Big data energy efficiency management system for digital twin smart industrial park based on internet of things

Abstract

A big data energy efficiency management system for a digital twin smart industrial park based on the Internet of Things, which system belongs to the technical field of smart industrial parks, and comprises a data collection module, a data processing module, a model training module, a testing and optimization module, a prediction and evaluation module, an energy efficiency management module, and a feedback and display module. The existing problem of the big data energy efficiency management effect of a smart industrial park being poor, which results from the inability to grasp the big data energy efficiency condition of the smart industrial park in a timely manner due to the inability to monitor the big data energy efficiency of the smart industrial park in real time, is solved. A digital twin model of a smart industrial park is used to simulate, predict and evaluate energy efficiency characterization data of the smart industrial park and perform big data energy efficiency management on a digital twin smart industrial park, such that the big data energy efficiency of the smart industrial park can be monitored in real time, and the big data energy efficiency condition of the smart industrial park can be grasped in a timely manner, thereby improving the big data energy efficiency management effect of the smart industrial park.

Description

IoT-based digital twin smart industrial park big data energy efficiency management system Technical Field

[0001] This invention relates to the field of smart industrial park technology, specifically to a digital twin smart industrial park big data energy efficiency management system based on the Internet of Things. Background Technology

[0002] Digital twin refers to the process of first establishing a digital twin model corresponding to a physical entity, and then using the physical entity's action data to change the state of the digital twin model, thereby enabling the digital twin model to change in accordance with the changes in the state of the physical entity. With the development of technology, digital twin technology has also been incorporated into the management and use of smart industrial parks. By simulating smart industrial parks in real time, it facilitates the intelligent management of smart industrial parks.

[0003] Chinese patent CN117408438A discloses a method and system for extracting inefficient land use in industrial parks based on multi-source big data. The method includes the following steps: acquiring remote sensing image data of the industrial park and preprocessing the nighttime remote sensing data; inferring the land use efficiency of the industrial park based on nighttime remote sensing data, land cover images, and high-resolution satellite images within a preset time period; acquiring the update status of the industrial park's official website and business registration data, and determining the activity status of the industrial park based on the website update status and business registration data; outputting the activity status conclusion of the industrial park and the location and area information of low-utilization areas based on the land use efficiency and activity status of the industrial park; enabling a comprehensive judgment of the land use situation of the industrial park. However, this patent has the following drawbacks:

[0004] The existing methods cannot monitor the energy efficiency of big data in smart industrial parks in real time, resulting in an inability to grasp the energy efficiency status of big data in smart industrial parks in a timely manner, and thus poor management of big data energy efficiency in smart industrial parks. Summary of the Invention

[0005] The purpose of this invention is to provide a digital twin-based smart industrial park big data energy efficiency management system based on the Internet of Things, which can monitor the energy efficiency of smart industrial park big data in real time, promptly grasp the energy efficiency status of smart industrial park big data, improve the management effect of smart industrial park big data energy efficiency, and solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] The IoT-based digital twin smart industrial park big data energy efficiency management system includes:

[0008] The data acquisition module is used to collect real-time data on water consumption, electricity consumption, oil consumption, and gas consumption in the smart industrial park, and to determine the real-time energy efficiency data of the smart industrial park based on the Internet of Things.

[0009] The data processing module is used to retrieve, sort, and integrate real-time energy efficiency data of smart industrial parks to determine the energy efficiency characterization data of smart industrial parks based on the Internet of Things.

[0010] The model training module is used to train a model architecture suitable for big data energy efficiency management in smart industrial parks based on the training set, and to determine a smart industrial park digital twin model suitable for big data energy efficiency management in smart industrial parks.

[0011] The test optimization module is used to perform performance testing and adjustment optimization on the digital twin model of the smart industrial park, and to determine a more suitable digital twin model for the smart industrial park.

[0012] The prediction and evaluation module is used to simulate and predict the energy efficiency characterization data of the smart industrial park using the digital twin model of the smart industrial park, and to determine the big data energy efficiency prediction and evaluation results of the digital twin smart industrial park.

[0013] The energy efficiency management module is used to perform big data-based energy efficiency management for digital twin smart industrial parks based on the big data energy efficiency management solution for digital twin smart industrial parks.

[0014] The feedback and display module is used to provide real-time feedback and visualization of the energy efficiency of big data in the digital twin smart industrial park, enabling real-time monitoring of the energy efficiency of big data in the digital twin smart industrial park.

[0015] Preferably, the data acquisition module includes:

[0016] The water usage data collection unit is used to collect water usage data in the smart industrial park in real time and determine the real-time water usage data of the smart industrial park based on the Internet of Things.

[0017] The power consumption data acquisition unit is used to collect real-time power consumption data in the smart industrial park and determine the real-time power consumption data of the smart industrial park based on the Internet of Things.

[0018] The oil consumption data collection unit is used to collect oil consumption data in real time within the smart industrial park and determine real-time oil consumption data for the smart industrial park based on the Internet of Things.

[0019] The gas consumption data collection unit is used to collect gas consumption data in the smart industrial park in real time and determine the real-time gas consumption data of the smart industrial park based on the Internet of Things.

[0020] Among them, based on the collected real-time data on water consumption, electricity consumption, oil consumption, and gas consumption, real-time energy efficiency data for smart industrial parks based on the Internet of Things were determined.

[0021] Preferably, the data acquisition module further includes:

[0022] The real-time monitoring module is used to monitor the time interval between each data collection moment of the water consumption collection unit, electricity consumption collection unit, oil consumption collection unit and gas consumption collection unit in real time;

[0023] The first data acquisition stability parameter acquisition module is used to acquire the first data acquisition stability parameter corresponding to the water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit, and gas consumption acquisition unit by utilizing the time interval between each data acquisition moment of the water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit, and gas consumption acquisition unit; wherein, the first data acquisition stability parameter is acquired by the following formula:

[0024] Among them, R 01 The first data acquisition stability parameter is represented by n; n represents the number of time intervals between the acquisition times corresponding to the water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit, and gas consumption acquisition unit; T i T represents the duration corresponding to the i-th time interval; i-1 T represents the duration of the (i-1)th time interval; maxb and T minb These represent the maximum and minimum values ​​within the time interval, respectively; T y This represents the preset time interval reference value; r represents the adjustment parameter.

[0025] The data acquisition unit marking module is used to mark the data acquisition unit whose first data acquisition stability parameter is lower than the preset first stability parameter threshold when the first data acquisition stability parameter corresponding to the water acquisition unit, electricity acquisition unit, oil acquisition unit and / or gas acquisition unit is lower than the preset first stability parameter threshold.

[0026] The data acquisition unit anomaly judgment module is used to determine whether there is an operational anomaly in the water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit and / or gas consumption acquisition unit starting from the time when the water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit and / or gas consumption acquisition unit is marked, and to issue an operational anomaly alarm when there is an operational anomaly in the water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit and / or gas consumption acquisition unit.

[0027] Preferably, the data acquisition unit anomaly detection module includes:

[0028] The real-time acquisition module is used to collect data from the marked water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit and / or gas consumption acquisition unit in real time.

[0029] The maximum value acquisition module is used to extract the maximum data acquisition time interval of the marked water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit and / or gas consumption acquisition unit;

[0030] The second data acquisition stability parameter acquisition module is used to combine the maximum data acquisition time interval of the marked water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit, and / or gas consumption acquisition unit with the second data acquisition stability parameter corresponding to the water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit, and / or gas consumption acquisition unit; wherein, the second data acquisition stability parameter is obtained by the following formula:

[0031] Among them, R 02 R represents the stability parameter of the second data acquisition. y T represents the preset threshold value for the first stability parameter; maxh This indicates the maximum data acquisition time interval for the marked water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit, and / or gas consumption acquisition unit; T b The value of the data acquisition time interval for the marked water consumption, electricity consumption, oil consumption, and / or gas consumption data acquisition units is denoted as ; m represents the number of data acquisition time intervals for the marked water consumption, electricity consumption, oil consumption, and / or gas consumption data acquisition units; T j T represents the time length corresponding to the j-th data acquisition time interval; lst The duration of the last data acquisition time interval preceding the marked water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit and / or gas consumption acquisition unit;

[0032] The data acquisition operation anomaly determination module is used to determine whether the water acquisition unit, electricity acquisition unit, oil acquisition unit and / or gas acquisition unit with the second data acquisition stability parameter lower than the preset second stability parameter threshold has a data acquisition operation anomaly when the second data acquisition stability parameter is lower than the preset second stability parameter threshold.

[0033] The data acquisition operation abnormality alarm module is used to issue an operation abnormality alarm when there is an abnormality in the data acquisition unit, the electricity acquisition unit, the oil acquisition unit and / or the gas acquisition unit.

[0034] Preferably, the data processing module includes:

[0035] The data retrieval unit is used to retrieve real-time energy efficiency data for smart industrial parks.

[0036] Obtain real-time energy efficiency data for smart industrial parks based on the Internet of Things;

[0037] Based on the sequential retrieval method, real-time energy efficiency data of smart industrial parks are retrieved;

[0038] Check the consistency of real-time energy efficiency data in the smart industrial park;

[0039] Remove data from the real-time energy efficiency data of smart industrial parks that are outside the normal range, logically unreasonable, or contradictory.

[0040] Handle invalid and missing values ​​in real-time energy efficiency data of smart industrial parks;

[0041] Remove invalid and missing data from the real-time energy efficiency data of smart industrial parks that are not valuable for big data energy efficiency management of smart industrial parks;

[0042] Identify real-time energy efficiency data for smart industrial parks that are valuable for big data-driven energy efficiency management in smart industrial parks;

[0043] The data sorting unit is used to sort the retrieved real-time energy efficiency data of the smart industrial park.

[0044] Obtain real-time energy efficiency data of smart industrial parks that is valuable for big data energy efficiency management in smart industrial parks after retrieval;

[0045] Based on the internal sorting method, the retrieved real-time energy efficiency data of smart industrial parks that are valuable for big data energy efficiency management in smart industrial parks are sorted.

[0046] Real-time energy efficiency data of smart industrial parks with a sorted order were determined;

[0047] The data fusion unit is used to fuse the sorted real-time energy efficiency data of the smart industrial park;

[0048] Acquire real-time energy efficiency data of smart industrial parks in a sorted order;

[0049] Real-time energy efficiency data from smart industrial parks that are arranged in a specific order are integrated.

[0050] Energy efficiency characterization data for smart industrial parks based on the Internet of Things were determined.

[0051] Preferably, the model training module includes:

[0052] Data storage unit is used to store pre-set historical energy efficiency data of the smart industrial park;

[0053] Based on the big data energy efficiency management needs of IoT-based digital twin smart industrial parks, historical energy efficiency data of smart industrial parks are pre-set and stored.

[0054] Data partitioning units are used to partition pre-defined historical energy efficiency data for smart industrial parks;

[0055] Obtain pre-set historical energy efficiency data for smart industrial parks;

[0056] The pre-defined historical energy efficiency data of the smart industrial park is divided into segments;

[0057] The training and test sets were determined;

[0058] The model selection unit is used to select the model architecture;

[0059] Based on the energy efficiency management requirements of big data in smart industrial parks using IoT-based digital twins, a model architecture suitable for big data energy efficiency management in smart industrial parks was selected from multiple model architectures.

[0060] The model training unit is used to build a digital twin model of a smart industrial park.

[0061] Obtain the training set;

[0062] Obtain a model architecture suitable for big data energy efficiency management in smart industrial parks;

[0063] Based on the training set, a model architecture suitable for big data energy efficiency management in smart industrial parks is trained.

[0064] Determine a digital twin model for smart industrial parks that is suitable for big data-driven energy efficiency management in smart industrial parks.

[0065] Preferably, the test optimization module includes:

[0066] The model testing unit is used to test the performance of the digital twin model of the smart industrial park.

[0067] Get the test set;

[0068] Obtain a digital twin model of a smart industrial park;

[0069] Performance testing of the digital twin model of a smart industrial park was conducted based on the test set.

[0070] The performance test results of the digital twin model of the smart industrial park were determined;

[0071] The adjustment and optimization unit is used to adjust and optimize the digital twin model of the smart industrial park;

[0072] Obtain the performance test results of the digital twin model of the smart industrial park;

[0073] In-depth analysis and related findings were conducted on the performance test results of the digital twin model of the smart industrial park.

[0074] A plan for adjusting and optimizing the digital twin model of the smart industrial park was determined.

[0075] The digital twin model of the smart industrial park is adjusted and optimized based on the adjustment and optimization scheme of the digital twin model of the smart industrial park;

[0076] A more suitable digital twin model for smart industrial parks was identified.

[0077] Preferably, the prediction and evaluation module includes:

[0078] The data extraction unit is used to extract energy efficiency characterization data from smart industrial parks.

[0079] Based on the energy efficiency management needs of IoT-based digital twin smart industrial parks, energy efficiency characterization data of IoT-based smart industrial parks are extracted.

[0080] The predictive evaluation unit is used to predict and evaluate the energy efficiency characterization data of smart industrial parks.

[0081] Obtain the extracted energy efficiency characterization data of the smart industrial park based on the Internet of Things;

[0082] To obtain a more suitable digital twin model for smart industrial parks;

[0083] Input the energy efficiency characterization data of the smart industrial park into the digital twin model of the smart industrial park;

[0084] A digital twin model of a smart industrial park is used to simulate and predict the energy efficiency characterization data of the smart industrial park.

[0085] The results of big data-driven energy efficiency prediction and assessment for the digital twin smart industrial park were determined.

[0086] Preferably, the energy efficiency management module includes:

[0087] The management formulation unit is used to formulate big data energy efficiency management solutions for digital twin smart industrial parks;

[0088] Obtain the energy efficiency prediction and assessment results of the digital twin smart industrial park using big data;

[0089] Correlation analysis was conducted on the energy efficiency prediction and assessment results of digital twin smart industrial parks based on big data.

[0090] A big data-driven energy efficiency management solution for a digital twin smart industrial park was determined.

[0091] The energy efficiency management unit is used for big data-driven energy efficiency management of digital twin smart industrial parks.

[0092] Obtain a big data-driven energy efficiency management solution for a digital twin smart industrial park;

[0093] A big data-based energy efficiency management solution for digital twin smart industrial parks is used to manage energy efficiency in digital twin smart industrial parks.

[0094] Preferably, the feedback display module includes:

[0095] The real-time feedback unit is used to provide real-time feedback on the energy efficiency of big data in the digital twin smart industrial park.

[0096] Obtain the energy efficiency prediction and assessment results of the digital twin smart industrial park using big data;

[0097] Real-time feedback on the energy efficiency of digital twin smart industrial parks based on big data energy efficiency prediction and evaluation results;

[0098] The energy efficiency feedback mechanism of big data in the digital twin smart industrial park was determined.

[0099] The visual display unit is used to visualize the energy efficiency feedback of big data in the digital twin smart industrial park;

[0100] Obtain energy efficiency feedback from big data in digital twin smart industrial parks;

[0101] The system provides a visual representation of the energy efficiency feedback from big data in the digital twin smart industrial park, enabling real-time monitoring of the park's energy efficiency.

[0102] Compared with the prior art, the beneficial effects of the present invention are:

[0103] This invention determines real-time energy efficiency data for smart industrial parks based on the Internet of Things (IoT) by collecting real-time data on water, electricity, oil, and gas consumption within the park. Through retrieval, sorting, and fusion of this data, it identifies IoT-based energy efficiency characterization data. A digital twin model of the smart industrial park is then used to simulate and predict the energy efficiency characterization data, resulting in a big data energy efficiency prediction and evaluation result. Furthermore, a big data energy efficiency management solution for the digital twin smart industrial park is implemented to manage the energy efficiency of the digital twin smart industrial park. Real-time feedback and visualization of the big data energy efficiency of the digital twin smart industrial park are provided, allowing for real-time monitoring and understanding of the big data energy efficiency situation, thus improving the effectiveness of big data energy efficiency management in smart industrial parks. Attached Figure Description

[0104] Figure 1 is a module structure diagram of the IoT-based digital twin smart industrial park big data energy efficiency management system of the present invention. Detailed Implementation

[0105] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0106] To address the problem that existing methods cannot monitor the energy efficiency of big data in smart industrial parks in real time, resulting in a lack of timely understanding of the energy efficiency status and poor management of big data energy efficiency in smart industrial parks, please refer to Figure 1. This embodiment provides the following technical solution:

[0107] The IoT-based digital twin smart industrial park big data energy efficiency management system includes: a data acquisition module, a data processing module, a model training module, a testing and optimization module, a prediction and evaluation module, an energy efficiency management module, and a feedback display module.

[0108] It should be noted that through the interactive communication between the data acquisition module, data processing module, model training module, testing and optimization module, prediction and evaluation module, energy efficiency management module, and feedback display module, the energy efficiency of big data in smart industrial parks can be monitored in real time, enabling timely understanding of the energy efficiency status of big data in smart industrial parks and improving the effectiveness of big data energy efficiency management in smart industrial parks.

[0109] The data acquisition module is used to collect real-time data on water consumption, electricity consumption, oil consumption, and gas consumption in the smart industrial park, and to determine the real-time energy efficiency data of the smart industrial park based on the Internet of Things.

[0110] In this embodiment, as a preferred technical solution of the present invention, the data acquisition module includes:

[0111] The water usage data collection unit is used to collect water usage data in the smart industrial park in real time and determine the real-time water usage data of the smart industrial park based on the Internet of Things.

[0112] The power consumption data acquisition unit is used to collect real-time power consumption data in the smart industrial park and determine the real-time power consumption data of the smart industrial park based on the Internet of Things.

[0113] The oil consumption data collection unit is used to collect oil consumption data in real time within the smart industrial park and determine real-time oil consumption data for the smart industrial park based on the Internet of Things.

[0114] The gas consumption data collection unit is used to collect gas consumption data in the smart industrial park in real time and determine the real-time gas consumption data of the smart industrial park based on the Internet of Things.

[0115] Among them, based on the collected real-time data on water consumption, electricity consumption, oil consumption, and gas consumption, real-time energy efficiency data for smart industrial parks based on the Internet of Things were determined.

[0116] The data processing module is used to retrieve, sort, and integrate real-time energy efficiency data of smart industrial parks to determine energy efficiency characterization data of smart industrial parks based on the Internet of Things.

[0117] Specifically, the data acquisition module also includes:

[0118] The real-time monitoring module is used to monitor the time interval between each data collection moment of the water consumption collection unit, electricity consumption collection unit, oil consumption collection unit and gas consumption collection unit in real time;

[0119] The first data acquisition stability parameter acquisition module is used to acquire the first data acquisition stability parameter corresponding to the water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit, and gas consumption acquisition unit by utilizing the time interval between each data acquisition moment of the water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit, and gas consumption acquisition unit; wherein, the first data acquisition stability parameter is acquired by the following formula:

[0120] Among them, R 01The first data acquisition stability parameter is represented by n; n represents the number of time intervals between the acquisition times corresponding to the water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit, and gas consumption acquisition unit; T i T represents the duration corresponding to the i-th time interval; i-1 T represents the duration of the (i-1)th time interval; maxb and T minb These represent the maximum and minimum values ​​within the time interval, respectively; T y This represents the preset time interval reference value; r represents the adjustment parameter.

[0121] The data acquisition unit marking module is used to mark the data acquisition unit whose first data acquisition stability parameter is lower than the preset first stability parameter threshold when the first data acquisition stability parameter corresponding to the water acquisition unit, electricity acquisition unit, oil acquisition unit and / or gas acquisition unit is lower than the preset first stability parameter threshold.

[0122] The data acquisition unit anomaly judgment module is used to determine whether there is an operational anomaly in the water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit and / or gas consumption acquisition unit starting from the time when the water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit and / or gas consumption acquisition unit is marked, and to issue an operational anomaly alarm when there is an operational anomaly in the water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit and / or gas consumption acquisition unit.

[0123] The technical effects of the above solution are as follows: the real-time monitoring module can continuously track the data acquisition time intervals between various data acquisition units (water, electricity, oil, and gas), ensuring the real-time nature and continuity of data acquisition. Simultaneously, the first data acquisition stability parameter acquisition module can calculate the data acquisition stability parameters based on these time intervals, thereby evaluating the stability and reliability of the data acquisition.

[0124] When the first data acquisition stability parameter of a data acquisition unit falls below a preset first stability parameter threshold, the acquisition unit marking module will mark it. This helps the system quickly identify data acquisition units that may have problems, facilitating subsequent processing and troubleshooting.

[0125] The data acquisition unit anomaly detection module can perform further analysis and judgment based on the tagged data acquisition units to determine whether there are any abnormalities in their acquisition operation. If an anomaly is found, the system will issue an operational anomaly alarm and promptly notify relevant personnel for handling, thereby preventing the problem from escalating or affecting the normal operation of other system modules.

[0126] When calculating the stability parameters of the first data acquisition, an adjustment parameter r is introduced, which allows the system to adjust and optimize the calculation of the stability parameters according to actual needs, so as to adapt to different application scenarios and requirements.

[0127] The entire technical solution covers data collection and monitoring of multiple aspects such as water, electricity, oil, and gas consumption, ensuring a comprehensive understanding and control of system resource consumption, and helping to achieve more refined and intelligent resource management.

[0128] In summary, this technical solution achieves comprehensive monitoring and intelligent management of system resource consumption by real-time monitoring and evaluation of the stability of the data acquisition unit and issuing alarms when anomalies are detected, thereby improving the stability and reliability of the system.

[0129] Specifically, the data acquisition unit anomaly detection module includes:

[0130] The real-time acquisition module is used to collect data from the marked water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit and / or gas consumption acquisition unit in real time.

[0131] The maximum value acquisition module is used to extract the maximum data acquisition time interval of the marked water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit and / or gas consumption acquisition unit;

[0132] The second data acquisition stability parameter acquisition module is used to combine the maximum data acquisition time interval of the marked water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit, and / or gas consumption acquisition unit with the second data acquisition stability parameter corresponding to the water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit, and / or gas consumption acquisition unit; wherein, the second data acquisition stability parameter is obtained by the following formula:

[0133] Among them, R 02 R represents the stability parameter of the second data acquisition. y T represents the preset threshold value for the first stability parameter; maxh This indicates the maximum data acquisition time interval for the marked water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit, and / or gas consumption acquisition unit; T b The value of the data acquisition time interval for the marked water consumption, electricity consumption, oil consumption, and / or gas consumption data acquisition units is denoted as ; m represents the number of data acquisition time intervals for the marked water consumption, electricity consumption, oil consumption, and / or gas consumption data acquisition units; T j T represents the time length corresponding to the j-th data acquisition time interval; lstThe duration of the last data acquisition time interval preceding the marked water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit and / or gas consumption acquisition unit;

[0134] The data acquisition operation anomaly determination module is used to determine whether the water acquisition unit, electricity acquisition unit, oil acquisition unit and / or gas acquisition unit with the second data acquisition stability parameter lower than the preset second stability parameter threshold has a data acquisition operation anomaly when the second data acquisition stability parameter is lower than the preset second stability parameter threshold.

[0135] The data acquisition operation abnormality alarm module is used to issue an operation abnormality alarm when there is an abnormality in the data acquisition unit, the electricity acquisition unit, the oil acquisition unit and / or the gas acquisition unit.

[0136] The technical effect of the above solution is that, through the real-time acquisition module and the maximum value acquisition module, the system can accurately capture the data acquisition time and the maximum value of the time interval of the marked water consumption acquisition unit, electricity consumption acquisition unit, oil consumption acquisition unit, and / or gas consumption acquisition unit. This helps the system to more accurately identify abnormal data acquisition units.

[0137] The second data acquisition stability parameter acquisition module not only considers the maximum value of the data acquisition time interval, but also combines the average value and number of other time intervals, as well as the length of the last time interval before the marking, to calculate the second data acquisition stability parameter. This dynamic evaluation method can more comprehensively and accurately reflect the stability of data acquisition.

[0138] The system uses a preset second stability parameter threshold to determine whether data acquisition is abnormal. This threshold can be adjusted according to actual needs to meet the stability requirements of different application scenarios.

[0139] When the system detects that the second data acquisition stability parameter of a data acquisition unit is lower than the preset second stability parameter threshold, the data acquisition operation anomaly detection module will immediately determine that the unit has a data acquisition operation anomaly and trigger the data acquisition operation anomaly alarm module to issue an alarm. This helps to promptly detect and handle faults in the data acquisition unit, ensuring the accuracy and reliability of data acquisition.

[0140] By implementing the above technical solutions, the system can monitor and evaluate the stability of the data acquisition unit in real time, and promptly alarm and handle any anomalies detected. This helps reduce the risk of a decline in overall system stability due to data acquisition unit failures, thereby improving the reliability and stability of the entire system.

[0141] In summary, the above technical solution achieves comprehensive monitoring and intelligent management of data acquisition units by accurately identifying abnormal acquisition units, dynamically evaluating data acquisition stability, flexibly adjusting stability thresholds, providing timely alarms and fault handling, and improving overall system stability, thus ensuring the accuracy and reliability of data acquisition.

[0142] In this embodiment, as a preferred technical solution of the present invention, the data processing module includes:

[0143] The data retrieval unit is used to retrieve real-time energy efficiency data for smart industrial parks.

[0144] Obtain real-time energy efficiency data for smart industrial parks based on the Internet of Things;

[0145] Based on the sequential retrieval method, real-time energy efficiency data of smart industrial parks are retrieved;

[0146] Check the consistency of real-time energy efficiency data in the smart industrial park;

[0147] Remove data from the real-time energy efficiency data of smart industrial parks that are outside the normal range, logically unreasonable, or contradictory.

[0148] Handle invalid and missing values ​​in real-time energy efficiency data of smart industrial parks;

[0149] Remove invalid and missing data from the real-time energy efficiency data of smart industrial parks that are not valuable for big data energy efficiency management of smart industrial parks;

[0150] Identify real-time energy efficiency data for smart industrial parks that are valuable for big data-driven energy efficiency management in smart industrial parks;

[0151] The data sorting unit is used to sort the retrieved real-time energy efficiency data of the smart industrial park.

[0152] Obtain real-time energy efficiency data of smart industrial parks that is valuable for big data energy efficiency management in smart industrial parks after retrieval;

[0153] Based on the internal sorting method, the retrieved real-time energy efficiency data of smart industrial parks that are valuable for big data energy efficiency management in smart industrial parks are sorted.

[0154] Real-time energy efficiency data of smart industrial parks with a sorted order were determined;

[0155] The data fusion unit is used to fuse the sorted real-time energy efficiency data of the smart industrial park;

[0156] Acquire real-time energy efficiency data of smart industrial parks in a sorted order;

[0157] Real-time energy efficiency data from smart industrial parks that are arranged in a specific order are integrated.

[0158] Energy efficiency characterization data for smart industrial parks based on the Internet of Things were determined.

[0159] Among them, the model training module is used to train the model architecture suitable for big data energy efficiency management in smart industrial parks based on the training set, and to determine the smart industrial park digital twin model suitable for big data energy efficiency management in smart industrial parks.

[0160] In this embodiment, as a preferred technical solution of the present invention, the model training module includes:

[0161] Data storage unit is used to store pre-set historical energy efficiency data of the smart industrial park;

[0162] Based on the big data energy efficiency management needs of IoT-based digital twin smart industrial parks, historical energy efficiency data of smart industrial parks are pre-set and stored.

[0163] Data partitioning units are used to partition pre-defined historical energy efficiency data for smart industrial parks;

[0164] Obtain pre-set historical energy efficiency data for smart industrial parks;

[0165] The pre-defined historical energy efficiency data of the smart industrial park is divided into segments;

[0166] The training and test sets were determined;

[0167] The model selection unit is used to select the model architecture;

[0168] Based on the energy efficiency management requirements of big data in smart industrial parks using IoT-based digital twins, a model architecture suitable for big data energy efficiency management in smart industrial parks was selected from multiple model architectures.

[0169] The model training unit is used to build a digital twin model of a smart industrial park.

[0170] Obtain the training set;

[0171] Obtain a model architecture suitable for big data energy efficiency management in smart industrial parks;

[0172] Based on the training set, a model architecture suitable for big data energy efficiency management in smart industrial parks is trained.

[0173] Determine a digital twin model for smart industrial parks that is suitable for big data-driven energy efficiency management in smart industrial parks.

[0174] The testing and optimization module is used to perform performance testing and adjustment optimization on the digital twin model of the smart industrial park, and to determine a more suitable digital twin model for the smart industrial park.

[0175] In this embodiment, as a preferred technical solution of the present invention, the test optimization module includes:

[0176] The model testing unit is used to test the performance of the digital twin model of the smart industrial park.

[0177] Get the test set;

[0178] Obtain a digital twin model of a smart industrial park;

[0179] Performance testing of the digital twin model of a smart industrial park was conducted based on the test set.

[0180] The performance test results of the digital twin model of the smart industrial park were determined;

[0181] The adjustment and optimization unit is used to adjust and optimize the digital twin model of the smart industrial park;

[0182] Obtain the performance test results of the digital twin model of the smart industrial park;

[0183] In-depth analysis and related findings were conducted on the performance test results of the digital twin model of the smart industrial park.

[0184] A plan for adjusting and optimizing the digital twin model of the smart industrial park was determined.

[0185] The digital twin model of the smart industrial park is adjusted and optimized based on the adjustment and optimization scheme of the digital twin model of the smart industrial park;

[0186] A more suitable digital twin model for smart industrial parks was identified.

[0187] Among them, the prediction and evaluation module is used to simulate and predict the energy efficiency characterization data of the smart industrial park using the digital twin model of the smart industrial park, and determine the big data energy efficiency prediction and evaluation results of the digital twin smart industrial park.

[0188] In this embodiment, as a preferred technical solution of the present invention, the prediction and evaluation module includes:

[0189] The data extraction unit is used to extract energy efficiency characterization data from smart industrial parks.

[0190] Based on the energy efficiency management needs of IoT-based digital twin smart industrial parks, energy efficiency characterization data of IoT-based smart industrial parks are extracted.

[0191] The predictive evaluation unit is used to predict and evaluate the energy efficiency characterization data of smart industrial parks.

[0192] Obtain the extracted energy efficiency characterization data of the smart industrial park based on the Internet of Things;

[0193] To obtain a more suitable digital twin model for smart industrial parks;

[0194] Input the energy efficiency characterization data of the smart industrial park into the digital twin model of the smart industrial park;

[0195] A digital twin model of a smart industrial park is used to simulate and predict the energy efficiency characterization data of the smart industrial park.

[0196] The results of big data-driven energy efficiency prediction and assessment for the digital twin smart industrial park were determined.

[0197] Among them, the energy efficiency management module is used to perform big data energy efficiency management of digital twin smart industrial parks based on the big data energy efficiency management solution of digital twin smart industrial parks;

[0198] In this embodiment, as a preferred technical solution of the present invention, the energy efficiency management module includes:

[0199] The management formulation unit is used to formulate big data energy efficiency management solutions for digital twin smart industrial parks;

[0200] Obtain the energy efficiency prediction and assessment results of the digital twin smart industrial park using big data;

[0201] Correlation analysis was conducted on the energy efficiency prediction and assessment results of digital twin smart industrial parks based on big data.

[0202] A big data-driven energy efficiency management solution for a digital twin smart industrial park was determined.

[0203] The energy efficiency management unit is used for big data-driven energy efficiency management of digital twin smart industrial parks.

[0204] Obtain a big data-driven energy efficiency management solution for a digital twin smart industrial park;

[0205] A big data-based energy efficiency management solution for digital twin smart industrial parks is used to manage energy efficiency in digital twin smart industrial parks.

[0206] The feedback and display module is used to provide real-time feedback and visualization of the energy efficiency of big data in the digital twin smart industrial park, enabling real-time monitoring of the energy efficiency of big data in the digital twin smart industrial park.

[0207] In this embodiment, as a preferred technical solution of the present invention, the feedback display module includes:

[0208] The real-time feedback unit is used to provide real-time feedback on the energy efficiency of big data in the digital twin smart industrial park.

[0209] Obtain the energy efficiency prediction and assessment results of the digital twin smart industrial park using big data;

[0210] Real-time feedback on the energy efficiency of digital twin smart industrial parks based on big data energy efficiency prediction and evaluation results;

[0211] The energy efficiency feedback mechanism of big data in the digital twin smart industrial park was determined.

[0212] The visual display unit is used to visualize the energy efficiency feedback of big data in the digital twin smart industrial park;

[0213] Obtain energy efficiency feedback from big data in digital twin smart industrial parks;

[0214] The system provides a visual representation of the energy efficiency feedback from big data in the digital twin smart industrial park, enabling real-time monitoring of the park's energy efficiency.

[0215] Therefore, by collecting real-time data on water consumption, electricity consumption, oil consumption, and gas consumption within the smart industrial park, real-time energy efficiency data based on the Internet of Things (IoT) is determined. Through retrieval, sorting, and fusion of this real-time energy efficiency data, IoT-based energy efficiency characterization data is identified. A digital twin model of the smart industrial park is then used to simulate and predict the energy efficiency characterization data, determining the big data energy efficiency prediction and evaluation results. Furthermore, a big data energy efficiency management solution for the digital twin smart industrial park is implemented to manage the energy efficiency of the digital twin smart industrial park. Simultaneously, real-time feedback and visualization of the big data energy efficiency of the digital twin smart industrial park are provided, allowing for real-time monitoring of the big data energy efficiency situation and improving the effectiveness of big data energy efficiency management in the smart industrial park.

[0216] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0217] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A digital twin intelligent industrial park big data energy efficiency management system based on the Internet of Things, comprising a data acquisition module, a data processing module, a model training module, a test optimization module, a prediction evaluation module, an energy efficiency management module, and a feedback display module, characterized in that, The data acquisition module comprises: With water acquisition unit, with electricity acquisition unit, with oil acquisition unit and with gas acquisition unit; Among them, based on the collected water real-time data, electricity real-time data, oil real-time data and gas real-time data, the real-time data of the energy efficiency of the smart industrial park based on the Internet of Things is determined; The data acquisition module further comprises: Real-time monitoring module, for real-time monitoring the time interval between each data acquisition time of the water acquisition unit, electricity acquisition unit, oil acquisition unit and gas acquisition unit; The first data collection stability parameter acquisition module is configured to acquire the first data collection stability parameters corresponding to the water collection unit, the electricity collection unit, the oil collection unit and the gas collection unit by using the time intervals between each data collection time of the water collection unit, the electricity collection unit, the oil collection unit and the gas collection unit; wherein the first data collection stability parameters are acquired by the following formula: wherein R 01 represents the first data collection stability parameter; n represents the number of time intervals between the collection time points corresponding to the water consumption collection unit, the electricity consumption collection unit, the oil consumption collection unit, and the gas consumption collection unit; T i represents the time length corresponding to the i-th time interval; T i-1 represents the time length corresponding to the i-1-th time interval; T maxb and T minb respectively represent the corresponding maximum value and minimum value in the time interval; T y represents a preset time interval reference value; and r represents an adjustment parameter. 2.The IoT-based digital-twin smart industrial park big data energy efficiency management system of claim 1, wherein, The data acquisition module further comprises: Acquisition unit marking module, for when the first data acquisition stability parameter corresponding to the water acquisition unit, electricity acquisition unit, oil acquisition unit and gas acquisition unit is lower than the preset first stability parameter threshold, then marking the water acquisition unit, electricity acquisition unit, oil acquisition unit and / or gas acquisition unit whose first data acquisition stability parameter is lower than the preset first stability parameter threshold; Acquisition unit abnormality judgment module, for starting from the time when the water acquisition unit, electricity acquisition unit, oil acquisition unit and / or gas acquisition unit is marked, judging whether the water acquisition unit, electricity acquisition unit, oil acquisition unit and / or gas acquisition unit has acquisition operation abnormality, and performing operation abnormality alarm when the water acquisition unit, electricity acquisition unit, oil acquisition unit and / or gas acquisition unit has acquisition operation abnormality. 3.The IoT-based digital-twin smart industrial park big data energy efficiency management system of claim 2, wherein, Acquisition unit abnormality judgment module, comprising: Real-time acquisition module, for real-time acquisition of the data acquisition time of the marked water acquisition unit, electricity acquisition unit, oil acquisition unit and / or gas acquisition unit; Maximum value acquisition module, for extracting the maximum value of the data acquisition time interval of the marked water acquisition unit, electricity acquisition unit, oil acquisition unit and / or gas acquisition unit; The second data collection stability parameter acquisition module is configured to acquire a second data collection stability parameter corresponding to the water collection unit, the electricity collection unit, the oil collection unit and / or the gas collection unit by using the maximum value of the data collection time interval of the marked water collection unit, electricity collection unit, oil collection unit and / or gas collection unit. wherein R 02 represents the second data collection stability parameter; R y represents a preset first stability parameter threshold; T maxh represents a maximum value of a data collection time interval of the marked water consumption collection unit, electricity consumption collection unit, oil consumption collection unit and / or gas consumption collection unit; T b represents an average value of a data collection time interval of the marked water consumption collection unit, electricity consumption collection unit, oil consumption collection unit and / or gas consumption collection unit; m represents a number of data collection time intervals of the marked water consumption collection unit, electricity consumption collection unit, oil consumption collection unit and / or gas consumption collection unit; T j represents a time length corresponding to the jth data collection time interval; T lst represents a time length of the last data collection time interval corresponding to the marked water consumption collection unit, electricity consumption collection unit, oil consumption collection unit and / or gas consumption collection unit before marking; Data acquisition operation abnormality determination module, for when the second data acquisition stability parameter is lower than the preset second stability parameter threshold, then determining whether the water acquisition unit, electricity acquisition unit, oil acquisition unit and / or gas acquisition unit whose second data acquisition stability parameter is lower than the preset second stability parameter threshold has data acquisition operation abnormality; Data acquisition operation abnormality alarm module, for performing operation abnormality alarm when the water acquisition unit, electricity acquisition unit, oil acquisition unit and / or gas acquisition unit has acquisition operation abnormality. 4.The IoT-based digital-twin smart industrial park big data energy efficiency management system of claim 3, wherein, The data processing module comprises: Data retrieval unit, for retrieving the real-time data of the energy efficiency of the smart industrial park; Acquiring the real-time data of the energy efficiency of the smart industrial park based on the Internet of Things; Retrieving the real-time data of the energy efficiency of the smart industrial park based on the sequential retrieval method; Checking the consistency of the real-time data of the energy efficiency of the smart industrial park; Removing the data in the real-time data of the energy efficiency of the smart industrial park which exceeds the normal range, is logically unreasonable or mutually contradictory; Processing the invalid values and missing values of the real-time data of the energy efficiency of the smart industrial park; Removing the invalid data and missing data in the real-time data of the energy efficiency of the smart industrial park which has no value for the big data energy efficiency management of the smart industrial park; Determine the real-time data of the smart industrial park energy efficiency which is valuable for the big data energy efficiency management of the smart industrial park; The data sorting unit is used for sorting the searched real-time data of the smart industrial park energy efficiency; The real-time data of the smart industrial park energy efficiency which is valuable for the big data energy efficiency management of the smart industrial park is obtained after searching; The searched real-time data of the smart industrial park energy efficiency which is valuable for the big data energy efficiency management of the smart industrial park is sorted based on the internal sorting method; The real-time data of the smart industrial park energy efficiency with the arrangement order is determined; The data fusion unit is used for fusing the sorted real-time data of the smart industrial park energy efficiency; The real-time data of the smart industrial park energy efficiency with the arrangement order is obtained; The real-time data of the smart industrial park energy efficiency with the arrangement order is fused; The energy efficiency characterization data of the smart industrial park based on the Internet of Things is determined. 5.The IoT-based digital-twin wise industrial park big data energy efficiency management system according to claim 4, characterized in that, The model training module comprises: The data storage unit is used for storing the pre-set historical data of the smart industrial park energy efficiency; The historical data of the smart industrial park energy efficiency is pre-set according to the demand of the digital twin smart industrial park big data energy efficiency management based on the Internet of Things, and the pre-set historical data of the smart industrial park energy efficiency is stored; The data division unit is used for dividing the pre-set historical data of the smart industrial park energy efficiency; The pre-set historical data of the smart industrial park energy efficiency is obtained; The pre-set historical data of the smart industrial park energy efficiency is divided; The training set and the test set are determined; The model selection unit is used for selecting the model architecture; According to the demand of the digital twin smart industrial park big data energy efficiency management based on the Internet of Things, the model architecture suitable for the big data energy efficiency management of the smart industrial park is selected from multiple model architectures; The model training unit is used for constructing the digital twin model of the smart industrial park; The training set is obtained; The model architecture suitable for the big data energy efficiency management of the smart industrial park is obtained; The model training of the model architecture suitable for the big data energy efficiency management of the smart industrial park is performed based on the training set; The digital twin model of the smart industrial park suitable for the big data energy efficiency management of the smart industrial park is determined. 6.The IoT-based digital-twin wise industrial park big data energy efficiency management system of claim 5, wherein, The test optimization module comprises: The model test unit is used for testing the performance of the digital twin model of the smart industrial park; The test set is obtained; The digital twin model of the smart industrial park is obtained; The performance of the digital twin model of the smart industrial park is tested based on the test set; The performance test result of the digital twin model of the smart industrial park is determined; The adjustment and optimization unit is used for adjusting and optimizing the digital twin model of the smart industrial park; The performance test result of the digital twin model of the smart industrial park is obtained; The performance test result of the digital twin model of the smart industrial park is deeply mined and analyzed; The adjustment and optimization scheme of the digital twin model of the smart industrial park is determined; The digital twin model of the smart industrial park is adjusted and optimized based on the adjustment and optimization scheme of the digital twin model of the smart industrial park; The more suitable digital twin model of the smart industrial park is determined. 7.The IoT-based digital-twin wise industrial park big data energy efficiency management system of claim 6, wherein, The prediction evaluation module comprises: The data extraction unit is used for extracting the energy efficiency characterization data of the smart industrial park; According to the digital twin wisdom industrial park big data energy efficiency management demand based on the Internet of Things, the wisdom industrial park energy efficiency characterization data based on the Internet of Things is extracted; The prediction evaluation unit is used for predicting and evaluating the wisdom industrial park energy efficiency characterization data; The wisdom industrial park energy efficiency characterization data based on the Internet of Things is extracted; A more suitable wisdom industrial park digital twin model is obtained; The wisdom industrial park energy efficiency characterization data is input into the wisdom industrial park digital twin model; The wisdom industrial park digital twin model is used to simulate and predict the wisdom industrial park energy efficiency characterization data; The digital twin wisdom industrial park big data energy efficiency prediction evaluation result is determined. 8.The IoT-based digital-twin wise industrial park big data energy efficiency management system of claim 7, wherein, The energy efficiency management module includes: The management formulation unit is used for formulating the digital twin wisdom industrial park big data energy efficiency management scheme; The digital twin wisdom industrial park big data energy efficiency prediction evaluation result is obtained; The digital twin wisdom industrial park big data energy efficiency prediction evaluation result is analyzed; The digital twin wisdom industrial park big data energy efficiency management scheme is determined; The energy efficiency management unit is used for managing the digital twin wisdom industrial park big data energy efficiency; The digital twin wisdom industrial park big data energy efficiency management scheme is obtained; The digital twin wisdom industrial park big data energy efficiency management scheme is used to manage the digital twin wisdom industrial park big data energy efficiency. 9.The IoT-based digital-twin wise industrial park big data energy efficiency management system of claim 8, wherein, The feedback display module includes: The real-time feedback unit is used for real-time feedback of the digital twin wisdom industrial park big data energy efficiency; The digital twin wisdom industrial park big data energy efficiency prediction evaluation result is obtained; The digital twin wisdom industrial park big data energy efficiency prediction evaluation result is used to feed back the digital twin wisdom industrial park big data energy efficiency in real time; The digital twin wisdom industrial park big data energy efficiency feedback is determined; The visual display unit is used for visual display of the digital twin wisdom industrial park big data energy efficiency feedback; The digital twin wisdom industrial park big data energy efficiency feedback is obtained; The digital twin wisdom industrial park big data energy efficiency feedback is visualized, and the digital twin wisdom industrial park big data energy efficiency is mastered in real time.

Images