Urban bus health degree evaluation system based on big data

Abstract

The invention provides an urban bus health degree evaluation system based on big data, which constructs a data-driven health degree evaluation model by extracting bus operation multi-source data, and realizes model calculation and evaluation. The method specifically comprises three cores of bus big data extraction and preprocessing, health degree evaluation model construction and model calculation and comprehensive evaluation. In order to solve the problems that an existing vehicle health degree evaluation method is high in theorization and insufficient in practicability, a health degree evaluation model which is close to actual business and can be expanded is constructed on the basis of big data analysis. The model can efficiently process mass data of a city-level public transportation system, realizes dynamic quantitative evaluation of the vehicle health state, and is beneficial to providing scientific vehicle operation and maintenance decision support for enterprise managers.

Description

Technical Field

[0001] This invention belongs to the field of urban public transportation big data analysis and intelligent assessment technology, specifically involving a big data-based urban bus health assessment system. Background Technology

[0002] Due to differences in vehicle models, operating conditions, and operational intensity, complex interactions exist between various systems and components within buses, making it difficult to accurately identify potential faults. Under the current bus management model, the primary reliance is on periodic maintenance and repair, relying on manual inspections and troubleshooting based on prior knowledge to identify potential problems. This approach is not only resource-intensive but also ill-suited to the demands of efficient and precise modern operations. To further improve bus operation management and promote a shift from "reactive maintenance" to "preventative maintenance," the industry urgently needs a framework. However, a systematic and practical evaluation framework is currently lacking for scientifically and comprehensively assessing the health status of buses and assisting operators in efficiently conducting vehicle health diagnoses.

[0003] In existing research, some scholars use mathematical methods such as reliability analysis and cost-benefit models to evaluate public transportation systems. These methods are more theoretical and have limited practical application value. Other studies focus only on one aspect of the public transportation system, such as punctuality rate and energy consumption level. Although they are more targeted, they are difficult to support a multi-dimensional and systematic evaluation of the operation of the public transportation system and are also difficult to provide effective support for overall optimization decisions. Summary of the Invention

[0004] In view of this, this invention proposes a big data-based urban bus health assessment system, aiming to achieve accurate quantification of vehicle health status through data mining and statistical modeling techniques. Through regular assessments and dynamic monitoring, it can provide data support for vehicle maintenance planning, resource optimization, and operational decisions, helping to improve the overall utilization efficiency of buses, reduce operating costs, and enhance safety capabilities.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, this invention discloses a big data-based urban bus health assessment system, which includes: a data extraction and preprocessing module, a health assessment model construction module, and a model calculation and comprehensive evaluation module; wherein... The data extraction and preprocessing module is used to extract multi-source data from the public transportation operation system and perform data cleaning and time alignment processing. The health assessment model construction module constructs a health assessment model based on the multi-source data, which includes an operational reliability unit and a comprehensive operational efficiency unit. Each of the operational reliability unit and the comprehensive operational efficiency unit has multiple characteristic indicators. The model calculation and comprehensive evaluation module is used to standardize and score the feature indicators, calculate the comprehensive health score of urban buses, and output the evaluation results.

[0006] Preferably, the multi-source data extracted by the data extraction and preprocessing module includes: vehicle operation data, fault records, energy consumption data, maintenance records, and CAN bus alarm data.

[0007] Preferably, the operational reliability unit includes characteristic indicators such as: number of failures, mean time between failures, and mean time between failures.

[0008] Preferably, the integrated operational efficiency unit includes characteristic indicators such as: material replacement cost, number of material replacements, number of accidents, energy consumption, bus alarm frequency, average alarm repair response time, and number of downtime days.

[0009] Preferably, in the model calculation and comprehensive evaluation module, the method for assigning scores to feature indicators includes: normal distribution, skewed distribution, and power-law distribution.

[0010] Preferably, in the model calculation and comprehensive evaluation module, the weights of each unit and indicator are determined by the analytic hierarchy process.

[0011] Preferably, in the model calculation and comprehensive evaluation module, a time-slice cyclic construction algorithm is used to obtain the comprehensive health score of urban buses by weighted summation of the scores of various indicators.

[0012] Secondly, this invention also provides a method for assessing the health of urban buses based on big data. Using the aforementioned system, the health assessment of urban buses is achieved. This method mainly includes the following steps: S1. Extract multi-source data from the public transportation operation system and perform data cleaning and time alignment processing; S2. Construct a health assessment model based on the multi-source data, which includes an operational reliability unit and a comprehensive operational efficiency unit, wherein the operational reliability unit and the comprehensive operational efficiency unit are each provided with multiple feature indicators; S3. Standardize and score the feature indicators, calculate the comprehensive health score of urban buses, and output the evaluation results. As can be seen from the above technical solution, compared with the prior art, the beneficial effects of the present invention include: This invention, based on multi-source public transport operation data, constructs a data-driven health assessment model, automating the entire process from data extraction to comprehensive evaluation. This invention innovatively transforms the traditional indicator system into a dynamic model, enhancing its practicality and scalability through statistical distribution analysis and weight optimization. This invention can efficiently complete a systematic assessment of the overall health status of a city-level public transport system and provides strong support for public transport company managers to formulate scientific and precise vehicle management strategies. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort. Figure 1 This is a schematic diagram of the bus health assessment model provided in an embodiment of the present invention. Detailed Implementation

[0014] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0015] To address the shortcomings of existing vehicle health assessment methods, such as insufficient data utilization and poor model adaptability, this invention proposes a big data-based urban bus health assessment system. This system uses multi-source bus operation data as a foundation to construct a data-driven health assessment model, achieving full automation from data extraction to comprehensive evaluation. The core innovation of this invention lies in transforming the traditional indicator system into a dynamic model, enhancing the model's practicality and scalability through statistical distribution analysis and weight optimization. This model can efficiently complete a systematic assessment of the overall health status of an urban public transport system and provide strong support for public transport company managers to formulate scientific and precise vehicle management strategies. To achieve the above objectives, the technical solutions provided by the embodiments of this invention are as follows: 1. Extraction and preprocessing of big data from public transportation operations: In one embodiment, multi-source data, including vehicle operation data, fault records, energy consumption data, maintenance records, CAN bus alarm data, etc., are extracted from the public transportation operation system and then cleaned and time-aligned.

[0016] 2. Construction of Health Assessment Model: In one embodiment, the present invention constructs an evaluation model comprising an operational reliability unit and an integrated operational efficiency unit. See also Figure 1 As shown, each unit has multiple feature indicators: (1) Operational reliability unit: number of general failures, number of major failures, mean time between failures, mean time between failures, etc.; (2) Comprehensive operational efficiency unit: material replacement amount, number of material replacements, number of accidents, energy consumption, bus alarm frequency, average alarm repair response time, number of downtime days, etc.

[0017] 3. Model calculation and evaluation results output: (1) Standardize and score each indicator, and use methods such as normal distribution, skewed distribution, and power law distribution to map the scores; (2) Apply the Analytic Hierarchy Process (AHP) to determine the weights of each module and indicator; (3) Calculate the overall health score for each vehicle and output the ranking results. The specific calculation formula is as follows:

[0018] in, Indicates the first The weights of each indicator (the weight values ​​are determined by the analytic hierarchy process, as shown in Table A). Indicates the first The standardized scores of each indicator (assigned using methods such as normal distribution, skewed distribution, or power law distribution). This represents the total number of indicators (11 indicators in this example).

[0019] In one embodiment, the calculation method for the corresponding indicators is shown in Tables (1) to (12) below: Table (1) Time-slice loop construction algorithm:

[0020] Table (2) Accident Count Calculation Algorithm:

[0021] Table (3) Algorithm for calculating the number of days of downtime:

[0022] Table (4) Algorithm for calculating material change frequency:

[0023] Table (5) Algorithm for calculating material replacement cost:

[0024] Table (6) Algorithm for calculating bus alarm frequency:

[0025] Table (7) Algorithm for calculating average alarm repair response time:

[0026] Table (8) Algorithm for calculating mean time between failures:

[0027] Table (9) Algorithm for calculating mean fault interval mileage:

[0028] Table (10) Algorithm for calculating the number of general failures:

[0029] Table (11) Algorithm for calculating the number of major failures:

[0030] Table (12) Calculation algorithm for charging range (nearly 5000 km):

[0031] In one embodiment, the scoring method for the corresponding indicator is as follows: ① Normal distribution (or approximately normal distribution): a. Calculate the mean (μ) and standard deviation (σ) of the data. Data points falling outside the interval [μ-3σ, μ+3σ] are usually considered outliers, which are used to define the "acceptable interval" and the "penalty interval".

[0032] b. Assignment method: [μ-σ,μ+σ]: 100 points; [μ±σ,μ±2σ]: 80-100 points; [μ±2σ,μ±3σ]: 60-80 points; [μ±3σ,∞]: 40-60 points.

[0033] c. Representative indicators: charging capacity (nearly 5000 kilometers), average alarm repair response time.

[0034] ② Skewed distribution: a. Compare the current vehicle's value with the historical data of all vehicles, calculate the percentile ranking, and then map it to the score according to the physical meaning.

[0035] b. Assignment method: <25th percentile: 40-60 points; 25th percentile - 75th percentile: 60-80 points; >75th percentile: 80-100 points.

[0036] c. Representative indicators: Mean time between failures (MTBF) and Mean time between failures (MTBF) mileage.

[0037] ③ Power-law distribution: a. Compare the current vehicle's value with the historical data of all vehicles, calculate the percentile ranking, and then map it to the score according to the physical meaning.

[0038] b. Assignment method: <25th percentile: 80-100 points; 25th percentile - 75th percentile: 60-80 points; >75th percentile: 40-60 points.

[0039] c. Representative indicators: number of accidents, number of downtime days, number of material replacements, material replacement cost, number of general failures, number of major failures, and frequency of bus alarms.

[0040] The following uses multi-source data collected during bus operation by Beijing Public Transport Group, with the case data being data related to BJ6123EVCA-37, to illustrate the specific application of this invention.

[0041] The weights assigned to each indicator are shown in Table A: Table A: Weights of Each Indicator

[0042] The final vehicle health assessment system data is shown in Table B: Table B: Health Calculation Results

[0043] In this embodiment, the specific calculation process for the health score is as follows: Taking the first row of data in Table B (time base date: 2025 / 6 / 30, period number: 1) as an example: a. Determination of calculation cycle: The system uses the "time slice loop construction algorithm" to determine a uniform evaluation cycle.

[0044] b. Obtain standardized scores for indicators: Perform refined calculations on each indicator and transform the original physical quantity values ​​into comparable standardized scores through a mapping function based on data distribution characteristics (such as normal distribution, skewed distribution, power-law distribution).

[0045] c. Assign corresponding weights to each indicator based on its importance in the overall evaluation (the total weights are 1).

[0046] d. By using a weighted summation method, the contributions of all indicators are combined into a comprehensive health score. See Table C below for details: Table C: Calculation of Overall Health Score

[0047] The evaluation process is shown in Table D below: Table D: Assessment Status Classification

[0048] a. Trend identification: If a vehicle's score curve shows a stable or slow downward trend, it is considered normal aging; if there is a precipitous drop, it indicates that a major hidden fault or systemic degradation may have occurred.

[0049] b. Predictive intervention: Based on this trend, the system can shift from "preventive maintenance" to a more proactive "predictive maintenance." Managers can proactively schedule maintenance plans before vehicle health falls below critical thresholds, thereby minimizing operational disruptions and optimizing resource allocation.

[0050] Furthermore, this embodiment of the invention also provides a method for assessing the health of urban buses based on big data. This method applies the above-mentioned system to assess the health of urban buses, and includes the following steps: S1. Extract multi-source data from the public transportation operation system and perform data cleaning and time alignment processing; S2. Construct a health assessment model based on multi-source data, which includes an operational reliability unit and a comprehensive operational efficiency unit. Each of the operational reliability unit and the comprehensive operational efficiency unit has multiple characteristic indicators. S3. Standardize and score the feature indicators, calculate the comprehensive health score of urban buses, and output the evaluation results.

[0051] The method provided in this embodiment of the invention has the same implementation principle and technical effect as the aforementioned system embodiment. For the sake of brevity, any parts not mentioned in this embodiment can be referred to the corresponding content in the aforementioned system embodiment, and will not be repeated here.

[0052] As described in the above embodiments, those skilled in the art will understand that this invention discloses a big data-based urban bus health assessment system and method. It extracts multi-source bus operation data, constructs a data-driven health assessment model, and performs model calculation and evaluation. Specifically, it includes three core components: bus big data extraction and preprocessing, health assessment model construction, and model calculation and comprehensive evaluation. This application addresses the problem of existing vehicle health assessment methods being overly theoretical and lacking practicality. Based on big data analysis, it constructs a scalable health assessment model that closely reflects actual business operations. This model can efficiently process massive amounts of data from urban bus systems, achieving dynamic quantitative assessment of vehicle health status and providing scientific vehicle operation and maintenance decision support for enterprise managers.

[0053] The present invention has been described in detail above. Specific examples have been used in this embodiment to illustrate the principle and implementation of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation and application scope based on the idea of ​​the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

[0054] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined in these embodiments may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A big data-based urban bus health degree evaluation system, characterized in that, The system comprises a data extraction and preprocessing module, a health degree evaluation model construction module and a model calculation and comprehensive evaluation module, wherein The data extraction and preprocessing module is configured to extract multi-source data from a public transport operation system and perform data cleaning and time alignment processing. The health degree evaluation model construction module is configured to construct a health degree evaluation model comprising a running reliability unit and a comprehensive operation efficiency unit based on the multi-source data, wherein the running reliability unit and the comprehensive operation efficiency unit are respectively provided with a plurality of feature indicators. The model calculation and comprehensive evaluation module is configured to normalize and score the feature indicators, calculate a comprehensive health degree score of the urban bus and output an evaluation result. 2.The big data-based urban bus health degree evaluation system according to claim 1, wherein, The multi-source data extracted by the data extraction and preprocessing module comprises vehicle operation data, fault records, energy consumption data, maintenance records and CAN bus alarm data. 3.The urban bus health evaluation system based on big data according to claim 1, wherein, The feature indicators in the running reliability unit comprise fault frequency, average fault interval time and average fault interval mileage. 4.The urban bus health evaluation system based on big data according to claim 1, wherein, The feature indicators in the comprehensive operation efficiency unit comprise refueling amount, refueling frequency, accident frequency, energy consumption, bus alarm frequency, average alarm repair response time and stop driving days. 5.The urban bus health evaluation system based on big data according to claim 1, wherein, The method for scoring the feature indicators in the model calculation and comprehensive evaluation module comprises normal distribution, skew distribution and power law distribution. 6.The urban bus health evaluation system based on big data according to claim 1, wherein, In the model calculation and comprehensive evaluation module, the analytic hierarchy process is applied to determine the weights of each unit and indicator. 7.The urban bus health evaluation system based on big data according to claim 1, wherein, In the model calculation and comprehensive evaluation module, a time slice cycle construction algorithm is adopted to obtain the comprehensive health degree score of the urban bus by weighting and summing the scores of each indicator.

8. A big data-based urban bus health degree evaluation method, characterized in that, The system according to any one of claims 1 to 7 is applied to realize urban bus health degree evaluation, and the method comprises the following steps: S1, extracting multi-source data from a public transport operation system and performing data cleaning and time alignment processing; S2, constructing a health degree evaluation model comprising a running reliability unit and a comprehensive operation efficiency unit based on the multi-source data, wherein the running reliability unit and the comprehensive operation efficiency unit are respectively provided with a plurality of feature indicators; S3, normalizing and scoring the feature indicators, calculating a comprehensive health degree score of the urban bus and outputting an evaluation result.

Images