Intelligent data detection method and system based on transportation hub energy management and control system

Abstract

The invention provides an intelligent data detection method and system based on a transportation junction energy management and control system. The method comprises the steps of receiving standardized multi-source heterogeneous energy data and performing data caching through a preset caching mechanism; based on the cached data features, loading a corresponding verification rule from a multi-source energy coupling rule base to output and obtain a verification strategy packet; verifying the data through a preset verification mechanism according to the loaded data change feature tag; wherein the verification mechanism comprises threshold verification, physical rationality verification, time sequence smoothness verification and multi-source consistency and coupling relation verification; and generating a structured quality label based on a verification result, and performing grading processing according to a data type. The method is suitable for real-time quality verification, abnormity identification and quality tagging output of multi-source heterogeneous energy data such as electricity, heat, cold and gas, and a high-credibility data basis is provided for subsequent data statistics, missing detection, intelligent additional recording and AI advanced application.

Description

Technical Field

[0001] This application belongs to the field of energy system management and control technology, and in particular relates to an intelligent data detection method and system based on a transportation hub energy management and control system. Background Technology

[0002] In the operation of integrated energy systems, high-quality raw data is a prerequisite for realizing intelligent applications such as load forecasting, energy efficiency optimization, fault diagnosis, carbon emission accounting, and digital twins. However, in actual operation, data anomalies such as exceeding limits, logical contradictions, timing jumps, and topology imbalances often occur due to sensor drift, communication interruption, equipment start-up and shutdown, and human configuration errors.

[0003] Traditional data preprocessing methods have the following serious drawbacks: 1) Relying solely on static threshold verification: For example, setting a uniform voltage fluctuation of ±5% cannot adapt to periodic fluctuations such as day and night load and seasonal changes, resulting in a large amount of normal data being misjudged as abnormal; 2) Ignoring the physical laws of multi-energy coupling: For example, the heat-to-power ratio of a combined heat and power (CHP) unit should be within a reasonable range (e.g., 0.7~1.3). If only the electrical power is checked for exceeding the limit, while ignoring its matching relationship with the thermal power, logically contradictory data will flow into the subsequent system. 3) Lack of topology consistency verification: For example, the total incoming power in a power distribution system should be equal to the sum of the power of each branch (with an allowable error of ±5%). Traditional methods cannot detect this type of system-level imbalance. 4) Crude anomaly handling: All abnormal data is discarded indiscriminately, resulting in the loss of effective transient information such as equipment start-up and shutdown and load changes, which affects data integrity; 5) Lack of a quality labeling system: It is unable to distinguish between "deterministic anomalies" (such as exceeding the range) and "suspicious anomalies" (such as minor fluctuations), making it difficult to support subsequent intelligent supplementary recording or AI model training. Summary of the Invention

[0004] In view of this, this application aims to propose an intelligent data detection method and system based on a transportation hub energy management system to solve at least one of the above problems.

[0005] To achieve the above objectives, the technical solution of this application is implemented as follows: Firstly, this application provides an intelligent data detection method based on a transportation hub energy management and control system, including: It receives standardized multi-source heterogeneous energy data and caches the data through a preset caching mechanism; Based on the cached data features, and by loading corresponding verification rules from the multi-source energy coupling rule base, a verification strategy package is output; wherein, the data features include the measurement point code and device type of the data; Based on the loaded data change feature tags, the data is verified through a preset verification mechanism; wherein, the verification mechanism includes threshold verification, physical rationality verification, temporal smoothing verification, and multi-source consistency and coupling relationship verification. Structured quality labels are generated based on the verification results, and then graded according to the data type.

[0006] Secondly, based on the same inventive concept, this application also provides an intelligent data detection system based on a transportation hub energy management and control system, comprising: The data receiving module is configured to receive standardized multi-source heterogeneous energy data and cache the data through a preset caching mechanism; The verification rule loading module is configured to load corresponding verification rules from the multi-source energy coupling rule base based on cached data features, and output a verification strategy package; wherein, the data features include the measurement point code and device type of the data; The verification module is configured to verify the data based on the loaded data change feature tags through a preset verification mechanism; wherein, the verification mechanism includes threshold verification, physical rationality verification, temporal smoothing verification, and multi-source consistency and coupling relationship verification. The hierarchical processing module is configured to generate structured quality labels based on the verification results and perform hierarchical processing according to the data type.

[0007] Thirdly, based on the same inventive concept, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method described in the first aspect.

[0008] Fourthly, based on the same inventive concept, this application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions for causing the computer to perform the method as described in the first aspect.

[0009] Compared with existing technologies, the intelligent data detection method and system based on the energy management and control system of transportation hubs described in this application have the following advantages: The intelligent data detection method based on the energy management and control system of transportation hubs described in this application establishes a multi-dimensional, adaptive, and refined energy data processing and anomaly detection mechanism by integrating physical mechanism models, data-driven methods, system topology and historical behavior patterns. It is applicable to real-time quality verification, anomaly identification and quality labeling output of multi-source heterogeneous energy data such as electricity, heat, cooling and gas, providing a highly reliable data foundation for subsequent data statistics, missing data detection, intelligent data supplementation and advanced AI applications. Attached Figure Description

[0010] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a flowchart of an intelligent data detection method based on a transportation hub energy management system, as described in an embodiment of this application. Figure 2 This is a flowchart illustrating the verification rule loading process described in the embodiments of this application. Figure 3 This is a flowchart illustrating the multi-source consistency and coupling relationship verification process described in the embodiments of this application. Figure 4 This is a flowchart illustrating the scalar label generation and data splitting process described in the embodiments of this application. Figure 5 This is a schematic diagram of the structure of an intelligent data detection system based on a transportation hub energy management and control system, as described in an embodiment of this application. Figure 6 This is a schematic diagram of the hardware structure of the electronic device described in an embodiment of this application. Detailed Implementation

[0011] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.

[0012] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this application should have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms "first," "second," and similar terms used in the embodiments of this application do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are only used to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0013] The embodiments of this application are described in detail below with reference to the accompanying drawings.

[0014] Please see Figure 1 As shown in the figure, this embodiment provides an intelligent data detection method based on a transportation hub energy management and control system, which specifically includes the following steps: Step S101: Receive standardized multi-source heterogeneous energy data and cache the data through a preset caching mechanism.

[0015] Specifically, in this embodiment, step S101 is the data entry point for the entire anomaly detection process, undertaking the tasks of standardized access to raw data, classification caching, and historical context construction.

[0016] The system receives standardized ValueReal data structures from the upstream data acquisition and parsing module. Each record contains five key fields: ① Timestamp: accurate to the second or millisecond, used for subsequent time series alignment and rate of change calculation; ② Unique device identifier (device_id): used to associate device files, operating status, and topology location; ③ Point code: A unique identifier for a physical quantity (such as "CHP_electric power" or "chilled water supply temperature"), which is the core key for rule matching and cache management; ④ Actual physical quantity value (ValueReal): A floating-point value after unit standardization (e.g., kW, ℃, m³ / h); ⑤ Communication status flag (comm_status): Indicates whether there is a transmission abnormality due to communication interruption, verification failure, etc. (such as "OK", "Timeout", "CRCError").

[0017] By establishing an independent real-time cache queue for each measuring point (e.g., using a circular buffer or time-series database), data from multiple energy types such as electricity, heat, cooling, and gas are logically isolated and processed to avoid cross-interference. Simultaneously, a dynamic historical data window is initialized for each measuring point, using a default strategy of "same time period for the past 7 days" (e.g., if the current time is 14:30 on Friday, October 24, 2025, the historical window includes data from 14:15–14:45 of the past 6 Fridays). This design effectively captures daily and weekly periodic load patterns (e.g., weekday peaks and nighttime troughs), providing highly relevant historical samples for dynamic threshold calculation.

[0018] Whenever new data arrives, old data is automatically discarded in chronological order to ensure that the historical window always reflects the latest operating conditions and avoids distortion of historical data due to seasonal changes or equipment upgrades.

[0019] Step S102: Based on the cached data features, and by loading the corresponding verification rules from the multi-source energy coupling rule base, a verification strategy package is output; wherein, the data features include the measurement point code and device type of the data.

[0020] Specifically, in this embodiment, after receiving and caching the data, corresponding verification rules need to be loaded based on the specific characteristics of the data to ensure the scientific validity and effectiveness of subsequent verification work. The core of this process lies in automatically matching and loading the corresponding verification strategy package from the multi-source energy coupling rule base based on the measurement point code and device type of the current data. The verification rule loading process is as follows: Figure 2 As shown.

[0021] Furthermore, the physical coupling model is based on the conversion laws between different energy forms and the physical characteristics of equipment operation. For example, the electro-thermal conversion efficiency is an important indicator for measuring the efficiency of converting electrical energy into thermal energy. Different types of electric heating equipment have different conversion efficiencies. The system will load the corresponding electro-thermal conversion efficiency standard range for the equipment based on the equipment type and measurement point code. The heat-to-power ratio of a CHP (combined heat and power) unit refers to the ratio of the heat energy it generates to the electrical energy it generates. Different models of CHP units have different reasonable ranges for their heat-to-power ratios. The system will accurately load the corresponding heat-to-power ratio range for the unit. For example, the reasonable range for the heat-to-power ratio of some CHP units is 0.7-1.3. The coefficient of performance (COP) is an indicator for measuring the cooling efficiency of refrigeration equipment. For common refrigeration equipment, its COP value is usually between 3.0 and 6.0. The system will load this standard range for subsequent verification. The gas-to-heat consumption ratio is for gas-fired boilers and reflects the proportional relationship between gas consumption and heat energy generated. The system will load the corresponding reasonable range for the gas-to-heat consumption ratio based on the type and specifications of the gas-fired boiler.

[0022] Rated parameters of equipment are crucial for its normal and safe operation, including rated power (Prated) and maximum permissible rate of change (Rmax). Rated power refers to the power value that the equipment can maintain stable operation under rated conditions over a long period. The system accurately loads the rated power of the equipment based on its model and specifications. For example, if a water pump has a rated power of 15kW, the system will use 15kW as an important reference standard for power verification. The maximum permissible rate of change refers to the maximum allowable variation of equipment operating parameters (such as flow rate and power) per unit time. Taking a water pump as an example, its flow rate variation rate is typically required to not exceed 10% / min. The system loads this parameter to determine whether the water pump's flow rate variation is within a safe and reasonable range, preventing damage to the equipment or disruption to system stability caused by excessively rapid parameter changes.

[0023] The system topology reflects the connection methods and energy flow relationships between various devices and measuring points in the integrated energy system. The verification rules formulated based on this embodiment can ensure the consistency and rationality of the overall system operation data.

[0024] For example, in a power distribution system, the total incoming power should theoretically be equal to the sum of the power of each branch. Considering factors such as line losses, an error of ±5% is allowed. The system will load this topology rule to verify the balance of the power data of the power distribution system. In a heating station, in order to ensure that heat can be transferred effectively, the supply water temperature usually needs to be 5°C higher than the return water temperature. The system will load the rule "supply water temperature > return water temperature + 5°C" to determine whether the temperature data of the heating station meets the operating requirements. In a chilled water plant, there is a certain matching relationship between the chilled water flow rate and the cooling water flow rate. In order to ensure the cooling effect and system stability of the chilled water plant, the deviation between the two is usually not allowed to exceed ±10%, and the system will load this flow balance verification rule.

[0025] The data from different measuring points exhibit varying characteristics during operation; some data change relatively smoothly, while others change more frequently. Data change characteristic labels categorize measuring points into "steady-state" and "dynamic" types. "Steady-state" data typically has a change rate of less than 5%, such as lighting voltage and ambient temperature. These data fluctuate little and are relatively stable under normal operating conditions. "Dynamic" data, on the other hand, has a change rate greater than or equal to 5%, such as variable frequency pump current and CHP unit output power. These data change significantly with factors such as system load variations and adjustments to equipment operating conditions.

[0026] The system accurately loads the data change feature tags corresponding to each measurement point based on the measurement point code and equipment type, providing a basis for adopting differentiated threshold judgment methods in subsequent dynamic threshold verification.

[0027] Step S103: Based on the loaded data change feature tags, verify the data through a preset verification mechanism; wherein, the verification mechanism includes threshold verification, physical rationality verification, temporal smoothing verification, and multi-source consistency and coupling relationship verification.

[0028] Specifically, in this embodiment, dynamic threshold verification uses different threshold judgment methods based on data change feature labels to make a preliminary judgment on whether the data is within the normal range, while giving priority to manual safety red line thresholds to ensure the safe operation of the system.

[0029] (1) Threshold judgment for steady-state data.

[0030] Steady-state data (such as lighting voltage and ambient temperature) change relatively smoothly during normal operation, with a relatively fixed operating range and minimal impact from external factors. Therefore, a fixed threshold range is used for verification of this type of data. For example, the normal operating range of lighting voltage is typically 220V ± 5%, or 209V-231V. This fixed threshold range is used as the verification standard for lighting voltage data. If the measured lighting voltage is within this range, it is considered normal; if it exceeds this range, it is marked as abnormal. The setting of the fixed threshold range is based on the equipment's technical parameters, relevant industry standards, and long-term operating experience, and can accurately reflect the normal operating range of steady-state data.

[0031] Traditional fixed thresholds (such as 220V ± 5%) cannot adapt to small but continuous drifts caused by equipment aging, changes in ambient temperature, etc., leading to false alarms. This embodiment introduces a confidence interval model based on a short-term sliding window, which can adaptively track the central trend and small fluctuations of steady-state data. The confidence interval model formula is as follows: ; in, , , ; In the formula, This represents the weighted average of a short-term sliding window (e.g., the most recent 30 data points); This represents the weighted standard deviation of the window. This represents the time decay weight; data closer to the current time has a higher weight, and λ is the decay factor. The confidence coefficient is typically taken as 1.5 to 2.0, corresponding to a confidence interval of approximately 85%-95%, which is more sensitive than the traditional 3σ (99.7%) and can capture minute anomalies. This is the size of the sliding window.

[0032] The model upgrades the "fixed threshold" to a "dynamic adaptive threshold". Through short-term weighted statistics, it can filter out random noise and slowly adapt to the drift of the benchmark value caused by equipment aging or environmental changes, which significantly reduces the false alarm rate of steady-state data.

[0033] (2) Threshold judgment for dynamic data Dynamic data (such as variable frequency pump current) is significantly affected by factors such as system load changes and equipment operating status adjustments. Its normal operating range varies with operating conditions, making it difficult to accurately determine whether the data is normal using a fixed threshold range. Therefore, calculating the average based on historical data from the same period (as opposed to variable frequency pump current) is necessary. ) and standard deviation ( ), and set the dynamic threshold range to [ , The window period is generally 7 days, and the calculation formula is as follows: ; In the formula, the mean ( ) reflects the average level of data for the same historical period, and the standard deviation ( This reflects the degree of dispersion of historical data from the same period.

[0034] By calculation [ , The specified range covers 99.73% of the data from the same historical period. This range is considered the normal range for dynamic data. If the measured data falls within this range, it is considered normal; if it exceeds this range, it is marked as abnormal. For example, the average current data of a variable frequency water pump during the 8:45-9:15 time period over the past six Mondays. 10A, standard deviation If the current is 0.5A, then the dynamic threshold range of the variable frequency pump current during this period is [10-3×0.5, 10+3×0.5], which is [8.5A, 11.5A]. If the current measured current is 12A, which exceeds this range, it is marked as abnormal.

[0035] (3) Prioritize the judgment of artificial safety red line threshold. Manually set safety thresholds are established based on the highest requirements for system safety and the ultimate capacity of equipment, serving as a crucial safeguard for system and equipment safety. If a system is configured with a manually set safety threshold (e.g., a voltage limit of 253V), this threshold will be used preferentially during dynamic threshold verification. Regardless of whether the data is steady-state or dynamic, any measured data exceeding the manually set safety threshold will be immediately marked as "safety exceeded" and trigger a high-priority alarm. High-priority alarms will promptly notify relevant maintenance personnel via pop-ups, audible alerts, etc., enabling them to quickly take measures to troubleshoot and prevent equipment damage, system failures, or even safety incidents caused by exceeding data limits.

[0036] For example, if the manual safety threshold for the voltage of a certain device is set to 253V, even if the dynamic threshold range of the device's voltage is [200V, 250V], when the measured voltage reaches 254V, although it exceeds the dynamic threshold range, more importantly, it exceeds the manual safety threshold. At this time, the system will prioritize marking it as "safety limit exceeded" and trigger a high-priority alarm.

[0037] Considering the real-time load rate of the equipment Environmental stress The impact on the safety threshold, and on the original artificial safety red line ( / Dynamic correction is performed using the following formula: The revised formula for the upper limit of the red line is: ; The revised formula for the lower limit of the red line is: ; In the formula, Sbase-lower indicates the upper limit of the device's original safety redline, and Sbase-lower indicates the lower limit of the device's original safety redline. Indicates the real-time load rate of the device: ; Indicates real-time power. Indicates rated power. Indicates the rated load rate of the equipment. This represents the load impact factor, set based on equipment type: 0.15 for electric heating equipment, 0.12 for CHP units, and 0.08 for water pumps. The environmental impact coefficient is set based on equipment sensitivity: 0.2 for precision instruments and 0.15 for ordinary motors. Among them, environmental stress coefficient The formula is: ; In the formula, Indicates the current temperature. Indicates the current humidity. , .

[0038] By introducing the "artificial safety red line dynamic correction model", "short-term weighted confidence interval of steady-state data", and "historical contemporaneous data of dynamic data", this approach is adopted. The multi-level threshold mechanism, including the "window" mechanism, effectively distinguishes between real anomalies and normal fluctuations. Combined with physical coupling relationships (such as CHP heat-to-power ratio and gas-fired heat production efficiency), topological consistency (such as power distribution balance and cooling station flow matching), and physical formula consistency (such as P=U×I) verification, it can accurately identify logically contradictory hidden anomalies, reducing the overall false detection rate by more than 30%.

[0039] Physical rationality verification is based on the physical constraints and basic physical rules of the equipment. It involves in-depth verification of the inherent consistency and rationality of the data to ensure that the data conforms to the physical laws governing the operation of the equipment.

[0040] (1) Judgment of the rationality of equipment operating conditions Equipment is designed and manufactured with rated operating parameters and operating ranges. Operating outside these ranges can adversely affect the equipment's performance and lifespan, and may even lead to damage. Therefore, it is necessary to determine whether the current operating power (P) of the equipment meets the operating requirements. Typically, the current power is specified... ( The regulation (referring to the rated power of the equipment) takes into account both the potential for short-term overload operation during actual operation and sets a reasonable upper limit for equipment operation safety. For example, the rated power of a certain motor... If the power is 20kW, then the maximum allowable operating power is 1.2 × 20 = 24kW. If the current measured motor power is 25kW, which exceeds the allowable range, it will be marked as "operating condition over the limit". This will prompt the maintenance personnel to check the equipment's operating status in a timely manner and investigate whether there are problems such as excessive load or equipment failure.

[0041] (2) Consistency judgment of physical formulas In integrated energy systems, many physical quantities have clearly defined mathematical relationships, and the consistency of relevant data can be verified based on these physical formulas. For example, the power calculation formula... ( For power, For voltage, Taking current as an example, for electrical equipment, the measured power, voltage, and current data should satisfy this formula. In actual measurement, due to factors such as the accuracy error of the measuring instrument and interference from the measurement environment, there may be a certain error between the measured data and the theoretical calculated value. However, this error should be controlled within a reasonable range. Generally, a relative error > 5% is considered abnormal. The formula for calculating the relative error is: (|Measured Power - Theoretical Calculated Power| / Theoretical Calculated Power) × 100%. For example, if the measured voltage U of a device is 220V and the measured current I is 10A, the theoretical power calculated according to the formula is P = 220 × 10 = 2200W. If the measured power is 2000W, then the relative error is (|2000 - 2200| / 2200) × 100% ≈ 9.09%, which is greater than 5%. Therefore, it is marked as "abnormal original data," prompting relevant personnel to check whether the measuring instrument is normal and whether the measurement data is accurate.

[0042] (3) Judgment of the rationality of energy efficiency boundary Energy efficiency is an important indicator for measuring the energy utilization efficiency of equipment. Different types of equipment have their own reasonable energy efficiency boundary ranges. Taking heat pumps as an example, their heating capacity (… ) and power consumption ( The ratio of heat capacity to power consumption reflects the energy efficiency of a heat pump. This ratio should be within a reasonable energy efficiency range, typically defined as [0.90, 0.98]. If the ratio of heat capacity to power consumption exceeds this range, it indicates abnormal energy efficiency, potentially indicating equipment malfunction or improper operating parameter settings. For example, the heat capacity of a certain heat pump... It has a power consumption of 9.5kW. The power rating is 10kW, and the ratio is 9.5 / 10 = 0.95, which is within the range of [0.90, 0.98], indicating that the energy efficiency is normal; if the heating capacity of this heat pump is... It has a power consumption of 8.5kW. If the value is 10kW and the ratio is 0.85, exceeding the lower limit, it will be marked as "energy efficiency abnormal," prompting maintenance personnel to inspect and maintain the heat pump to improve the energy utilization efficiency of the equipment and reduce energy consumption.

[0043] During the operation of an integrated energy system, equipment start-up and shutdown, load surges, and other events can cause transient changes in data. These transient data often contain crucial equipment operating information; directly filtering them out as abnormal data would result in the loss of valuable information. Therefore, time-series smoothness verification introduces a "suspicious mutation retention mechanism" to reasonably assess time-series changes in data and avoid mistakenly deleting valid transient data. A detailed analysis follows: First, calculate the data value at the current time ( ) and the data value of the previous moment ( The first difference of ) The formula for calculating the first-order difference is: The first-order difference can intuitively reflect the magnitude of change in data values ​​between two adjacent moments. This value can be used to preliminarily determine whether a significant change has occurred in the data. For example, the flow rate of a water pump at a previous moment... The flow rate is 10 m³ / h at the current moment. If the flow rate is 15 m³ / h, then the first-order difference... =|15-10|=5m³ / h. This value indicates that the pump flow rate changed by 5m³ / h between these two times.

[0044] Secondly, query the maximum allowable rate of change for this device ( (unit: % / min), and combined with the sampling interval ( (Unit: % / min), determine whether the current data change exceeds the allowable range. If it meets the requirements... If so, it is marked as "mutation suspected". Indicates the sampling interval Within this, the maximum permissible variation in equipment parameters. For example, the maximum permissible rate of change in flow rate for a certain fan. The sampling rate is 10% / min, with a sampling interval of [missing information]. If the sampling interval is 1 minute, and the flow rate of the fan at the previous moment was 20 m³ / min, then the maximum allowable change in flow rate within the 1-minute sampling interval is 20 × 10% × 1 = 2 m³ / min. If the current fan flow rate is 23 m³ / min, then the first-order difference... If the rate is 3 m³ / min, which is greater than the maximum allowable change of 2 m³ / min, it is marked as "suspected mutation".

[0045] Unlike traditional methods that directly filter out abnormal data, data marked as "suspected mutation" is not filtered directly. Instead, it is retained and pushed to the subsequent statistics module. The subsequent statistics module then considers the trend of changes in the next 2-3 data points to further determine whether the "suspected mutation" data is valid transient data (such as equipment startup shock). For example, when a motor starts, the current may experience a brief, significant increase. If the first-order difference is calculated only based on the current data at the moment of startup and the current data at the previous moment, it is likely to be marked as "suspected mutation." However, the current in the next 2-3 data points will gradually decrease and stabilize. At this point, the subsequent statistics module, considering the trend of these data changes, can determine that the "suspected mutation" data is valid transient data from motor startup, rather than truly abnormal data, thus avoiding the accidental deletion of valid data.

[0046] This embodiment employs a suspected mutation retention mechanism. Data exceeding the maximum rate of change but potentially belonging to scenarios such as equipment start-up / shutdown or load surges is not directly discarded. Instead, it is marked as "suspected mutation" and pushed to the subsequent statistics module for secondary verification in conjunction with start-up / shutdown signals and the changing trends of associated measurement points. This mechanism significantly avoids the erroneous deletion of valid transient information by traditional "one-size-fits-all" filtering strategies, ensuring data integrity and process traceability.

[0047] like Figure 3 As shown, the verification of multi-source consistency and coupling relationship is based on the system topology and multi-source energy coupling model. It verifies the consistency of the overall system operation data and the rationality of the energy coupling relationship, ensuring that the operation data of each part of the system are coordinated and consistent, and that energy conversion and utilization conform to physical laws.

[0048] Among them, multi-source consistency and coupling relationship verification includes topology consistency verification and coupling relationship verification; the topology consistency verification includes: In a power distribution system, according to the law of conservation of energy and the system topology, the total incoming power ( Theoretically, it should be equal to the sum of the power of each branch. Due to factors such as line loss and measurement errors, a certain relative error is allowed between the total incoming power and the sum of the power of each branch, as shown below: ; For example, the total incoming power of a power distribution system The total power is 100kW, with branch circuits having power ratings of 30kW, 25kW, 28kW, and 15kW respectively. The sum of the power ratings of all branches is... =30+25+28+15=98kW, the relative error is (|100-98| / 98)×100%≈2.04%, which is within the allowable range, indicating that the power data of the power distribution system is balanced; if the total incoming power The total power of each branch is 105kW. =98kW, the relative error is (|105-98| / 98)×100%≈7.14%, which exceeds the allowable range. Therefore, the relevant branch is marked as "power imbalance", prompting the operation and maintenance personnel to check whether there are line faults, abnormal measuring instruments or other problems in the power distribution system.

[0049] In a heating system, to ensure that heat can be effectively transferred from the heat source to the user, the water supply temperature ( It needs to be higher than the return water temperature. Within a certain range, it is generally stipulated that the supply water temperature should be at least 5°C higher than the return water temperature. > +5℃. If the water supply temperature does not meet this condition, it indicates a potential problem with heat transfer in the heating system, such as poor pipe insulation or insufficient heat supply from the heat source. For example, the water supply temperature of a certain heating station... The return water temperature is 80℃. The temperature is 72℃, and 80℃ > 72 + 5℃, which meets the requirements, indicating that the temperature data of the heating system is normal; if the supply water temperature Tout is 75℃, the return water temperature... If the temperature is 72℃ and 75℃ < 72+5℃, and the condition is not met, it will be marked as "logical conflict," prompting relevant personnel to check the operating status of the thermal system.

[0050] In a chilled water plant system, chilled water is used to deliver cooling capacity to users, while cooling water is used to remove heat generated by the refrigeration equipment. There is a certain matching relationship between their flow rates. To ensure the cooling effect and stable operation of the chilled water plant, the deviation between the chilled water flow rate and the cooling water flow rate is typically specified to be no more than ±10%. For example, if the chilled water flow rate of a chilled water plant is 500 m³ / h and the cooling water flow rate is 530 m³ / h, the deviation is (530-500) / 500×100%=6%, which is within ±10%, indicating that the chilled water plant's flow data is balanced. If the chilled water flow rate is 500 m³ / h and the cooling water flow rate is 560 m³ / h, the deviation is (560-500) / 500×100%=12%, which exceeds the allowable range. This is marked as a flow imbalance, prompting maintenance personnel to check the operating status of the chilled water plant system's pumps, valve openings, etc., to ensure flow balance.

[0051] The coupling relationship verification includes: CHP (Combined Heat and Power) units can simultaneously generate electricity and heat. The heat-to-power ratio (CHP ratio) is a crucial indicator of the unit's overall energy efficiency; that is, the ratio of heat to electricity generated by the unit should be within a reasonable range. Different CHP unit models have different reasonable CHP ranges. The system loads the corresponding reasonable CHP range based on the specific parameters of the CHP unit. If the measured CHP ratio exceeds this range, it is marked as "energy efficiency abnormal." For example, the reasonable CHP range for a certain model is 0.8-1.2. If the unit generates 10MW of heat and 8MW of electricity at a certain moment, the CHP ratio is 10 / 8 = 1.25, exceeding the reasonable range. This is marked as "energy efficiency abnormal," prompting maintenance personnel to check the CHP unit's operating parameters, fuel supply, etc., to improve the unit's overall energy efficiency.

[0052] Gas-fired boilers generate heat energy by burning natural gas. The heat output per unit volume of natural gas is a key indicator of the boiler's energy efficiency; that is, the heat produced after burning a unit volume or mass of natural gas should be within a reasonable range. The system loads a reasonable range for the heat output per unit volume of natural gas based on the type and specifications of the boiler and the type of natural gas used. If the measured heat output per unit volume exceeds this range, it indicates abnormal energy efficiency of the boiler, potentially due to incomplete combustion or boiler scaling. For example, a gas-fired boiler using natural gas has a reasonable heat output per unit volume of natural gas of 35 MJ / m³-38 MJ / m³. If the measured heat output per unit volume is 33 MJ / m³, exceeding the lower limit, it is marked as abnormal, prompting maintenance personnel to inspect and maintain the boiler, such as cleaning the boiler's heating surfaces and adjusting burner parameters, to improve its energy efficiency.

[0053] Maintaining a balance between chilled water and cooling water flow rates in a chiller plant is crucial for its normal operation. Chilled water absorbs heat in the evaporator, rises in temperature, returns to the chiller plant, is cooled, and then is delivered to the user end. Cooling water absorbs heat released by the refrigerant in the condenser, rises in temperature, is sent to the cooling tower for cooling, and then returns to the condenser. Excessive deviation between chilled water and cooling water flow rates can reduce the heat exchange efficiency of the evaporator or condenser, affecting the chiller plant's refrigeration efficiency and potentially causing equipment damage. Therefore, in addition to the aforementioned requirement that the deviation should not exceed ±10%, a comprehensive judgment must be made considering factors such as the chiller plant's refrigeration load and equipment operating status. For example, when the chiller plant's refrigeration load increases, both chilled water and cooling water flow rates should increase accordingly, and the ratio of their increases should remain within a reasonable range. If one flow rate does not increase as expected, resulting in a deviation exceeding the allowable range, it should be marked as abnormal, and the cause should be further analyzed.

[0054] Step S104: Generate structured quality labels based on the verification results, and perform hierarchical processing according to the data type.

[0055] Specifically, in this embodiment, such as Figure 4 As shown, quality label generation and data diversion are a comprehensive summary of the results of all previous verification steps. Accurate quality labels are generated for each piece of data, and the data is differentiated according to the label type to ensure that high-quality data enters the subsequent application stage, while abnormal data is handled appropriately.

[0056] Furthermore, by integrating the results of all verification steps, including dynamic threshold verification, physical rationality verification, temporal smoothness verification, and multi-source consistency and coupling relationship verification, a structured quality label is generated for each piece of data. Quality label types include "Normal," "Exceeding Limits," "Safety Limit Exceeding Limits," "Operating Condition Exceeding Limits," "Suspicious Mutation," "Logical Conflict," "Energy Efficiency Abnormality," and "Power Imbalance." Each label corresponds to a specific type of abnormality or normal state, clearly reflecting the data's quality status. For example, if data exceeds the manual safety red line threshold in dynamic threshold verification and also does not meet equipment operating condition requirements in physical rationality verification, it will be simultaneously labeled "Safety Limit Exceeding Limits" and "Operating Condition Exceeding Limits." If no abnormalities are found after all verification steps, it is labeled "Normal."

[0057] The tiered processing strategy includes handling deterministic anomalies, handling suspicious anomalies, and handling normal data; a detailed analysis follows: Deterministically identified anomaly data refers to data that has been explicitly determined to be abnormal through verification, such as partial data corresponding to tags like "over-limit anomaly," "safety limit violation," "operating condition over-limit," "logic conflict," "energy efficiency anomaly," and "power imbalance." This type of data is directly filtered out and does not proceed to subsequent statistical analysis and AI applications. Simultaneously, detailed anomaly information is recorded, including the anomaly tag type, occurrence time, equipment identifier, measurement point code, and measured data value, forming an anomaly log. The anomaly log provides crucial information for operations and maintenance personnel to troubleshoot and analyze the causes of anomalies. Based on the information in the anomaly log, operations and maintenance personnel can promptly inspect and maintain equipment and systems, eliminate safety hazards, and restore normal system operation.

[0058] Suspicious anomaly data mainly refers to data marked as "suspected mutation". This type of data cannot be directly determined as anomaly and requires further verification. Its content includes: a) Verification by reading device start / stop signals: The system reads the start / stop signals of the corresponding device. If a data mutation occurs within 30 seconds after the device starts (start-up time may vary for different devices and can be adjusted according to device type), and related data (such as current, voltage, power, etc.) also changes synchronously, conforming to the operating characteristics of the device during startup (e.g., the current increases instantaneously when the motor starts, then gradually decreases and tends to stabilize), it is determined to be "normal transient data," the "suspected mutation" flag is removed, and it is pushed to subsequent modules as normal data. For example, if a motor's current rapidly increases from 0A to 20A within 5 seconds after startup, then gradually decreases to 15A and stabilizes within 10 seconds, while the voltage data remains stable, then this current mutation data will be determined to be "normal transient data."

[0059] b) Consistency Verification of Related Data: If a sudden change occurs in the data of a certain measuring point, but the corresponding related data (such as voltage, current, flow rate, etc. related to that measuring point) does not change significantly, which does not conform to normal physical laws and equipment operating characteristics, it is judged as a "deterministic anomaly," the "suspected mutation" mark is retained (or updated to a more accurate anomaly mark), and the data is filtered and recorded in the anomaly log. For example, if the power data of a water pump suddenly increases from 10kW to 20kW, but the corresponding current data remains unchanged at 5A, and the voltage data is also stable at 220V, according to the power calculation formula P=U×I, the theoretical power is calculated to be 1100W, which is significantly different from the measured power of 20kW. In this case, the power data is judged as a "deterministic anomaly," filtered, and recorded in the log.

[0060] c) Update data quality labels and push notifications: After the above verification, update the data quality labels, change the label of "normal transient data" to "normal", and push it to the subsequent statistics module for missing data detection and supplementation, data statistical analysis, and advanced AI applications; update the label of "deterministic anomaly" data to the corresponding anomaly label (such as "raw data anomaly") and include it in the anomaly log management.

[0061] Normal data refers to data labeled "normal." This type of data has undergone all verification steps, ensuring its reliable quality and meeting the needs of subsequent data statistics, missing data detection, intelligent data entry, and advanced AI applications such as load forecasting, energy efficiency optimization, fault diagnosis, carbon emission accounting, and digital twins. Therefore, directly pushing normal data to the statistics module provides a highly reliable data foundation for subsequent applications, ensuring the accuracy and effectiveness of various intelligent applications. For example, normal voltage, current, power, temperature, and flow rate data can provide accurate historical data support for load forecasting models, improving the accuracy of load forecasting, providing reliable data for energy efficiency optimization analysis, and helping operation and maintenance personnel identify problems in the energy utilization process and formulate reasonable energy efficiency optimization solutions.

[0062] This embodiment constructs a structured and interpretable quality labeling system to generate refined quality labels for each piece of data, achieving semantic classification of anomaly types. This labeling system not only facilitates maintenance personnel in quickly locating the root cause of problems, but also provides a highly reliable, interpretable, and traceable data foundation for subsequent applications.

[0063] The intelligent data detection method based on the energy management and control system of transportation hubs described in this embodiment establishes a multi-dimensional, adaptive, and refined energy data processing and anomaly detection mechanism by integrating physical mechanism models, data-driven methods, system topology, and historical behavior patterns. It is applicable to real-time quality verification, anomaly identification, and quality labeling output of multi-source heterogeneous energy data such as electricity, heat, cooling, and gas, providing a highly reliable data foundation for subsequent data statistics, missing data detection, intelligent data supplementation, and advanced AI applications.

[0064] It should be noted that the above description describes some embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0065] Based on the same inventive concept, and corresponding to any of the above embodiments, the embodiments of this application also provide an intelligent data detection system based on a transportation hub energy management and control system.

[0066] like Figure 5 As shown, the intelligent data detection system based on the transportation hub energy management and control system includes: The data receiving module 11 is configured to receive standardized multi-source heterogeneous energy data and cache the data through a preset caching mechanism; The verification rule loading module 12 is configured to load corresponding verification rules from the multi-source energy coupling rule base based on cached data features, and output a verification strategy package; wherein, the data features include the measurement point code and device type of the data; The verification module 13 is configured to verify the data based on the loaded data change feature tags through a preset verification mechanism; the verification mechanism includes threshold verification, physical rationality verification, temporal smoothing verification, and multi-source consistency and coupling relationship verification. The hierarchical processing module 14 is configured to generate structured quality labels based on the verification results and perform hierarchical processing according to the data type.

[0067] For ease of description, the above system is described by dividing it into various modules based on their functions. Of course, in implementing the embodiments of this application, the functions of each module can be implemented in one or more software and / or hardware.

[0068] The system described in the above embodiments is used to implement the corresponding method in any of the foregoing embodiments and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0069] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, embodiments of this application also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the methods described in any of the above embodiments.

[0070] Figure 6 This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0071] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0072] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0073] The input / output interface 1030 is used to connect input / output modules to realize information input and output. The input / output modules can be configured as components in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touch screens, microphones, various sensors, etc., and output devices may include displays, speakers, vibrators, indicator lights, etc.

[0074] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0075] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0076] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0077] The electronic devices described above are used to implement the corresponding methods in any of the foregoing embodiments and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0078] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides a non-transitory computer-readable storage medium that stores computer instructions for causing the computer to perform the methods described in any of the above embodiments.

[0079] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0080] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to perform the methods described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0081] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this application (including the claims) is limited to these examples; within the framework of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this application as described above, which are not provided in the details for the sake of brevity.

[0082] Although this application has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0083] The embodiments of this application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this application should be included within the protection scope of this application.

Claims

1. An intelligent data detection method based on a transportation hub energy management and control system, characterized in that, include: It receives standardized multi-source heterogeneous energy data and caches the data through a preset caching mechanism; Based on the cached data features, and by loading corresponding verification rules from the multi-source energy coupling rule base, a verification strategy package is output; wherein, the data features include the measurement point code and device type of the data; Based on the loaded data change feature tags, the data is verified through a preset verification mechanism; wherein, the verification mechanism includes threshold verification, physical rationality verification, temporal smoothing verification, and multi-source consistency and coupling relationship verification. Structured quality labels are generated based on the verification results, and then graded according to the data type.

2. The method according to claim 1, characterized in that: The verification rules include at least the loading of physical coupling models, loading of equipment rated parameters, loading of system topology relationships, and loading of data change feature labels.

3. The method according to claim 1, characterized in that: The threshold verification includes threshold verification for steady-state data, threshold verification for dynamic data, and priority verification of manual safety red line thresholds. The steady-state data threshold verification is performed based on a confidence interval model with a constructed short-term sliding window. The dynamic data threshold verification is performed based on a set dynamic threshold range; The priority determination of the artificial safety red line threshold is based on the dynamically corrected artificial safety red line threshold verification and triggers priority alarms.

4. The method according to claim 1, characterized in that: The physical rationality verification is based on the physical constraints of the equipment and physical rules, and conducts in-depth verification of the inherent consistency and rationality of the data. The physical rationality verification includes judging the rationality of equipment operating conditions, judging the consistency of physical rules, and judging the rationality of energy efficiency boundaries.

5. The method according to claim 1, characterized in that: The time-series smoothing verification is achieved by calculating the first-order difference between the current data value and the previous data value, and comparing the first-order difference with the product of the maximum allowable rate of change of the device and the sampling interval to determine whether the current data change exceeds a preset threshold and mark it as a suspected mutation.

6. The method according to claim 1, characterized in that: The multi-source consistency and coupling relationship verification includes topology consistency verification and coupling relationship verification; The topology consistency verification includes: power balance verification based on the power distribution system, temperature relationship verification based on the thermal system, and flow balance verification based on the chiller system. The coupling relationship verification includes the hot spot ratio verification of the cogeneration unit, the unit gas heat production verification of the gas boiler, and the balance verification of chilled water flow and cooling water flow in the chiller station.

7. The method according to claim 1, characterized in that, Based on a hierarchical processing strategy, different types of data are processed in a hierarchical manner, including: Filter out the abnormal data marked with deterministic labels and log the anomalies. The abnormal data marked with the mutation suspicion label is read to verify the start and stop signals of the device and the consistency of the associated data, and the data quality is updated and pushed to the verified data indicator labels; Data marked with normal labels will be pushed out.

8. An intelligent data detection system based on a transportation hub energy management and control system, characterized in that, include: The data receiving module is configured to receive standardized multi-source heterogeneous energy data and cache the data through a preset caching mechanism; The verification rule loading module is configured to load corresponding verification rules from the multi-source energy coupling rule base based on cached data features, and output a verification strategy package; wherein, the data features include the measurement point code and device type of the data; The verification module is configured to verify the data based on the loaded data change feature tags through a preset verification mechanism; wherein, the verification mechanism includes threshold verification, physical rationality verification, temporal smoothing verification, and multi-source consistency and coupling relationship verification. The hierarchical processing module is configured to generate structured quality labels based on the verification results and perform hierarchical processing according to the data type.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the method as claimed in any one of claims 1-7.

10. A non-transitory computer-readable storage medium, characterized in that, in, The non-transitory computer-readable storage medium stores computer instructions for causing a computer to perform the method described in any one of claims 1-7.

Images