters of the assembly equipment can be adjusted.
[0141] In some embodiments, the industrial Internet of Things management platform can adjust the second setting parameters of the quality inspection equipment so that the operating parameters of the quality inspection equipment reach the target quality inspection parameters. The controller of the quality inspection equipment is a control system that controls the quality inspection equipment, which can be a PLC. The second setting parameters may include parameters related to the accuracy parameters, measurement range parameters, environmental simulation parameters, response time parameters, etc. of the quality inspection equipment. By adjusting the controller of the quality inspection equipment to adjust the second setting parameters of the quality inspection equipment, the accuracy parameters, measurement range parameters, environmental simulation parameters, response time parameters, etc. of the quality inspection equipment can be adjusted.
[0142] In the embodiments of this specification, through the industrial Internet of Things system and cloud platform, it is determined whether to adjust the operating parameters of the production line equipment based on production data. The cloud platform can be used to integrate the massive data in various industrial Internet of Things, and advanced data analysis and artificial intelligence technologies can be used to achieve intelligent recommendations on production processes, helping manufacturing companies to quickly select the optimal production process plan and improve production efficiency and product quality.
[0143] It should be noted that the above description of the process 200 is only for example and illustration, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to the process 200 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.
[0144] Figure 4 It is an exemplary schematic diagram of generating production process parameters according to some embodiments of this specification.
[0145] In some embodiments, the cloud platform can generate at least one set of candidate production process parameters 410; based on at least one set of candidate production process parameters 410, production data 420 of the production line, and historical production data 430, determine the estimated production characteristics 450 corresponding to each set of candidate production process parameters in at least one set of candidate production process parameters through a production feature model 440; based on the estimated production characteristics 450 corresponding to each set of candidate production process parameters in at least one set of candidate production process parameters, determine the production process parameters 460.
[0146] The candidate production process parameters are candidate production process parameters. In some embodiments, a set of candidate process parameters may include at least one of candidate screening parameters, candidate conveying parameters, candidate assembly parameters, and candidate quality inspection parameters.
[0147] In some embodiments, the cloud platform can generate candidate production process parameters in a variety of ways. In some embodiments, the cloud platform can randomly adjust based on the current operating parameters of the production line equipment to generate candidate production process parameters.
[0148] In some embodiments, the cloud platform can obtain user demand information 412; based on the user demand information 412, equipment status data 413, material parameter data 414, and with reference to production data 415, determine initial production process parameters 411; based on the initial production process parameters 411, generate at least one set of candidate production process parameters 410.
[0149] User demand information is the user's requirements for production products or production processes. In some embodiments, user demand information may include product quality requirements and target production efficiency. In some embodiments, the cloud platform may obtain user demand information through the industrial Internet of Things management platform.
[0150] User demand information can be obtained in a variety of ways. For example, factory users actively input user demand information. Another example is that the cloud platform reminds factory users to input user demand information. It should be noted that if the user actively inputs and changes the production demand, it is necessary to wait until the production process of the previous batch of products is completed before adjusting the operating parameters.
[0151] For more information about device status data and reference production data, see Figure 2 and related instructions.
[0152] Material parameter data is data related to raw materials. In some embodiments, material parameter data may include thermostat type, specifications (e.g., rated voltage, current, measurement range, etc.), thermistor type and specifications (e.g., resistance value, thermal index, operating temperature range, resistance temperature characteristics, etc.), material type, material specifications, etc.
[0153] The initial production process parameters are the initially set production process parameters. In some embodiments, the cloud platform can construct a production feature vector based on product quality requirements, equipment status data, material parameter data, and target production efficiency, and match the production feature vector in the production database to determine the initial production process parameters.
[0154] In some embodiments, for non-numerical features (e.g., connection mode, thermostat type, etc.), the cloud platform may perform encoding processing. The encoding processing method may include one-hot encoding or label encoding. The cloud platform may combine the processed features to form a vector.
[0155] The production database may include multiple groups of reference production feature vectors and corresponding reference production process parameters. In some embodiments, the cloud platform may construct at least one reference production feature vector in the same manner as constructing the production feature vector based on the product quality requirements, equipment status data, material parameter data, and target production efficiency in the historical data, and determine the reference production process parameters corresponding to the reference production feature vector. In some embodiments, professionals may design corresponding reference production process parameters based on each reference production feature vector. In some embodiments, multiple groups of production process parameters may be actually used to conduct experiments under the conditions corresponding to the reference production feature vector, and a group of production process parameters with the best effect (for example, fast production rate and high qualified rate) may be selected as the reference production process parameters corresponding to this reference production feature vector. The cloud platform may store multiple groups of reference production feature vectors and corresponding reference production process parameters in the database to complete the construction of the production database.
[0156] In some embodiments, the production database may be an open source library such as Milvus or Faiss that is specifically designed for vector similarity search.
[0157] In some embodiments, the cloud platform may determine the initial production process parameters corresponding to the standard production feature vector that is closest to the production feature vector as the initial production process parameters corresponding to the production feature vector.
[0158] In some embodiments, the cloud platform may randomly generate at least one set of candidate production process parameters based on the initial production process parameters.
[0159] In some embodiments, the cloud platform can define an adjustment range for each parameter based on the initial production process parameters. The cloud platform can randomly select a value from the adjustment range of the initial production process parameters, and combine them to obtain a randomly generated set of candidate production process parameters. The adjustment range is a preset range of optional production process parameters.
[0160] As an example only, for the conveying beat in the initial production process parameters, which is 30 s / piece, the adjustment range is ±20%. When generating candidate production process parameters, the conveying beat in the candidate production process parameters can be selected from 24 s / piece to 36 s / piece.
[0161] When the user inputs a clear requirement, for example, the connection method between the temperature controller and the thermistor or the number of thermistors is determined, the relevant welding parameters need to be modified accordingly, and the modification method is also fixed. These parameters that clearly need to be modified and are relatively fixed can be reflected in the initial production process parameters without random generation. Therefore, in the embodiments of this specification, generating candidate production process parameters through user demand information can speed up the calculation speed and provide a good initial value. At the same time, it can also reduce the number of times bad candidate production process parameters are generated, and the optimal production process parameters can be found more quickly, thereby improving production efficiency.
[0162] In some embodiments, the production feature model is a machine learning model. In some embodiments, the production feature model can be a machine learning model of a custom structure. The production feature model can also be a machine learning model of other structures, such as a neural network model, a recurrent neural network model, etc.
[0163] In some embodiments, the input of the production feature model may include at least one set of candidate production process parameters, production data of the production line, and historical production data, and the output may include estimated production features corresponding to each set of candidate production process parameters in at least one set of candidate production process parameters.
[0164] The estimated production features are estimated features related to the production process and production results of the production line. In some embodiments, the estimated production features may include at least one of an estimated production rate, an estimated production qualification rate, an estimated defect type sequence, etc. The estimated defect type sequence may include the defect type that is expected to occur and the proportion of the defect type in all defect types.
[0165] like Figure 4 As shown, in some embodiments, the input of the production characteristic model 440 may also include current operating parameters 471, historical operating parameters 472, material parameter data 473, and product parameter data 474. For more information about operating parameters and product parameter data, see Figure 2 and related instructions.
[0166] In some embodiments, the production feature model can obtain multiple third training samples with third labels to form a third training sample set, which is obtained through training with the third training sample set. The third training sample set can be obtained from historical data. In some embodiments, each third training sample in the third training sample set may include sample production process parameters, sample current production data, sample historical production data, sample current operating parameters, sample historical operating parameters, sample material parameter data, and sample product parameter data. The third label of each third training sample in the third training sample set may be the actual production feature corresponding to the training sample. The third label can be determined by the system or after manual collection. The production feature model can refer to Figure 2 The training process of the fault prediction model is similar to that of training acquisition.
[0167] In some embodiments, the training process of the production feature model may include a first training phase and a second training phase.
[0168] The first training phase is the pre-training phase before connecting to a specific factory. In the first training phase, training samples are obtained based on a large number of general data sets on the cloud platform. The cloud platform can collect a large number of general data sets, so the production feature model can be pre-trained first. The purpose of pre-training is to allow the production feature model to learn some generally applicable features and rules, laying the foundation for subsequent specific scenario training.
[0169] The second training phase is a phase of personalized training based on a specific factory. In the second training phase, the training sample set is composed of data actually collected by the specific factory, and the proportion of training samples corresponding to each defect type in the training sample set is not less than the preset sample threshold. The preset sample threshold can be set manually.
[0170] In the second training phase, the cloud platform can use the real production data of a single factory for reinforcement training to obtain the production feature model corresponding to each factory. The reinforcement algorithms used in the reinforcement training can include: Q-learning, Deep Q-Networks (DQN), Proximal Policy Optimization (PPO), etc.
[0171] In the second training stage, when collecting the third label, the specific defect type corresponding to each training sample can also be collected. Some of these defect types are more serious, while others are less serious. Therefore, when designing the composition of the sample, the specific defect type can also be considered. For example, for serious defects, even if the frequency of occurrence is low, it should be ensured that there are enough representative samples in the sample.
[0172] In some embodiments, the cloud platform can classify different types of defects, for example, manually perform the classification. Different preset thresholds can be set for different levels of defect types, such as "serious defects", "medium defects" and "minor defects". Among them, the preset threshold corresponding to serious defects can be set to the highest. For example, if the proportion of serious defects in the defect type sequence of the second label of a training sample is the highest, then this type of sample should be collected more in the sample set.
[0173] In the embodiments of this specification, the production feature model is pre-trained first to ensure the robustness and versatility of the model. Then, when the production feature model is further trained, the number of samples of various defect types is ensured to improve the accuracy of the model.
[0174] In some embodiments, a temperature sensor deployed at at least one position on the production line can be configured to obtain temperature data at the position corresponding to the temperature sensor, and a humidity sensor deployed at at least one position on the production line can be configured to obtain humidity data at the position corresponding to the humidity sensor. The temperature data and the humidity data can constitute environmental parameters.
[0175] like Figure 4 As shown, in some embodiments, the input of the production feature model 440 may also include environmental parameters 481 and a fault probability sequence 482. Accordingly, the third training sample set of the production feature model may also include sample environmental parameters and sample fault probability sequences. For more information about the fault probability sequence, see Figure 2 and related instructions.
[0176] Environmental parameters have a significant impact on equipment operation and product quality. In the embodiments of this specification, incorporating environmental parameters into the model input can help the model predict production characteristics more accurately, and changes in environmental conditions may cause fluctuations in equipment performance. By considering these changes, the obtained production characteristic model can be more robust and maintain high prediction performance even when environmental conditions change. In addition, potential failures can also cause a decrease in production rate or production quality (e.g., pass rate). Incorporating the failure probability sequence into the input range of the model can make the prediction of the production characteristic model more comprehensive.
[0177] In some embodiments, for each of at least one group of candidate production process parameters, the cloud platform can determine the adjustment effect score corresponding to the group of candidate production process parameters based on the estimated production characteristics corresponding to the group of candidate production process parameters, and select a group of candidate production process parameters with the highest adjustment effect score and an adjustment effect score higher than a score threshold from at least one group of candidate production process parameters as the production process parameters.
[0178] The adjustment effect score is an estimated score of the effect achieved after the candidate production process parameters take effect. The score threshold can be set manually.
[0179] In some embodiments, for each of at least one group of candidate production process parameters, the cloud platform can determine the adjustment effect score corresponding to the group of candidate production process parameters based on the estimated production speed, estimated production qualification rate and proportion of minor defects in the estimated production characteristics.
[0180] In some embodiments, the adjustment effect score may be determined by the following formula (1):
[0181] (1)
[0182] in, To adjust the effect score, To estimate the production speed, To estimate the production qualification rate, is the proportion of minor defects. , , is a weight, indicating that the selected production process parameters can achieve a high production qualification rate while also taking into account the production rate. In some embodiments, the coefficient , , Can be set by the user. For example, if the user values production speed more than pass rate, the coefficient can be set Higher than coefficient .
[0183] In some embodiments, if the adjustment effect scores corresponding to each group of candidate production process parameters do not reach the score threshold, the cloud platform can expand the adjustment range to generate more candidate production process parameters.
[0184] After the process adjustment instruction is executed, the actual adjustment effect may be good or bad. For example, the production rate or qualified rate still cannot meet the expectations.
[0185] In some embodiments, if the actual adjustment effect does not meet expectations, the cloud platform can Figure 2 In the manner described, the production feature model and the acquired related data are called to redefine the production process parameters.
[0186] In some embodiments, the cloud platform may collect actual production characteristics after the process adjustment instruction is executed; and dynamically adjust the process adjustment instruction based on the actual production characteristics.
[0187] In some embodiments, the cloud platform may collect actual production features, and compare the actual effect score calculated based on the actual production features with the original adjustment effect score (hereinafter referred to as the original effect score) when the process adjustment instruction is not executed. The calculation method of the actual effect score and the original effect score is the same as the calculation method of the adjustment effect score. The actual production features are the features of the actual production process after the process adjustment instruction is executed. In some embodiments, the actual production features may include at least one of the actual production rate, the actual production qualification rate, the actual defect type, etc.
[0188] In some embodiments, if the actual effect score is higher than the original effect score, the adjustment can be continued directly according to the previous adjustment direction (i.e., the adjustment direction in the above-executing process adjustment instruction); if the actual effect score is lower than the original effect score, the adjustment can be performed in the opposite direction of the previous adjustment direction. The previous adjustment direction is a comparison between the currently issued production process parameters and the operating parameters before adjustment.
[0189] For example, if the current actual effect score is higher than the original effect score, and the previous adjustment direction is to increase the pressure of the over-temperature sensor package and reduce the packaging speed, then the pressure of the over-temperature sensor package can be further increased and the packaging speed can be increased. On the contrary, if the current actual effect score is lower than the original effect score, then the pressure of the over-temperature sensor package can be reduced and the packaging speed can be increased.
[0190] In some embodiments, when adjusting according to the adjustment direction, the adjustment may be made with a preset adjustment amplitude, or the adjustment amplitude may be negatively correlated to the increase in the actual effect score compared to the original effect score. For example, if the preset adjustment amplitude of the power of the device is 10W, then when continuing to adjust, the adjustment is made with an amplitude of 10W each time to prevent over-adjustment.
[0191] In the embodiments of this specification, the process adjustment instructions are dynamically adjusted according to the actual production characteristics, which can avoid the situation where the adjustment effect is not ideal for a long time and change the adjustment direction in time according to the actual situation.
[0192] In some embodiments, the user demand information may further include a cost budget constraint. The cloud platform may determine the production process parameters based on the cost budget constraint and the estimated production characteristics corresponding to each set of candidate production process parameters.
[0193] The cost budget limit is the upper limit of the set production line cost. In the embodiment of this specification, the cost is mainly represented by power consumption.
[0194] In some embodiments, the cloud platform may determine the candidate production process parameters whose adjustment effect scores are greater than the score threshold as candidate production process parameters, and calculate the cost index for each candidate production process parameter. The cost index can be understood as the average power consumption required to produce a product.
[0195] In some embodiments, the cloud platform can determine the cost index of the candidate production process parameters through a fitting function based on historical data. The fitting function can be expressed by formula (2):
[0196] (2)
[0197] in, For product specifications, To estimate the production rate, are the corresponding alternative production process parameters, is the cost indicator corresponding to the alternative production process parameters. For more information about product specifications and estimated production rates, please refer to the previous description. , , are coefficients, which can be obtained by fitting the large amount of historical data mentioned above using a fitting algorithm.
[0198] In some embodiments, the cloud platform may further determine the production process parameters based on the cost index corresponding to the candidate production process parameters. In some embodiments, the cloud platform may determine the correction score of the candidate production process parameters based on the adjustment effect score and the cost index of the candidate production process parameters, and select the one with the highest correction score from multiple candidate production process parameters as the production process parameter.
[0199] In some embodiments, the modified score may be determined by the following formula (3):
[0200] (3)
[0201] in, To correct the rating, To adjust the effect score, is the cost indicator corresponding to the alternative production process parameters, is the coefficient. A negative number indicates that under the same conditions, the lower the cost index (i.e., power consumption), the better. In some embodiments, the coefficient It can be related to the electricity price. The more expensive the electricity price is, the higher the coefficient The larger the absolute value of .
[0202] If the user specifies a cost budget limit, when selecting production process parameters from candidate production process parameters, it is also necessary to consider whether the production cost exceeds the cost budget limit. In the embodiments of this specification, determining the production process parameters through cost budget limits can meet the user's cost requirements and save costs. Therefore, it can be ensured that the selected production process parameters can meet the requirements of product quality and production efficiency without exceeding the user's cost budget limit. This helps to optimize costs and improve economic benefits while ensuring product quality, and can flexibly adjust production strategies according to different cost budgets to better meet market demand.
[0203] In the embodiments of this specification, by generating candidate production process parameters and production feature models, the production process parameters can be accurately determined, thereby realizing intelligent recommendation of production processes. The production features corresponding to each set of candidate production process parameters are estimated by the production feature prediction model, and the effect score is adjusted based on the production features, so that the optimal production process parameters can be selected. This method not only improves production efficiency and product quality, but also reduces production costs, enhances the flexibility and controllability of the production process, and provides data-driven decision support for production line managers, ensuring the effective use of resources and reducing uncertainty in the production process.
[0204] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.
[0205] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.
Claims
1. Intelligent recommendation method for production process sharing based on industrial IoT information cloud, It is characterized in that The method is performed by a cloud platform, which includes a distributed server; The cloud platform is connected to multiple industrial Internet of Things systems corresponding to multiple factories through the distributed server; the industrial Internet of Things system includes an industrial Internet of Things user platform, an industrial Internet of Things service platform, an industrial Internet of Things management platform, an industrial Internet of Things sensor network platform and an industrial Internet of Things perception control platform; wherein the industrial Internet of Things perception control platform is configured as production line equipment and a data acquisition device deployed on the production line, and the industrial Internet of Things perception control platform realizes data interaction with the industrial Internet of Things management platform through the industrial Internet of Things sensor network platform, and the industrial Internet of Things management platform realizes data interaction with the cloud platform; The method comprises: Based on the industrial Internet of Things management platform, the production data of the production line is acquired and stored; Based on the production data, determining whether it is necessary to adjust the operating parameters of the production line equipment; In response to the need to adjust the operating parameters of the production line equipment: Based on the production data, generating production process parameters and adjustment time; and Based on the production process parameters and the adjustment time, a process adjustment instruction is generated and sent to the industrial Internet of Things management platform; The process adjustment instruction is parsed by the industrial Internet of Things management platform, and the industrial Internet of Things management platform adjusts the operating parameters of the production line equipment through the control system of the industrial Internet of Things perception control platform based on the process adjustment instruction when the adjustment time is reached; Wherein, the production process parameters include at least one of a target screening parameter, a target conveying parameter, a target assembly parameter and a target quality inspection parameter, and the production line equipment includes at least one of a screening device, a conveying device, an assembly device and a quality inspection device; The controlling of the operating parameters of the production line equipment by the control system of the industrial Internet of Things perception control platform based on the process adjustment instruction includes: Based on the process adjustment instruction, regulating a first operating parameter of the screening device so that the operating parameter of the screening device reaches the target screening parameter; Based on the process adjustment instruction, regulating a second operating parameter of the conveying device so that the operating parameter of the conveying device reaches the target conveying parameter; Based on the process adjustment instruction, regulating a first setting parameter of the assembly equipment so that an operating parameter of the assembly equipment reaches the target assembly parameter; or Based on the process adjustment instruction, the second setting parameter of the quality inspection device is adjusted so that the operating parameter of the quality inspection device reaches the target quality inspection parameter.
2. The method according to claim 1, It is characterized in that The generating production process parameters comprises: generating at least one set of candidate production process parameters; Based on the at least one set of candidate production process parameters, the production data of the production line, and the historical production data, determining the estimated production characteristics corresponding to each set of candidate production process parameters in the at least one set of candidate production process parameters through a production characteristic model; The production process parameters are determined based on the estimated production characteristics corresponding to each group of candidate production process parameters in the at least one group of candidate production process parameters.
3. The method according to claim 2, It is characterized in that Generating at least one set of candidate production process parameters comprises: Obtain information about user needs; Determine initial production process parameters based on the user demand information, equipment status data, and material parameter data; Based on the initial production process parameters, the at least one set of candidate production process parameters is generated.
4. The method according to claim 2, It is characterized in that The method further comprises: After the process adjustment instruction is executed, actual production characteristics are collected; Based on the actual production characteristics, the process adjustment instructions are dynamically adjusted.
5. The method according to claim 1, It is characterized in that The data acquisition device includes a vibration sensor deployed on the production line, and the vibration sensor is configured to acquire vibration data. The method further includes: Determine a fault probability sequence through a fault prediction model based on production data, historical fault records, vibration data, parameter data of currently produced products, historical maintenance records and reference data of the production line; Based on the result of determining whether the fault probability sequence satisfies the fault condition, determining whether it is necessary to adjust the operating parameters of the production line equipment; In response to the need to adjust the operating parameters of the production line equipment: Based on the failure probability sequence, determining possible failures of the production line; Based on the possible faults and production characteristics, the production process parameters are determined.
6. Intelligent production process recommendation system shared by industrial Internet of Things information cloud, It is characterized in that The system includes a cloud platform, which includes a distributed server, a data receiving module, a data processing module, an intelligent recommendation module and a user interaction module; The cloud platform is connected to the corresponding multiple industrial Internet of Things systems of multiple factories through the distributed server; the industrial Internet of Things system includes an industrial Internet of Things user platform, an industrial Internet of Things service platform, an industrial Internet of Things management platform, an industrial Internet of Things sensor network platform and an industrial Internet of Things perception control platform; wherein the industrial Internet of Things perception control platform is configured as production line equipment and a data acquisition device deployed on the production line, and the industrial Internet of Things perception control platform realizes data interaction with the industrial Internet of Things management platform through the industrial Internet of Things sensor network platform, and the industrial Internet of Things management platform realizes data interaction with the cloud platform; The data receiving module performs data connection with the industrial Internet of Things management platform of the industrial Internet of Things system through the distributed server to receive the corresponding production data of the industrial Internet of Things system, the data processing module processes the production data obtained by the data receiving module, the intelligent recommendation module performs intelligent recommendation of production process based on the processed production data, and the user interaction module displays the recommendation results for users to view and perform interactive operations; The cloud platform is configured as follows: Based on the industrial Internet of Things management platform, the production data of the production line is acquired and stored; Based on the production data, determining whether it is necessary to adjust the operating parameters of the production line equipment; In response to the need to adjust the operating parameters of the production line equipment: Based on the production data, generating production process parameters and adjustment time; and Based on the production process parameters and the adjustment time, a process adjustment instruction is generated and sent to the industrial Internet of Things management platform; The process adjustment instruction is parsed by the industrial Internet of Things management platform, and the industrial Internet of Things management platform adjusts the operating parameters of the production line equipment through the control system of the industrial Internet of Things perception control platform based on the process adjustment instruction when the adjustment time is reached; Wherein, the production process parameters include at least one of a target screening parameter, a target conveying parameter, a target assembly parameter and a target quality inspection parameter, and the production line equipment includes at least one of a screening device, a conveying device, an assembly device and a quality inspection device; In order to control the operating parameters of the production line equipment through the control system of the industrial Internet of Things perception control platform based on the process adjustment instruction, the cloud platform is further configured as follows: Based on the process adjustment instruction, regulating a first operating parameter of the screening device so that the operating parameter of the screening device reaches the target screening parameter; Based on the process adjustment instruction, regulating a second operating parameter of the conveying device so that the operating parameter of the conveying device reaches the target conveying parameter; Based on the process adjustment instruction, regulating a first setting parameter of the assembly equipment so that an operating parameter of the assembly equipment reaches the target assembly parameter; or Based on the process adjustment instruction, the second setting parameter of the quality inspection device is adjusted so that the operating parameter of the quality inspection device reaches the target quality inspection parameter.
7. The system according to claim 6, It is characterized in that The cloud platform is further configured as follows: generating at least one set of candidate production process parameters; Based on the at least one set of candidate production process parameters, the production data of the production line, and the historical production data, determining the estimated production characteristics corresponding to each set of candidate production process parameters in the at least one set of candidate production process parameters through a production characteristic model; The production process parameters are determined based on the estimated production characteristics corresponding to each group of candidate production process parameters in the at least one group of candidate production process parameters.
8. The system according to claim 7, It is characterized in that The cloud platform is further configured as follows: Obtain information about user needs; Determine initial production process parameters based on the user demand information, equipment status data, and material parameter data; Based on the initial production process parameters, the at least one set of candidate production process parameters is generated.
9. The system according to claim 6, It is characterized in that The data acquisition device includes a vibration sensor deployed on the production line, and the vibration sensor is configured to acquire vibration data. The cloud platform is further configured to: Determine the fault probability sequence through a fault prediction model based on the production data, historical fault records, vibration data, parameter data of currently produced products, and historical maintenance records of the production line; Based on the result of determining whether the fault probability sequence satisfies the fault condition, determining whether it is necessary to adjust the operating parameters of the production line equipment; In response to the need to adjust the operating parameters of the production line equipment: Based on the failure probability sequence, determining possible failures of the production line; Based on the possible faults and production characteristics, the production process parameters are determined.
10. A computer-readable storage medium, It is characterized in that The storage medium stores computer instructions, and when the computer instructions are executed by the processor, the production process intelligent recommendation method for industrial Internet of Things information cloud sharing as claimed in claim 1 is implemented.
Citation Information
Cited By
Automatic production line management method and system integrated with intelligent manufacturing unit
CN121785232A
An integrated intelligent manufacturing unit automatic production line management method and system
CN121785232B
