Intelligent park energy efficiency management system and method based on IBMS

Abstract

The invention relates to the technical field of park management, in particular to a smart park energy efficiency management system and method based on an IBMS. The method comprises the following steps: acquiring real-time park data; based on a preset energy efficiency prediction model, analyzing the real-time park data, and predicting energy efficiency change; analyzing the energy efficiency change based on the real-time park data, and determining the credibility of each energy efficiency change; and determining an energy efficiency management scheme according to the credibility. Energy distribution is optimized, and energy waste is reduced. The credibility evaluation model is helpful for identifying the reliability of the prediction result, and ensures that the prediction result is not trust blindly. By analyzing the equipment health degree index and the fault reason, the credibility of each energy efficiency change is more accurately judged, so that wrong scheduling caused by inaccurate prediction is avoided. And according to the credibility of the prediction result, a corresponding energy efficiency management scheme is generated, so that the accuracy and effectiveness of energy scheduling are ensured, and energy waste and equipment failure are avoided.

Description

Technical Field

[0001] This application relates to the technical field of park management, and in particular, to an intelligent park energy efficiency management system and method based on IBMS. Background Art

[0002] With the rapid development of intelligent parks and intelligent buildings, the energy efficiency management of intelligent parks has gradually become one of the key technologies to improve energy utilization efficiency and achieve sustainable development. As the core component of an intelligent park, the Intelligent Building Management System (IBMS) has been widely applied to various intelligent buildings for real-time monitoring and adjustment of energy consumption in the intelligent park, especially the operation of equipment such as air conditioners, lighting, and Heating, Ventilation, and Air Conditioning (HVAC).

[0003] With the diversification of park equipment types and usage requirements, traditional IBMS leads to energy waste in park management when facing complex park environments and ever-changing real-time data. Therefore, how to optimize the energy management of parks has become a hot topic in current research and practice. Summary of the Invention

[0004] This application provides an intelligent park energy efficiency management system and method based on IBMS to solve the above problems.

[0005] In a first aspect, this application provides an intelligent park energy efficiency management method based on IBMS, and the method includes: Obtain real-time park data; analyze the real-time park data based on a preset energy efficiency prediction model to predict energy efficiency changes; Analyze the energy efficiency changes based on the real-time park data to determine the credibility of each energy efficiency change; Determine an energy efficiency management plan according to the credibility.

[0006] Through this solution, real-time park data collection can provide the real-time operating status of various devices in the park, such as temperature, humidity, device operating status, etc., which helps the preset energy efficiency prediction model and device scheduling, so as to make decisions based on the latest environment and usage conditions. Presetting the energy efficiency prediction model through device historical operating data and deep learning algorithms helps to more accurately predict the energy demand and consumption trends in different situations in the park, and at the same time helps to optimize energy distribution and reduce energy waste. The credibility evaluation model helps to identify the reliability of the prediction results and ensure that the prediction results are not blindly trusted. By analyzing device health indicators and failure reasons, the credibility of each energy efficiency change can be judged more accurately, thus avoiding incorrect scheduling caused by inaccurate prediction. Generating a corresponding energy efficiency management plan according to the credibility of the prediction results helps to ensure the accuracy and effectiveness of energy scheduling, and avoid energy waste and equipment failures.

[0007] Optionally, analyzing the real-time campus data based on a preset energy efficiency prediction model to predict energy efficiency changes includes: Analyze the real-time campus data to determine the campus topographic map, pedestrian flow heat map, and campus equipment information; According to the campus equipment information, divide the campus into several sub-regions; Analyze the campus topographic map and the pedestrian flow heat map to determine the regional characteristics of each sub-region; Based on a preset energy efficiency prediction model, predict energy efficiency changes according to the regional characteristics of each sub-region.

[0008] Through this solution, by determining the campus topographic map, pedestrian flow heat map, and campus equipment information, the geographical layout, pedestrian flow distribution, and equipment operation status of the campus are comprehensively identified, providing basic data for regional division and energy efficiency prediction. Regional division helps to carry out personalized management for the energy efficiency requirements of different regions, improve energy utilization efficiency, and reduce unnecessary energy waste. By analyzing the campus topographic map and the pedestrian flow heat map, the building structure characteristics and movement trajectory characteristics of each sub-region are identified, so as to more accurately predict the energy efficiency requirements of each sub-region. The preset energy efficiency prediction model can predict the future energy demand and consumption trends according to the regional characteristics of each sub-region, providing a basis for dynamic scheduling and intelligent decision-making.

[0009] Optionally, determining an energy efficiency management plan according to the credibility includes: Compare the credibility with a preset credibility threshold to obtain a comparison result; If the comparison result shows that the credibility is higher than the preset credibility threshold, determine an energy efficiency management plan according to the energy efficiency changes; If the comparison result shows that the credibility is lower than the preset credibility threshold, determine the regional connection of adjacent sub-regions according to the campus equipment information; Obtain an energy efficiency impact knowledge graph; According to the regional connection and the energy efficiency impact knowledge graph, determine the energy efficiency impact association; According to the energy efficiency impact association and the preset energy efficiency prediction model, determine the abnormal causal contribution degree of each energy efficiency impact; According to the abnormal causal contribution degree, determine the abnormal root cause, and according to the abnormal root cause, revise the energy efficiency management plan to obtain the best management plan for dealing with the abnormality.

[0010] Through this solution, by comparing the credibility with the pre-set credibility threshold, the reliability of the prediction result can be quickly judged, providing a basis for the energy efficiency management decision-making. If the credibility is higher than the pre-set credibility threshold, an energy efficiency management plan is formulated and implemented according to the predicted energy efficiency change to optimize the energy distribution and improve the energy efficiency. If the credibility is lower than the pre-set credibility threshold, the implementation of the energy efficiency management plan based on the prediction result is suspended to avoid potential risks and energy waste. By analyzing the park equipment information in adjacent sub-regions, the mutual influence between adjacent sub-regions is identified, providing clues for anomaly handling. Constructing an energy efficiency impact knowledge graph helps to identify the energy transfer and influence relationships between devices, providing data support for anomaly detection. Determining the energy efficiency impact association helps to analyze anomalies more comprehensively and provides more accurate guidance for anomaly handling. By analyzing the abnormal causal contribution degree of each energy efficiency impact to the prediction deviation, it helps to accurately locate the root cause of the anomaly. Identifying the root cause of the anomaly helps to revise the energy efficiency management plan. According to the root cause of the anomaly, the device operation parameters are adjusted, the energy distribution strategy is optimized, or necessary device maintenance is carried out, so as to generate the best management plan to deal with the anomaly and ensure the accuracy and effectiveness of the park energy efficiency management.

[0011] Optionally, analyzing the energy efficiency change based on the real-time park data and determining the credibility of each energy efficiency change includes: Based on the park equipment information, analyzing the real-time park data to determine the device current waveform, the number of compressor starts and stops, and the valve opening degree of each device; Analyzing the device current waveform through fast Fourier transform to determine the harmonic distortion rate; Obtaining the device historical operation data, analyzing the device historical operation time to determine the historical fault information; Analyzing the historical fault information to determine the cause of the fault; According to the cause of the fault, determining the correlation between the harmonic distortion rate and each historical fault information; According to the correlation, determining the harmonic distortion rate threshold; According to the harmonic distortion rate threshold and the number of compressor starts and stops, constructing a device health index; Based on the device health index, analyzing the energy efficiency change to determine the credibility of each energy efficiency change.

[0012] Through this solution, by determining the device current waveform, the start-stop times of the compressor, and the valve opening degree of each device, problems in the device operation can be discovered in a timely manner, providing a basis for energy efficiency management and maintenance. By analyzing the device current waveform, abnormal conditions in the device operation can be identified. For example, a too high harmonic distortion rate indicates that there are faults or abnormal operation in the device. The analysis of historical operation data helps to identify the long-term operation trends and potential problems of the device, providing data support for predicting device faults. Determining historical fault information helps to identify the fault modes of the device, providing a basis for preventive maintenance and fault prediction. Analyzing the causes of faults helps to take targeted measures, such as replacing device components, adjusting operation parameters, etc., to reduce the occurrence of faults. Determining the correlation relationship between the harmonic distortion rate and each historical fault information helps to more accurately predict device faults, providing guidance for device maintenance. Setting a harmonic distortion rate threshold helps to timely discover abnormal conditions in the device operation, providing a standard for device maintenance and fault prediction. The device health index helps to reflect the overall operation status of the device, providing a basis for device maintenance and operation optimization. Based on the device health index, the credibility of the energy efficiency change is evaluated, providing support for energy efficiency management decisions.

[0013] Optionally, the determining the energy efficiency impact association according to the regional connection and the energy efficiency impact knowledge graph includes: Analyze the energy efficiency impact knowledge graph and the regional connection to determine the device topology relationship; According to the device topology relationship, determine the energy transfer path between any two devices; Analyze the real-time park data to determine the real-time environmental parameters of each sub-region; Based on the graph neural network model, analyze the coupling relationship between the energy transfer path and the real-time environmental parameters to generate the dynamic energy efficiency impact weight; According to the dynamic energy efficiency impact weight, quantify the energy efficiency association strength between adjacent sub-regions; According to the energy efficiency association strength between adjacent sub-regions, determine the energy efficiency impact association.

[0014] Through this solution, by analyzing the energy efficiency impact knowledge graph and regional connections, identifying the physical and logical connections between devices helps in the analysis of energy transfer paths. Identifying the energy transfer paths between any two devices helps to identify how energy is transferred within the park, providing a basis for energy efficiency analysis and prediction. By analyzing real-time park data and collecting real-time environmental parameters such as temperature, humidity, and lighting in each sub-region, it provides real-time data support for energy efficiency prediction. Based on the graph neural network model, analyzing the coupling relationship between energy transfer paths and real-time environmental parameters generates dynamic energy efficiency impact weights, providing a more accurate decision-making basis for energy efficiency management. Through the dynamic energy efficiency impact weights, quantifying the energy efficiency correlation strength between adjacent sub-regions helps in the energy efficiency coordination and optimization between adjacent sub-regions. Identifying energy efficiency impact associations helps to more comprehensively identify the mutual influences between adjacent sub-regions, providing a basis for energy efficiency management and device scheduling, and achieving more precise energy allocation and device control.

[0015] Optionally, the determining the abnormal causal contribution degree of each energy efficiency impact according to the energy efficiency impact association and the preset energy efficiency prediction model includes: Based on the preset energy efficiency prediction model, analyzing the energy efficiency change to determine the prediction deviation; Invoking the preset causal forest model, and based on the preset causal forest model, according to the energy efficiency impact association and the prediction deviation, determining the abnormal causal contribution degree of each energy efficiency impact.

[0016] Through this solution, by analyzing the energy efficiency change, identifying the energy efficiency performance of devices provides a basis for the analysis of prediction deviation, thereby improving the accuracy of the preset energy efficiency prediction model, reducing energy demand and the consumption trend. By determining the prediction deviation, identifying the accuracy of the prediction result provides a basis for anomaly detection and correction, reducing the risk of energy waste and equipment failures. Invoking the preset causal forest model helps to quantify the contribution degree of each energy efficiency impact to the energy efficiency fluctuation, providing a tool for determining the abnormal causal contribution degree. By determining the abnormal causal contribution degree of each energy efficiency impact, quantifying the influence degree of each energy efficiency impact on the prediction deviation provides a scientific basis for anomaly handling and energy efficiency management, thereby improving the intelligent level of devices.

[0017] Optionally, the constructing the device health index according to the harmonic distortion rate threshold and the number of compressor starts and stops includes: Obtaining the vibration spectrum of the compressor bearing and the refrigerant pressure curve; Analyzing the vibration spectrum to determine the mechanical wear level; Analyzing the pressure curve to determine the fluctuation amplitude at the start and stop moments; Calculating the sealing performance attenuation coefficient according to the fluctuation amplitude; Establish a three-dimensional health assessment space, where the X-axis is the harmonic distortion rate, the Y-axis is the mechanical wear level, and the Z-axis is the sealing performance attenuation coefficient; Determine the health benchmark cluster at the current moment according to the three-dimensional health assessment space; Calculate the deviation degree between the current device state and the health benchmark cluster through the Mahalanobis distance; Generate a device health index according to the deviation degree.

[0018] Through this solution, detailed data on the operation of the device is obtained by collecting the vibration spectrum of the compressor bearing and the refrigerant pressure curve in real time. By analyzing the vibration spectrum, the mechanical wear level is determined, thereby predicting potential device failures and maintenance requirements. Determine the fluctuation amplitude at the start and stop moments, evaluate the sealing performance, and provide a basis for sealing maintenance and optimization. Calculate the sealing performance attenuation coefficient, which helps to predict the change trend of the sealing performance and prevent seal failure in advance. By establishing a three-dimensional health assessment space, the health status of the device is evaluated more comprehensively, providing multi-dimensional references for device maintenance and operation optimization. According to the three-dimensional health assessment space, determine the health benchmark cluster, that is, the health distribution of the device in the normal state, providing a standard for the assessment of the device state. Calculate the deviation degree between the current device state and the health benchmark cluster through the Mahalanobis distance, quantify the abnormality degree of the device state, and provide a basis for fault warning and maintenance decision-making. Generate a device health index according to the deviation degree, reflecting the overall health status of the device, and providing a scientific basis for device maintenance and operation optimization.

[0019] Optionally, the modifying the energy efficiency management plan according to the root cause of the abnormality includes: Obtain the park activity schedule and weather forecast data; Determine the schedule activities according to the park activity schedule and weather forecast data; Analyze the spatio-temporal overlap degree between the root cause of the abnormality and the schedule activities to determine the human influence factors; Generate a multi-objective optimization strategy according to the human influence factors and the weather forecast data; Adjust the device operation parameters and regional linkage rules according to the multi-objective optimization strategy.

[0020] Through this solution, by obtaining the park activity schedule and weather forecast data, energy demand can be better predicted and planned, thereby optimizing energy distribution and equipment scheduling. According to the park activity schedule and weather forecast data, upcoming schedule activities are determined, so as to predict the energy demand and equipment usage in different time periods. By analyzing the spatio-temporal overlap between the root cause of anomalies and schedule activities, human influencing factors are identified, and targeted corrective measures are taken. Based on the human influencing factors and weather forecast data, multi-objective optimization strategies are generated, such as adjusting equipment operation parameters, optimizing energy distribution, etc., to improve energy utilization efficiency. According to the multi-objective optimization strategy, the equipment operation parameters and regional linkage rules are adjusted to optimize energy efficiency and improve the operation efficiency and stability of the equipment.

[0021] Optionally, analyzing the park topographic map and the pedestrian flow heat map to determine the regional characteristics of each sub-region, including: Analyze the park topographic map to determine the building structure characteristics; According to the building structure characteristics, determine the distribution of ventilation corridors; Extract the moving trajectory characteristics of the pedestrian flow heat map to determine the distribution of personnel stay time; According to the distribution of the ventilation corridors and the distribution of personnel stay time, calculate the heat load index of each sub-region; According to the building structure characteristics, determine the thermal parameters of the building envelope structure; According to the thermal parameters, correct the heat load index; Based on the corrected heat load index, generate a regional characteristic description vector containing dynamic weight coefficients to obtain the regional characteristics of each sub-region.

[0022] Through this solution, by analyzing the park topographic map and identifying the building structure characteristics, it helps in the analysis of the distribution of ventilation corridors and heat load calculation. According to the building structure characteristics, determining the distribution of ventilation corridors in the park helps in natural ventilation and air-conditioning design. By analyzing the pedestrian flow heat map and extracting the characteristics of personnel movement trajectories, it helps in the analysis of personnel flow and personnel stay time. According to the pedestrian flow heat map, determining the distribution of personnel stay time in each sub-region of the park helps in evaluating the heat load demand of each sub-region. Combining the distribution of ventilation corridors and the distribution of personnel stay time, calculating the heat load index of each sub-region provides a basis for energy efficiency management. According to the building structure characteristics, determining the thermal parameters of the building envelope structure provides data support for correcting the heat load index. According to the thermal parameters of the building envelope structure, correcting the heat load index improves the accuracy and practicality of the building envelope structure. Based on the corrected heat load index, generating a regional characteristic description vector containing dynamic weight coefficients reflects the characteristics of each sub-region and provides a basis for personalized energy efficiency management.

[0023] Second aspect, the present application provides an energy efficiency management system for an intelligent park based on IBMS, and the system includes: A data analysis module, configured to obtain real-time park data; analyze the real-time park data based on a preset energy efficiency prediction model, and predict energy efficiency changes; A change analysis module, configured to analyze the energy efficiency changes based on the real-time park data, and determine the credibility of each energy efficiency change; A solution determination module, configured to determine an energy efficiency management solution according to the credibility.

[0024] Optionally, when the data analysis module analyzes the real-time park data based on a preset energy efficiency prediction model to predict energy efficiency changes, it is used for: Analyze the real-time park data to determine the park topographic map, the pedestrian flow heat map, and the park equipment information; According to the park equipment information, divide the park into several sub-regions; Analyze the park topographic map and the pedestrian flow heat map to determine the regional characteristics of each sub-region; Based on a preset energy efficiency prediction model, predict energy efficiency changes according to the regional characteristics of each sub-region.

[0025] Optionally, when the solution determination module determines an energy efficiency management solution according to the credibility, it is used for: Compare the credibility with a preset credibility threshold to obtain a comparison result; If the comparison result is that the credibility is higher than the preset credibility threshold, determine an energy efficiency management solution according to the energy efficiency changes; If the comparison result is that the credibility is lower than the preset credibility threshold, determine the regional connection of adjacent sub-regions according to the park equipment information; Obtain an energy efficiency impact knowledge graph; Determine an energy efficiency impact association according to the regional connection and the energy efficiency impact knowledge graph; Determine the abnormal causal contribution degree of each energy efficiency impact according to the energy efficiency impact association and the preset energy efficiency prediction model; Determine the abnormal root cause according to the abnormal causal contribution degree, and correct the energy efficiency management solution according to the abnormal root cause to obtain the best management solution for dealing with the abnormality.

[0026] Optionally, when the change analysis module analyzes the energy efficiency changes based on the real-time park data to determine the credibility of each energy efficiency change, it is used for: Based on the park equipment information, analyze the real-time park data to determine the device current waveform, the number of compressor starts and stops, and the valve opening of each device; Analyze the current waveform of the device through fast Fourier transform to determine the harmonic distortion rate; Obtain the historical operation data of the device, analyze the historical operation time of the device, and determine the historical fault information; Analyze the historical fault information to determine the cause of the fault; According to the cause of the fault, determine the correlation between the harmonic distortion rate and each piece of historical fault information; According to the correlation, determine the harmonic distortion rate threshold; Construct a device health index according to the harmonic distortion rate threshold and the number of compressor starts and stops; Based on the device health index, analyze the energy efficiency change and determine the credibility of each energy efficiency change.

[0027] Optionally, when the solution determination module determines the energy efficiency impact correlation according to the regional connection and the energy efficiency impact knowledge graph, it is used for: Analyze the energy efficiency impact knowledge graph and the regional connection to determine the device topology relationship; According to the device topology relationship, determine the energy transfer path between any two devices; Analyze the real-time park data to determine the real-time environmental parameters of each sub-region; Based on the graph neural network model, analyze the coupling relationship between the energy transfer path and the real-time environmental parameters to generate a dynamic energy efficiency impact weight; Quantify the energy efficiency correlation strength between adjacent sub-regions according to the dynamic energy efficiency impact weight; Determine the energy efficiency impact correlation according to the energy efficiency correlation strength between adjacent sub-regions.

[0028] Optionally, when the solution determination module determines the abnormal causal contribution degree of each energy efficiency impact according to the energy efficiency impact correlation and the preset energy efficiency prediction model, it is used for: Based on the preset energy efficiency prediction model, analyze the energy efficiency change to determine the prediction deviation; Retrieve the preset causal forest model, and based on the preset causal forest model, determine the abnormal causal contribution degree of each energy efficiency impact according to the energy efficiency impact correlation and the prediction deviation.

[0029] Optionally, when the change analysis module constructs a device health index according to the harmonic distortion rate threshold and the number of compressor starts and stops, it is used for: Obtain the compressor bearing vibration spectrum and the refrigerant pressure curve; Analyze the vibration spectrum to determine the mechanical wear level; Analyze the pressure curve to determine the fluctuation amplitude at the start and stop moments; Calculate the sealing performance attenuation coefficient according to the amplitude of the fluctuation. Establish a three-dimensional health assessment space, where the X-axis is the harmonic distortion rate, the Y-axis is the mechanical wear level, and the Z-axis is the sealing performance attenuation coefficient. Determine the health benchmark cluster at the current moment according to the three-dimensional health assessment space. Calculate the deviation degree between the current device state and the health benchmark cluster through the Mahalanobis distance. Generate a device health index according to the deviation degree.

[0030] Optionally, when the solution determination module corrects the energy efficiency management solution according to the abnormal root cause, it is used for: Obtain the park activity schedule and weather forecast data. Determine the schedule activities according to the park activity schedule and weather forecast data. Analyze the spatio-temporal overlap degree between the abnormal root cause and the schedule activities to determine the human influence factors. Generate a multi-objective optimization strategy according to the human influence factors and the weather forecast data. Adjust the device operation parameters and regional linkage rules according to the multi-objective optimization strategy.

[0031] Optionally, when the data analysis module analyzes the park topographic map and the pedestrian flow heat map to determine the regional characteristics of each sub-region, it is used for: Analyze the park topographic map to determine the building structure characteristics. Determine the distribution of ventilation corridors according to the building structure characteristics. Extract the moving trajectory characteristics of the pedestrian flow heat map to determine the distribution of personnel stay time. Calculate the heat load index of each sub-region according to the distribution of ventilation corridors and the distribution of personnel stay time. Determine the thermal parameters of the building envelope according to the building structure characteristics. Correct the heat load index according to the thermal parameters. Based on the corrected heat load index, generate a regional characteristic description vector containing dynamic weight coefficients to obtain the regional characteristics of each sub-region. Description of the Drawings

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained according to these drawings without creative efforts.

[0033] Figure 1 A schematic diagram of an application scenario provided by an embodiment of the present application; Figure 2 A flowchart of a method for energy efficiency management of a smart park based on IBMS provided by an embodiment of the present application; Figure 3 A schematic diagram of the structure of a system for energy efficiency management of a smart park based on IBMS provided by an embodiment of the present application. Detailed implementation manners

[0034] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Apparently, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the scope of protection of the present application.

[0035] In addition, the term "and / or" in this document is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, unless otherwise specified.

[0036] The embodiments of the present application will be further described in detail below with reference to the drawings in the specification.

[0037] With the diversification of the types of park equipment and usage requirements, traditional prediction methods often have difficulty accurately capturing complex energy efficiency fluctuations and uncertain factors. Therefore, how to optimize the energy management of the park has become a hot topic in current research and practice Based on this, the present application provides an intelligent park energy efficiency management system and method based on IBMS, which acquires real-time park data; analyzes the real-time park data based on a preset energy efficiency prediction model to predict energy efficiency changes; analyzes the energy efficiency changes based on the real-time park data to determine the credibility of each energy efficiency change; and determines an energy efficiency management plan according to the credibility. The real-time park data collection can provide the real-time operating status of various devices in the park, such as temperature, humidity, device operating status, etc., which helps the preset energy efficiency prediction model and device scheduling, so as to make decisions based on the latest environment and usage conditions. Presetting the energy efficiency prediction model through device historical operation data and deep learning algorithms helps to more accurately predict the energy demand and consumption trends in different situations in the park, and at the same time helps to optimize energy distribution and reduce energy waste. The credibility evaluation model helps to identify the reliability of the prediction results and ensures that the prediction results are not blindly trusted. By analyzing the device health indicators and failure reasons, the credibility of each energy efficiency change can be judged more accurately, thus avoiding incorrect scheduling caused by inaccurate prediction. Generating a corresponding energy efficiency management plan according to the credibility of the prediction results helps to ensure the accuracy and effectiveness of energy scheduling, and avoid energy waste and equipment failures.

[0038] Figure 1 FIG. 4 is a schematic diagram of an application scenario provided by the present application. When performing park energy efficiency management, the method provided by the present application is applied. Specifically, the method provided by the present application is applied to any server. The server interacts with a number of sensors, and the park data is collected in real time through the number of sensors, so as to make decisions based on the latest environment and usage conditions reflected by the park data. Generating a corresponding energy efficiency management plan helps to ensure the accuracy and effectiveness of energy scheduling, and avoid energy waste and equipment failures.

[0039] The specific implementation manner can refer to the following embodiments.

[0040] Figure 2 FIG. 5 is a flowchart of an intelligent park energy efficiency management method based on IBMS provided by an embodiment of the present application. The method of this embodiment can be applied to the server in the above scenario. As Figure 2 shown, the method includes: S201. Acquire real-time park data; analyze the real-time park data based on a preset energy efficiency prediction model to predict energy efficiency changes; The real-time park data can be data such as device operating status and device energy consumption data that are extracted in real time from sensors and devices in the park, such as temperature, humidity, light, concentration, etc.

[0041] The preset energy efficiency prediction model can be a model that is preset based on the historical operation data of the equipment and deep learning algorithms and is used to predict the energy demand and consumption trend in the park for a period of time in the future. It is pre-stored in the server and is called when in use.

[0042] The energy efficiency change can be the fluctuation of the energy use efficiency in the park.

[0043] Specifically, sensors such as temperature, humidity, light, concentration, and equipment operation status are deployed in the park to collect park data in real time. Using the historical operation data of the equipment and the preset energy efficiency prediction model, data such as equipment operation status and equipment energy consumption data are extracted from the real-time park data, and the extracted data is input into the trained preset energy efficiency prediction model to predict the energy efficiency change.

[0044] S202. Based on the real-time park data, analyze the energy efficiency change and determine the credibility of each energy efficiency change; The credibility can be the degree of credibility of the energy efficiency prediction result.

[0045] Specifically, data such as the historical operation status of the equipment is extracted from the real-time park data, the historical operation status of the equipment such as the current waveform and start-stop times of the equipment is analyzed, the harmonic distortion rate is determined by methods such as fast Fourier transform (FFT), and the equipment health index is evaluated. Combining the historical operation data of the equipment, analyze the historical operation time of the equipment, identify historical fault information, and determine the cause of the fault. According to the evaluation results of the equipment health index and the cause of the fault, construct a credibility evaluation model. Input the real-time park data into the credibility evaluation model to calculate the credibility of each energy efficiency change.

[0046] S203. Determine the energy efficiency management plan according to the credibility.

[0047] The energy efficiency management plan can be an energy use optimization plan formulated for the park based on the energy efficiency prediction result and credibility evaluation.

[0048] Specifically, set a credibility threshold for judging whether the prediction result is reliable. Compare the credibility of each energy efficiency change with the preset credibility threshold to judge the reliability of the prediction result. If the credibility is higher than the preset credibility threshold, determine that the prediction result is reliable and formulate an energy efficiency management plan based on the prediction result.

[0049] Through this solution, real-time park data collection can provide the real-time operating status of various devices in the park, such as temperature, humidity, device operating status, etc., which helps to preset the energy efficiency prediction model and device scheduling, so as to make decisions based on the latest environment and usage conditions. Presetting the energy efficiency prediction model through device historical operation data and deep learning algorithms helps to more accurately predict the energy demand and consumption trends in different situations in the park, and at the same time helps to optimize energy distribution and reduce energy waste. The credibility assessment model helps to identify the reliability of the prediction results and ensure that the prediction results are not blindly trusted. By analyzing the device health indicators and failure reasons, the credibility of each energy efficiency change can be judged more accurately, thus avoiding incorrect scheduling caused by inaccurate prediction. According to the credibility of the prediction results, corresponding energy efficiency management plans are generated, which helps to ensure the accuracy and effectiveness of energy scheduling, and avoid energy waste and equipment failures.

[0050] In some embodiments, analyze the real-time park data to determine the park topographic map, pedestrian flow heat map and park device information; according to the park device information, divide the park into several sub-regions; analyze the park topographic map and pedestrian flow heat map to determine the regional characteristics of each sub-region; based on the preset energy efficiency prediction model, predict the energy efficiency change according to the regional characteristics of each sub-region.

[0051] The park topographic map can be a plan view of the geographical features such as buildings, roads, and greenery in the park.

[0052] The pedestrian flow heat map can be a data visualization method that represents the pedestrian flow density in different areas of the park by the depth of color.

[0053] The park device information can be information such as the type, model, location, operating status, and energy consumption data of the devices in the park.

[0054] The sub-region can be several small regions divided from the park based on data such as the park topographic map, park device information, and pedestrian flow heat map.

[0055] The regional characteristics can be the unique attributes and features of each sub-region.

[0056] Specifically, obtain the topographic map of the park, such as the building layout, road distribution, and greening areas, through Geographic Information System (GIS) technology. Analyze the personnel flow situation using surveillance cameras and real-time park data to generate a heat map of the personnel flow, showing the distribution of the number of people in different areas. Collect the information of park equipment, such as the status and energy consumption of air conditioners, lighting, and HVAC in the park, through the Internet of Things technology. Based on the park equipment information and the topographic map of the park, use the clustering algorithm to divide the park into several sub-regions. Analyze the building height, orientation, number of windows, etc. of each sub-region according to the topographic map of the park. Analyze the movement trajectory characteristics of each sub-region, such as the stay time of personnel and the peak activity period, according to the heat map of the personnel flow. Determine the regional characteristics of each sub-region according to the building structure characteristics and movement trajectory characteristics. Based on the preset energy efficiency prediction model, use the historical equipment operation data and regional characteristics to train the preset energy efficiency prediction model. Extract features such as equipment load, environmental parameters, and personnel activities from the real-time park data and regional characteristics, and input the extracted features into the trained preset energy efficiency prediction model to predict the change in energy efficiency.

[0057] In a specific implementation manner, a regional classification model can be established through the topographic map of the park, the heat map of the personnel flow, and the park equipment information, so as to use this regional classification model to achieve regional division, and then regional association analysis can be carried out to facilitate the determination of the energy efficiency management plan.

[0058] Through this solution, by determining the topographic map of the park, the heat map of the personnel flow, and the park equipment information, comprehensively identify the geographical layout, personnel flow distribution, and equipment operation status of the park, providing basic data for regional division and energy efficiency prediction. Regional division helps to carry out personalized management for the energy efficiency requirements of different regions, improve energy utilization efficiency, and reduce unnecessary energy waste. By analyzing the topographic map of the park and the heat map of the personnel flow, identify the building structure characteristics and movement trajectory characteristics of each sub-region, so as to more accurately predict the energy efficiency requirements of each sub-region. The preset energy efficiency prediction model can predict the future energy demand and consumption trend according to the regional characteristics of each sub-region, providing a basis for dynamic scheduling and intelligent decision-making.

[0059] In some embodiments, compare the credibility with a preset credibility threshold to obtain a comparison result; if the comparison result is that the credibility is higher than the preset credibility threshold, determine the energy efficiency management plan according to the change in energy efficiency; if the comparison result is that the credibility is lower than the preset credibility threshold, determine the regional connection of adjacent sub-regions according to the park equipment information; obtain the energy efficiency impact knowledge graph; determine the energy efficiency impact association according to the regional connection and the energy efficiency impact knowledge graph; determine the abnormal causal contribution degree of each energy efficiency impact according to the energy efficiency impact association and the preset energy efficiency prediction model; determine the abnormal root cause according to the abnormal causal contribution degree, and modify the energy efficiency management plan according to the abnormal root cause to obtain the best management plan for dealing with the abnormality.

[0060] The preset trust threshold can be a criterion set in advance for evaluating the reliability of the energy efficiency prediction result. It is stored in the server in advance and is called when in use.

[0061] Adjacent sub-regions can be two or more sub-regions that are adjacent geographically in the park area division.

[0062] Regional connection can be the energy transfer and mutual influence between adjacent sub-regions.

[0063] The energy efficiency impact knowledge graph can be a data structure used to represent the mutual relationships between devices, energy equipment, and environmental factors in the park.

[0064] The energy efficiency impact association can be the specific association of energy transfer and mutual influence between devices in the energy efficiency impact knowledge graph.

[0065] The energy efficiency impact can be the impact of device operation data, environmental factors, or other factors on energy consumption and energy efficiency performance.

[0066] The abnormal causal contribution degree can be the contribution degree of each factor causing the energy efficiency prediction deviation to the abnormal situation.

[0067] The abnormal root cause can be the fundamental reason for the deviation of the energy efficiency prediction.

[0068] The best management plan can be the best plan for optimizing energy use in the park according to the abnormal root cause and the energy efficiency prediction result.

[0069] Specifically, a credible threshold is set based on the analysis of the historical operation data of the equipment and the evaluation of the model performance. The credibility evaluation model is used to evaluate the prediction results of each energy efficiency change and calculate the credibility. The calculated credibility is compared with the preset credibility threshold to obtain the comparison result. The comparison results are analyzed. If the credibility is higher than the preset credibility threshold, a corresponding energy efficiency management plan such as adjusting the equipment operation parameters and optimizing energy distribution is formulated according to the predicted energy efficiency change. If the credibility is lower than the preset credibility threshold, the equipment connectivity between adjacent sub-areas is analyzed according to the equipment information of the park, so as to determine the regional connection of energy between adjacent sub-areas. Natural language processing technology is used to extract knowledge information from equipment manuals, technical documents and expert knowledge. The knowledge graph construction tool is used to store the extracted knowledge information in the form of a graph to construct an energy efficiency impact knowledge graph. The energy efficiency impact association is determined by combining the regional connection and the energy efficiency impact knowledge graph. The prediction results generated by the preset energy efficiency prediction model are compared with the actual energy efficiency data to determine the prediction deviation. According to the energy efficiency impact knowledge graph, the energy efficiency impact that causes the prediction deviation is determined. The causal analysis model is used to calculate the abnormal causal contribution of each energy efficiency impact to the prediction deviation. According to the calculation results of abnormal causal contribution, the factor with the greatest impact on the forecast deviation, i.e. the abnormal root cause, is determined. According to the determined abnormal root cause, the existing energy efficiency management plan is revised. The revised energy efficiency management plan is evaluated to determine the best management plan for dealing with the abnormality.

[0070] Through this solution, by comparing the credibility with the pre-credible threshold, the reliability of the prediction results can be quickly judged, providing a basis for energy efficiency management decisions. If the credibility is higher than the preset credibility threshold, the energy efficiency management plan is formulated and implemented according to the predicted energy efficiency changes, energy allocation is optimized, and energy efficiency is improved. If the credibility is lower than the preset credibility threshold, the energy efficiency management plan based on the prediction results is suspended to avoid potential risks and energy waste. By analyzing the park equipment information of adjacent sub-areas, the mutual influence between adjacent sub-areas is identified, providing clues for abnormal handling. Constructing an energy efficiency impact knowledge graph helps to identify the energy transfer and influence relationship between devices and provide data support for anomaly detection. Determining the energy efficiency impact association helps to analyze abnormal situations more comprehensively and provide more accurate guidance for abnormal handling. By analyzing the abnormal causal contribution of each energy efficiency impact to the prediction deviation, it is helpful to accurately locate the root cause of the abnormality. Identifying the root cause of the abnormality helps to correct the energy efficiency management plan. According to the root cause of the abnormality, adjust the equipment operating parameters, optimize the energy allocation strategy, or perform necessary equipment maintenance, so as to generate the best management plan to deal with the abnormality and ensure the accuracy and effectiveness of the park energy efficiency management.

[0071] In some embodiments, based on the park equipment information, the real-time park data is analyzed to determine the equipment current waveform, the number of compressor starts and stops, and the valve opening degree of each equipment; by performing a fast Fourier transform, the equipment current waveform is analyzed to determine the harmonic distortion rate; the historical operation data of the equipment is obtained, the historical operation time of the equipment is analyzed to determine the historical fault information; the historical fault information is analyzed to determine the cause of the fault; according to the cause of the fault, the correlation between the harmonic distortion rate and each historical fault information is determined; according to the correlation, the harmonic distortion rate threshold is determined; according to the harmonic distortion rate threshold and the number of compressor starts and stops, an equipment health index is constructed; based on the equipment health index, the energy efficiency change is analyzed to determine the credibility of each energy efficiency change.

[0072] The equipment current waveform can be a curve of the current changing with time during the operation of the equipment.

[0073] The number of compressor starts and stops can be the number of starts and stops of the compressor within a certain period of time.

[0074] The valve opening degree can be the degree to which the valve controlling the fluid flow is opened.

[0075] The fast Fourier transform can be a mathematical algorithm used to convert a time-domain signal into a frequency-domain signal.

[0076] The harmonic distortion rate can be the relative content of harmonic components in the equipment voltage waveform.

[0077] The historical operation data of the equipment can be operation data such as the start time, operation time, energy consumption data, and fault records of the equipment in the past period of time. This past period of time can be obtained according to experience or specified by a person.

[0078] The historical operation time of the equipment can be the cumulative operation time of the equipment in the past period of time. This past period of time can be obtained according to experience or specified by a person.

[0079] The historical fault information can be information such as the fault type, occurrence time, duration, and repair record of the equipment when a fault occurred in the past.

[0080] The cause of the fault can be the root causes such as equipment aging, insufficient maintenance, improper operation, and external environmental factors that cause the equipment to malfunction.

[0081] The correlation can be the mutual relationship between the harmonic distortion rate and each historical fault information.

[0082] The harmonic distortion rate threshold can be a preset limit value of the harmonic distortion rate.

[0083] The equipment health index can be a comprehensive index used to evaluate the overall operation status of the equipment.

[0084] Specifically, based on the park equipment information, the equipment current waveform, the number of compressor starts and stops, and the valve opening of each device are collected in real time through sensors and monitoring devices. The fast Fourier transform is performed on the collected equipment current waveform to analyze the frequency components of the current waveform and determine the harmonic distortion rate. The historical operation data of the equipment, such as the operation time and fault records of the equipment, are extracted from the historical database. By analyzing the historical operation data of the equipment, the historical fault information such as the fault type, occurrence time, and duration of the equipment is determined. According to the historical fault information, the fault causes such as equipment aging, insufficient maintenance, and improper operation are analyzed. For each type of fault cause, the harmonic distortion rate of the relevant equipment at the time of fault occurrence is analyzed. Statistical analysis methods are used to identify the correlation between the harmonic distortion rate and each historical fault information. The correlation between the harmonic distortion rate and each historical fault information is analyzed. Statistical analysis methods are used to calculate the harmonic distortion rate threshold based on the analysis results of the correlation between the harmonic distortion rate and the fault. Statistical analysis methods are used to construct an equipment health index based on the harmonic distortion rate threshold and the number of compressor starts and stops. A credibility evaluation model is constructed using a deep learning algorithm, and the equipment health index and energy efficiency change are input into the credibility evaluation model to calculate the credibility of each energy efficiency change.

[0085] Through this solution, by determining the equipment current waveform, the number of compressor starts and stops, and the valve opening of each device, problems in equipment operation can be discovered in a timely manner, providing a basis for energy efficiency management and maintenance. By analyzing the equipment current waveform, abnormal situations in equipment operation can be identified. For example, too high a harmonic distortion rate indicates that there is a fault or abnormal operation in the equipment. The analysis of historical operation data helps to identify the long-term operation trend and potential problems of the equipment, providing data support for predicting equipment failures. Determining historical fault information helps to identify the fault modes of the equipment, providing a basis for preventive maintenance and fault prediction. Analyzing the fault causes helps to take targeted measures, such as replacing equipment components and adjusting operation parameters, to reduce the occurrence of faults. Determining the correlation between the harmonic distortion rate and each historical fault information helps to more accurately predict equipment failures and provide guidance for equipment maintenance. Setting the harmonic distortion rate threshold helps to timely discover abnormal situations in equipment operation and provide a standard for equipment maintenance and fault prediction. The equipment health index helps to reflect the overall operation status of the equipment and provide a basis for equipment maintenance and operation optimization. Based on the equipment health index, the credibility of energy efficiency changes is evaluated, providing support for energy efficiency management decisions.

[0086] In some embodiments, analyze the knowledge graph of energy efficiency impact and regional connections to determine the device topology relationship; according to the device topology relationship, determine the energy transfer path between any two devices; analyze the real-time park data to determine the real-time environmental parameters of each sub-region; based on the graph neural network model, analyze the coupling relationship between the energy transfer path and the real-time environmental parameters to generate the dynamic energy efficiency impact weight; according to the dynamic energy efficiency impact weight, quantify the energy efficiency association strength between adjacent sub-regions; according to the energy efficiency association strength between adjacent sub-regions, determine the energy efficiency impact association.

[0087] The device topology relationship can be the physical and logical connection methods between any two devices in the park.

[0088] The energy transfer path can be the path through which energy flows between any two devices in the park.

[0089] The real-time environmental parameters can be environmental parameters such as temperature, humidity, light intensity, etc. that affect the operation of devices in the park.

[0090] The graph neural network model can be a deep learning model used to process the coupling relationship between the energy transfer path and the real-time environmental parameters.

[0091] The coupling relationship can be the mutual dependence and mutual influence between the energy transfer path and the real-time environmental parameters.

[0092] The dynamic energy efficiency impact weight can be the degree of influence of a device on the overall energy efficiency in the real-time operating state.

[0093] The energy efficiency association strength can be the strength of the energy efficiency impact between adjacent sub-regions in the park.

[0094] Specifically, use the knowledge graph of energy efficiency impact and regional connections to analyze the connection relationship between devices and determine the device topology relationship. According to the path search algorithm, determine the energy transfer path between any two devices in the device topology relationship. Analyze the real-time park data and collect real-time environmental parameters such as temperature, humidity, light intensity, carbon dioxide concentration, etc. in each sub-region of the park. Construct a graph neural network model and use the device historical operation data and device real-time operation data to train the graph neural network model so that the graph neural network model learns the coupling relationship between the energy transfer path and the real-time environmental parameters. Based on the trained graph neural network model, analyze the coupling relationship to generate the dynamic energy efficiency impact weight. According to the dynamic energy efficiency impact weight, use the association strength coefficient to quantify the energy efficiency association strength between adjacent sub-regions. According to the energy efficiency association strength between adjacent sub-regions, determine the energy efficiency impact association.

[0095] Through this solution, by analyzing the energy efficiency impact knowledge graph and regional connections, the physical and logical connections between devices are identified, which helps to analyze the energy transfer path. Identifying the energy transfer path between any two devices helps to identify how energy is transferred within the park, providing a basis for energy efficiency analysis and prediction. By analyzing real-time park data, real-time environmental parameters such as temperature, humidity, and light in each sub-area are collected to provide real-time data support for energy efficiency prediction. Based on the graph neural network model, the coupling relationship between the energy transfer path and the real-time environmental parameters is analyzed to generate dynamic energy efficiency impact weights, providing a more accurate decision-making basis for energy efficiency management. Through the dynamic energy efficiency impact weights, the energy efficiency correlation strength between adjacent sub-areas is quantified, which helps to coordinate and optimize the energy efficiency between adjacent sub-areas. Identifying energy efficiency impact associations helps to more comprehensively identify the mutual influence between adjacent sub-areas, providing a basis for energy efficiency management and equipment scheduling, and achieving more accurate energy allocation and equipment control.

[0096] In some embodiments, based on a preset energy efficiency prediction model, energy efficiency changes are analyzed to determine prediction deviations; a preset causal forest model is called, and based on the preset causal forest model, the abnormal causal contribution of each energy efficiency impact is determined according to energy efficiency impact correlations and prediction deviations.

[0097] The prediction deviation can be the difference between the result predicted by the preset energy efficiency prediction model and the actual energy efficiency data.

[0098] The preset causal forest model may be a preset machine learning model that quantifies the contribution of each energy efficiency impact to energy efficiency fluctuations, and is pre-stored in the server and called when used.

[0099] Specifically, use the preset energy efficiency prediction model to analyze the energy efficiency changes of the park equipment. Compare the prediction results of the preset energy efficiency prediction model with the actual energy efficiency data to determine the prediction deviation. Retrieve the preset causal forest model, and input the energy efficiency impact association and prediction deviation into the preset causal forest model. Use the causal forest model to analyze the input energy efficiency impact association and prediction deviation, and determine the abnormal causal contribution of each energy efficiency impact to the prediction deviation.

[0100] Through this solution, by analyzing energy efficiency changes and identifying the energy efficiency performance of equipment, a basis is provided for the analysis of prediction deviations, thereby improving the accuracy of the preset energy efficiency prediction model, reducing energy demand and reducing consumption trends. By determining the prediction deviation and identifying the accuracy of the prediction results, a basis is provided for anomaly detection and correction, reducing the risk of energy waste and equipment failure. Calling the preset causal forest model helps to quantify the contribution of each energy efficiency impact to energy efficiency fluctuations and provides a tool for determining abnormal causal contributions. By determining the abnormal causal contribution of each energy efficiency impact and quantifying the degree of influence of each energy efficiency impact on the prediction deviation, a scientific basis is provided for abnormal handling and energy efficiency management, thereby improving the level of equipment intelligence.

[0101] In some embodiments, the vibration spectrum of the compressor bearing and the refrigerant pressure curve are obtained; the vibration spectrum is analyzed to determine the mechanical wear level; the pressure curve is analyzed to determine the fluctuation amplitude at the start-stop moment; according to the fluctuation amplitude, the sealing performance attenuation coefficient is calculated; a three-dimensional health assessment space is established, where the X-axis is the harmonic distortion rate, the Y-axis is the mechanical wear level, and the Z-axis is the sealing performance attenuation coefficient; according to the three-dimensional health assessment space, the health benchmark cluster at the current moment is determined; the deviation degree between the current device state and the health benchmark cluster is calculated by the Mahalanobis distance; according to the deviation degree, the device health index is generated.

[0102] The vibration spectrum of the compressor bearing can be a frequency component distribution map converted from the vibration signal generated by the compressor bearing during operation through Fourier transform.

[0103] The refrigerant pressure curve can be a curve showing the change of the refrigerant pressure in the compressor device over time.

[0104] The mechanical wear level can be the degree of wear of the mechanical components in the device.

[0105] The start-stop moment can be the moment when the device starts and stops.

[0106] The fluctuation amplitude can be the difference between the maximum value and the minimum value of the fluctuation of the refrigerant pressure curve at the start-stop moment.

[0107] The sealing performance attenuation coefficient can be the rate of attenuation of the refrigerant sealing performance over time.

[0108] The three-dimensional health assessment space can be a three-dimensional coordinate system used to evaluate the health status of the device.

[0109] The health benchmark cluster can be the health distribution of the device in the normal state in the three-dimensional health assessment space.

[0110] The Mahalanobis distance can be a method for calculating the distance between the current device state and the health benchmark cluster in the three-dimensional health assessment space.

[0111] The current device state can be the operating state of the device at the current time point.

[0112] The deviation degree can be the degree of difference between the current device state and the health benchmark cluster.

[0113] Specifically, sensors and monitoring devices are used to collect the vibration spectrum of the compressor bearing and the refrigerant pressure curve data in real time. The vibration spectrum is analyzed through fast Fourier transform to determine the mechanical wear level. The refrigerant pressure curve is analyzed to determine the difference between the maximum and minimum values at the start and stop moments, that is, the fluctuation amplitude. A sealing performance decay model is established through statistical methods. Using the sealing performance decay model, the sealing performance decay coefficient is calculated based on the fluctuation amplitude data. A three-dimensional coordinate system is established, namely the three-dimensional health assessment space, where the X-axis is the harmonic distortion rate, the Y-axis is the mechanical wear level, and the Z-axis is the sealing performance decay coefficient. The collected harmonic distortion rate, mechanical wear level, and sealing performance decay coefficient are mapped into the three-dimensional health assessment space to form a point set of the current equipment state. The clustering analysis algorithm is used to cluster the point set of the current equipment state to determine the health benchmark cluster at the current moment. The Mahalanobis distance is used to calculate the distance between the current equipment state and the health benchmark cluster. The calculated distance is analyzed to determine the deviation degree between the current equipment state and the health benchmark cluster. The calculation method of the equipment health index is defined, and according to the defined calculation method, the deviation degree is converted into the equipment health index.

[0114] Through this solution, by collecting the vibration spectrum of the compressor bearing and the refrigerant pressure curve in real time, detailed data on the equipment operation is obtained. By analyzing the vibration spectrum, the mechanical wear level is determined, thereby predicting potential equipment failures and maintenance requirements. The fluctuation amplitude at the start and stop moments is determined to evaluate the sealing performance, providing a basis for sealing maintenance and optimization. Calculating the sealing performance decay coefficient helps predict the change trend of the sealing performance and prevent sealing failure in advance. By establishing a three-dimensional health assessment space, the health status of the equipment is evaluated more comprehensively, providing multi-dimensional references for equipment maintenance and operation optimization. According to the three-dimensional health assessment space, the health benchmark cluster is determined, that is, the health distribution of the equipment in the normal state, providing a standard for the evaluation of the equipment state. The Mahalanobis distance is used to calculate the deviation degree between the current equipment state and the health benchmark cluster, quantifying the abnormality degree of the equipment state, and providing a basis for fault warning and maintenance decision-making. According to the deviation degree, an equipment health index is generated, reflecting the overall health status of the equipment, and providing a scientific basis for equipment maintenance and operation optimization.

[0115] In some embodiments, the park activity schedule and weather forecast data are obtained; according to the park activity schedule and weather forecast data, the scheduled activities are determined; the spatio-temporal overlap degree between the abnormal root cause and the scheduled activities is analyzed to determine the human influence factors; according to the human influence factors and the weather forecast data, a multi-objective optimization strategy is generated; the equipment operation parameters and regional linkage rules are adjusted according to the multi-objective optimization strategy.

[0116] The park activity schedule can be a schedule of various activities in the park.

[0117] Weather forecast data can be prediction data on future weather conditions provided by meteorological departments.

[0118] Scheduled activities can be activities such as meetings, exhibitions, and festival celebrations arranged within the park.

[0119] The spatio-temporal overlap degree can be the degree of overlap between the abnormal root cause and the scheduled activities in terms of time and space.

[0120] Human influence factors can be the impacts of the behaviors and activities of the personnel within the park on energy efficiency.

[0121] The multi-objective optimization strategy can be the optimal scheduling strategy formulated considering objectives such as energy efficiency, cost, and user comfort.

[0122] Device operation parameters can be adjustable parameters such as the temperature setting of the air conditioner and the brightness of the lighting during the operation of the device.

[0123] The area linkage rule can be the linkage control rule for the operation of devices between different areas within the park.

[0124] Specifically, obtain the park activity schedule and weather forecast data through the park management department and the meteorological department. According to the park activity schedule and weather forecast data, determine the schedule activities such as activity type, time, location, and expected number of people. Analyze the matching degree between the abnormal root cause and the time period of the schedule activities, that is, the spatio-temporal overlap degree. Determine the human influence factors based on the analysis result of the spatio-temporal overlap degree. Construct a multi-objective optimization model through an optimization algorithm. Use the multi-objective optimization model to generate a multi-objective optimization strategy based on the human influence factors and weather forecast data. Adjust the device operation parameters such as the temperature setting of the air conditioner, the brightness of the lighting, and the HVAC operation mode and optimize the area linkage rule according to the multi-objective optimization strategy.

[0125] Through this solution, by obtaining the park activity schedule and weather forecast data, better predict and plan energy demand, thereby optimizing energy distribution and device scheduling. Determine the upcoming schedule activities according to the park activity schedule and weather forecast data, thereby predicting the energy demand and device usage in different time periods. Identify human influence factors by analyzing the spatio-temporal overlap degree between the abnormal root cause and the schedule activities, and take targeted corrective measures. Generate a multi-objective optimization strategy based on the human influence factors and weather forecast data, such as adjusting device operation parameters and optimizing energy distribution, to improve energy utilization efficiency. Adjust the device operation parameters and area linkage rule according to the multi-objective optimization strategy to optimize energy efficiency and improve the operation efficiency and stability of the device.

[0126] In some embodiments, analyze the topographic map of the park to determine the building structure characteristics; based on the building structure characteristics, determine the distribution of ventilation corridors; extract the movement trajectory characteristics of the crowd heat map to determine the distribution of personnel stay time; according to the distribution of ventilation corridors and the distribution of personnel stay time, calculate the heat load index of each sub-region; according to the building structure characteristics, determine the thermal parameters of the building envelope structure; according to the thermal parameters, correct the heat load index; based on the corrected heat load index, generate a regional characteristic description vector including dynamic weight coefficients to obtain the regional characteristics of each sub-region.

[0127] The building structure characteristics can be physical structure and design features such as the height, layout, orientation, materials, window size and location of the building.

[0128] The distribution of ventilation corridors can be natural ventilation channels designed within the park.

[0129] The movement trajectory characteristics can be the movement paths and patterns of personnel within the park.

[0130] The distribution of personnel stay time can be the length and frequency of stay of personnel in each sub-region within the park.

[0131] The heat load index can be a quantitative index used to represent the heat load of each sub-region within the park.

[0132] The building envelope structure can be the envelope structures such as the exterior walls, roofs, floors, windows and doors of the building.

[0133] The thermal parameters can be parameters describing the thermal performance of the building envelope structure.

[0134] The dynamic weight coefficient can be a coefficient used to adjust the influence of different factors on the heat load index.

[0135] The regional characteristic description vector can be a multi-dimensional data structure used to describe the characteristics of each sub-region within the park.

[0136] Specifically, use a geographic information device to analyze the topographic map of the park and identify building structure features such as building height, layout, and orientation. Use a building information model to analyze the structure of the building. Evaluate the ventilation requirements of the building and determine the necessity of ventilation corridors. Based on the building structure features and the necessity of ventilation corridors, design the distribution of ventilation corridors. Extract the movement trajectory features of personnel such as movement speed, movement direction, and movement frequency from the pedestrian heat map. Analyze the movement trajectory features and determine the personnel stay time distribution in each sub-region of the park. Establish a heat load calculation model and use the heat load calculation model to calculate the heat load index of each sub-region according to the ventilation corridor distribution and the personnel stay time distribution. According to the building structure features, identify the thermal parameters of the building envelope such as thermal conductivity, thermal resistance, heat capacity, and solar heat gain coefficient. Update the heat load calculation model and integrate the collected thermal parameters into the model. Use the updated heat load calculation model to recalculate the heat load index of each sub-region. Modify the heat load index according to the calculation results of the heat load calculation model. Based on the modified heat load index, construct a multi-dimensional feature vector. Use data analysis methods to determine the dynamic weight coefficients of each feature in the multi-dimensional feature vector. According to the determined dynamic weight coefficients, generate a regional feature description vector containing the dynamic weight coefficients. According to the generated regional feature description vector, obtain the regional features of each sub-region.

[0137] Through this solution, by analyzing the topographic map of the park and identifying the building structure features, it helps in the analysis of the ventilation corridor distribution and heat load calculation. Based on the building structure features, determining the ventilation corridor distribution in the park helps in natural ventilation and air conditioning design. By analyzing the pedestrian heat map and extracting the movement trajectory features of personnel, it helps in the analysis of personnel flow and personnel stay time. According to the pedestrian heat map, determining the personnel stay time distribution in each sub-region of the park helps in evaluating the heat load demand of each sub-region. Combining the ventilation corridor distribution and the personnel stay time distribution to calculate the heat load index of each sub-region provides a basis for energy efficiency management. According to the building structure features, determining the thermal parameters of the building envelope provides data support for the correction of the heat load index. According to the thermal parameters of the building envelope, modifying the heat load index improves the accuracy and practicality of the building envelope. Based on the modified heat load index, generating a regional feature description vector containing dynamic weight coefficients reflects the characteristics of each sub-region and provides a basis for personalized energy efficiency management.

[0138] Figure 3 This is a schematic structural diagram of an intelligent park energy efficiency management system based on IBMS provided by an embodiment of the present application, as Figure 3 shown, the intelligent park energy efficiency management system 300 based on IBMS in this embodiment includes: a data analysis module 301, a change analysis module 302, and a solution determination module 303.

[0139] The data analysis module 301 is used to obtain real-time park data; analyze the real-time park data based on a preset energy efficiency prediction model, and predict energy efficiency changes; The change analysis module 302 is used to analyze the energy efficiency changes based on the real-time park data, and determine the credibility of each energy efficiency change; The solution determination module 303 is used to determine an energy efficiency management solution according to the credibility.

[0140] Optionally, when the data analysis module 301 analyzes the real-time park data based on a preset energy efficiency prediction model to predict energy efficiency changes, it is used for: Analyze the real-time park data to determine the park topographic map, the pedestrian flow heat map, and the park equipment information; According to the park equipment information, divide the park into several sub-regions; Analyze the park topographic map and the pedestrian flow heat map to determine the regional characteristics of each sub-region; Based on a preset energy efficiency prediction model, predict energy efficiency changes according to the regional characteristics of each sub-region.

[0141] Optionally, when the solution determination module 303 determines an energy efficiency management solution according to the credibility, it is used for: Compare the credibility with a preset credibility threshold to obtain a comparison result; If the comparison result is that the credibility is higher than the preset credibility threshold, determine an energy efficiency management solution according to the energy efficiency changes; If the comparison result is that the credibility is lower than the preset credibility threshold, determine the regional connection of adjacent sub-regions according to the park equipment information; Obtain an energy efficiency impact knowledge graph; Determine an energy efficiency impact association according to the regional connection and the energy efficiency impact knowledge graph; Determine the abnormal causal contribution degree of each energy efficiency impact according to the energy efficiency impact association and the preset energy efficiency prediction model; Determine the abnormal root cause according to the abnormal causal contribution degree, and modify the energy efficiency management solution according to the abnormal root cause to obtain the best management solution for dealing with the abnormality.

[0142] Optionally, when the change analysis module 302 analyzes the energy efficiency changes based on the real-time park data to determine the credibility of each energy efficiency change, it is used for: Based on the park equipment information, analyze the real-time park data to determine the equipment current waveform, the number of compressor starts and stops, and the valve opening degree of each device; Analyze the equipment current waveform by fast Fourier transform to determine the harmonic distortion rate; Obtain the historical operation data of the device, analyze the historical operation time of the device, and determine the historical fault information; Analyze the historical fault information to determine the cause of the fault; According to the cause of the fault, determine the correlation between the harmonic distortion rate and each historical fault information; According to the correlation, determine the harmonic distortion rate threshold; According to the harmonic distortion rate threshold and the number of compressor starts and stops, construct a device health index; Based on the device health index, analyze the energy efficiency change and determine the credibility of each energy efficiency change.

[0143] Optionally, when the solution determination module 303 determines the energy efficiency impact correlation according to the regional connection and the energy efficiency impact knowledge graph, it is used for: Analyze the energy efficiency impact knowledge graph and the regional connection to determine the device topology relationship; According to the device topology relationship, determine the energy transfer path between any two devices; Analyze the real-time park data to determine the real-time environmental parameters of each sub-region; Based on the graph neural network model, analyze the coupling relationship between the energy transfer path and the real-time environmental parameters to generate a dynamic energy efficiency impact weight; According to the dynamic energy efficiency impact weight, quantify the energy efficiency correlation strength between adjacent sub-regions; According to the energy efficiency correlation strength between adjacent sub-regions, determine the energy efficiency impact correlation.

[0144] Optionally, when the solution determination module 303 determines the abnormal causal contribution degree of each energy efficiency impact according to the energy efficiency impact correlation and the preset energy efficiency prediction model, it is used for: Based on the preset energy efficiency prediction model, analyze the energy efficiency change to determine the prediction deviation; Retrieve the preset causal forest model, and based on the preset causal forest model, according to the energy efficiency impact correlation and the prediction deviation, determine the abnormal causal contribution degree of each energy efficiency impact.

[0145] Optionally, when the change analysis module 302 constructs a device health index according to the harmonic distortion rate threshold and the number of compressor starts and stops, it is used for: Obtain the compressor bearing vibration spectrum and the refrigerant pressure curve; Analyze the vibration spectrum to determine the mechanical wear level; Analyze the pressure curve to determine the fluctuation amplitude at the start and stop moments; According to the fluctuation amplitude, calculate the sealing performance attenuation coefficient; Establish a three-dimensional health assessment space, where the X-axis is the harmonic distortion rate, the Y-axis is the mechanical wear level, and the Z-axis is the sealing performance attenuation coefficient; According to the three-dimensional health assessment space, determine the health benchmark cluster at the current moment; Calculate the deviation degree between the current device state and the health benchmark cluster through the Mahalanobis distance; Generate a device health index according to the deviation degree.

[0146] Optionally, when the scheme determination module 303 corrects the energy efficiency management scheme according to the abnormal root cause, it is used for: Obtain the park activity schedule and weather forecast data; Determine the schedule activities according to the park activity schedule and weather forecast data; Analyze the spatio-temporal overlap degree between the abnormal root cause and the schedule activities to determine the human influence factors; Generate a multi-objective optimization strategy according to the human influence factors and the weather forecast data; Adjust the device operation parameters and regional linkage rules according to the multi-objective optimization strategy.

[0147] Optionally, when the data analysis module 301 analyzes the park topographic map and the pedestrian flow heat map to determine the regional characteristics of each sub-region, it is used for: Analyze the park topographic map to determine the building structure characteristics; Determine the distribution of ventilation corridors according to the building structure characteristics; Extract the movement trajectory characteristics of the pedestrian flow heat map to determine the distribution of personnel stay time; Calculate the heat load index of each sub-region according to the distribution of ventilation corridors and the distribution of personnel stay time; Determine the thermal parameters of the building envelope according to the building structure characteristics; Correct the heat load index according to the thermal parameters; Based on the corrected heat load index, generate a regional characteristic description vector containing dynamic weight coefficients to obtain the regional characteristics of each sub-region.

[0148] The system of this embodiment can be used to execute the method of any of the above embodiments, and its implementation principle and technical effects are similar, so they will not be elaborated here.

Claims

1. A smart park energy efficiency management method based on IBMS, characterized in that: include: Get real-time park data; Based on a preset energy efficiency prediction model, the real-time park data is analyzed to predict energy efficiency changes; Based on the real-time park data, analyzing the energy efficiency changes and determining the credibility of each energy efficiency change; An energy efficiency management plan is determined based on the credibility.

2. The method according to claim 1, characterized in that The analyzing the real-time park data based on the preset energy efficiency prediction model to predict energy efficiency changes includes: Analyze the real-time park data to determine the park topographic map, human flow heat map and park equipment information; According to the park equipment information, the park is divided into regions to obtain a plurality of sub-regions; Analyze the park topographic map and the human flow heat map to determine the regional characteristics of each sub-area; Based on the preset energy efficiency prediction model, the energy efficiency changes are predicted according to the regional characteristics of each sub-region.

3. The method according to claim 2, characterized in that Determining an energy efficiency management plan according to the credibility includes: Comparing the credibility with a preset credibility threshold to obtain a comparison result; If the comparison result is that the credibility is higher than the preset credibility threshold, determining an energy efficiency management plan according to the energy efficiency change; If the comparison result is that the credibility is lower than the preset credibility threshold, determining the regional connection of adjacent sub-areas according to the park equipment information; Obtain the knowledge graph of energy efficiency impact; Determining energy efficiency impact associations based on the regional connections and the energy efficiency impact knowledge graph; Determining the abnormal causal contribution of each energy efficiency impact according to the energy efficiency impact association and the preset energy efficiency prediction model; According to the abnormal causal contribution, the root cause of the abnormality is determined, and according to the abnormal root cause, the energy efficiency management plan is corrected to obtain the best management plan for dealing with the abnormality.

4. The method according to claim 2, characterized in that: The step of analyzing the energy efficiency change based on the real-time park data and determining the credibility of each energy efficiency change includes: Based on the park equipment information, the real-time park data is analyzed to determine the equipment current waveform, compressor start and stop times, and valve opening of each equipment; Analyzing the current waveform of the device by fast Fourier transform to determine the harmonic distortion rate; Obtain historical operation data of the equipment, analyze the historical operation time of the equipment, and determine historical fault information; Analyze the historical fault information to determine the cause of the fault; According to the fault cause, determining the correlation between the harmonic distortion rate and each historical fault information; According to the association relationship, determining a harmonic distortion rate threshold; Constructing an equipment health index according to the harmonic distortion rate threshold and the number of compressor starts and stops; Based on the equipment health index, the energy efficiency change is analyzed to determine the credibility of each energy efficiency change.

5. The method according to claim 3, characterized in that: The determining of energy efficiency impact association according to the regional connection and the energy efficiency impact knowledge graph includes: Analyze the energy efficiency impact knowledge graph and the regional connections to determine the equipment topology relationship; Determine an energy transfer path between any two devices according to the device topology relationship; Analyze the real-time park data to determine the real-time environmental parameters of each sub-area; Based on the graph neural network model, the coupling relationship between the energy transfer path and the real-time environmental parameters is analyzed to generate a dynamic energy efficiency impact weight; quantifying the energy efficiency correlation strength between adjacent sub-regions according to the dynamic energy efficiency impact weight; The energy efficiency impact association is determined according to the energy efficiency association strength between the adjacent sub-regions.

6. The method according to claim 3, characterized in that Determining the abnormal causal contribution of each energy efficiency impact according to the energy efficiency impact association and the preset energy efficiency prediction model includes: Based on the preset energy efficiency prediction model, analyzing the energy efficiency change and determining the prediction deviation; A preset causal forest model is retrieved, and based on the preset causal forest model, the abnormal causal contribution of each energy efficiency impact is determined according to the energy efficiency impact association and the prediction deviation.

7. The method according to claim 4, characterized in that The constructing of the equipment health index according to the harmonic distortion rate threshold and the number of compressor starts and stops includes: Obtain compressor bearing vibration spectrum and refrigerant pressure curve; Analyzing the vibration spectrum to determine the level of mechanical wear; Analyze the pressure curve to determine the fluctuation amplitude at the start and stop moments; Calculating the sealing performance attenuation coefficient according to the fluctuation amplitude; Establish a three-dimensional health assessment space, where the X-axis is the harmonic distortion rate, the Y-axis is the mechanical wear level, and the Z-axis is the sealing performance attenuation coefficient; Determining a health benchmark cluster at a current moment according to the three-dimensional health assessment space; Calculate the deviation between the current device state and the health benchmark cluster by Mahalanobis distance; A device health indicator is generated according to the deviation.

8. The method according to claim 3, characterized in that The step of modifying the energy efficiency management scheme according to the abnormal root cause includes: Get park activity schedules and weather forecast data; Determine the scheduled activities according to the park activity schedule and weather forecast data; Analyze the temporal and spatial overlap between the root cause of the anomaly and the schedule activities to determine the human influencing factors; Generate a multi-objective optimization strategy based on the human influencing factors and the weather forecast data; The equipment operating parameters and regional linkage rules are adjusted according to the multi-objective optimization strategy.

9. The method according to claim 5, characterized in that The analyzing the park topographic map and the human flow heat map to determine the regional characteristics of each sub-area includes: Analyze the topographic map of the park to determine the characteristics of the building structure; Determine the distribution of ventilation corridors according to the structural characteristics of the building; Extract the movement trajectory characteristics of the crowd flow heat map and determine the distribution of people's stay time; Calculate the heat load index of each sub-area according to the ventilation corridor distribution and the personnel residence time distribution; Determining thermal parameters of the building envelope structure according to the building structure characteristics; According to the thermal parameters, modifying the heat load index; Based on the modified heat load index, a regional characteristic description vector including a dynamic weight coefficient is generated to obtain the regional characteristics of each sub-region.

10. A smart park energy efficiency management system based on IBMS, characterized in that: The method as claimed in any one of claims 1 to 9 comprises: A data analysis module is used to obtain real-time park data; based on a preset energy efficiency prediction model, the real-time park data is analyzed to predict energy efficiency changes; A change analysis module, used to analyze the energy efficiency changes based on the real-time park data and determine the credibility of each energy efficiency change; A scheme determination module is used to determine an energy efficiency management scheme according to the credibility.

Images