Equipment management method and system for 3D digital factory

Abstract

The invention relates to the technical field of industrial equipment management, and discloses an equipment management method for a 3D digital factory, and the method comprises the following steps: sensing the operation parameters of a network collection device through the Internet of Things; processing the operation parameters by utilizing a cloud computing or edge computing technology; dynamically generating an equipment health state based on the processed data; the equipment management system of the 3D digital factory comprises an Internet of Things sensing network used for collecting operation parameters of the equipment; the data processing module is used for carrying out cleaning, noise reduction, dynamic modeling and anomaly detection on equipment operation parameters; and the equipment health state generation module is used for generating the health state of the equipment. According to the invention, through the Internet of Things sensing network, dynamic modeling, intelligent scheduling and full-life-cycle management technology, the effects of equipment state real-time monitoring, accurate maintenance, energy efficiency optimization and comprehensive asset management are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial equipment management, and in particular to an equipment management method and system for a 3D digital factory. Background Art

[0002] With the rapid advancement of industry, intelligent manufacturing has become the main direction of modern industrial development. In industrial production, equipment management is an important link to ensure production efficiency, reduce operating costs, and extend equipment life. Through efficient equipment management, the operating status of equipment can be monitored in real time, resource scheduling can be optimized, and equipment failure rate can be reduced, thereby achieving production stability and economy.

[0003] In the existing technology, some digital means have been adopted to solve some problems in equipment management. For example, the equipment status monitoring technology based on a single sensor can collect basic operating parameters of the equipment such as temperature and vibration, and assist in the equipment status assessment; through fixed-cycle equipment maintenance methods, the loss caused by long-term operation of the equipment can be avoided to a certain extent; for energy consumption management, some technologies achieve energy-saving effects by manually adjusting equipment operating parameters. These technologies have played a certain role in improving equipment operation management, avoiding sudden failures and improving certain production efficiency, and have laid a certain foundation for the digitization and automation of equipment management.

[0004] However, the existing technology still has significant shortcomings in many aspects, which have become key issues restricting the further development of industrial intelligent manufacturing. For example, the existing technology lacks real-time collection of equipment operating parameters and has limited coverage, resulting in the inability to fully grasp the equipment status; the equipment health status assessment method is single and mostly based on static threshold judgment, which is difficult to adapt to dynamic changes in equipment; maintenance management relies on fixed cycle methods and manual task allocation, lacks accuracy and intelligence; equipment energy efficiency optimization cannot adjust operating parameters in real time, and overall energy consumption management is difficult to coordinate the operation of multiple devices; data in life cycle management is scattered and lacks decision support, making it difficult to quantify the economic efficiency of equipment. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides an equipment management method and system for a 3D digital factory, which solves the problems in the prior art of insufficient real-time and coverage of equipment operating parameter collection, a single health status assessment method with poor dynamic adaptability, lack of precision and intelligence in maintenance management, inability to adjust operating parameters in real time for equipment energy efficiency optimization, and scattered life cycle management data and insufficient decision support.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a 3D digital factory equipment management method, comprising the following steps: Collect equipment operating parameters through the IoT sensing network; Processing the operating parameters using cloud computing or edge computing technology; Dynamically generate equipment health status based on processed data; generating an equipment maintenance plan according to the equipment health status; Adjust equipment operating parameters in real time to optimize equipment energy efficiency; Comprehensively manage equipment lifecycle information.

[0007] Preferably, the step of collecting equipment operating parameters includes: Install temperature sensors, vibration sensors, pressure sensors and current sensors at key parts of the equipment; Transmit equipment operating parameters to the industrial cloud platform through the industrial gateway; The data is uploaded in real time using a low-latency communication protocol.

[0008] Preferably, the step of processing the operating parameters comprises: Use data cleaning algorithms to reduce noise on equipment operating parameters; Calculate the health status index of the equipment through dynamic modeling methods; Perform trend analysis and anomaly detection based on historical and real-time data.

[0009] Preferably, the step of generating an equipment maintenance plan includes: Dynamically adjust equipment maintenance cycle according to equipment health status index; Intelligently schedule equipment maintenance tasks based on task priority and fault severity; The generated maintenance tasks are pushed to the mobile terminal for execution.

[0010] Preferably, the step of comprehensive management of equipment life cycle information includes: Record the entire process data of equipment procurement, installation, operation, maintenance and scrapping; Build equipment lifecycle models and generate equipment replacement or upgrade recommendations based on data analysis.

[0011] The present invention also provides an equipment management system for a 3D digital factory, including: IoT sensing network, used to collect equipment operating parameters; Data processing module, used for cleaning, noise reduction, dynamic modeling and anomaly detection of equipment operating parameters; A device health status generation module is used to generate the health status of the device; Maintenance plan generation module, used to dynamically adjust equipment maintenance plans based on equipment health status; Energy efficiency optimization module, used to adjust equipment operating parameters in real time to optimize equipment energy consumption; Lifecycle management module, used to record the entire lifecycle information of the equipment and generate equipment replacement or upgrade suggestions; User interaction terminal, used to display equipment status and maintenance task information.

[0012] Preferably, the Internet of Things perception network includes: Multiple types of sensors are configured on the equipment to collect parameters such as temperature, vibration, pressure and current; Industrial gateway, used to transmit equipment operating parameters to the industrial cloud platform; Devices that support low-latency communication protocols ensure real-time data transmission.

[0013] Preferably, the data processing module includes: Data cleaning unit, used for noise filtering and data smoothing of operating parameters; A dynamic modeling unit for generating equipment health status index; An anomaly detection unit is used to identify abnormal conditions in operating parameters.

[0014] Preferably, the maintenance plan generating module includes: A priority calculation unit, used to calculate the task priority according to the fault severity and the remaining running time; A scheduling unit for allocating maintenance tasks according to priority; The notification unit is used to push the maintenance plan to the user terminal.

[0015] Preferably, the lifecycle management module includes: Data storage unit, used to store the full life cycle data of the equipment during the procurement, operation, maintenance and scrapping stages; The data analysis unit is used to analyze the equipment life cycle data and predict the equipment replacement or upgrade time.

[0016] The present invention provides a 3D digital factory equipment management method and system, which has the following beneficial effects: 1. The present invention realizes the comprehensive real-time collection of equipment operating parameters through the Internet of Things perception network combined with multiple types of sensors and low-latency communication protocols, and performs noise reduction processing on the data through Kalman filtering and sliding window technology, while combining long-term and short-term memory network dynamic modeling to improve data quality and prediction accuracy. Compared with the technical solutions in the prior art with delayed data collection, insufficient accuracy and limited modeling capabilities, the present invention has significantly improved data integrity, real-time performance and prediction capabilities.

[0017] 2. The present invention achieves accurate allocation and timely response of maintenance resources by constructing a health status index to quantify the operating status of the equipment, and combines dynamic adjustment of the maintenance cycle and intelligent priority scheduling algorithm. Compared with the technical solutions of the prior art that use fixed maintenance cycles or simple priority sorting, the present invention significantly improves maintenance efficiency, rationality of task allocation and dynamic adaptability, and solves the problem that traditional technologies cannot adapt to dynamic changes in equipment status.

[0018] 3. The present invention optimizes energy efficiency based on real-time adjustment of equipment operating parameters, and achieves energy consumption minimization and improvement of overall equipment efficiency by dynamically optimizing key parameters such as motor frequency and working pressure. At the same time, combined with the life cycle cost model and the health state decay model, the present invention can accurately predict the remaining life of the equipment, optimize the timing of equipment replacement, and achieve comprehensive management of the entire life cycle. Compared with the technical solutions in the prior art that have untimely energy consumption optimization, scattered cost data, and insufficient decision support, the efficiency and economy of equipment asset management are improved, and the realization of green manufacturing is promoted. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a flow chart of the method of the present invention; Figure 2 It is a system structure diagram of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the specification of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Please see attached Figure 1 The embodiment of the present invention provides a method for managing equipment in a 3D digital factory, comprising the following steps: S1. Collect the operating parameters of the equipment through the IoT sensing network; Through the application of IoT sensing network, real-time monitoring and accurate acquisition of key operating parameters of equipment can be achieved, providing basic data support for subsequent modules; Generally speaking, collecting the operating parameters of equipment through the IoT sensing network requires relying on a variety of sensors installed in key parts of the equipment, combined with industrial gateways and low-latency communication protocols to ensure the real-time, integrity and reliability of the data. In one possible implementation, the collected operating parameters include but are not limited to vibration, temperature, pressure, current and energy consumption, which can fully reflect the operating status and potential problems of the equipment.

[0022] Specifically, in this embodiment, the specific implementation steps of collecting device operating parameters through the Internet of Things sensing network are as follows: Sensor deployment and operation parameter collection In this embodiment, various types of sensors are deployed at key parts of the equipment, including vibration sensors, temperature sensors, pressure sensors, and current sensors, etc., to monitor the operating status of the equipment in real time. The deployment locations of the sensors are optimized according to the operating characteristics of the equipment and the requirements of key components, for example: Vibration sensors are used to monitor the vibration state of rotating parts (such as bearings and gears) and output vibration signals. , the unit is .

[0023] The temperature sensor is used to collect the temperature of key heating components of the equipment (such as motors and drive devices) and output temperature signals. , unit is ℃.

[0024] Pressure sensors are used to collect pressure changes in hydraulic or pneumatic systems and output pressure signals. , the unit is .

[0025] The current sensor is used to collect the current of the motor or drive device and output the current signal , the unit is .

[0026] As an option, in devices with high energy consumption management requirements, real-time energy consumption data can also be collected through smart meters or power measurement devices. , to further support energy efficiency optimization analysis.

[0027] Data transmission and communication protocols In this embodiment, the collected operating parameters are transmitted through the industrial gateway. The industrial gateway is responsible for preliminarily summarizing the sensor data and uploading it to the data processing module through the industrial Internet protocol.

[0028] In one possible implementation, the industrial gateway supports low-latency communication protocols, such as MQTT or OPC-UA, to ensure real-time and reliable data transmission. Specifically: The MQTT protocol can achieve high-frequency transmission of small data packets and is suitable for data uploading from multiple types of sensors.

[0029] The OPC-UA protocol provides a secure and standardized data interaction method, suitable for cross-platform data integration.

[0030] Generally speaking, in order to improve the integrity and security of data, a data verification module can also be embedded in the gateway to perform preliminary verification of sensor data and eliminate obvious abnormal data.

[0031] Data preprocessing In this embodiment, the collected raw data needs to be pre-processed before being uploaded to the data processing module. The pre-processing includes but is not limited to operations such as noise reduction, data smoothing and format unification.

[0032] As an option, in this embodiment, a Kalman filter algorithm is used to perform noise reduction processing on the collected data to eliminate the influence of environmental interference and improve data quality. The implementation formula of the Kalman filter is as follows:

[0033] in, Represents the estimated value at the current moment; Indicates the measurement value at the current moment; represents the Kalman gain, and the calculation formula is:

[0034] in, : The prediction error covariance of the previous moment; : measurement error covariance; As an optimization method, in some embodiments, the sliding window technology can also be used to smooth the sensor data, thereby further improving the reliability of the data. The implementation formula of the sliding window is as follows:

[0035] in: : smoothed data; : sliding window size; :The current moment forward The original data of the sampling points; In general, the collection of device operating parameters through the IoT sensing network can also be extended to other types of data collection, such as: In equipment with liquid cooling systems, the monitoring of coolant temperature and flow rate can be added; in pneumatic equipment, the monitoring of compressed air humidity and flow rate can be added; in some special equipment, the collection of parameters such as noise, light or environmental vibration can be added; through this expansion, the system's monitoring capabilities for the operating status of diversified equipment can be further improved to meet the needs of different application scenarios.

[0036] S2. Use cloud computing or edge computing technology to process operating parameters; In the implementation of the present invention, step S2 is used to process the operating parameters collected through the IoT sensing network. This step is one of the core links of the entire equipment management method. Its main purpose is to clean, reduce noise, model, extract features and detect anomalies of the original data, and provide accurate basic data for subsequent health status assessment, maintenance plan generation and energy consumption optimization steps; Generally speaking, the processing of operating parameters can rely on cloud computing and edge computing technologies, which combine distributed data computing with centralized processing to achieve real-time and efficient data analysis. In one possible implementation, edge computing is mainly used for fast-response local data processing, while cloud computing is used for more complex modeling and analysis. Specific processing content includes data noise reduction, feature extraction, anomaly detection, and trend prediction; Data cleaning and noise reduction In this embodiment, the processing of the operating parameters first performs data cleaning and noise reduction to eliminate the influence of sensor errors and environmental noise on the data. As an option, a Kalman filter algorithm can be used to dynamically reduce the noise of the data. Specifically: In this embodiment, in order to further extract useful information from the operating parameters, a dynamic model is constructed for equipment health status analysis and trend prediction. In a possible implementation, the feature extraction process includes the following: Calculate the mean of the running parameters :

[0037] Calculate standard deviation :

[0038] Calculate Kurtosis :

[0039] The above features can reflect the overall distribution characteristics of the operating parameters. In the specific implementation, these features are further fed into the dynamic modeling module to establish a time series model of the equipment health status; in one possible implementation, dynamic modeling can be implemented through a long short-term memory network (LSTM). LSTM is a neural network suitable for processing time series data and has the ability to remember long-term dependencies. Its basic formula is as follows: Calculation of the forget gate:

[0040] Calculation of input gate:

[0041]

[0042] Unit status update:

[0043] Calculation of output gate:

[0044]

[0045] in: : Input data at the current moment; : The hidden layer output at the previous moment; : The unit status at the current moment; , , , : weight matrix; , , , : Bias term. Through the above model, the time-dependent characteristics of equipment operation parameters can be effectively captured, providing support for subsequent anomaly detection and trend prediction; In this embodiment, an edge computing module is used to perform anomaly detection in real time to determine whether the operating parameters deviate from the normal range. As an option, anomaly detection can be implemented based on a support vector machine (SVM).

[0046] The objective function of the support vector machine is as follows:

[0047] The constraints are:

[0048] in: : normal vector of the classification hyperplane; : Input data; : classification label; : slack variable; : Penalty parameter, used to balance classification accuracy and hyperplane complexity. The anomaly detection results can be used to trigger early warning signals to notify maintenance personnel to conduct inspections; In this embodiment, in order to achieve a reasonable allocation between edge computing and cloud computing, some embodiments adopt the following strategies: For processing tasks that require real-time response (such as anomaly detection and noise reduction), they are preferentially deployed in edge computing modules.

[0049] For tasks that require large-scale data analysis and trend prediction (such as LSTM modeling), they are preferentially deployed in the cloud computing module.

[0050] Generally speaking, the edge computing module is mainly responsible for real-time data processing at the equipment site, while the cloud computing module is responsible for centralized complex analysis and global optimization tasks.

[0051] S3, dynamically generate equipment health status based on processed data; In the implementation of the present invention, step S3 dynamically generates the health status of the equipment based on the processed data. This step is an important part of the equipment management method, which directly affects the generation of subsequent equipment maintenance plans and the optimization adjustment of operating parameters. The generation of equipment health status requires the integration of multiple operating parameters, combined with dynamic modeling and feature extraction technology, to achieve quantitative evaluation of the current status of the equipment, providing a basis for subsequent predictive maintenance and optimization management.

[0052] Generally, the health status of equipment is generated by combining the characteristic calculation and weight of vibration, temperature, pressure, current and other key operating parameters. As an option, the generation of equipment health status can be based on the construction of index evaluation indicators based on dynamic modeling methods to reflect the equipment operation status in real time. In one possible implementation, the health status of equipment is expressed in the form of a health status index (HealthIndex, HI), and its value range can be defined as 0 to 1, where the closer the value is to 1, the better the health status of the equipment; In this embodiment, the health status of the device is quantitatively described by the health status index (HI). The calculation formula of HI is as follows: in: , , :Respectively indicate the time when the device Temperature, vibration, pressure and current parameters; , , : Respectively represent the maximum safety threshold of each parameter of the device; , , , : is the weight coefficient of each parameter, which is determined according to the equipment type and operating characteristics; In general, the selection of weight coefficients must meet the following conditions:

[0053] Through the above calculation formula, multi-dimensional operating parameters can be unified into a single health status index, which is convenient for intuitively evaluating the equipment status; In this embodiment, the generation of the equipment health status needs to dynamically reflect the changes in the operating parameters. As an implementation method, a sliding time window technology can be used for real-time updates. The specific formula is as follows:

[0054] in: : Health status index within the sliding window; : The time span of the sliding window; :time The health status index of the system; through the sliding time window method, the impact of short-term fluctuations on the health status can be reduced and the stability of the calculation results can be improved; Specifically, in this embodiment, the feature extraction method of each operating parameter is as follows: Vibration parameters , extract statistical features such as mean, standard deviation, kurtosis, etc.:

[0055] Among them, the temperature parameter ), based on the trend fitting model of the temperature distribution curve, extract its maximum value, average value and slope; for the pressure parameter , the frequency domain characteristics are calculated by Fourier transform to capture the main frequency component of pressure fluctuation; the current parameters , extract the periodic fluctuation characteristics and analyze the load condition of the equipment in combination with the power factor; In terms of weight allocation, this embodiment sets the initial weight coefficient according to the equipment operation characteristics and dynamically adjusts it through historical data training. As an option, the least squares method can be used to optimize the weight coefficient to minimize the error of the health status index:

[0056] in: : Reference value of the real health status of the equipment; : Health status index calculated according to the current weight; In a possible implementation, this embodiment performs abnormal marking and classification processing on the generated health status index. Specifically: when When <0.3, it is judged that the equipment status is seriously abnormal; when 0.3≤ When <0.7, it is judged that the equipment status needs attention; when When ≥0.7, the device is judged to be in normal state; In some embodiments, the classification standard can be further adjusted in combination with the equipment type. For example, for high-precision machine tool equipment, the classification threshold of the health status can be appropriately increased; In some embodiments, the generated device health status may be used in the following scenarios: When the health status index When it falls below a certain set threshold, an early warning signal is triggered and an inspection task is generated; the remaining life of the equipment is predicted based on the health status trend to provide a basis for maintenance planning and resource scheduling; the health status index is passed to the energy consumption optimization module to dynamically adjust the equipment operating parameters to extend the equipment life.

[0057] S4. Generate equipment maintenance plan according to equipment health status; In the implementation of the present invention, step S4 formulates a corresponding equipment maintenance plan based on the dynamic generation result of the equipment health status. This step is an important link in realizing predictive maintenance of equipment and optimizing resource scheduling. By combining the equipment health status index (HI) and equipment operation data, the specific maintenance cycle, priority and specific maintenance tasks of the equipment can be determined to provide guarantee for the efficient operation of the equipment.

[0058] Generally speaking, the generation of equipment maintenance plans includes three main contents: the dynamics of the maintenance cycle Adjustment, maintenance task priority sorting, task allocation and scheduling. As an option, the equipment maintenance plan can be formulated by analyzing the trend of the health status index and combining the equipment's operating history data to meet the real-time and accurate maintenance strategy. In a possible implementation, the generation of the maintenance plan can also integrate multi-dimensional information such as equipment type and operating environment to further optimize the maintenance strategy; In this embodiment, the equipment maintenance cycle is dynamically adjusted according to the equipment health index (HI). The adjustment rule of the maintenance cycle can be described by the following formula:

[0059] in: : Dynamically adjusted maintenance cycle; : Equipment initial maintenance cycle; : Equipment health index. Specifically, when the equipment is in poor health, the maintenance cycle will be shortened so that the equipment can be inspected and repaired in time; when the equipment is in good health, the maintenance cycle will be extended to reduce unnecessary maintenance frequency; As an option, in some embodiments, trend analysis can also be performed in combination with historical health status data to further optimize the dynamic adjustment of the maintenance cycle. For example, the average health status index is calculated based on the sliding time window:

[0060] in: : The average health status index within the sliding window; : Sliding window time span; Through the above method, it is possible to avoid excessive impact of a single health status fluctuation on the maintenance cycle; In this embodiment, the priority of the equipment maintenance task is calculated by a multi-factor weighted model. The specific priority calculation formula is as follows:

[0061] in: : Task priority; : The remaining operating time of the equipment, in hours; : Fault severity, ranging from 0 to 1; : The importance of the equipment in the production line, ranging from 0 to 1; , , : Weight coefficient, satisfying , =1; Specifically, when the remaining operating time of the equipment is short, the fault severity is high, and the equipment importance is high, its task priority value The larger the weight, the higher the priority. The weight coefficient can be adjusted according to different equipment types and factory operation requirements; As a possible implementation method, the weight coefficient can be dynamically adjusted through regression analysis of historical maintenance task data to optimize the accuracy of priority calculation; In a possible implementation, this embodiment formulates a specific task allocation and scheduling strategy by combining the equipment operation status and maintenance task priority. The goal of task allocation is to minimize the response time of maintenance tasks while optimizing resource utilization. The scheduling objective function of maintenance tasks can be described as:

[0062] The constraints are:

[0063] in: : No. Response time for maintenance tasks; :time Available maintenance personnel resources; : No. Tasks at time The resources needed; Specifically, when assigning tasks, priority is given to the location of the equipment, the skill matching of the maintenance personnel, and the urgency of the task. For example: When multiple tasks are located in the same production area, maintenance personnel with relevant skills can be assigned first to save task switching time; for advanced and complex tasks (such as replacing key components), the system can recommend experienced technicians and automatically generate task notifications.

[0064] In some embodiments, the equipment maintenance plan may also be expanded to include the following: Spare parts demand prediction: Generate corresponding spare parts lists and inventory warnings based on the health status of the equipment to avoid maintenance delays due to insufficient spare parts; Inspection content guidance: Generate detailed inspection steps and precautions for specific maintenance tasks, such as checking whether there is abnormal vibration in the bearing, checking whether there is leakage in the hydraulic system, etc.; Task tracking and feedback: After the task is executed, the maintenance results are recorded and the equipment ledger data is updated to provide support for subsequent health status generation.

[0065] As an option, in equipment with sensor redundancy design, multi-sensor data fusion technology can be combined to further improve the accuracy of maintenance planning. For example, Bayesian methods can be used to fuse temperature and vibration data to identify the risk of mechanical component failure due to overheating, so that maintenance can be scheduled in advance.

[0066] In some practical applications, the maintenance plan generation of this embodiment may include the following scenarios: In the continuous production process, priority is given to the inspection tasks of key equipment to reduce the risk of downtime; in the customized production scenario, the priority of the equipment maintenance plan is adjusted according to the order requirements to ensure that the production plan is not affected; in the scenario with high energy consumption optimization requirements, energy-saving optimization suggestions are generated through the maintenance plan, such as cleaning the cooling system of overloaded equipment; through the above implementation methods, step S4 realizes the generation of efficient and dynamic maintenance plans based on the health status of the equipment; S5. Adjust equipment operating parameters in real time to optimize equipment energy efficiency; In the implementation of the present invention, step S5 further optimizes the energy efficiency of the equipment based on real-time monitoring of equipment operating parameters and dynamic evaluation of health status. By adjusting the operating parameters of the equipment, such as motor frequency, working pressure, operating power, etc., it is possible to reduce energy consumption, extend the service life of the equipment, and reduce operating costs. This step is closely connected with the operating parameter collection and health status generation of the previous steps to ensure that the equipment operates in a safe and efficient state.

[0067] Generally speaking, equipment energy efficiency optimization needs to be combined with the actual working conditions of the equipment and its health status, while ensuring that the output performance meets production requirements and reducing unnecessary energy consumption. As an option, the key operating parameters of the equipment can be dynamically adjusted through edge computing devices combined with real-time collected data and operating status models. In one possible implementation, historical operating data and machine learning models can also be used to predict the optimal operating point of the equipment, and the operating parameters can be adjusted in real time based on the prediction results; In this embodiment, the optimization of equipment operating parameters aims to minimize the unit energy consumption of the equipment while ensuring that the equipment output meets production requirements. The optimization objective function can be expressed as:

[0068] in: : Total energy consumption of the equipment; : No. Devices at time Power; : sampling time interval; Specifically, during the optimization process, it is necessary to ensure that the actual output of the device meets the following constraints:

[0069] in: :The device is at time Output volume; :The minimum output required for the production task. Through the above objective function and constraints, it can be ensured that the adjustment of equipment operating parameters will not affect normal production while optimizing energy consumption; In this embodiment, key operating parameters of different devices are optimized according to their characteristics, including but not limited to the following situations: For motor drive equipment, the motor operating frequency can be adjusted in real time through frequency conversion control :

[0070] Among them, reducing the motor frequency It can reduce its power consumption ; For hydraulic or pneumatic systems, the working pressure can be adjusted To reduce energy loss:

[0071] in, The instantaneous flow rate of the system. For equipment with heating devices, the temperature setting value can be adjusted dynamically. To optimize energy consumption. In one possible implementation, the output power of the temperature control system can be adjusted in real time based on production demand and ambient temperature; In this embodiment, the optimization adjustment of the equipment operating parameters is achieved through a real-time optimization algorithm based on edge computing. As an option, a reinforcement learning algorithm (such as Q learning) can be used to intelligently optimize the equipment operating parameters. Specifically: State Space Defined as the current operating parameters and health status of the device, for example:

[0072] Action Space Defined as the range of adjustable parameters, such as adjusting motor frequency, hydraulic pressure, etc.; Reward Function Defined as indicators for energy efficiency optimization, such as:

[0073] in, It is a balancing parameter used to weigh energy optimization and production requirements; The core algorithm update formula of reinforcement learning is:

[0074] in: :state Take action The quality value of : learning rate; : discount factor; : The new state after taking action; : In new state Through the above method, the system can dynamically adjust the equipment parameters in real-time operation to optimize energy efficiency; In one possible implementation, this embodiment further improves overall energy efficiency through collaborative optimization of multiple devices. Specifically, a distributed optimization method can be used to coordinate the adjustment of operating parameters of multiple devices to minimize overall energy consumption. The objective function is:

[0075] The constraints are:

[0076] in: :All devices at time Total energy consumption; : No. The output of each device; through collaborative optimization, it is possible to avoid the negative impact of energy efficiency optimization of a single device on other devices or overall production efficiency; In some embodiments, specific application scenarios of equipment energy efficiency optimization include: for motor-driven production lines, dynamically adjusting the frequency to reduce idling energy consumption while avoiding equipment overload; in hydraulic or pneumatic systems, adjusting system pressure according to load demand to reduce unnecessary power output; for equipment with periodic tasks, automatically reducing power or entering standby mode during task intervals to reduce ineffective energy consumption; The adjustment of equipment operating parameters is based on health status and production needs, and is closely linked to the aforementioned operating parameter collection, health status generation and maintenance plan. This step not only ensures the efficient operation of the equipment, but also effectively reduces energy consumption, providing technical support for green manufacturing in digital factories; S6. Comprehensively manage the life cycle information of the equipment; In the implementation of the present invention, the core of step S6 is to record, analyze and manage various types of information throughout the life cycle of the equipment from procurement to scrapping. This step forms a management chain throughout the entire life cycle of the equipment by combining the operating parameters, health status, maintenance plan and energy efficiency data collected in the previous steps to ensure the visualization, quantification and predictability of equipment management. The comprehensive management of equipment life cycle information helps to maximize the value of equipment assets, optimize decisions on equipment upgrades and replacements, and improve overall production efficiency; Generally speaking, equipment lifecycle management includes stages such as equipment procurement, installation, operation, maintenance, and scrapping. Key data at each stage must be managed uniformly and updated dynamically. As an option, a lifecycle model can be constructed to reflect the status and cost of the equipment at each stage with quantitative indicators, thereby providing data support for lifecycle management. In one possible implementation, data processing and management can be based on the industrial Internet platform to achieve multi-dimensional data analysis and decision support; In this embodiment, the record of equipment life cycle data covers the entire process from equipment procurement to scrapping, including but not limited to the following: Procurement stage: record basic information such as equipment model, supplier, purchase date, initial cost, etc.

[0077] Installation phase: record the equipment’s installation location, initial debugging parameters, initial operation values ​​and other data.

[0078] Operation phase: Combine the operating parameters, health status and energy efficiency data collected in the previous steps to record the equipment's operating time, production efficiency, energy consumption level, etc.

[0079] Maintenance phase: record the maintenance history of the equipment, including maintenance date, task content, spare parts used, and other information.

[0080] Scrap stage: record the scrapping time of the equipment, residual value estimation, replacement equipment and other information.

[0081] As a possible implementation method, a unified industrial data platform can be used to classify, store and dynamically update the above data to ensure the integrity and timeliness of the data; In this embodiment, in order to optimize the management decision of the equipment life cycle, an equipment life cycle cost model (LifeCycleCost, LCC) is constructed, and its formula is as follows:

[0082] in: : Total life cycle cost of the equipment; :The equipment is in Unit costs at each stage, including procurement cost, operating cost, maintenance cost, etc.; :The equipment is in the duration of each phase; Specifically, the operating cost of the equipment can be further broken down into:

[0083] in: :The device is at time Power; : Energy unit price; :Operation and maintenance costs of equipment; Through the above model, the cost distribution of equipment at different stages can be quantitatively evaluated, providing a basis for equipment maintenance strategy, energy efficiency optimization and replacement decisions; In this embodiment, in order to facilitate management and decision-making, the equipment life cycle data is analyzed and visualized in multiple dimensions through the industrial Internet platform. Specifically: Trend analysis: Analyze the changing trends of equipment health status, operating costs, energy consumption levels, etc. through time series. For example:

[0084] Used to assess the rate of change in health status; Visualization of key indicators: Display key data of the equipment life cycle through dashboards, such as: Total equipment operating time; average energy consumption level; maintenance frequency and maintenance cost.

[0085] Obsolescence prediction: Based on the decline model of the equipment health status, the remaining useful life (RUL) of the equipment is predicted. The formula is:

[0086] in: : The scrap threshold of the equipment health status; : The decay rate of health status; As an option, data visualization can be in the form of heat maps, line graphs, pie charts, etc., so as to intuitively reflect the life cycle status of the equipment; In this embodiment, the comprehensive management of equipment life cycle information also includes the optimization decision of equipment upgrade and replacement. Generally, the replacement timing of equipment can be comprehensively evaluated by combining indicators such as operating cost, health status and maintenance frequency. For example: When the health status index of the device When it is lower than a certain set value for a long time, it is recommended to initiate a replacement plan.

[0087] When the unit operating cost of the equipment When the threshold exceeds the industry average, it is recommended to upgrade the equipment technology or scrap and replace it.

[0088] As a possible implementation method, the equipment replacement decision can be optimized by genetic algorithm, and the objective function is:

[0089] The constraints are:

[0090] in: : Life cycle costs of existing equipment; : The life cycle cost of new equipment; through the above optimization algorithm, the best replacement time and equipment selection plan can be determined under the premise of ensuring economy and reliability; In some embodiments, the comprehensive management of device lifecycle information can be further extended to the following application scenarios: Asset management: Through the life cycle information of the equipment, the asset status of all equipment in the factory is monitored in real time, and an asset utilization efficiency analysis report is generated.

[0091] Green Manufacturing: Combine life cycle data to evaluate the carbon emission level and resource utilization efficiency of equipment, and provide data support for achieving energy conservation and emission reduction goals.

[0092] Fault prediction and prevention: Combine lifecycle data with fault records to build equipment failure prediction models to identify high-risk equipment in advance and take preventive measures; Through dynamic recording and in-depth analysis of life cycle information, the present invention can effectively improve the utilization rate and economic value of equipment assets, while promoting the digital and intelligent transformation of factory management.

[0093] The equipment management system of the 3D digital factory described below and the equipment management method of the 3D digital factory described above can be referred to each other.

[0094] Please see attached Figure 2The present invention also provides an equipment management system for a 3D digital factory, including: IoT sensing network, used to collect equipment operating parameters; Data processing module, used for cleaning, noise reduction, dynamic modeling and anomaly detection of equipment operating parameters; A device health status generation module is used to generate the health status of the device; Maintenance plan generation module, used to dynamically adjust equipment maintenance plans based on equipment health status; Energy efficiency optimization module, used to adjust equipment operating parameters in real time to optimize equipment energy consumption; Lifecycle management module, used to record the entire lifecycle information of the equipment and generate equipment replacement or upgrade suggestions; User interaction terminal, used to display equipment status and maintenance task information.

[0095] The system of this embodiment can be used to execute the above method embodiments, and its principles and technical effects are similar, which will not be repeated here.

[0096] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. The equipment management method of 3D digital factory is characterized by: The following steps are involved: Collect equipment operating parameters through the IoT sensing network; Processing the operating parameters using cloud computing or edge computing technology; Dynamically generate equipment health status based on processed data; generating an equipment maintenance plan according to the equipment health status; Adjust equipment operating parameters in real time to optimize equipment energy efficiency; Comprehensively manage equipment lifecycle information.

2. The equipment management method of a 3D digital factory according to claim 1, characterized in that: The step of collecting equipment operating parameters comprises: Install temperature sensors, vibration sensors, pressure sensors and current sensors at key parts of the equipment; Transmit equipment operating parameters to the industrial cloud platform through the industrial gateway; The data is uploaded in real time using a low-latency communication protocol.

3. The equipment management method of a 3D digital factory according to claim 1, characterized in that: The step of processing the operating parameters comprises: Use data cleaning algorithms to reduce noise on equipment operating parameters; Calculate the health status index of the equipment through dynamic modeling methods; Perform trend analysis and anomaly detection based on historical and real-time data.

4. The equipment management method of a 3D digital factory according to claim 1, characterized in that: The step of generating the equipment maintenance plan comprises: Dynamically adjust equipment maintenance cycle according to equipment health status index; Intelligently schedule equipment maintenance tasks based on task priority and fault severity; The generated maintenance tasks are pushed to the mobile terminal for execution.

5. The equipment management method of a 3D digital factory according to claim 1, characterized in that: The steps of comprehensive management of equipment life cycle information include: Record the entire process data of equipment procurement, installation, operation, maintenance and scrapping; Build equipment lifecycle models and generate equipment replacement or upgrade recommendations based on data analysis. 6.3D digital factory equipment management system, characterized by: The equipment management method of a 3D digital factory using any one of claims 1 to 5 comprises: IoT sensing network, used to collect equipment operating parameters; Data processing module, used for cleaning, noise reduction, dynamic modeling and anomaly detection of equipment operating parameters; A device health status generation module is used to generate the health status of the device; Maintenance plan generation module, used to dynamically adjust equipment maintenance plans based on equipment health status; Energy efficiency optimization module, used to adjust equipment operating parameters in real time to optimize equipment energy consumption; Lifecycle management module, used to record the entire lifecycle information of the equipment and generate equipment replacement or upgrade suggestions; User interaction terminal, used to display equipment status and maintenance task information.

7. The equipment management system of the 3D digital factory according to claim 6, characterized in that: The IoT sensing network includes: Multiple types of sensors are configured on the equipment to collect parameters such as temperature, vibration, pressure and current; Industrial gateway, used to transmit equipment operating parameters to the industrial cloud platform; Devices that support low-latency communication protocols ensure real-time data transmission.

8. The equipment management system of the 3D digital factory according to claim 6, characterized in that: The data processing module comprises: Data cleaning unit, used for noise filtering and data smoothing of operating parameters; Dynamic modeling unit for generating equipment health status index; An anomaly detection unit is used to identify abnormal conditions in operating parameters.

9. The equipment management system of the 3D digital factory according to claim 6, characterized in that: The maintenance plan generation module includes: A priority calculation unit, used to calculate the task priority according to the fault severity and the remaining running time; A scheduling unit for allocating maintenance tasks according to priority; The notification unit is used to push the maintenance plan to the user terminal.

10. The equipment management system of the 3D digital factory according to claim 6, characterized in that: The life cycle management module includes: Data storage unit, used to store the full life cycle data of the equipment during the procurement, operation, maintenance and scrapping stages; The data analysis unit is used to analyze the equipment life cycle data and predict the equipment replacement or upgrade time.

Images