Urban rail transit station energy efficiency level evaluation method based on multi-source data fusion

Abstract

The application discloses a kind of urban rail transit station energy efficiency grade evaluation method based on multi-source data fusion, it is related to urban rail transit energy management technical field.The method obtains the multi-source basic data of station, constructs standardization multi-source fusion dataset after cleaning, fusion and association mapping processing;Based on the dataset, establish the hierarchical energy efficiency evaluation index system including target layer, criterion layer and index layer, determine the weight of each index by analytic hierarchy process, calculate to obtain the comprehensive score of station energy efficiency;According to the preset score interval, determine the energy efficiency grade, and generate the structured evaluation results including energy efficiency grade and ranking.The method can systematically integrate various energy efficiency related data, accurately present the real energy utilization efficiency of station, realize the automatic, fair evaluation and fine spatial analysis of energy efficiency, and provide reliable quantitative support for subway energy-saving operation, equipment optimization and energy consumption quota management.

Description

Technical Field

[0001] This invention relates to the field of urban rail transit energy management technology, and in particular to a method for evaluating the energy efficiency level of urban rail transit stations based on multi-source data fusion. Background Technology

[0002] In the actual operation of urban rail transit stations, different stations have significant inherent differences in building scale, structural form, equipment configuration, etc. At the same time, station energy consumption is continuously affected by a variety of dynamic factors such as changes in passenger flow, seasonal climate fluctuations, differences in equipment operating load, and adjustments in operating hours. The composition of energy consumption data is highly complex and heterogeneous.

[0003] The existing station energy efficiency evaluation does not effectively separate and correct for the various inherent differences and dynamic fluctuations that affect energy consumption. It directly conducts horizontal comparisons and grade determinations based on raw energy consumption data, which makes it impossible to conduct fair energy efficiency benchmarking for stations with different basic conditions and different operating conditions. The evaluation results are seriously deviated from the actual energy utilization level of the stations and cannot provide a scientific and reliable quantitative basis for energy-saving renovation, equipment optimization and energy consumption quota management. Summary of the Invention

[0004] This invention provides a method for evaluating the energy efficiency level of urban rail transit stations based on multi-source data fusion to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides a method for evaluating the energy efficiency level of urban rail transit stations based on multi-source data fusion, comprising: Acquire multi-source basic data of urban rail transit stations, clean, fuse and perform correlation mapping on the multi-source basic data, and construct a standardized multi-source fusion dataset; Based on the standardized multi-source fusion dataset, a hierarchical index system for station energy efficiency evaluation is constructed, and the weight of each index in the hierarchical index system is determined. Based on the indicator data and weights of the hierarchical indicator system, the station's comprehensive energy efficiency score is calculated. Based on the comprehensive energy efficiency score, the energy efficiency level of the station is determined according to the preset energy efficiency level classification rules, and an evaluation result including energy efficiency level and ranking is generated.

[0006] Preferably, the acquisition of multi-source basic data of urban rail transit stations includes: Obtain static data of the building information model of the station, which includes the station's spatial volume and zone area; Obtain the sub-item energy consumption data of the station, which includes traction power consumption and power and lighting power consumption; The station's dynamic passenger flow data is obtained, including inbound passenger flow and transfer passenger flow. The environmental parameters and equipment operating parameters of the station are obtained. The environmental parameters include outdoor temperature and humidity, and the equipment operating parameters include the energy efficiency ratio of the chiller unit and the escalator load rate. Obtain the station's operational data, which includes operating duration and train formation information.

[0007] Preferably, the cleaning, fusion, and correlation mapping processing of the multi-source basic data includes: Anomaly detection is performed on the energy consumption data, dynamic passenger flow data, environmental parameters, and equipment operating parameters, and data points exceeding three times the standard deviation of the mean are removed. For the missing data points resulting from the removal process, linear interpolation is used to complete them. The calculation method for linear interpolation is as follows: In the formula, Time to be completed The value, and These are the data values ​​at the adjacent times before and after the missing time; All the completed data will be normalized to a preset numerical range; Based on the spatial identifiers in the static data of the building information model, a unique mapping relationship is established with the energy consumption measurement point identifiers in the sub-item energy consumption data, and an association mapping table is generated.

[0008] Preferably, the hierarchical index system for constructing station energy efficiency evaluation includes: Establish a three-layer structure comprising a target layer, a criterion layer, and an indicator layer; The criteria layer includes a comprehensive energy consumption intensity dimension, an equipment energy consumption dimension, an equipment energy efficiency dimension, and an operation-related dimension. Under the aforementioned comprehensive energy intensity dimension, energy consumption per unit area and energy consumption per person per visit are set. Under the aforementioned equipment energy consumption dimension, set the energy consumption index per unit area for the air conditioning system and the energy consumption index per unit area for the escalator; Under the aforementioned equipment energy efficiency dimension, the energy efficiency ratio index of the chiller unit and the transformer load rate index are set; Under the aforementioned operational correlation dimension, passenger flow intensity index and seasonal impact coefficient index are set.

[0009] Preferably, determining the weight of each indicator in the hierarchical indicator system includes: For each element within the same level in the criterion layer and the index layer, a judgment matrix is ​​constructed using a pairwise comparison scaling method; Calculate the eigenvectors of the judgment matrix as the initial weights of each element; The judgment matrix is ​​subjected to consistency verification. When the verification passes, the initial weights are determined as the final weights.

[0010] Preferably, the step of calculating the station's comprehensive energy efficiency score based on the indicator data of the hierarchical indicator system and the weights includes: Obtain the measured data of each indicator in the hierarchical indicator system, and calculate the indicator value of each indicator based on the measured data; Multiply the value of each indicator by its corresponding final weight to obtain the weighted score of each indicator. The weighted scores of all indicators are summed to generate the overall energy efficiency score of the station.

[0011] Preferably, the association mapping process for establishing the association mapping between static data of the building information model and sub-item energy consumption data includes: Extract the spatial component identifiers and corresponding spatial volumes and partition areas of each station from the static data of the building information model; Extract the physical location identifier and energy consumption value of each energy consumption measurement point from the sub-item energy consumption data; Create a unique station identifier for each station, and associate the spatial component identifier with the energy consumption measurement point identifier under the station identifier; Based on the spatial relationship between the spatial component identifier and the energy consumption measurement point identifier, establish a component-measurement point association pair; Based on the component-measuring point association pair, the initial value of energy efficiency density for each spatial partition is calculated. The initial value of energy efficiency density is the ratio of the total energy consumption of the partition to the spatial volume of the partition. The initial value of energy efficiency density is used as the output field of the association mapping and written into the association mapping table.

[0012] Preferably, the association mapping process further includes spatial energy efficiency analysis of the association mapping table, including: Read each component-measuring point association pair and its corresponding initial energy efficiency density value from the association mapping table; Using the station identifier as an index, aggregate the initial energy efficiency density values ​​of all spatial partitions within the same station to generate a station-level spatial energy efficiency distribution vector; The station-level spatial energy efficiency distribution vector is spatially superimposed with the passenger flow density of the corresponding time period in the dynamic passenger flow data to calculate the spatial energy efficiency value under the unit passenger flow carrying capacity. The spatial energy efficiency value under the unit passenger flow carrying capacity is used as a spatial energy efficiency evaluation feature and written back to the standardized multi-source fusion dataset.

[0013] Preferably, determining the station's energy efficiency level according to a preset energy efficiency level classification rule includes: Obtain the comprehensive energy efficiency score; The comprehensive energy efficiency score is compared with multiple preset scoring intervals. Each scoring interval corresponds to an energy efficiency level. The multiple scoring intervals correspond to low energy efficiency level, qualified energy efficiency level, good energy efficiency level and excellent energy efficiency level in order from low to high. When the comprehensive energy efficiency score falls into any score range, the energy efficiency level corresponding to that score range is determined as the current energy efficiency level of the station.

[0014] Preferably, generating the evaluation results including energy efficiency levels and rankings includes: For all stations on the same line or within the same area, sort them from highest to lowest according to their respective comprehensive energy efficiency scores to generate a sorting sequence; The energy efficiency level of each station, its ranking position in the sorting sequence, and the deviation of the station's key energy consumption indicators are combined and packaged to generate a structured evaluation result data body. Output the structured evaluation result data body, wherein the deviation of the key energy consumption index is the difference between the energy consumption per person at the station and the average energy consumption per person on the same line.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. By standardizing the cleaning, fusion, and correlation mapping of multi-source basic data from urban rail transit stations, a unified and standardized multi-source fusion dataset is constructed. This dataset can systematically integrate various data resources related to station energy efficiency, eliminate the adverse effects of data anomalies, missing data, and differences in dimensions, and obtain a quantitative comprehensive energy efficiency score by combining a hierarchical indicator system and scientific weight calculation. It can also automatically complete the energy efficiency level determination and ranking generation according to preset rules, accurately presenting the station's true energy utilization efficiency and providing stable and reliable quantitative support for energy-saving operation and management.

[0016] 2. By establishing a spatial correlation mapping between static data and sub-item energy consumption data in the building information model, and conducting spatial energy efficiency analysis on this basis, it is possible to achieve refined spatial dimension analysis of station energy efficiency, accurately map energy consumption data to specific building space zones, and combine passenger flow data to correct spatial energy efficiency evaluation results, further improving the precision and rationality of energy efficiency evaluation, and providing direct data support for accurately locating weak links in energy efficiency. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating an embodiment of the energy efficiency rating method for urban rail transit stations based on multi-source data fusion provided by the present invention. Detailed Implementation

[0018] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0020] Reference Figure 1 The diagram shown is a flowchart illustrating an urban rail transit station energy efficiency rating method based on multi-source data fusion, according to an embodiment of the present invention. In this embodiment, the urban rail transit station energy efficiency rating method based on multi-source data fusion includes: Acquire multi-source basic data of urban rail transit stations, clean, fuse and perform correlation mapping on the multi-source basic data, and construct a standardized multi-source fusion dataset; Based on the standardized multi-source fusion dataset, a hierarchical index system for station energy efficiency evaluation is constructed, and the weight of each index in the hierarchical index system is determined. Based on the indicator data and weights of the hierarchical indicator system, the station's comprehensive energy efficiency score is calculated. Based on the comprehensive energy efficiency score, the energy efficiency level of the station is determined according to the preset energy efficiency level classification rules, and an evaluation result including energy efficiency level and ranking is generated.

[0021] In this embodiment, firstly, all station data related to building, energy consumption, passenger flow, environment, equipment and operation are collected uniformly. Through a standardized preprocessing process, data anomalies, missing data and dimensional differences are eliminated. At the same time, the correspondence between building space and energy consumption measurement points is established to form a unified dataset that can be directly used for evaluation.

[0022] Based on this dataset, a three-tiered evaluation index system covering energy consumption intensity, equipment status, and operational impact is constructed. The contribution of each index to energy efficiency is determined through a scientific and objective weighting method. Then, the comprehensive energy efficiency score of each station is calculated by combining the index data and weights. Finally, the energy efficiency level is divided according to the preset level threshold, and the horizontal ranking of stations on the same line is completed, outputting a structured evaluation result that can be directly used for operational decision-making.

[0023] In one embodiment of the present invention, the acquisition of multi-source basic data of urban rail transit stations includes: Obtain static data of the building information model of the station, which includes the station's spatial volume and zone area; Obtain the sub-item energy consumption data of the station, which includes traction power consumption and power and lighting power consumption; The station's dynamic passenger flow data is obtained, including inbound passenger flow and transfer passenger flow. The environmental parameters and equipment operating parameters of the station are obtained. The environmental parameters include outdoor temperature and humidity, and the equipment operating parameters include the energy efficiency ratio of the chiller unit and the escalator load rate. Obtain the station's operational data, which includes operating duration and train formation information.

[0024] In practice, static data of the building information model of each station can be extracted from the Revit format as-built BIM model provided by the rail transit design institute. For example, the total building area of ​​underground station No. 03 of Line 2 is 2,200 square meters, the public area is 1,200 square meters, the equipment area is 800 square meters, the public area space volume is 4,800 cubic meters, as well as parameters such as station burial depth and heat transfer coefficient of the enclosure structure.

[0025] Energy consumption data is collected through smart electricity meters and water meters installed in the station, with a collection frequency of once every 15 minutes. The data covers traction power consumption, power and lighting power consumption, power consumption of air conditioning systems, escalator power consumption, ventilation and drainage power consumption, and water consumption. All data is uploaded to the metro energy management system database via the Modbus protocol.

[0026] Dynamic passenger flow data is obtained from the AFC (Automatic Fare Collection) system, with a statistical granularity of one hour per instance, including daily inbound passenger flow, outbound passenger flow, transfer passenger flow, and peak hour cross-sectional passenger flow. Environmental parameters are obtained from the local meteorological department's public interface for hourly outdoor temperature and humidity data, and equipment operating parameters are collected from the BAS (Building Automation System), including chiller unit energy efficiency ratio, escalator load rate, fan operating time, transformer load rate, etc.

[0027] Operational data is obtained from the OCC Operations Control Center and includes daily operating hours, train numbers, and train formation.

[0028] In this embodiment of the invention, the cleaning, fusion, and correlation mapping processing of the multi-source basic data includes: Anomaly detection is performed on the energy consumption data, dynamic passenger flow data, environmental parameters, and equipment operating parameters, and data points exceeding three times the standard deviation of the mean are removed. For the missing data points resulting from the removal process, linear interpolation is used to complete them. The calculation method for linear interpolation is as follows: In the formula, Time to be completed The value, and These are the data values ​​at the adjacent times before and after the missing time; All the completed data will be normalized to a preset numerical range; Based on the spatial identifiers in the static data of the building information model, a unique mapping relationship is established with the energy consumption measurement point identifiers in the sub-item energy consumption data, and an association mapping table is generated.

[0029] In practice, the 3σ principle can be used to detect outliers in dynamically collected energy consumption, passenger flow, environmental and equipment parameters. The 3σ principle means that if the difference between a data point and the mean of the dataset exceeds three times the standard deviation, it is judged as an outlier. For example, the traction power consumption data of station 05 at 12:00 on a certain day is 2100kWh. The mean of traction power consumption of stations of the same type during the same period is 850kWh and the standard deviation is 320kWh. The calculated mean plus three times the standard deviation is 1810kWh. This data exceeds the threshold range and is judged as an outlier and removed.

[0030] Then, the missing data points generated after removing outliers are filled using a linear interpolation method. For example, the load rate data of an escalator in station 07 is missing from 14:00 to 14:15. The load rate at 13:45 is 42% and the load rate at 14:30 is 48%. The filled value at 14:00 is 42% plus the difference between 48% and 42% multiplied by 15 and divided by 45, resulting in 44%. If the missing data is missing for more than 3 consecutive collection cycles, the moving average method is used to fill the missing data, and the sliding window size is set to 5 collection cycles.

[0031] Then, all the completed data were normalized to the [0,1] range using the maximum-minimum normalization method to eliminate the influence of different dimensions and orders of magnitude on the evaluation results. For negative indicators of energy consumption, the lower the value, the higher the energy efficiency, and reverse normalization was used.

[0032] Finally, based on the spatial component identifiers in the BIM model, a one-to-one correspondence is established with the physical location identifiers of energy consumption measurement points, generating an association mapping table containing site ID, component ID, measurement point ID, and related relationships.

[0033] In this embodiment of the invention, the construction of a hierarchical index system for station energy efficiency evaluation includes: Establish a three-layer structure comprising a target layer, a criterion layer, and an indicator layer; The criteria layer includes a comprehensive energy consumption intensity dimension, an equipment energy consumption dimension, an equipment energy efficiency dimension, and an operation-related dimension. Under the aforementioned comprehensive energy intensity dimension, energy consumption per unit area and energy consumption per person per visit are set. Under the aforementioned equipment energy consumption dimension, set the energy consumption index per unit area for the air conditioning system and the energy consumption index per unit area for the escalator; Under the aforementioned equipment energy efficiency dimension, the energy efficiency ratio index of the chiller unit and the transformer load rate index are set; Under the aforementioned operational correlation dimension, passenger flow intensity index and seasonal impact coefficient index are set.

[0034] In practice, the hierarchical indicator system will be constructed with the comprehensive energy efficiency evaluation of subway stations as the target layer, serving as the final output target of the entire evaluation system.

[0035] The criteria layer sets up four independent yet interconnected core evaluation dimensions, comprehensively covering the key factors affecting station energy efficiency.

[0036] Each dimension of the indicator layer has corresponding quantifiable evaluation indicators. Energy consumption per unit area is the ratio of the station's total energy consumption to the total building area within the evaluation period, expressed in kWh / m², used to measure the energy efficiency of the building space. Energy consumption per person is the ratio of the station's total energy consumption to the total passenger flow within the evaluation period, expressed in kWh / person, used to measure the energy efficiency under passenger flow capacity. Air conditioning system energy consumption per unit area is the ratio of the total energy consumption of the air conditioning system (both large and small) to the station's total building area. Escalator energy consumption per unit area is the ratio of the total energy consumption of all escalators to the total energy consumption of escalator operation. The time-to-duration ratio is used to measure the energy consumption level of core energy-consuming equipment; the energy efficiency ratio (EER) of the refrigeration unit refers to the ratio of the refrigeration capacity of the refrigeration unit to the input electrical power; the transformer load rate is the ratio of the actual output power of the transformer to the rated power, used to measure the operating energy efficiency of the equipment itself; the passenger flow intensity is the ratio of the average daily passenger flow to the total building area of ​​the station, with the unit being people / m²·day; the seasonal influence coefficient is determined based on the average monthly outdoor temperature, with 1.2 for summer, 1.1 for winter, and 1.0 for spring and autumn, used to correct for the impact of different operating conditions on energy consumption.

[0037] In this embodiment of the invention, determining the weight of each indicator in the hierarchical indicator system includes: For each element within the same level in the criterion layer and the index layer, a judgment matrix is ​​constructed using a pairwise comparison scaling method; Calculate the eigenvectors of the judgment matrix as the initial weights of each element; The judgment matrix is ​​subjected to consistency verification. When the verification passes, the initial weights are determined as the final weights.

[0038] In practice, the 1-9 scale method can be used to construct the judgment matrix. The 1-9 scale method refers to using integers from 1 to 9 to represent the relative importance of two elements. 1 indicates that the two elements are equally important, 3 indicates that one element is slightly more important than the other, 5 indicates that it is obviously important, 7 indicates that it is strongly important, and 9 indicates that it is extremely important. The intermediate values ​​2, 4, 6, and 8 represent the intermediate states of adjacent scales.

[0039] Then, for the four dimensions of the criteria layer, a 4×4 judgment matrix is ​​constructed, where the comparison scale between comprehensive energy intensity and equipment energy consumption is 3, the comparison scale with equipment energy efficiency is 5, and the comparison scale with operation correlation is 2.

[0040] Next, the eigenvectors of the judgment matrix are calculated. First, the product of all elements in each row is obtained by multiplying the rows. Then, the fourth root of each row product is taken. Finally, the root result is normalized to obtain the initial weight vector of the criterion layer as [0.42, 0.31, 0.18, 0.09].

[0041] Finally, the consistency of the judgment matrix is ​​checked, and the consistency index CI and consistency ratio CR are calculated. The random consistency index RI is 0.90 when the matrix order is 4. If CR is less than 0.1, the judgment matrix has satisfactory consistency. In this embodiment, the CR value of the criterion layer judgment matrix is ​​0.07, which is less than 0.1, so the weights are effective.

[0042] It should be noted that the same method can be used to calculate the weight of each indicator in the indicator layer relative to its corresponding criterion layer, and then multiply the indicator layer weight by the corresponding criterion layer weight to obtain the final comprehensive weight of each indicator.

[0043] In this embodiment of the invention, calculating the station's comprehensive energy efficiency score based on the indicator data of the hierarchical indicator system and the weights includes: Obtain the measured data of each indicator in the hierarchical indicator system, and calculate the indicator value of each indicator based on the measured data; Multiply the value of each indicator by its corresponding final weight to obtain the weighted score of each indicator. The weighted scores of all indicators are summed to generate the overall energy efficiency score of the station.

[0044] The specific implementation involves first extracting the measured data of each indicator from the standardized multi-source fusion dataset, and then calculating the original indicator value according to the indicator definition. For example, if the total energy consumption of station 03 in a certain month is 84,000 kWh and the total passenger flow is 105,000, then the energy consumption per person is 0.8 kWh / person.

[0045] The original values ​​of each indicator are normalized. Negative energy consumption indicators are normalized in reverse, while positive equipment energy efficiency indicators are normalized in forward. For example, in this embodiment, the maximum EER of all station chiller units is 4.2 and the minimum is 3.0. The EER of chiller unit No. 03 is 3.6, so its normalized value is 0.5.

[0046] Then, the normalized value of each indicator is multiplied by its corresponding final comprehensive weight to obtain the weighted score of that indicator. For example, the normalized value of energy consumption per unit area of ​​station 03 is 0.45, and the final weight is 0.252, so the weighted score of this indicator is approximately 0.113.

[0047] The weighted scores of all 8 indicators are summed, and the sum is multiplied by 100 to obtain the comprehensive energy efficiency score in the range of 0-100. For example, the sum of the weighted scores of all indicators of station 03 is 0.81, and after multiplying by 100, the comprehensive energy efficiency score is 81.

[0048] In this embodiment of the invention, the association mapping process for establishing the association mapping between static data of the building information model and sub-item energy consumption data includes: Extract the spatial component identifiers and corresponding spatial volumes and partition areas of each station from the static data of the building information model; Extract the physical location identifier and energy consumption value of each energy consumption measurement point from the sub-item energy consumption data; Create a unique station identifier for each station, and associate the spatial component identifier with the energy consumption measurement point identifier under the station identifier; Based on the spatial relationship between the spatial component identifier and the energy consumption measurement point identifier, establish a component-measurement point association pair; Based on the component-measuring point association pair, the initial value of energy efficiency density for each spatial partition is calculated. The initial value of energy efficiency density is the ratio of the total energy consumption of the partition to the spatial volume of the partition. The initial value of energy efficiency density is used as the output field of the association mapping and written into the association mapping table.

[0049] In practice, the unique identifiers of spatial components such as public areas, equipment areas, and office areas of each station are first extracted from the BIM model, along with their corresponding spatial volumes and partition areas. At the same time, the physical location identifiers and corresponding energy consumption values ​​of each smart meter and water meter are extracted from the energy consumption database.

[0050] Then, a globally unique site identifier is created for each station. For example, the site ID of the third station on Line 2 is "METRO-2-03". All BIM component identifiers and energy consumption measurement point identifiers of this station are associated with this site identifier to achieve station-level data aggregation. Component-measurement point association pairs are established based on the physical location affiliation of spatial components and energy consumption measurement points. For example, the lighting meter measurement point in the public area is associated with the public area component ID, and the chiller unit meter measurement point in the refrigeration room is associated with the refrigeration room component ID in the equipment area.

[0051] Then, based on the established correlation pairs, the total energy consumption of each spatial partition during the evaluation period is statistically analyzed, and the initial value of the energy efficiency density of that partition is calculated. For example, if the total energy consumption of the public area of ​​Station 03 in a certain month is 13200 kWh and the volume of the public area is 4800 cubic meters, then the initial value of the energy efficiency density of the public area is 2.75 kWh / m³. 3 .

[0052] Finally, the calculated initial values ​​of energy efficiency density for each zone are used as output fields of the association mapping and written into the association mapping table to complete the binding of building space and energy consumption data.

[0053] In this embodiment of the invention, the association mapping process further includes spatial energy efficiency analysis of the association mapping table, including: Read each component-measuring point association pair and its corresponding initial energy efficiency density value from the association mapping table; Using the station identifier as an index, aggregate the initial energy efficiency density values ​​of all spatial partitions within the same station to generate a station-level spatial energy efficiency distribution vector; The station-level spatial energy efficiency distribution vector is spatially superimposed with the passenger flow density of the corresponding time period in the dynamic passenger flow data to calculate the spatial energy efficiency value under the unit passenger flow carrying capacity. The spatial energy efficiency value under the unit passenger flow carrying capacity is used as a spatial energy efficiency evaluation feature and written back to the standardized multi-source fusion dataset.

[0054] In practice, all component-measuring point association pairs and their corresponding initial energy efficiency density values ​​are read from the association mapping table. Data aggregation is performed using the station ID as the index. The initial energy efficiency density values ​​of different spatial zones within the same station are combined into a station-level spatial energy efficiency distribution vector. For example, the spatial energy efficiency distribution vector of station 03 is [public area 2.75, equipment area 3.6, office area 0.9].

[0055] Next, passenger flow density data for each spatial zone during the same period was extracted from the multi-source fusion dataset. Passenger flow density refers to the average daily passenger flow per unit area, measured in people / m²·day. The spatial energy efficiency distribution vector was spatially superimposed with the passenger flow density data to calculate the spatial energy efficiency value per unit passenger flow. For example, if the average daily passenger flow density of the public area of ​​Station 03 is 2.2 people / m², then the spatial energy efficiency value per unit passenger flow in the public area is approximately 1.25 kWh / (m²· ... 3 • Person / ㎡).

[0056] The calculated spatial energy efficiency value per unit passenger flow is used as a new spatial energy efficiency evaluation feature and written back to the standardized multi-source fusion dataset to provide spatial dimension support data for subsequent energy efficiency evaluation.

[0057] In this embodiment of the invention, determining the energy efficiency level of a station according to a preset energy efficiency level classification rule includes: Obtain the comprehensive energy efficiency score; The comprehensive energy efficiency score is compared with multiple preset scoring intervals. Each scoring interval corresponds to an energy efficiency level. The multiple scoring intervals correspond to low energy efficiency level, qualified energy efficiency level, good energy efficiency level and excellent energy efficiency level in order from low to high. When the comprehensive energy efficiency score falls into any score range, the energy efficiency level corresponding to that score range is determined as the current energy efficiency level of the station.

[0058] In practice, scoring ranges can be preset based on experience or needs. For example, four energy efficiency levels and corresponding scoring ranges can be preset: 90-100 points is the excellent energy efficiency level, which means that the station's energy utilization efficiency is at the leading level in the industry; 80-89 points is the good energy efficiency level, which means that the energy utilization efficiency is relatively good; 70-79 points is the qualified energy efficiency level, which means that the energy utilization efficiency meets the basic requirements of the industry; and below 70 points is the low efficiency level, which means that the energy utilization efficiency is poor and there is great potential for energy saving.

[0059] Finally, the calculated comprehensive energy efficiency score for each station is compared with the above scoring range to determine its corresponding energy efficiency level. For example, the comprehensive energy efficiency score for station 03 is 81 points, which falls within the 80-89 point range, and is judged as a good energy efficiency level; the comprehensive energy efficiency score for station 08 is 68 points, which is lower than 70 points, and is judged as a low efficiency level.

[0060] In this embodiment of the invention, generating an evaluation result that includes energy efficiency level and ranking includes: For all stations on the same line or within the same area, sort them from highest to lowest according to their respective comprehensive energy efficiency scores to generate a sorting sequence; The energy efficiency level of each station, its ranking position in the sorting sequence, and the deviation of the station's key energy consumption indicators are combined and packaged to generate a structured evaluation result data body. Output the structured evaluation result data body, wherein the deviation of the key energy consumption index is the difference between the energy consumption per person at the station and the average energy consumption per person on the same line.

[0061] In practice, the 10 stations on Line 2 can be sorted from high to low according to their comprehensive energy efficiency scores to generate a ranking sequence of station energy efficiency. The station with the highest score of 93 points ranks first and is judged to be of excellent energy efficiency level. Station No. 03 ranks third.

[0062] Then, the deviation of key energy consumption indicators for each station is calculated. First, the average energy consumption per person for all stations on the same line is calculated, which is 0.72 kWh / person in this embodiment. Then, the difference between the energy consumption per person for each station and this average value is calculated. For example, the energy consumption per person for station 03 is 0.8 kWh / person, so its deviation is 0.08 kWh / person.

[0063] Then, the station ID, station name, energy efficiency level, ranking position, deviation of key energy consumption indicators, spatial energy efficiency distribution vector, and energy efficiency data of major equipment for each station are combined and packaged to generate a structured evaluation result data body in JSON format.

[0064] Finally, the data is output to the subway energy management system and smart operation platform, which automatically generates visualized energy efficiency rating reports, line station energy efficiency ranking bar charts, and station space energy efficiency heat maps. For stations with low energy efficiency ratings, the system automatically generates energy-saving potential analysis reports, locates high-energy-consuming zones and inefficient equipment, and provides quantitative basis for operation optimization.

[0065] It should be emphasized that, in alternative embodiments of the present invention, the entropy weight method can be used instead of the AHP analytic hierarchy process to calculate the index weights, and the LSTM long short-term memory neural network and the multiple linear regression algorithm can be used to construct the energy efficiency evaluation model. The overall multi-source data fusion architecture, hierarchical index system, energy efficiency level classification rules and evaluation result generation method remain unchanged, making the present invention more scalable and adaptable.

[0066] In the several embodiments provided by this invention, it should be understood that the disclosed method can be implemented in other ways.

[0067] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0068] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, and technology that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0069] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for evaluating the energy efficiency level of urban rail transit stations based on multi-source data fusion, characterized in that, The method includes: Acquire multi-source basic data of urban rail transit stations, clean, fuse and perform correlation mapping on the multi-source basic data, and construct a standardized multi-source fusion dataset; Based on the standardized multi-source fusion dataset, a hierarchical index system for station energy efficiency evaluation is constructed, and the weight of each index in the hierarchical index system is determined. Based on the indicator data and weights of the hierarchical indicator system, the station's comprehensive energy efficiency score is calculated. Based on the comprehensive energy efficiency score, the energy efficiency level of the station is determined according to the preset energy efficiency level classification rules, and an evaluation result including energy efficiency level and ranking is generated.

2. The method for evaluating the energy efficiency level of urban rail transit stations based on multi-source data fusion as described in claim 1, characterized in that, The acquisition of multi-source basic data for urban rail transit stations includes: Obtain static data of the building information model of the station, which includes the station's spatial volume and zone area; Obtain the sub-item energy consumption data of the station, which includes traction power consumption and power and lighting power consumption; The station's dynamic passenger flow data is obtained, including inbound passenger flow and transfer passenger flow. The environmental parameters and equipment operating parameters of the station are obtained. The environmental parameters include outdoor temperature and humidity, and the equipment operating parameters include the energy efficiency ratio of the chiller unit and the escalator load rate. Obtain the station's operational data, which includes operating duration and train formation information.

3. The method for evaluating the energy efficiency level of urban rail transit stations based on multi-source data fusion as described in claim 2, characterized in that, The cleaning, fusion, and correlation mapping processing of the multi-source basic data includes: Anomaly detection is performed on the energy consumption data, dynamic passenger flow data, environmental parameters, and equipment operating parameters, and data points exceeding three times the standard deviation of the mean are removed. For the missing data points resulting from the removal process, linear interpolation is used to complete them. The calculation method for linear interpolation is as follows: In the formula, Time to be completed The value, and These are the data values ​​at the adjacent times before and after the missing time; All the completed data will be normalized to a preset numerical range; Based on the spatial identifiers in the static data of the building information model, a unique mapping relationship is established with the energy consumption measurement point identifiers in the sub-item energy consumption data, and an association mapping table is generated.

4. The method for evaluating the energy efficiency level of urban rail transit stations based on multi-source data fusion as described in claim 1, characterized in that, The hierarchical index system for evaluating station energy efficiency includes: Establish a three-layer structure comprising a target layer, a criterion layer, and an indicator layer; The criteria layer includes a comprehensive energy consumption intensity dimension, an equipment energy consumption dimension, an equipment energy efficiency dimension, and an operation-related dimension. Under the aforementioned comprehensive energy intensity dimension, energy consumption per unit area and energy consumption per person per visit are set. Under the aforementioned equipment energy consumption dimension, set the energy consumption index per unit area for the air conditioning system and the energy consumption index per unit area for the escalator; Under the aforementioned equipment energy efficiency dimension, the energy efficiency ratio index of the chiller unit and the transformer load rate index are set; Under the aforementioned operational correlation dimension, passenger flow intensity index and seasonal impact coefficient index are set.

5. The method for evaluating the energy efficiency level of urban rail transit stations based on multi-source data fusion as described in claim 4, characterized in that, Determining the weights of each indicator in the hierarchical indicator system includes: For each element within the same level in the criterion layer and the index layer, a judgment matrix is ​​constructed using a pairwise comparison scaling method; Calculate the eigenvectors of the judgment matrix as the initial weights of each element; The judgment matrix is ​​subjected to consistency verification. When the verification passes, the initial weights are determined as the final weights.

6. The method for evaluating the energy efficiency level of urban rail transit stations based on multi-source data fusion as described in claim 5, characterized in that, The step of calculating the station's comprehensive energy efficiency score based on the indicator data of the hierarchical indicator system and the weights includes: Obtain the measured data of each indicator in the hierarchical indicator system, and calculate the indicator value of each indicator based on the measured data; Multiply the value of each indicator by its corresponding final weight to obtain the weighted score of each indicator. The weighted scores of all indicators are summed to generate the overall energy efficiency score of the station.

7. The method for evaluating the energy efficiency level of urban rail transit stations based on multi-source data fusion as described in claim 1, characterized in that, The association mapping process establishes an association mapping between static data of the building information model and sub-item energy consumption data, including: Extract the spatial component identifiers and corresponding spatial volumes and partition areas of each station from the static data of the building information model; Extract the physical location identifier and energy consumption value of each energy consumption measurement point from the sub-item energy consumption data; Create a unique station identifier for each station, and associate the spatial component identifier with the energy consumption measurement point identifier under the station identifier; Based on the spatial relationship between the spatial component identifier and the energy consumption measurement point identifier, establish a component-measurement point association pair; Based on the component-measuring point association pair, the initial value of energy efficiency density for each spatial partition is calculated. The initial value of energy efficiency density is the ratio of the total energy consumption of the partition to the spatial volume of the partition. The initial value of energy efficiency density is used as the output field of the association mapping and written into the association mapping table.

8. The method for evaluating the energy efficiency level of urban rail transit stations based on multi-source data fusion as described in claim 7, characterized in that, The association mapping process also includes spatial energy efficiency analysis of the association mapping table, including: Read each component-measuring point association pair and its corresponding initial energy efficiency density value from the association mapping table; Using the station identifier as an index, aggregate the initial energy efficiency density values ​​of all spatial partitions within the same station to generate a station-level spatial energy efficiency distribution vector; The station-level spatial energy efficiency distribution vector is spatially superimposed with the passenger flow density of the corresponding time period in the dynamic passenger flow data to calculate the spatial energy efficiency value under the unit passenger flow carrying capacity. The spatial energy efficiency value under the unit passenger flow carrying capacity is used as a spatial energy efficiency evaluation feature and written back to the standardized multi-source fusion dataset.

9. The method for evaluating the energy efficiency level of urban rail transit stations based on multi-source data fusion as described in claim 1, characterized in that, The process of determining the station's energy efficiency level according to a preset energy efficiency level classification rule includes: Obtain the comprehensive energy efficiency score; The comprehensive energy efficiency score is compared with multiple preset scoring intervals. Each scoring interval corresponds to an energy efficiency level. The multiple scoring intervals correspond to low energy efficiency level, qualified energy efficiency level, good energy efficiency level and excellent energy efficiency level in order from low to high. When the comprehensive energy efficiency score falls into any score range, the energy efficiency level corresponding to that score range is determined as the current energy efficiency level of the station.

10. The method for evaluating the energy efficiency level of urban rail transit stations based on multi-source data fusion as described in claim 1, characterized in that, The generation of evaluation results, which include energy efficiency levels and rankings, includes: For all stations on the same line or within the same area, sort them from highest to lowest according to their respective comprehensive energy efficiency scores to generate a sorting sequence; The energy efficiency level of each station, its ranking position in the sorting sequence, and the deviation of the station's key energy consumption indicators are combined and packaged to generate a structured evaluation result data body. Output the structured evaluation result data body, wherein the deviation of the key energy consumption index is the difference between the energy consumption per person at the station and the average energy consumption per person on the same line.

Images