Intelligent monitoring method and system for refrigeration equipment in refrigeration unit

Abstract

The present application relates to the technical field of refrigeration equipment supervision, including a method and system for intelligent supervision of refrigeration equipment in a refrigeration unit, the method comprising the steps of: obtaining physical parameter information and equipment operation information of the refrigeration equipment, generating a digital model of the refrigeration equipment based on a preset Nvidia Omniverse platform according to the physical parameter information and the equipment operation information; importing the digital model of the refrigeration equipment into a preset Nvidia SimNet platform to generate a simulation model of the refrigeration equipment; generating operation prediction information according to the simulation model of the refrigeration equipment, and importing the operation prediction information into the digital model of the refrigeration equipment to generate visual prediction information; generating an operation supervision report according to the operation prediction information and the visual prediction information; thereby realizing multi-dimensional and high-precision detection of the status information of the refrigeration equipment, and intuitively presenting the operation status of the refrigeration equipment to the user through the operation supervision report, so as to facilitate the user to supervise and maintain the refrigeration equipment.

Description

Technical Field

[0001] The present application relates to the technical field of refrigeration equipment supervision, and in particular to a method and system for intelligent supervision of refrigeration equipment in a refrigeration unit. Background Art

[0002] Refrigeration units are widely used in industrial, commercial and civil fields. The core of refrigeration units is to realize the circulation of refrigerants through compression, condensation and evaporation to provide a low-temperature environment. However, the operation of refrigeration equipment, especially screw refrigeration units, involves complex physical processes and the collaboration between multiple components. These components may experience performance degradation, failure or abnormality under long-term operation, and the status monitoring and prediction of equipment in traditional methods rely on manual experience or detection methods based on a single parameter, which cannot monitor the entire equipment in a comprehensive and real-time manner.

[0003] The compressor, condenser, evaporator, throttle valve and other components in the screw refrigeration unit may fail due to environmental factors, material fatigue or operational errors. In particular, the failure of refrigeration equipment not only affects the refrigeration effect, but may also lead to problems such as increased energy consumption and equipment damage. Traditional monitoring methods are difficult to monitor the overall operating status of the equipment in real time, and it is also difficult to simulate and predict multi-physics field problems. Summary of the invention

[0004] Based on this, it is necessary to provide a method and system for intelligent supervision of refrigeration equipment in a refrigeration unit in response to the above-mentioned technical problems, so as to solve the technical problems that the existing refrigeration equipment supervision method has a single detection dimension, poor detection accuracy, and cannot intuitively understand the equipment status based on the detection data.

[0005] The present invention provides a method for intelligently monitoring refrigeration equipment in a refrigeration unit, comprising:

[0006] Acquire physical parameter information and equipment operation information of the refrigeration equipment, and generate a digital model of the refrigeration equipment based on a preset Nvidia Omniverse platform according to the physical parameter information and the equipment operation information;

[0007] Importing the digital model of the refrigeration equipment into a preset Nvidia SimNet platform to generate a simulation model of the refrigeration equipment;

[0008] Generate operation prediction information according to the refrigeration equipment simulation model, and import the operation prediction information into the refrigeration equipment digital model to generate visual prediction information;

[0009] An operation supervision report is generated according to the operation prediction information and the visualization prediction information.

[0010] As a preferred solution, obtaining physical parameter information and equipment operation information of the refrigeration equipment, and generating a digital model of the refrigeration equipment based on a preset Nvidia Omniverse platform according to the physical parameter information and the equipment operation information include:

[0011] Acquiring physical parameter information of the refrigeration equipment, wherein the physical parameter information includes basic structure data, component material data, physical behavior data and dynamic behavior data;

[0012] Generate a three-dimensional framework based on the preset Nvidia Omniverse platform according to the basic structure data, and generate a physical framework based on the three-dimensional framework according to the component material data;

[0013] Importing the physical behavior data and the dynamic behavior data into the physical framework to generate a framework model;

[0014] Acquiring equipment operation information of the refrigeration equipment, wherein the equipment operation information includes historical operation data, historical fault data and real-time monitoring data;

[0015] Importing the historical operation data and the historical fault data into the framework model to generate a modified framework model;

[0016] Generate a complete digital model based on the modified framework model and the real-time monitoring data;

[0017] A first fluid mechanics model, a first heat conduction model and a first structural mechanics model are generated based on the complete digital model, and a digital model of the refrigeration equipment is generated by coupling the first fluid mechanics model, the first heat conduction model and the first structural mechanics model.

[0018] As a preferred solution, the digital model of the refrigeration equipment is imported into a preset Nvidia SimNet platform to generate a simulation model of the refrigeration equipment, including:

[0019] Discretizing the digital model of the refrigeration equipment to generate a simulation grid, generating boundary conditions according to the physical parameter information and the equipment operation information, and generating a preliminary simulation model based on a preset Nvidia SimNet platform according to the digital model of the refrigeration equipment, the simulation grid and the boundary conditions;

[0020] Generate a second fluid mechanics model, a second heat conduction model and a second structural mechanics model based on a preset physical field model according to the preliminary simulation model;

[0021] A coupled simulation model is generated according to the coupling of the second fluid mechanics model, the second heat conduction model and the second structural mechanics model, and a numerical solution is performed on the coupled simulation model to generate a refrigeration equipment simulation model.

[0022] As a preferred solution, generating operation prediction information according to the refrigeration equipment simulation model; importing the operation prediction information into the refrigeration equipment digital model to generate visual prediction information includes:

[0023] Acquire simulation result information generated according to the refrigeration equipment simulation model;

[0024] Training a prediction neural network model through a physical information neural network according to the simulation result information, wherein the physical information neural network is pre-set on the Nvidia SimNet platform;

[0025] Inputting the real-time monitoring data into the prediction neural network model to generate operation prediction information;

[0026] The operation prediction information is imported into the digital model of the refrigeration equipment to generate visualized prediction information.

[0027] As a preferred solution, the operation prediction information is imported into the digital model of the refrigeration equipment to generate visualized prediction information, including:

[0028] Comparing and analyzing the operation prediction information and the simulation result information to generate a deviation value, and determining whether the deviation value is less than a preset deviation threshold;

[0029] If the judgment is no, the prediction neural network model is corrected according to the deviation value, and a corrected neural network model is generated;

[0030] Inputting the real-time monitoring data into the correction neural network model to generate correction prediction information;

[0031] Importing the corrected prediction information into the digital model of the refrigeration equipment to generate visualized prediction information;

[0032] If the judgment is yes, the operation prediction information is imported into the digital model of the refrigeration equipment to generate visualized prediction information.

[0033] As a preferred solution, the operation prediction information and simulation result information include a time point set, a component type set, and a parameter type set; a prediction matrix is ​​generated according to the operation prediction information; and a simulation matrix is ​​generated according to the simulation result information; and a deviation value is generated according to the prediction matrix and the simulation matrix based on the following formula:

[0034] ;

[0035] Where E is the deviation value, α is the preset first weight parameter, T is the total number of time points in the time point set, k is the ordinal number of the time point, N is the total number of component types in the component type set, i is the ordinal number of the component type, Mi is the total number of parameter types in the parameter type set of the i-th component, j is the ordinal number of the parameter type, Wij is the preset weight matrix, P i，j，k is the predicted value of parameter type j of component type i at time point k, S i，j，k is the simulation value of parameter type j of component type i at time point k; is the preset second weight parameter.

[0036] As a preferred solution, generating an operation supervision report according to the operation prediction information and the visual prediction information includes:

[0037] Generate a preliminary analysis report based on the operation prediction information and the simulation result information;

[0038] Generate an error analysis report based on the Nvidia SimNet platform according to the deviation value and the historical operation data;

[0039] An operation supervision report is generated based on the preliminary analysis report, the error analysis report and the visualized prediction information.

[0040] The present invention also provides an intelligent monitoring system for refrigeration equipment in a refrigeration unit, comprising:

[0041] A digital model generation module, used to obtain physical parameter information and equipment operation information of the refrigeration equipment, and generate a digital model of the refrigeration equipment based on a preset Nvidia Omniverse platform according to the physical parameter information and the equipment operation information;

[0042] A simulation model generation module, used for importing the digital model of the refrigeration equipment into a preset Nvidia SimNet platform to generate a simulation model of the refrigeration equipment;

[0043] A prediction information generation module, used to generate operation prediction information according to the refrigeration equipment simulation model; import the operation prediction information into the refrigeration equipment digital model to generate visual prediction information;

[0044] A supervision report generation module is used to generate an operation supervision report based on the operation prediction information and the visualization prediction information.

[0045] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned method for intelligently monitoring refrigeration equipment in a refrigeration unit when executing the computer program.

[0046] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for intelligently monitoring refrigeration equipment in a refrigeration unit are implemented.

[0047] The technical effects achieved by the present invention are as follows: the above-mentioned intelligent supervision method and system for refrigeration equipment in the refrigeration unit obtains physical parameter information and equipment operation information of the refrigeration equipment in turn, generates a digital model of the refrigeration equipment based on the preset Nvidia Omniverse platform according to the physical parameter information and the equipment operation information; imports the digital model of the refrigeration equipment into the preset Nvidia SimNet platform to generate a refrigeration equipment simulation model; generates operation prediction information according to the refrigeration equipment simulation model, and imports the operation prediction information into the digital model of the refrigeration equipment to generate visualization prediction information; generates an operation supervision report according to the operation prediction information and the visualization prediction information; thereby realizing multi-dimensional and high-precision detection of refrigeration equipment, and intuitively presenting the operation status of the refrigeration equipment to the user through the operation supervision report, so as to facilitate the user to supervise and maintain the refrigeration equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 A schematic diagram of a flow chart of a method for intelligently monitoring refrigeration equipment in a refrigeration unit in one embodiment;

[0049] Figure 2 The structure block diagram of the intelligent monitoring system of refrigeration equipment in a refrigeration unit in one embodiment. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0051] In one embodiment, a terminal is provided, which obtains physical parameter information and equipment operation information of a refrigeration equipment, generates a digital model of the refrigeration equipment based on a preset Nvidia Omniverse platform according to the physical parameter information and the equipment operation information; imports the digital model of the refrigeration equipment into a preset Nvidia SimNet platform to generate a simulation model of the refrigeration equipment; generates operation prediction information according to the refrigeration equipment simulation model, and imports the operation prediction information into the digital model of the refrigeration equipment to generate visualization prediction information; and generates an operation supervision report according to the operation prediction information and the visualization prediction information.

[0052] The terminal may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices.

[0053] In this embodiment, Figure 1 As shown, a method for intelligently monitoring refrigeration equipment in a refrigeration unit is provided, which is applicable to various refrigeration units, especially to screw refrigeration units. The method for intelligently monitoring refrigeration equipment in a refrigeration unit includes:

[0054] Step S100: obtaining physical parameter information and equipment operation information of the refrigeration equipment, and generating a digital model of the refrigeration equipment based on a preset Nvidia Omniverse platform according to the physical parameter information and the equipment operation information.

[0055] In this step, the physical parameter information and equipment operation information of the refrigeration equipment are collected. The physical parameter information includes the geometric dimensions of the refrigeration equipment, the material properties of each component, the connection relationship between the components, etc. At the same time, the equipment operation information is obtained from the regulated refrigeration equipment. The equipment operation information includes the real-time status of the refrigeration equipment during operation, such as the flow rate, pressure change, temperature distribution and other information of the refrigerant. The Nvidia Omniverse platform is used for digital modeling. First, the basic structural framework is built through the physical parameter information, and then the equipment operation information is imported to build the digital model of the refrigeration equipment.

[0056] Step S200: importing the digital model of the refrigeration equipment into a preset Nvidia SimNet platform to generate a simulation model of the refrigeration equipment.

[0057] In this step, in the intelligent supervision of refrigeration equipment, the accuracy of the digital model of the refrigeration equipment directly affects the accuracy of simulation and prediction. Through modeling on the Nvidia Omniverse platform, all components of the refrigeration equipment (such as compressors, evaporators, condensers, etc.) can accurately reflect the geometry and operating parameters of the actual physical system, making subsequent simulations closer to reality. The digital model of refrigeration equipment established on the Nvidia Omniverse platform can be seamlessly imported into the Nvidia SimNet platform for multi-physics simulation, avoiding problems with data accuracy and integrity due to platform compatibility issues.

[0058] Step S300: generating operation prediction information according to the refrigeration equipment simulation model, and importing the operation prediction information into the refrigeration equipment digital model to generate visualized prediction information.

[0059] In this step, based on the simulation model of the refrigeration equipment, the model is run to obtain the changing trends of key parameters (such as temperature, pressure, fluid flow, etc.), generate operation prediction information, and realize multi-dimensional and high-precision intelligent equipment supervision. The operation prediction information is imported into the digital model of the Omniverse platform, and the equipment status is updated in real time through graphical display, and potential fault points and operating efficiency changes are displayed, which can intuitively present the operating status of the refrigeration equipment.

[0060] Step S400: Generate an operation supervision report based on the operation prediction information and the visualization prediction information.

[0061] In this step, based on the previously generated operation prediction information and visual prediction information, the system will automatically generate an operation supervision report for comprehensive evaluation and analysis of the equipment status. The generated operation supervision report not only provides reliable data support for the daily maintenance of the equipment, but also assists users in making decisions, improving equipment operation efficiency, reducing the frequency of failures, and extending the service life of the equipment.

[0062] In one embodiment, the step S100: obtaining physical parameter information and equipment operation information of the refrigeration equipment, and generating a digital model of the refrigeration equipment based on a preset Nvidia Omniverse platform according to the physical parameter information and the equipment operation information, includes:

[0063] Step S110: Acquire physical parameter information of the refrigeration equipment, wherein the physical parameter information includes basic structure data, component material data, physical behavior data and dynamic behavior data;

[0064] In this step, the basic structure data includes the geometric dimensions, shapes and structural drawings of the compressor, condenser, throttle valve, evaporator, oil separator, oil cooler and filter dryer of the refrigeration equipment. The accuracy of 3D modeling is ensured through detailed basic structure data. Component material data includes material information of each component, including thermal conductivity, density and elastic modulus of the material, which is used for the subsequent construction of the physical framework. Physical behavior information includes density, specific heat capacity and fluid dynamic parameters of refrigerant / cooling water. Dynamic behavior data includes the speed, flow rate and pressure of each component under different working conditions.

[0065] Step S120: Generate a three-dimensional framework based on a preset Nvidia Omniverse platform according to the basic structure data, and generate a physical framework based on the three-dimensional framework according to the component material data;

[0066] Step S130: importing the physical behavior data and the dynamic behavior data into the physical framework to generate a framework model;

[0067] Step S140: Acquire equipment operation information of the refrigeration equipment, wherein the equipment operation information includes historical operation data, historical fault data and real-time monitoring data;

[0068] In this step, historical operation data includes the temperature, pressure, flow, and energy efficiency information of the refrigeration equipment during a previous working period. Historical operation data can be obtained from the refrigeration equipment under supervision, or the historical operation data of other refrigeration equipment of the same type / model can be directly obtained as a reference to improve the speed and accuracy of model building. Real-time monitoring data includes the temperature, pressure, flow, and energy efficiency information of the refrigeration equipment during the current working period. Historical fault data includes fault type, fault frequency, and fault recovery time.

[0069] Step S150: importing the historical operation data and the historical fault data into the framework model to generate a modified framework model;

[0070] Step S160: generating a complete digital model according to the modified framework model and the real-time monitoring data;

[0071] Step S170: Generate a first fluid mechanics model, a first heat conduction model and a first structural mechanics model based on the complete digital model, and generate a digital model of the refrigeration equipment according to the coupling of the first fluid mechanics model, the first heat conduction model and the first structural mechanics model.

[0072] In this step, during the operation of the refrigeration equipment, multiple physical phenomena interact with each other, such as the flow of refrigerant, heat transfer, and the mechanical response of the equipment structure. These physical phenomena jointly affect the overall performance of the equipment. Therefore, a single physical modeling method is difficult to accurately reflect the actual operation of the equipment. In order to solve this problem, this embodiment models from three different physical dimensions: fluid mechanics, heat conduction, and structural mechanics, and generates a more accurate digital model of the refrigeration equipment through multi-physical field coupling.

[0073] In refrigeration equipment, the flow behavior of the refrigerant directly affects the refrigeration efficiency, pressure distribution and flow control of the equipment. By establishing the first fluid mechanics model, the flow path, flow rate and pressure distribution of the refrigerant in components such as the compressor, evaporator and condenser can be simulated to analyze the fluid dynamics characteristics inside the equipment.

[0074] The core working principle of refrigeration equipment is to exchange heat through the evaporation and condensation process of refrigerant. The heat conduction model can simulate the heat transfer between different parts of the equipment, analyze the temperature gradient, heat dissipation efficiency and thermal performance of each component. By establishing the first heat conduction model, the thermal efficiency of the equipment under different working conditions can be predicted and overheating and overcooling problems can be prevented.

[0075] During the operation of refrigeration equipment, various components (such as compressors, pipes, condensers, etc.) will be subjected to different mechanical stresses. Long-term operation may cause component deformation, wear and even structural failure. By establishing the first structural mechanics model, the stress and strain of the equipment under different loads and working conditions can be simulated to evaluate the stability and durability of the equipment structure.

[0076] There are complex interactions between various physical fields. For example, the flow of refrigerant will bring about heat transfer, and the change in heat will affect the expansion and stress distribution of the equipment structure. Therefore, the coupled model can integrate these interdependent physical fields to make the generated digital model of the refrigeration equipment more comprehensive and accurate. Through the coupled modeling of fluid mechanics, heat conduction and structural mechanics, it is ensured that the digital model of the refrigeration equipment can simultaneously simulate the interaction between fluid, thermal and mechanical behaviors, provide a full understanding of the operation of the equipment, and thus achieve accurate prediction of equipment performance, failure points and energy efficiency.

[0077] In this embodiment, information of multiple dimensions such as infrastructure data, component material data, physical behavior data, and dynamic behavior data of the refrigeration equipment is obtained to establish a digital model. Modeling is performed using the USD format through Omniverse Create, and the infrastructure data is imported to generate a three-dimensional framework. The component material data is imported into the three-dimensional framework to generate a physical framework, and then the component material data, physical behavior data, and dynamic behavior data are written into the physical framework to generate a framework model. Historical operation data, historical fault data, and real-time monitoring data are imported into the framework model, and a complete digital model of the refrigeration equipment reflecting the actual operating status is generated through model correction and data fusion.

[0078] In one embodiment, the step S170: generating a first fluid mechanics model, a first heat conduction model and a first structural mechanics model based on the complete digital model, and generating a digital model of the refrigeration equipment according to the coupling of the first fluid mechanics model, the first heat conduction model and the first structural mechanics model, further includes:

[0079] Step S180: updating the digital model of the refrigeration equipment according to the real-time monitoring data and generating a dynamic model of the refrigeration equipment.

[0080] In this embodiment, based on the actual operating status of the refrigeration equipment, the digital model of the refrigeration equipment generated in the early stage is updated using real-time monitoring data to reflect the dynamic changes of the equipment at different times and under different working conditions, thereby generating a dynamic model of the refrigeration equipment, which is also the digital model of the refrigeration equipment. Specifically, the real-time monitoring data includes real-time collection information of key parameters during the operation of the equipment, such as temperature, pressure, flow, vibration, energy consumption, etc. These data are continuously collected through sensors and transmitted to the system through the Internet of Things or data acquisition system. Unlike static models, dynamic models can reflect the working status of the equipment in real time as the equipment operation data is continuously updated.

[0081] In one embodiment, the step S200: importing the digital model of the refrigeration equipment into a preset NvidiaSimNet platform to generate a simulation model of the refrigeration equipment includes:

[0082] Step S210: discretizing the digital model of the refrigeration equipment to generate a simulation grid, generating boundary conditions according to the physical parameter information and the equipment operation information, and generating a preliminary simulation model based on a preset Nvidia SimNet platform according to the digital model of the refrigeration equipment, the simulation grid and the boundary conditions;

[0083] In this step, the digital model of the refrigeration equipment contains the complex geometric structure and multiple physical properties of the refrigeration equipment. Before simulation, the digital model of the refrigeration equipment is discretized, that is, the continuous geometric structure is divided into grids, the grid density is determined according to the accuracy requirements of the refrigeration equipment and the balance calculation complexity, and a simulation grid suitable for numerical simulation is generated to ensure the accuracy and calculation efficiency of the simulation results. In this step, in order to ensure that the simulation environment matches the actual operating environment of the refrigeration equipment, thereby ensuring the authenticity of the simulation results, boundary conditions are defined for the simulation model based on the acquired physical parameter information and the equipment operation information, and the boundary conditions include the inlet and outlet of the fluid, the distribution of pressure, and the gradient of temperature.

[0084] Step S220: generating a second fluid mechanics model, a second heat conduction model and a second structural mechanics model according to the preliminary simulation model based on a preset physical field model;

[0085] In this embodiment, the second fluid mechanics model, the second heat conduction model and the second structural mechanics model are based on the preliminary simulation model, combined with the Nvidia SimNet platform for multi-physics field coupling, and further optimized and generated with higher precision. The numerical solution and discretization processing of the first fluid mechanics model, the first heat conduction model and the first structural mechanics model generated in the above steps are relatively simple, suitable for standard working conditions or preliminary analysis; while the second fluid mechanics model, the second heat conduction model and the second structural mechanics model are generated on the Nvidia SimNet platform, specifically for complex working conditions and multi-physics field coupling problems, and more efficient solutions are obtained through physical information neural networks.

[0086] Step S230: generating a coupled simulation model according to the coupling of the second fluid mechanics model, the second heat conduction model and the second structural mechanics model, numerically solving the coupled simulation model and generating a refrigeration equipment simulation model.

[0087] In this step, the fluid mechanics, heat conduction and structural mechanics models are not independent of each other. They affect each other during the operation of the equipment. The flow of fluid will bring about heat transfer, and the change in temperature will affect the expansion and mechanical stress of the material. These physical fields are coupled to form a comprehensive multi-physical field coupled simulation model. The coupled simulation model is numerically solved through the Nvidia SimNet platform to obtain complete simulation data of the refrigeration equipment under actual operating conditions. The refrigeration equipment simulation model can accurately reflect the operating status of the equipment and simulate the physical behavior of each component under actual working conditions.

[0088] In this embodiment, an accurate refrigeration equipment simulation model is generated through comprehensive modeling of fluid mechanics, heat conduction and structural mechanics. This simulation model provides a powerful tool for equipment performance evaluation, fault prediction and energy efficiency optimization, which can improve the intelligent level of equipment management and improve the reliability and operation efficiency of equipment.

[0089] In one embodiment, the step S300: generating operation prediction information according to the refrigeration equipment simulation model; and importing the operation prediction information into the refrigeration equipment digital model to generate visual prediction information includes:

[0090] Step S310: Acquire simulation result information generated according to the refrigeration equipment simulation model;

[0091] Step S320: training a physical information neural network according to the simulation result information to establish a prediction neural network model, wherein the physical information neural network is pre-set on the Nvidia SimNet platform;

[0092] Step S330: inputting the real-time monitoring data into the prediction neural network model to generate operation prediction information;

[0093] Step S340: importing the operation prediction information into the digital model of the refrigeration equipment to generate visualized prediction information.

[0094] In this embodiment, based on the simulation model of the refrigeration equipment, the Nvidia SimNet platform is used to simulate and analyze the equipment under different working conditions when it is running to generate simulation result information to reflect the physical state of the refrigeration equipment under specific conditions and its changing trend. Through the physical information neural network (Physics-InformedNeural Networks) preset in the Nvidia SimNet platform, the physical information neural network is trained based on the simulation result information generated in the above steps. The physical information neural network combines the physical model and operation data of the refrigeration equipment, can more accurately capture the complex operating characteristics of the equipment, and establish a predictive neural network model through the learning ability of the neural network. The real-time monitoring data is input into the predictive neural network model to generate the operation prediction information of the equipment. These real-time data include the current temperature, pressure, flow, energy efficiency and other information of the equipment. The predictive neural network predicts the future operation state of the equipment based on these real-time input data. The operation prediction information generated by the predictive neural network model is imported into the digital model of the refrigeration equipment and displayed through visualization technology. Through the Nvidia Omniverse platform, the possible future operation states of the refrigeration equipment (such as temperature distribution, fluid flow, pressure change, etc.) are presented in a graphical manner to help users intuitively understand the future operation trend of the equipment.

[0095] In one embodiment, the step S340: importing the operation prediction information into the digital model of the refrigeration equipment to generate visual prediction information includes:

[0096] Step S341: performing comparative analysis on the operation prediction information and the simulation result information to generate a deviation value, and determining whether the deviation value is less than a preset deviation threshold;

[0097] Step S342: If the judgment is no, the prediction neural network model is corrected according to the deviation value, and a corrected neural network model is generated;

[0098] Step S343: inputting the real-time monitoring data into the correction neural network model to generate correction prediction information;

[0099] Step S344: importing the corrected prediction information into the digital model of the refrigeration equipment to generate visualized prediction information;

[0100] Step S345: If the judgment is yes, the operation prediction information is imported into the digital model of the refrigeration equipment to generate visual prediction information.

[0101] In this embodiment, by comparing the operation prediction information with the simulation result information, the accuracy of the prediction model can be effectively monitored. When the deviation value between the prediction information and the simulation result exceeds the preset threshold, it means that the prediction model may have errors under specific working conditions. At this time, the prediction neural network model needs to be corrected according to the deviation value. The corrected neural network model can better reflect the actual operation of the equipment, thereby improving the accuracy of the prediction. The corrected prediction information is also imported into the digital model of the refrigeration equipment and presented in a visual manner. In this way, users can take measures in advance based on more accurate operation prediction information to optimize the operation of the equipment and avoid potential failures or inefficient operations.

[0102] In one embodiment, the operation prediction information and simulation result information include a time point set, a component type set, and a parameter type set. A prediction matrix is ​​generated according to the operation prediction information, and a simulation matrix is ​​generated according to the simulation result information. A deviation value is generated according to the prediction matrix and the simulation matrix based on the following formula:

[0103] ;

[0104] Where E is the deviation value, α is the preset first weight parameter, T is the total number of time points in the time point set, k is the ordinal number of the time point, N is the total number of component types in the component type set, i is the ordinal number of the component type, Mi is the total number of parameter types in the parameter type set of the i-th component, j is the ordinal number of the parameter type, Wij is the preset weight matrix, P i，j，k is the predicted value of parameter type j of component type i at time point k, S i，j，k is the simulation value of parameter type j of component type i at time point k; is the preset second weight parameter.

[0105] In this embodiment, the prediction matrix and the simulation matrix are used to store the prediction values ​​and simulation results of the refrigeration equipment at different time points, respectively. The prediction matrix is ​​generated based on the operation prediction data of the equipment and the aforementioned prediction neural network model, and each element thereof represents the prediction value at a specific time point, a certain component type, and a certain parameter type. Similarly, the simulation matrix is ​​obtained by simulation analysis under a variety of different working conditions using the physical simulation model on the NVIDIA SimNet platform, and each element thereof represents the simulation value under the same conditions.

[0106] Specifically, the structure of the prediction matrix and simulation matrix can be represented as a three-dimensional array, which contains a set of time points, a set of component types, and a set of parameter types. Each dimension of the matrix represents:

[0107] Time point set (T): represents the discrete time points when the device is running. Each row in the matrix corresponds to a different time point.

[0108] Component type set (N): represents different components in the refrigeration equipment, such as compressor, evaporator, condenser, etc. Each column in the matrix corresponds to a different component type.

[0109] Parameter Type Set (Mi): For each component, there can be multiple parameter types, such as temperature, pressure, flow, energy efficiency, etc. These parameter types reflect the key operating status of the equipment.

[0110] Therefore, each element P of the prediction matrix and simulation matrix i，j，k and S i，j，k Both represent the predicted value and simulated value of the jth parameter of the ith component at time point k. The above steps can effectively capture the state changes of the refrigeration equipment at different times, different components and different parameter dimensions.

[0111] The deviation value calculation formula includes the square error part and the relative error part. The square error part assigns different importance to the parameter type of each component through the weight matrix Wij, and calculates the predicted value P at each time point i，j，k and the simulation value S i，j，k The squared difference between the predicted and simulated results reflects the accuracy difference between them. This part can capture the degree of deviation between the predicted results and the actual simulation situation, so as to better optimize and correct the model. The relative error part expresses the proportional difference between the predicted value and the simulated value. When the difference between the two is small, the relative error calculated in the formula will approach zero, indicating that the accuracy of the prediction model is high. The relative importance of the error contribution of the two parts is adjusted by the preset first weight parameter α and the second weight parameter β.

[0112] In one embodiment, the step S400: generating an operation supervision report according to the operation prediction information and the visual prediction information includes:

[0113] Step S410: generating a preliminary analysis report according to the operation prediction information and the simulation result information;

[0114] Step S420: generating an error analysis report based on the Nvidia SimNet platform according to the deviation value and the historical operation data;

[0115] Step S430: Generate an operation supervision report based on the preliminary analysis report, the error analysis report and the visualized prediction information.

[0116] In this embodiment, a preliminary analysis report on the operation of the refrigeration equipment is generated based on the operation prediction information and the simulation result information. The report will record in detail the current status, future change trends and potential risks of the key performance indicators of the equipment (such as efficiency, energy consumption, temperature, etc.), help operators understand the possible future operating status of the equipment, and provide important reference for subsequent maintenance decisions. Generate a deviation value based on the difference between the operation prediction information and the simulation result information, perform error correction analysis in combination with historical operation data, generate an accurate error analysis report, and evaluate the accuracy of the prediction model. Integrate the preliminary analysis report, error analysis report and visual prediction information to generate a complete equipment operation supervision report, providing decision-making basis such as fault warning and performance optimization suggestions. The supervision operation report and its related prediction information and monitoring data are stored in the database as historical operation data.

[0117] In one embodiment, Figure 2 As shown, a smart supervision system for refrigeration equipment in a refrigeration unit is provided, comprising: a digital model generation module, a simulation model generation module, a prediction information generation module and a supervision report generation module.

[0118] The digital model generation module is used to obtain the physical parameter information and equipment operation information of the refrigeration equipment, and generate the digital model of the refrigeration equipment based on the preset Nvidia Omniverse platform according to the physical parameter information and the equipment operation information. The simulation model generation module is used to import the digital model of the refrigeration equipment into the preset NvidiaSimNet platform to generate a simulation model of the refrigeration equipment. The prediction information generation module is used to generate operation prediction information according to the simulation model of the refrigeration equipment; and import the operation prediction information into the digital model of the refrigeration equipment to generate visual prediction information. The supervision report generation module is used to generate an operation supervision report according to the operation prediction information and the visual prediction information.

[0119] In one embodiment, the digital model generation module is also used to: obtain physical parameter information of the refrigeration equipment, wherein the physical parameter information includes basic structure data, component material data, physical behavior data and dynamic behavior data; generate a three-dimensional framework based on a preset Nvidia Omniverse platform according to the basic structure data, and generate a physical framework based on the three-dimensional framework according to the component material data; import the physical behavior data and the dynamic behavior data into the physical framework to generate a framework model; obtain equipment operation information of the refrigeration equipment, wherein the equipment operation information includes historical operation data, historical fault data and real-time monitoring data; import the historical operation data and the historical fault data into the framework model to generate a modified framework model; generate a complete digital model based on the modified framework model in combination with the real-time monitoring data; generate a first fluid mechanics model, a first heat conduction model and a first structural mechanics model based on the complete digital model, and generate a digital model of the refrigeration equipment according to the coupling of the first fluid mechanics model, the first heat conduction model and the first structural mechanics model.

[0120] In one embodiment, the digital model generation module is further used to: update the digital model of the refrigeration equipment according to the real-time monitoring data and generate a dynamic model of the refrigeration equipment.

[0121] In one embodiment, the simulation model generation module is further used to: discretize the digital model of the refrigeration equipment to generate a simulation grid, generate boundary conditions according to the physical parameter information and the equipment operation information, generate a preliminary simulation model based on a preset Nvidia SimNet platform according to the digital model of the refrigeration equipment, the simulation grid and the boundary conditions; generate a second fluid mechanics model, a second heat conduction model and a second structural mechanics model based on the preliminary simulation model and a preset physical field model;

[0122] A coupled simulation model is generated according to the coupling of the second fluid mechanics model, the second heat conduction model and the second structural mechanics model, and a numerical solution is performed on the coupled simulation model to generate a refrigeration equipment simulation model.

[0123] In one embodiment, the prediction information generation module is further used to:

[0124] Acquire simulation result information generated according to the refrigeration equipment simulation model; train a physical information neural network according to the simulation result information to establish a prediction neural network model, wherein the physical information neural network is pre-set on the Nvidia SimNet platform; input the real-time monitoring data into the prediction neural network model to generate operation prediction information; and import the operation prediction information into the digital model of the refrigeration equipment to generate visual prediction information.

[0125] In one embodiment, the prediction information generation module is further used to:

[0126] Compare and analyze the operation prediction information and the simulation result information to generate a deviation value, and determine whether the deviation value is less than a preset deviation threshold; if it is judged as no, calibrate the prediction neural network model according to the deviation value, and generate a corrected neural network model; input the real-time monitoring data into the corrected neural network model to generate corrected prediction information; import the corrected prediction information into the digital model of the refrigeration equipment to generate visualized prediction information; if it is judged as yes, import the operation prediction information into the digital model of the refrigeration equipment to generate visualized prediction information.

[0127] In one embodiment, the prediction information generation module is further used to:

[0128] The operation prediction information and simulation result information include a time point set, a component type set, and a parameter type set. A prediction matrix is ​​generated according to the operation prediction information, and a simulation matrix is ​​generated according to the simulation result information. A deviation value is generated according to the prediction matrix and the simulation matrix based on the following formula:

[0129] ;

[0130] Where E is the deviation value, α is the preset first weight parameter, T is the total number of time points in the time point set, k is the ordinal number of the time point, N is the total number of component types in the component type set, i is the ordinal number of the component type, Mi is the total number of parameter types in the parameter type set of the i-th component, j is the ordinal number of the parameter type, Wij is the preset weight matrix, P i，j，k is the predicted value of parameter type j of component type i at time point k, S i，j，k is the simulation value of parameter type j of component type i at time point k; is the preset second weight parameter.

[0131] In one embodiment, the regulatory report generation module is further used to:

[0132] Generate a preliminary analysis report based on the operation prediction information and the simulation result information; generate an error analysis report based on the Nvidia SimNet platform according to the deviation value and the historical operation data; generate an operation supervision report based on the preliminary analysis report, the error analysis report and the visual prediction information.

[0133] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned method for intelligently monitoring refrigeration equipment in a refrigeration group when executing the computer program.

[0134] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for intelligently monitoring refrigeration equipment in a refrigeration unit are implemented.

[0135] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0136] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0137] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for intelligently monitoring refrigeration equipment in a refrigeration unit, characterized in that: include: Acquire physical parameter information and equipment operation information of the refrigeration equipment, and generate a digital model of the refrigeration equipment based on a preset Nvidia Omniverse platform according to the physical parameter information and the equipment operation information; Importing the digital model of the refrigeration equipment into a preset Nvidia SimNet platform to generate a simulation model of the refrigeration equipment; Generate operation prediction information according to the refrigeration equipment simulation model, and import the operation prediction information into the refrigeration equipment digital model to generate visual prediction information; Generate an operation supervision report according to the operation prediction information and the visual prediction information; Acquiring physical parameter information and equipment operation information of the refrigeration equipment, and generating a digital model of the refrigeration equipment based on a preset Nvidia Omniverse platform according to the physical parameter information and the equipment operation information, including: Acquiring physical parameter information of the refrigeration equipment, wherein the physical parameter information includes basic structure data, component material data, physical behavior data and dynamic behavior data; Generate a three-dimensional framework based on the preset Nvidia Omniverse platform according to the basic structure data, and generate a physical framework based on the three-dimensional framework according to the component material data; Importing the physical behavior data and the dynamic behavior data into the physical framework to generate a framework model; Acquiring equipment operation information of the refrigeration equipment, wherein the equipment operation information includes historical operation data, historical fault data and real-time monitoring data; Importing the historical operation data and the historical fault data into the framework model to generate a modified framework model; Generate a complete digital model based on the modified framework model and the real-time monitoring data; A first fluid mechanics model, a first heat conduction model and a first structural mechanics model are generated based on the complete digital model, and a digital model of the refrigeration equipment is generated by coupling the first fluid mechanics model, the first heat conduction model and the first structural mechanics model.

2. The intelligent monitoring method for refrigeration equipment in a refrigeration unit according to claim 1 is characterized in that: The digital model of the refrigeration equipment is imported into a preset Nvidia SimNet platform to generate a simulation model of the refrigeration equipment, including: Discretizing the digital model of the refrigeration equipment to generate a simulation grid, generating boundary conditions according to the physical parameter information and the equipment operation information, and generating a preliminary simulation model based on a preset Nvidia SimNet platform according to the digital model of the refrigeration equipment, the simulation grid and the boundary conditions; Generate a second fluid mechanics model, a second heat conduction model and a second structural mechanics model based on a preset physical field model according to the preliminary simulation model; A coupled simulation model is generated according to the coupling of the second fluid mechanics model, the second heat conduction model and the second structural mechanics model, and a numerical solution is performed on the coupled simulation model to generate a refrigeration equipment simulation model.

3. The intelligent monitoring method for refrigeration equipment in a refrigeration unit according to claim 2 is characterized in that: generating operation prediction information according to the refrigeration equipment simulation model; Importing the operation prediction information into the refrigeration equipment digital model to generate visual prediction information includes: Acquire simulation result information generated according to the refrigeration equipment simulation model; Training a prediction neural network model through a physical information neural network according to the simulation result information, wherein the physical information neural network is pre-set on the Nvidia SimNet platform; Inputting the real-time monitoring data into the prediction neural network model to generate operation prediction information; The operation prediction information is imported into the digital model of the refrigeration equipment to generate visualized prediction information.

4. The intelligent monitoring method for refrigeration equipment in a refrigeration unit according to claim 3 is characterized in that: Importing the operation prediction information into the digital model of the refrigeration equipment to generate visual prediction information includes: Comparing and analyzing the operation prediction information and the simulation result information to generate a deviation value, and determining whether the deviation value is less than a preset deviation threshold; If the judgment is no, the prediction neural network model is corrected according to the deviation value, and a corrected neural network model is generated; Inputting the real-time monitoring data into the correction neural network model to generate correction prediction information; Importing the corrected prediction information into the digital model of the refrigeration equipment to generate visualized prediction information; If the judgment is yes, the operation prediction information is imported into the digital model of the refrigeration equipment to generate visualized prediction information.

5. The method for intelligently monitoring refrigeration equipment in a refrigeration unit according to claim 4, characterized in that: The operation prediction information and simulation result information include a time point set, a component type set, and a parameter type set. A prediction matrix is ​​generated according to the operation prediction information, and a simulation matrix is ​​generated according to the simulation result information. A deviation value is generated according to the prediction matrix and the simulation matrix based on the following formula: ; Where E is the deviation value, α is the preset first weight parameter, T is the total number of time points in the time point set, k is the ordinal number of the time point, N is the total number of component types in the component type set, i is the ordinal number of the component type, Mi is the total number of parameter types in the parameter type set of the i-th component, j is the ordinal number of the parameter type, Wij is the preset weight matrix, P i，j，k is the predicted value of parameter type j of component type i at time point k, S i，j，k is the simulation value of parameter type j of component type i at time point k; is the preset second weight parameter.

6. The intelligent monitoring method for refrigeration equipment in a refrigeration unit according to claim 4 or 5, characterized in that: Generating an operation supervision report according to the operation prediction information and the visual prediction information, including: Generate a preliminary analysis report based on the operation prediction information and the simulation result information; Generate an error analysis report based on the Nvidia SimNet platform according to the deviation value and the historical operation data; An operation supervision report is generated based on the preliminary analysis report, the error analysis report and the visualized prediction information.

7. An intelligent monitoring system for refrigeration equipment in a refrigeration unit, the intelligent monitoring system for refrigeration equipment in a refrigeration unit applying the method according to any one of claims 1 to 6, characterized in that: include: A digital model generation module, used to obtain physical parameter information and equipment operation information of the refrigeration equipment, and generate a digital model of the refrigeration equipment based on a preset Nvidia Omniverse platform according to the physical parameter information and the equipment operation information; A simulation model generation module, used for importing the digital model of the refrigeration equipment into a preset Nvidia SimNet platform to generate a simulation model of the refrigeration equipment; A prediction information generation module, used to generate operation prediction information according to the refrigeration equipment simulation model; Importing the operation prediction information into the refrigeration equipment digital model to generate visualized prediction information; A supervision report generating module, used for generating an operation supervision report according to the operation prediction information and the visual prediction information; The digital model generation module is also used to: obtain physical parameter information of the refrigeration equipment, wherein the physical parameter information includes basic structure data, component material data, physical behavior data and dynamic behavior data; generate a three-dimensional framework based on the preset Nvidia Omniverse platform according to the basic structure data, and generate a physical framework based on the three-dimensional framework according to the component material data; import the physical behavior data and the dynamic behavior data into the physical framework to generate a framework model; obtain equipment operation information of the refrigeration equipment, wherein the equipment operation information includes historical operation data, historical fault data and real-time monitoring data; import the historical operation data and the historical fault data into the framework model to generate a modified framework model; generate a complete digital model based on the modified framework model in combination with the real-time monitoring data; generate a first fluid mechanics model, a first heat conduction model and a first structural mechanics model based on the complete digital model, and generate a digital model of the refrigeration equipment according to the coupling of the first fluid mechanics model, the first heat conduction model and the first structural mechanics model.

Images