An energy-saving strategy generation method based on rail transit operation mode recognition

Abstract

The application discloses an energy-saving strategy generation method based on rail transit operation mode recognition, and belongs to the technical field of rail transit operation. The application collects and pre-processes multi-source data, extracts time characteristics, passenger flow characteristics, operation characteristics, energy consumption characteristics and vehicle and environment characteristics, and forms a characteristic data set after standardization processing. The initial clustering center is selected based on the probability distribution of the sample points of the characteristic data set, the typical operation mode set is obtained through sample point clustering distribution and cluster center correction, and the noise points are recognized as abnormal operation modes. The all-scene energy-saving operation strategy is customized for each typical operation mode, the corresponding energy-saving strategy or the early warning strategy is executed through real-time data acquisition, standardization processing and mode matching. The application covers all operation scenes by combining typical and abnormal mode classification, significantly improves the energy-saving scheduling accuracy and scene adaptability, and provides technical support for realizing efficient and energy-saving operation of rail transit.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of rail transit operation, in particular to a kind of energy-saving strategy generation method based on rail transit operation mode identification. BACKGROUND

[0002] As the backbone system of urban public transport, urban rail transit has the advantages of large capacity, high speed, safety and punctuality, but it is also a large energy consumer. With the acceleration of urbanization and the expansion of rail transit network, the proportion of rail transit energy consumption in the total energy consumption of the city is increasing year by year, and energy saving has become an important challenge for rail transit operating companies.

[0003] Currently, energy-saving technologies in the field of rail transit are mainly divided into two categories: one is the energy-saving technology at the device level, such as using high-efficiency traction transmission system, regenerative energy recovery device, etc.; the other is the energy-saving strategy at the operation level, such as optimizing the operation curve, adjusting the train organization, etc. The former requires a large amount of hardware investment, and the latter is more economical and flexible.

[0004] In terms of operational energy saving, existing technologies mostly use fixed strategies or strategies based on simple rules. For example, a single energy-saving operation diagram is used during off-peak hours, and the regular operation diagram is restored during peak hours. This method is simple and easy to implement, but it has poor adaptability and cannot cope with the complex and variable conditions in actual operation. Rail transit operating scenarios are diverse, such as different scenarios on weekdays, peak, off-peak, weekends, and special event days, with significant differences in passenger flow, train density, and power grid load. Fixed strategies are difficult to achieve optimal energy-saving results in all scenarios.

[0005] In recent years, with the development of intelligent rail transit, some data-based energy-saving methods have been proposed. For example, Chinese Patent Publication No. CN111831658A proposes a rail transit big data analysis method and system that can preliminarily analyze and predict energy consumption data. However, such methods are mostly limited to data analysis and visualization and fail to directly translate the analysis results into executable energy-saving strategies. In addition, existing methods mostly focus on single-dimensional (such as energy consumption) data analysis and lack comprehensive multi-dimensional identification of operating modes, especially failing to fully consider the internal relationship between operating modes and energy consumption characteristics. At the same time, existing data-driven methods mostly rely on structured data, but have insufficient processing capacity for a large amount of unstructured data in the rail transit system, resulting in insufficient utilization of data value and low energy-saving scheduling accuracy. SUMMARY

[0006] To address the above deficiencies in the prior art, the present application provides a kind of energy-saving strategy generation method based on rail transit operation mode identification, which solves the problem of low energy-saving scheduling accuracy in the prior art.

[0007] In order to achieve the above object, the present application adopts the technical scheme as follows: a kind of energy-saving strategy generation method based on rail transit operation mode recognition, comprising the following steps:

[0008] S1, collect and pretreat multi-source data, and extract time characteristics, passenger flow characteristics, operation characteristics, energy consumption characteristics and vehicle and environmental characteristics from the pretreated multi-source data;

[0009] S2, standardize each feature to obtain standardized features and form a feature data set;

[0010] S3, according to the probability distribution of sample points in the feature data set, select multiple initial cluster centers from the feature data set;

[0011] S4, each sample point is first assigned to the cluster where the nearest initial cluster center is located, and the cluster center is corrected, the cluster is updated to obtain a typical operation mode set;

[0012] S5, classify each sample point in the feature data set, find noise points, and mark noise points as abnormal operation modes;

[0013] S6, for each cluster in the typical operation mode set, first label its operation mode, and then customize multiple energy-saving operation strategies covering all scenarios based on each labeled operation mode;

[0014] S7, real-time data acquisition and standardization, matching the typical operation mode executes the corresponding energy-saving strategy, and matching the abnormal operation mode triggers the early warning strategy.

[0015] Further, the multi-source data in S1 includes train operation data, energy consumption data, passenger flow data and equipment state data.

[0016] Further, S3 includes the following steps:

[0017] S31, randomly select a sample point from the feature data set as an initial cluster center, and place the initial cluster center in the initial cluster center set;

[0018] S32, calculate the shortest distance between each sample point in the feature data set and the initial cluster center in the initial cluster center set;

[0019] S33, calculate the probability distribution according to the shortest distance corresponding to each sample point in the feature data set;

[0020] S34, according to the probability distribution, use the roulette method to select the next sample point from the feature data set as a new initial cluster center, and continue to include the new initial cluster center in the initial cluster center set;

[0021] S35, repeat steps S32-S34 until K initial cluster centers are selected, K being an upper limit number of initial cluster centers.

[0022] Further, the formula for calculating the shortest distance in S32 is: ,

[0023] where D(x i ) is the shortest distance of the i-th sample point in the feature data set, x i is the i-th sample point, c j is the j-th initial cluster center in the current initial cluster center set, k is the number of initial cluster centers in the current initial cluster center set, j is the number of initial cluster centers, || || is the Euclidean distance, and min is the minimum value of k distances.

[0024] Further, the formula for calculating the probability distribution in S33 is: ,

[0025] where P(x i ) is the probability distribution of each sample point in the feature data set, D is the number of sample points in the feature data set, x n is the n-th sample point in the feature data set, D(x n ) is the shortest distance of the n-th sample point in the feature data set, and D is the feature data set.

[0026] Further, S4 includes the following steps:

[0027] S41, calculate the distance between the sample points in the feature data set and the plurality of initial cluster centers, select the initial cluster center corresponding to the shortest distance, and add the corresponding sample points to the cluster;

[0028] S42, traverse the sample points in the feature data set through step S41 to obtain K initial clusters;

[0029] S43, take the centroid of each initial cluster as a new initial cluster center, and re-execute S41 and S42 with the new initial cluster center until convergence is obtained, thereby obtaining K clusters;

[0030] S44, form a typical operation mode set from the clusters.

[0031] Further, S5 includes the following steps:

[0032] S51, randomly select an unvisited sample point p in the feature data set, and obtain the ε-neighborhood point set of the sample point p, where ε is the neighborhood radius;

[0033] S52, if the number of points in the e-neighborhood point set of the sample point p is greater than or equal to the minimum number of neighborhood points minPts required by the core point, the sample point p is marked as a core point p;

[0034] S53, all sample points in the neighborhood point set of the core point p are added to the "neighbor set";

[0035] S54, any sample point in the "neighbor set" is taken to obtain a current neighbor point Q;

[0036] S55, it is judged whether the current neighbor point Q is visited;

[0037] S56, when not visited, it is checked that the number of points in the e-neighborhood point set of the current neighbor point Q is greater than or equal to the minimum number of neighborhood points minPts required by the core point, the current neighbor point Q is marked as a core point, and the sample points not belonging to the cluster in the e-neighborhood point set of the current neighbor point Q are added to the "neighbor set" of the core point p, when less than the minimum number of neighborhood points minPts required by the core point, the current neighbor point Q is marked as a boundary point, and the boundary point is classified into the "neighbor set" of the core point p;

[0038] S57, when visited, jump to S54 to select a new sample point, until the "neighbor set" of the core point p is traversed, and the "neighbor set" of the current core point p is taken as a complete cluster;

[0039] S58, jump to step S51 to construct the next cluster, and traverse the sample points in the feature data set to obtain multiple clusters, and mark the remaining sample points not included in the cluster as noise points;

[0040] S59, the noise points are marked as abnormal operation modes.

[0041] Further, the e-neighborhood point set in S51 is: ,

[0042] Wherein, N ϵ (p) is the e-neighborhood point set of the sample point p, dist(p,q) is the distance between the sample points p and q, D is the feature data set, and e is the neighborhood radius.

[0043] Further, the types of the marked operation modes in S6 include: "summer weekday evening peak high-density" mode, "winter weekend flat peak low passenger flow" mode and "spring and autumn best idling" mode;

[0044] The multiple energy-saving operation strategies include: low passenger load long station distance coasting optimization strategy, peak high density cooperative regenerative braking strategy, seasonal temperature control and lighting adaptive strategy, line topology adaptive traction strategy, energy storage scheduling strategy based on time-of-use electricity price, redundant time dynamic allocation strategy, multi-vehicle cooperative speed guidance strategy, intelligent sleep strategy of equipment during non-operation period and dynamic response strategy for special events.

[0045] The beneficial effects of the present application are:

[0046] 1. The present application realizes full-scene recognition of "typical operation mode + abnormal operation mode" through multi-dimensional feature extraction (5 types of features such as time, passenger flow, operation, etc.) and two clustering methods, breaking the limitations of existing fixed strategies or single-dimensional analysis. For example, special energy-saving strategies are customized for "peak high density" and "low passenger load long station distance" labeled modes, and corresponding solutions are executed in real time to match the scene, solving the problem that existing technologies cannot adapt to complex operation scenes and the energy-saving effect is unstable, making the energy-saving dispatching accurately fit the differences in passenger flow, train density and other parameters in different scenes, greatly improving the pertinence and effectiveness of energy-saving strategies and improving the energy-saving dispatching precision.

[0047] 2. Unlike existing data-driven methods which only stay at the level of energy consumption analysis and visualization, the present application not only integrates multi-source data (including unstructured data potential processing capability) and mines the internal correlation between operation mode and energy consumption characteristics, but also directly converts the patterns obtained by clustering into executable energy-saving strategies (such as cooperative regenerative braking, seasonal temperature control, etc.), constructing a complete closed loop of "data collection - pattern recognition - strategy generation - real-time execution", fully releasing the value of multi-source data of rail transit and avoiding waste of data resources.

[0048] 3. The present application identifies abnormal operation modes (such as sudden faults and sudden increase of passenger flow in large-scale activities) and triggers warning strategies, rather than applying conventional energy-saving solutions, which not only ensures efficient energy saving in conventional scenes, but also prioritizes operational safety in abnormal scenes, solving the problem of "prioritizing energy saving over safety" or "difficulty in balancing safety and energy saving" in existing technologies, and improving the overall robustness of rail transit systems. BRIEF DESCRIPTION OF DRAWINGS

[0049] Figure 1 It is a flowchart of an energy-saving strategy generation method based on rail transit operation mode recognition. DETAILED DESCRIPTION

[0050] The specific embodiments of the present application are described below to facilitate the understanding of the present application for those skilled in the art, but it should be clear that the present application is not limited to the scope of the specific embodiments, and for those skilled in the art, it is obvious that various changes are within the spirit and scope of the present application defined and determined by the appended claims, and all the inventions utilizing the concept of the present application are within the scope of protection.

[0051] As shown in the figure, a kind of energy-saving strategy generation method based on rail transit operation mode recognition includes the following steps: Figure 1

[0052] S1, collect and pre-process multi-source data, and extract time features, passenger flow features, running features, energy consumption features and vehicle and environment features from the pre-processed multi-source data;

[0053] S2, standardize each feature to obtain standardized features and form a feature data set;

[0054] S3, according to the probability distribution of the sample points in the feature data set, select a plurality of initial cluster centers from the feature data set;

[0055] S4, assign each sample point to the cluster where the nearest initial cluster center is located first, and correct the cluster center, update the cluster, to obtain a typical operation mode set;

[0056] S5, classify each sample point in the feature data set, find noise points, and mark the noise points as abnormal operation modes;

[0057] S6, for each cluster in the typical operation mode set, first label its operation mode, and then based on each labeled operation mode, customize a plurality of energy-saving operation strategies covering all scenarios;

[0058] S7, real-time data acquisition and standardization, matching the typical operation mode executes the corresponding energy-saving strategy, and matching the abnormal operation mode triggers the early warning strategy.

[0059] In this embodiment, the multi-source data in S1 includes train operation data, energy consumption data, passenger flow data and equipment state data.

[0060] Data collection covers all aspects of rail transit operation, and the main data includes:

[0061] Train operation data: obtain the number of trains on the line, train position, speed, acceleration, inter-station running time, stopping time, etc. from the train automatic monitoring system ATS; obtain control instructions (corresponding traction level under different speeds, coasting instructions, braking instructions) from the train automatic driving system ATO, etc.

[0062] ​Energy consumption data: Obtain energy consumption data of each period and each section from the traction power supply system, including traction energy consumption and regenerative energy feedback.

[0063] Passenger flow data: Obtain the in-out passenger flow of each station and each period, and OD data from the AFC.

[0064] Equipment status data: including the running status and fault information of track, catenary, power supply system and other equipment.

[0065] The data preprocessing process includes data cleaning, data integration and feature engineering.

[0066] Data cleaning: handle missing values, outliers and duplicate data. For missing values in important fields, use multiple filling strategies (such as mean filling, regression filling, etc.); for outliers, identify and correct them according to business rules.

[0067] Data integration: align and integrate different sources and formats of data in time and space to form a unified operation data record.

[0068] Feature engineering: extract features related to energy consumption, such as period features (morning peak, evening peak, flat peak, etc.), passenger flow features (high passenger flow, low passenger flow, etc.), and operation features (speed stability, acceleration distribution, etc.).

[0069] From the preprocessed data, extract multi-dimensional features strongly related to energy consumption to form a high-dimensional feature vector for clustering analysis. These features include but are not limited to:

[0070] Time feature T includes: time period T1 (such as dividing a day into 24 time periods or "morning peak", "flat peak", "evening peak", "night" and other category labels, and performing one-hot encoding), day status T2: weekday / weekend / holiday flag and season T3: spring, summer, autumn, winter.

[0071] Passenger flow feature P includes: average cross-section passenger flow (person / hour) P1, maximum load rate (%) P2 and passenger flow unevenness coefficient P3 (maximum cross-section passenger flow / average cross-section passenger flow).

[0072] Running feature O: average train density (number of trains / hour) O1, minimum train interval (seconds) O2, average travel speed (km / h) O3, speed curve smoothness (measured by standard deviation of acceleration, m² / s³) O4 and average inter-station running time (seconds) O5.

[0073] Energy consumption feature E: unit vehicle kilometer traction energy consumption (kWh / vehicle kilometer) E1, regenerative energy feedback rate (feedback energy / traction energy consumption, %) E2 and unit passenger flow energy consumption (kWh / person kilometer) E3.

[0074] Vehicle and environment features V: train formation number (sections) V1, vehicle model identification (different vehicle models have different efficiencies) V2, and average ambient temperature (℃) V3.

[0075] Since the dimensions and orders of magnitude of various feature parameters are different, standardization processing must be performed to eliminate their influence. The present application adopts a Z-Score standardization method, so that the mean of each feature is 0 and the standard deviation is 1:

[0076] wherein, is a feature after standardization processing, is an original feature, is the mean of the feature on all samples, is the standard deviation of the feature.

[0077] In the present embodiment, a correspondence between data features and running mode recognition outputs adopts a co-clustering strategy, an improved K-Means++ algorithm is adopted as a core algorithm to identify typical running modes of rail transit, an improved DBSCAN algorithm is adopted to analyze running data to identify abnormal running data points that do not belong to any typical mode, and when real-time data is identified as an abnormal point, the system enables a default running strategy and gives an alarm.

[0078] In the present embodiment, S3 includes the following steps:

[0079] S31, randomly selecting a sample point from a feature data set D={x1, x2,..., xN} as an initial clustering center, placing the initial clustering center in an initial clustering center set, x1, x2,..., xN being 1~N sample points in the feature data set, and N being the number of sample points in the feature data set; N N x1, x2,..., xN being 1~N sample points in the feature data set, and N being the number of sample points in the feature data set;

[0080] S32, calculating the shortest distance between each sample point in the feature data set and the initial clustering center in the initial clustering center set;

[0081] S33, calculating a probability distribution according to the shortest distance corresponding to each sample point in the feature data set;

[0082] S34, according to the probability distribution, using a roulette wheel method to select a next sample point from the feature data set as a new initial clustering center, and continuously including the new initial clustering center in the initial clustering center set;

[0083] S35, repeating steps S32~S34 until K initial clustering centers are selected, K being the upper limit number of initial clustering centers.

[0084] In the present embodiment, the calculation formula of the shortest distance in S32 is: ​​,

[0085] Where D(x) i x is the shortest distance to the i-th sample point in the feature dataset. i For the i-th sample point, c j Let be the j-th initial cluster center in the current initial cluster center set, k be the number of initial cluster centers in the current initial cluster center set, j be the index of the initial cluster center, || || be the Euclidean distance, and min be the minimum value among the k distances.

[0086] In this embodiment, the formula for calculating the probability distribution in S33 is: ,

[0087] Wherein, P(x i Let be the probability distribution of each sample point in the feature dataset, and D be the number of sample points in the feature dataset. n Let D(x) be the nth sample point in the feature dataset. n ) represents the shortest distance to the nth sample point in the feature dataset, and D represents the feature dataset.

[0088] this This represents the "qualification" of a point to be selected as the next center; the farther a point is from an already selected center, the lower its qualification. The larger the value, the greater the probability of being selected. This ensures that the new center point will be selected in an area far away from existing points, making the initial centers as dispersed as possible.

[0089] The formula for calculating the probability distribution is used to divide each point Converting to the probability of being selected, this formula makes the probability of a point being selected proportional to the square of its distance from the already selected center point.

[0090] In this embodiment, the goal of S4 is to assign each sample point to the cluster containing the nearest cluster center. S4 includes the following sub-steps:

[0091] S41. Calculate the distance between sample points in the feature dataset and multiple initial cluster centers, select the cluster containing the initial cluster center corresponding to the shortest distance, and add the corresponding sample points to that cluster;

[0092] S42. By traversing all sample points in the feature dataset in step S41, K initial clusters are obtained;

[0093] S43. Take the centroid of each initial cluster as the new initial cluster center. With the new initial cluster centers, re-execute S41 and S42 until convergence, and obtain K clusters.

[0094] S44. Form a set of typical operating modes for each cluster.

[0095] The centroid formula is: wherein, is the new initial cluster center of the jth cluster, x i is the ith sample point, C j is the jth cluster, and L is the number of sample points in the jth cluster.

[0096] In this embodiment, the convergence condition includes: 1, the position of the cluster center no longer changes significantly (i.e., ||x is less than a preset threshold, is the old initial cluster center). 2, the members of the cluster no longer change. 3, the preset maximum number of iterations is reached.

[0097] Determining the optimal number of clusters K includes two methods. The first method assists in selecting K by measuring the compactness of the model under different K values. The core index is the sum of squared errors within the cluster.

[0098] The formula for the sum of squared errors within the cluster is: ,

[0099] wherein, is the total sum of squared errors within the cluster when the number of clusters is K, is the sum of squared Euclidean distances of all sample points in the cluster C j to its c j , which measures the compactness of the cluster.

[0100] Calculate SSE(K) corresponding to K from 1 to a maximum value (such as 10). Draw the relationship curve of K and SSE(K). Observe the curve and find the "elbow point". Before this point, SSE(K) rapidly decreases with the increase of K; after this point, the decrease speed suddenly slows down. The K value corresponding to this inflection point is the recommended value.

[0101] The second method comprehensively evaluates the clustering quality from two dimensions of intra-cluster cohesion and inter-cluster separation.

[0102] For sample point i (belonging to cluster C a ), calculate the average intra-cluster distance: ,

[0103] wherein, is the average distance of the ith sample point to all other points in the same cluster C a , is the number of elements in the set, The smaller the value, the more the point i should belong to this cluster, and the higher the intra-cluster cohesion.

[0104] Calculate the average nearest cluster distance: ,

[0105] where b(i) is the average nearest cluster distance of the ith sample point, C b is another cluster, x m is the mth sample point.

[0106] The formula for calculating the average nearest cluster distance is used to calculate the average distance from the ith sample point to all points in all non-affiliated clusters C a , and then the minimum value of these average distances is taken. b(i) can be understood as the average distance of point i to the "suboptimal affiliation cluster". The larger b(i) is, the better the point i is separated from other clusters.

[0107] The silhouette coefficient of sample point i is calculated as: ,

[0108] where s(i) is the silhouette coefficient of the ith sample point, and max is the maximum value.

[0109] In the formula for calculating the silhouette coefficient of sample point i, the numerator b(i)−a(i): measures the difference between the separation degree and the cohesion degree. The denominator max[a(i),b(i)]: is the normalization factor. The value range of s(i) is [−1,1]. s(i) close to 1: indicates that the clustering of point i is reasonable. s(i) close to 0: indicates that point i is on the boundary of two clusters. s(i) close to -1: indicates that sample point i may be assigned to the wrong cluster.

[0110] The process of determining the optimal K value includes: clustering for each K value. Calculate the average value S(K) of the silhouette coefficient s(i) of all sample points. Select the K value that makes the average silhouette coefficient S(K) maximum as the optimal clustering number.

[0111] In this embodiment, S5 includes the following steps:

[0112] S51, randomly select an unvisited sample point p in the feature data set, and obtain the ε-neighborhood point set of sample point p, where ε is the neighborhood radius;

[0113] S52, if the number of points in the ε-neighborhood point set of sample point p is greater than or equal to the minimum number of neighborhood points minPts required by the core point, mark the sample point p as a core point p;

[0114] S53, add all sample points in the neighborhood point set of core point p to the "neighbor set";

[0115] S54, randomly select a sample point in the "neighbor set" to obtain the current neighbor point Q;

[0116] S55, judge whether the current neighbor point Q is visited;

[0117] S56, if not visited, check the number of points in the e-neighborhood point set of the current neighbor point Q, if greater than or equal to the minimum number of neighbor points required by the core point minPts, mark the current neighbor point Q as a core point, and add the sample points in the e-neighborhood point set of the current neighbor point Q that have not been clustered to the "neighbor set" of the core point p, if less than the minimum number of neighbor points required by the core point minPts, mark the current neighbor point Q as a boundary point, and add the boundary point to the "neighbor set" of the core point p;

[0118] S57, if visited, jump to S54 to select a new sample point, until the "neighbor set" of the core point p is traversed, and the "neighbor set" of the current core point p is taken as a complete cluster;

[0119] S58, jump to step S51 to construct the next cluster, and traverse the sample points in the feature data set to obtain multiple clusters, and mark the remaining sample points that have not been included in the cluster as noise points;

[0120] S59, mark the noise points as abnormal operation mode.

[0121] These noise points correspond to sudden failures, large activities, extreme weather and other atypical abnormal operation states. When the system is online, once it is found that the real-time data is determined as noise by DBSCAN, a warning is triggered, and a conservative default operation strategy is adopted, instead of any energy-saving strategy, so as to ensure the operation safety. This greatly enhances the intelligence and robustness of the entire system.

[0122] In the embodiment, the e-neighborhood point set in S51 is: ,

[0123] Wherein, N ϵ (p) is the e-neighborhood point set of the sample point p, dist(p, q) is the distance between the sample point p and the sample point q, D is the feature data set, and e is the neighborhood radius.

[0124] Summary of the algorithm process in step S5: Given an object (sample point) p and a radius e (specified by the parameter eps), the e-neighborhood of point p is the set of all points within the hypersphere (circle in two-dimensional space) centered at p with radius e.

[0125] Core point, boundary point and noise point:

[0126] The type of a point depends on the number of points in its e-neighborhood (including the point itself).

[0127] Core point: if the e-neighborhood of a sample point p contains at least minPts points (i.e. the density reaches the threshold), the point is a core point, i.e. the judgment condition: |N ϵ (p) | ≥ minPts.

[0128] Border points: If a sample point q has less than minPts points in its e-neighborhood, but it falls in the e-neighborhood of some core point, then the point is a border point, i.e. the condition: |N ϵ (q) | < minPts, and ∃p ∈ D such that p is a core point and q ∈ N ϵ (p).

[0129] Noise points: Points that are neither core points nor border points. These points are in low-density regions and do not belong to any cluster. The condition is not satisfied for core points and border points.

[0130] The specific implementation process starts from any unvisited point. If the number of points in its e-neighborhood exceeds minPts, a new cluster is created, and all density-reachable points are recursively added to the cluster. Points that cannot be assigned to any cluster are considered noise.

[0131] In this embodiment, the types of the running mode marked in S6 include: "summer weekday evening peak high-density" mode, "winter weekend flat peak low passenger flow" mode, and "spring and autumn best coasting" mode;

[0132] The various energy-saving operation strategies include: low-load passenger long-station-distance coasting optimization strategy, peak high-density cooperative regenerative braking strategy, seasonal temperature control and lighting adaptive strategy, line topology adaptive traction strategy, energy storage scheduling strategy based on time-of-use electricity price, redundant time dynamic allocation strategy, multi-car cooperative speed guidance strategy, intelligent hibernation strategy of equipment during non-operation period, and dynamic response strategy for special events.

[0133] Business interpretation is performed on each cluster, and a label with clear energy-saving significance is assigned, for example:

[0134] "summer weekday evening peak high-density" mode: characterized by T1= evening peak, T3= summer, O1> 30 trains / hour, V3> 30℃, and E1 and E2 are both high.

[0135] "Winter weekend flat peak low passenger flow" mode: characterized by T1= flat peak, T2= weekend, P1< 50% full load rate, and V3< 10℃.

[0136] "spring and autumn best coasting" mode: characterized by T3= spring / autumn, O1 is moderate, O4 (speed smoothness) is good, and V3 is suitable (no need for high-power air conditioning).

[0137] At the same time, a detailed feature portrait is generated for each mode, i.e. the statistical distribution (such as mean, quantile, etc.) of each feature parameter of all sample points in the cluster, providing accurate data support for subsequent customized energy-saving strategies.

[0138] This embodiment sets 9 different energy-saving operation modes.

[0139] 1. Low passenger load and long station distance coasting optimization strategy

[0140] Target mode: Suitable for suburban lines and night period, characterized by low passenger flow, long station distance, and no urgent punctual pressure.

[0141] Characteristic parameters: Passenger flow < 30% full load rate, station distance > 2 km, planned redundancy time > 1 minute.

[0142] Strategy content: On the premise of ensuring the minimum travel time, significantly reduce the maximum running speed (such as from 100 km / h to 80 km / h), and extend the coasting phase in advance. The system will calculate the optimal "acceleration-coasting-braking" curve to maximize the use of train kinetic energy and reduce braking energy consumption.

[0143] 2. Peak high-density coordinated regenerative braking strategy

[0144] Target mode: Suitable for morning and evening peak hours, characterized by extremely high train density (minimum interval < 2 minutes) and frequent train start-stop.

[0145] Characteristic parameters: Train density > 30 pairs / hour, large energy consumption fluctuation per unit time, and frequent regenerative energy generation.

[0146] Strategy content: Dynamically optimize the coordinated operation of trains within the same power supply partition. When a train brakes, the system will slightly adjust the traction of adjacent accelerating trains, or preferentially use the regenerative energy through the energy management system (EMS) rather than feeding it back to the power grid, increasing the "immediate utilization rate" of regenerative energy from the usual 30-40% to more than 50%.

[0147] 3. Seasonal temperature control and lighting adaptive strategy

[0148] Target mode: Suitable for all operation modes, but with parameter fine-tuning according to season and external environment.

[0149] Characteristic parameters: Ambient temperature, humidity, light intensity, and car full load rate.

[0150] Strategy content:

[0151] Summer: Within the acceptable comfort range of passengers, dynamically set the target temperature of the car (such as from 24°C to 26°C), and optimize the operation mode of the fresh air system.

[0152] Winter: Utilize passenger body heat and equipment heat dissipation to reduce electric heating power.

[0153] Lighting: Automatically adjust the brightness of platform and car lighting based on daylight intensity and whether the train is entering or leaving the station.

[0154] 4. Line topology adaptive traction strategy

[0155] Target mode: Suitable for lines with many slopes and large curves.

[0156] Characteristic parameters: Real-time train position, line slope curve, current train load.

[0157] Strategy content: The system pre-stores the accurate slope map of the line. Before climbing, the train is allowed to slightly exceed the speed on the flat section to accumulate kinetic energy; before descending, it enters the coasting or slight braking mode in advance to convert potential energy and reduce net traction energy consumption.

[0158] 5. Energy storage scheduling strategy based on time-of-use electricity price

[0159] Target mode: Suitable for vehicle depots, parking lots, and sites on the line equipped with energy storage devices (such as flywheels, batteries).

[0160] Characteristic parameters: Real-time electricity price (peak / flat / valley), energy storage device SOC (state of charge), predicted next peak period energy consumption.

[0161] Strategy content: Charge the energy storage device during the electricity price valley period (such as late at night), and discharge it during the electricity price peak period (such as the evening peak), to directly reduce electricity costs for train starting or station equipment power supply.

[0162] 6. Dynamic allocation of redundant time strategy

[0163] Target mode: Suitable for timetables with planned redundant time (buffer time).

[0164] Characteristic parameters: Current delay status, remaining time to the next station, scheduled redundant time.

[0165] Strategy content: If the train is on time or slightly ahead of schedule, the system will automatically enable the energy-saving operation curve to smoothly allocate redundant time, rather than waiting for a long time before the station. If the train is late, switch to the on-time priority mode.

[0166] 7. Multi-vehicle coordinated speed guidance strategy

[0167] Target mode: Suitable for medium to high density lines and with continuous communication capabilities between vehicles (V2V) or between vehicles and the ground.

[0168] Characteristic parameters: Distance between front and rear vehicles, speed, real-time running status.

[0169] Strategy content: Not only single vehicle optimization, but also the whole system optimization of multiple trains. By slightly adjusting the speed of the front vehicle, it creates more favorable coasting or braking conditions for the rear vehicle, forming a "green wave" to reduce the average energy consumption of the entire section.

[0170] 8. Intelligent hibernation strategy for non-operation period

[0171] Target mode: Suitable for depots and stations during non-operation period at night.

[0172] Characteristic parameters: Operation timetable, last use time of equipment, equipment inspection plan.

[0173] Strategy content: Implement hierarchical and time-based hibernation for non-critical equipment (such as part of the lighting, advertising screen, automatic ticket vending machine, station hall ventilation), rather than simply turning off all equipment, to balance energy saving and equipment wake-up preparation, and safety monitoring.

[0174] 9. Dynamic response strategy for special events

[0175] Target mode: Suitable for sudden or planned special events such as large-scale activities, sports events, and extreme weather.

[0176] Characteristic parameters: AFC abnormal passenger flow data, dispatching instructions, and warning information released by social media or transportation department.

[0177] Strategy content: After the system recognizes the special event mode, it dynamically overrides the regular energy-saving strategy to prioritize capacity and safety. For example, during the dispersal peak, a high-acceleration performance timetable is used, and empty cars are dispatched in advance, at which time energy saving becomes a secondary goal.

[0178] The matching details of the nine different operation energy-saving modes, characteristic parameters, and clustering algorithms are shown in Table 1.

[0179] Table 1 details the characteristic parameters corresponding to each operation mode and the core logic of the clustering algorithm for identifying the mode,

[0180] Table 1 Energy-saving operation mode and characteristic parameter, clustering identification matching table

[0181] Operation mode Corresponding characteristic parameters Clustering algorithm execution and optimization Mode labeling and identification description 1. Low passenger load and long station distance inertial optimization strategy Passenger flow characteristics: P1 (average cross-section passenger flow) low, P2 (maximum full load rate) < 30%. Operating characteristics: O5 (average station-to-station running time) long (corresponding to a station spacing > 2 km), O3 (average travel speed) possibly lower. Time characteristics: T1 (time period) is night or flat peak, T2 (weekday / weekend) can be a low demand day. Supplementary parameters: the "station spacing" parameter is derived from the data Algorithm optimization: KMeans++ algorithm, because the mode characteristics are relatively concentrated (such as low passenger flow and long station distance). The number of clusters K is determined by the elbow rule and the silhouette coefficient (such as K=35 may include this mode). Execution process: the algorithm clusters based on characteristics such as P1, P2, and O5, and finds a cluster with low P1 and P2 values and high O5 values. The silhouette coefficient is used to evaluate the tightness within the cluster. Business labeling: after clustering, the cluster is labeled as "low passenger load and long station distance mode", with characteristics of low passenger flow and long inter-station running time. The energy-saving strategy triggers the inertial optimization. 2. Peak high-density collaborative regenerative braking strategy Time feature: T1 (period) is early or late peak. Operational feature: O1 (average vehicle density) > 30 pairs / hour, O2 (minimum vehicle interval) < 2 minutes. Energy consumption feature: E2 (regenerative energy feedback rate) is high, E1 (unit vehicle-kilometer traction energy consumption) fluctuates greatly. Supplementary parameter: "Vehicle density maximum" flag derived from O1 and O2. Algorithm optimization: KMeans++ or DBSCAN. DBSCAN may be more optimal, as the peak mode may form a dense cluster (high O1 and O2), and can handle noise (such as sudden events). The value of K is determined by maximizing the silhouette coefficient. Execution process: the algorithm clusters based on T1, O1, O2, and E2, and identifies a cluster with high density and high feedback rate. The silhouette coefficient evaluates the separation degree of the cluster. Business labeling: labeled as "peak high-density mode", with characteristics of high train density and frequent regenerative energy. The strategy triggers collaborative regenerative braking. 3. Seasonal temperature control and lighting adaptive strategy Time characteristics: T3 (season) is winter, summer, spring and autumn. Vehicle and environmental characteristics: V3 (average environmental temperature) is high or low, and V1 (train formation) may affect air conditioning load. Passenger flow characteristics: P2 (maximum full load rate) affects car heat load. Supplementary parameters: add "light intensity" parameter (from environmental data). Algorithm optimization: KMeans++ algorithm, because the seasonal mode characteristics are distributed in a spherical shape. The number of clusters K is divided by season (such as K=4 corresponds to four seasons). The elbow rule helps determine K. Execution process: the algorithm clusters based on T3, V3, and P2, and generates multiple clusters such as "summer high temperature and high passenger flow" and "winter low temperature and low passenger flow". The silhouette coefficient evaluates the quality of the seasonal cluster. Business labeling: labeled as "summer high temperature mode" or "winter low temperature mode", etc. The strategy triggers temperature control and lighting adaptation. 4. Line topology adaptive traction strategy Running characteristics: O4 (speed curve smoothness) is poor (due to slope changes) and O3 (average travel speed) fluctuates greatly. Supplementary parameters: need to clearly add "line slope" and "radius of curvature" parameters (derived from line topology data, mentioned in high-dimensional feature vector but not listed in the table, can be considered as an extension of running characteristics). Vehicle characteristics: V2 (vehicle type identification) affects traction performance. Algorithm optimization: KMeans++ or hierarchical clustering. Hierarchical clustering is suitable for the hierarchical structure of line topology (such as different sections). The value of K is determined by business knowledge (such as the number of line sections). Execution process: the algorithm clusters based on slope, O4, and O3, and finds a cluster with large slope changes (such as a continuous uphill section). The silhouette coefficient evaluates the reasonableness of the cluster. Business labeling: labeled as "large slope line mode" or "bend-intensive mode". The strategy triggers traction optimization. 5. Energy storage scheduling strategy based on time-of-use electricity price Time feature: T1 (period) corresponds to electricity price peak valley flat (e.g. valley period is midnight). Energy consumption feature: E1 (unit vehicle kilometer traction energy consumption) is high in peak period. Supplementary parameter: add "time-of-use electricity price" parameter (obtained from grid data, mentioned in high-dimensional feature vector). Operating feature: O1 (traffic density) is low in valley period. Algorithm preference: KMeans++ algorithm, as the electricity price pattern has periodicity. The number of clusters K is divided according to the electricity price period (e.g. K=3 corresponds to peak, flat, valley). The silhouette coefficient is used for verification. Execution process: the algorithm clusters based on T1, E1, and electricity price parameters, and identifies the "electricity price valley period low energy consumption" cluster. The elbow rule determines K. Business annotation: annotated as "electricity price valley period mode" or "high peak high cost mode". The strategy triggers energy storage scheduling. 6. Dynamic allocation strategy of redundant time Operating feature: O5 (average inter-station operating time) compared with "graph scheduling time" to derive the "redundant time" parameter. Time feature: T1 (period) may be flat peak or period with buffer. Supplementary parameter: add "delay level" or "schedule deviation" parameter (obtained from scheduling data). Algorithm preference: DBSCAN or KMeans++. DBSCAN may be more optimal, as the redundant time pattern may be an outlier (e.g. delay event). The value of K is selected through the silhouette coefficient. Execution process: the algorithm clusters based on redundant time, O5, and delay parameters, and finds the "planned redundancy" cluster. The silhouette coefficient evaluates the tightness of the cluster. Business annotation: annotated as "redundant time mode" or "on-time buffer mode". The strategy triggers dynamic allocation. 7. Multi-vehicle coordinated speed guidance strategy Operating feature: O1 (average traffic density) is high, O2 (minimum traffic interval) is small. Energy consumption feature: E2 (regenerative energy feedback rate) is high. Supplementary parameter: add "vehicle-vehicle distance" or "coordination coefficient" parameter (derived from V2V communication data). Time feature: T1 (period) is peak. Algorithm preference: KMeans++ algorithm, as the multi-vehicle coordination feature is relatively continuous. The number of clusters K is determined by the elbow rule (e.g. number of medium-high density sections). Execution process: the algorithm clusters based on O1, O2, vehicle-vehicle distance, etc., and identifies the "small vehicle distance, synchronized speed" cluster. The silhouette coefficient evaluates the coordination. Business annotation: annotated as "high-density coordination mode" or "green wave mode". The strategy triggers speed guidance. 8. Intelligent hibernation strategy of equipment during non-operating period Time feature: T1 (period) is the night non-operating period. Operating feature: O1 (average traffic density) is close to zero, O5 (inter-station operating time) is none. Energy consumption feature: E1 (unit vehicle kilometer traction energy consumption) is low, E3 (unit passenger flow energy consumption) is low. Supplementary parameter: add "equipment status" parameter (obtained from inspection data). Algorithm preference: KMeans++ algorithm is simple and effective, as non-operating period data is obviously separated. K=2 or 3 (operating / non-operating). The elbow rule is obvious. Execution process: the algorithm clusters based on T1, O1, and E1, and directly separates the "non-operating" cluster. The high silhouette coefficient indicates good separation. Business annotation: Annotated as "non-operating period mode". Strategy trigger device dormancy. 9. Special event dynamic response strategy Time characteristics: T2 (weekday / holiday) is a special holiday or event day. Passenger flow characteristics: P1 (average cross-section passenger flow) is abnormally high, and P3 (passenger flow unevenness coefficient) is high. Supplementary parameters: add "event warning" parameter (obtained from AFC or social media data). Running characteristics: O1 (train running density) may temporarily increase. Algorithm optimization: DBSCAN algorithm is most suitable, because special events are abnormal points (noise), and DBSCAN can automatically identify abnormal clusters. K value is not fixed. Execution process: The algorithm clusters based on T2, P1, and event parameters. DBSCAN will cluster normal points into clusters, and special events will be identified as noise points. The contour coefficient is used to evaluate normal clusters. Business annotation: Annotated as "special event mode" or "abnormal passenger flow mode". Strategy trigger dynamic response.

[0182] The present application first proposes and systematically implements a method of automatically identifying typical operation modes of rail transit based on big data clustering analysis, and dynamically generating and recommending customized energy-saving strategies for each mode. It breaks through the current static energy-saving method that relies on fixed timetables or simple rules (such as only dividing peak and off-peak), and solves the pain point that it cannot adapt to complex and variable operation scenarios.

[0183] The present application establishes a complete learning closed loop of "data collection → mode discovery → strategy generation → effect evaluation → strategy optimization". The system can continuously optimize itself as data accumulates, continuously improving energy-saving effect. It changes the traditional mode of relying on manual experience adjustment, lacking of quantitative feedback and continuous improvement ability, and realizes the automation and intelligentization of energy-saving management.

[0184] The present application defines an unprecedented multi-dimensional feature parameter system dedicated to energy consumption pattern recognition. The system not only contains conventional time series, passenger flow, and operation data, but also creatively introduces line topology (slope, curvature), time-of-use electricity price, environmental temperature, equipment status, and other parameters that have a significant impact on energy consumption but have been overlooked before. This makes pattern recognition more accurate and is the key to distinguishing it from other general big data analysis solutions.

[0185] The present application uses a first clustering algorithm to efficiently identify major and conventional operation patterns (such as peak and flat peaks). A second clustering algorithm is specifically used to discover abnormal operation patterns (such as emergencies and faults), which is the key to ensuring system robustness.

[0186] The present application first constructs a strategy library containing nine fine energy-saving strategies. Each strategy accurately corresponds to an operation pattern identified by clustering and provides specific solutions from control instructions (such as speed regulation) to scheduling suggestions (such as coordinated braking).

[0187] The above is only a preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A method for generating energy-saving strategies based on rail transit operation mode recognition, characterized in that, Includes the following steps: S1. Collect and preprocess multi-source data, and extract time features, passenger flow features, operation features, energy consumption features, and vehicle and environmental features from the preprocessed multi-source data; S2. Standardize each feature to obtain standardized features and form a feature dataset; S3. Select multiple initial cluster centers from the feature dataset based on the probability distribution of sample points in the feature dataset; S4. Assign each sample point to the cluster containing the nearest initial cluster center, correct the cluster center, update the cluster, and obtain a set of typical operating modes; S5. Classify each sample point in the feature dataset, find noise points, and mark the noise points as abnormal operating modes; S6. For each cluster in the typical operation mode set, first label its operation mode, and then based on each labeled operation mode, customize a variety of energy-saving operation strategies covering the whole scenario. S7. Collect and standardize data in real time, and execute corresponding energy-saving strategies if the data matches the typical operating mode, and trigger early warning strategies if the data matches the abnormal operating mode. S3 includes the following steps: S31. Randomly select a sample point from the feature dataset as the initial cluster center, and place the initial cluster center in the initial cluster center set; S32. Calculate the shortest distance between each sample point in the feature dataset and the initial cluster center in the initial cluster center set; S33. Calculate the probability distribution based on the shortest distance corresponding to each sample point in the feature dataset; S34. Based on the probability distribution, the roulette wheel method is used to select the next sample point from the feature dataset as the new initial cluster center, and the new initial cluster center is then added to the initial cluster center set. S35. Repeat steps S32 to S34 until K initial cluster centers are selected, where K is the upper limit of the number of initial cluster centers; The formula for calculating the shortest distance in S32 is: , Where D(x) i x is the shortest distance to the i-th sample point in the feature dataset. i For the i-th sample point, c j Let be the j-th initial cluster center in the current initial cluster center set, k be the number of initial cluster centers in the current initial cluster center set, j be the index of the initial cluster center, || || be the Euclidean distance, and min be the minimum value among the k distances; The formula for calculating the probability distribution in S33 is: , Wherein, P(x i Let be the probability distribution of each sample point in the feature dataset, and D be the number of sample points in the feature dataset. n Let D(x) be the nth sample point in the feature dataset. n ) represents the shortest distance to the nth sample point in the feature dataset, and D represents the feature dataset.

2. The energy-saving strategy generation method based on rail transit operation mode recognition according to claim 1, characterized in that, The multi-source data in S1 includes: train operation data, energy consumption data, passenger flow data, and equipment status data.

3. The energy-saving strategy generation method based on rail transit operation mode recognition according to claim 1, characterized in that, S4 includes the following sub-steps: S41. Calculate the distance between sample points in the feature dataset and multiple initial cluster centers, select the cluster containing the initial cluster center corresponding to the shortest distance, and add the corresponding sample points to that cluster; S42. By traversing all sample points in the feature dataset in step S41, K initial clusters are obtained; S43. Take the centroid of each initial cluster as the new initial cluster center. With the new initial cluster centers, re-execute S41 and S42 until convergence, and obtain K clusters. S44. Form a set of typical operating modes for each cluster.

4. The energy-saving strategy generation method based on rail transit operation mode recognition according to claim 1, characterized in that, S5 includes the following steps: S51. Randomly select an unvisited sample point p in the feature dataset and obtain the ϵ-neighborhood point set of sample point p, where ϵ is the neighborhood radius. S52. When the number of points in the ϵ-neighborhood set of sample point p is greater than or equal to the minimum number of neighborhood points minPts required for the core point, the sample point p is marked as the core point p. S53. Add all sample points in the neighborhood point set of the core point p to the "neighbor set"; S54. Take any sample point from the "neighbor set" to obtain the current neighbor point Q; S55. Determine whether the current neighbor point Q has been visited; S56. When not visited, check the number of points in the ϵ-neighborhood set of the current neighbor point Q. If it is greater than or equal to the minimum number of neighborhood points minPts required for the core point, mark the current neighbor point Q as the core point and add the unclustered sample points in the ϵ-neighborhood set of the current neighbor point Q to the "neighborhood set" of the core point p. If it is less than the minimum number of neighborhood points minPts required for the core point, mark the current neighbor point Q as a boundary point and assign the boundary points to the "neighborhood set" of the core point p. S57. When a point has already been visited, jump to S54 to select a new sample point until the "neighbor set" of the core point p has been traversed. Treat the "neighbor set" of the current core point p as a complete cluster. S58. Jump to step S51 to construct the next cluster. After traversing all the sample points in the feature dataset, multiple clusters are obtained. The remaining sample points that are not included in the cluster are marked as noise points. S59. Mark the noise points as abnormal operating modes.

5. The energy-saving strategy generation method based on rail transit operation mode recognition according to claim 4, characterized in that, The set of ϵ-neighborhood points in S51 is: , Where, N ϵ (p) is the set of ϵ-neighborhood points of sample point p, dist(p,q) is the distance between sample point p and sample point q, D is the feature dataset, and ϵ is the neighborhood radius.

6. The energy-saving strategy generation method based on rail transit operation mode recognition according to claim 1, characterized in that, The types of operating modes marked in S6 include: "High-density evening peak on summer weekdays" mode, "Low passenger flow on weekends in winter" mode, and "Optimal inertia mode in spring and autumn" mode. Multiple energy-saving operation strategies include: low-passenger-load long-station-distance coasting optimization strategy, peak-hour high-density collaborative regenerative braking strategy, seasonal temperature control and lighting adaptive strategy, line topology adaptive traction strategy, energy storage scheduling strategy based on time-of-use pricing, redundant time dynamic allocation strategy, multi-vehicle collaborative speed guidance strategy, equipment intelligent hibernation strategy during non-operation periods, and special event dynamic response strategy.

Images