Full-life-cycle management system and method for rail transit equipment

Abstract

The invention relates to a full-life-cycle management system and method for rail transit equipment, the system comprises a full-life-cycle management platform, a historical database, a database server and a monitoring acquisition server, and a health result is obtained by calculating a final score through objective weight, subjective weight and probability distribution; the full life cycle management platform is in communication connection with the historical database, the historical database receives data collected by the database server and the monitoring collection server as historical data, an equipment health trend model is established and used for predicting the health life of the equipment, and the process is achieved through the method. According to the method, objective weights and subjective weights are set, existing rail transit equipment state evaluation basically adopts a chromatographic analysis method taking subjective evaluation as a main method or an entropy weight method taking data mining as a basis, but in practical application, the problem of evaluation result distortion or lack of credibility exists. And subjective and objective evaluation methods are combined to ensure that the evaluation result is more reasonable.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment life cycle management, and in particular to a full life cycle management system and method for rail transit equipment. Background Art

[0002] The full life cycle management of rail transit equipment refers to the comprehensive management throughout the entire process of rail transit equipment from procurement, installation, operation, maintenance to scrapping. It relies on high-precision and low-cost sensor technology to collect the real-time status of equipment, and uses information technologies such as cloud computing, big data, Internet of Things, and artificial intelligence to make advance judgments, so as to achieve preventive maintenance and repair, which can significantly reduce the maintenance and replacement costs of equipment, extend the service life of equipment, reduce unexpected downtime, and improve the overall economic benefits.

[0003] The invention patent with the publication number of CN113466597A discloses an intelligent detection method for the status of rail transit power supply system equipment. Based on the historical data of relevant subway companies, this invention constructs a method for the fault monitoring and health management (PHM) system of urban rail transit power supply system, with the overall goals of ensuring the safety of the power supply system, evaluating the status of the power supply system, and realizing predictive maintenance, and conducts real-time status monitoring of multi-parameter information data of two different systems, namely the external environment system and the internal system of electrical equipment of the power supply system; establishes a dynamic real-time fault diagnosis, reliability evaluation and safety warning platform for multi-information parameter key systems; this patent only detects whether the equipment is faulty based on historical data and proposes a health management system method, and the data collected is less, without reflecting the management of the equipment life cycle. By managing the life cycle, timely replacement can be carried out before the equipment reaches its service life or fails, avoiding the occurrence of failures.

[0004] Therefore, providing a full life cycle management system and method for rail transit equipment is an urgent problem to be solved at present. Summary of the Invention

[0005] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and provide a full life cycle management system and method for rail transit equipment.

[0006] The purpose of the present invention can be achieved by the following technical solutions:

[0007] According to one aspect of the present invention, a full life cycle management system for rail transit equipment is provided, including a full life cycle management platform, a historical database, a database server, and a monitoring and acquisition server. The full life cycle management platform is communicatively connected to the database server and the monitoring and acquisition server respectively. The full life cycle management platform receives and analyzes the data of the database server and the monitoring and acquisition server, obtains a health result and displays it, and is used to monitor the life cycle of the equipment;

[0008] The health result is obtained by calculating the final score through objective weight, subjective weight and probability distribution; the whole life cycle management platform is communicatively connected to the historical database, and the historical database receives the collected data from the database server and the monitoring and acquisition server as historical data, and establishes a device health trend model for predicting the health life of the device.

[0009] As a preferred technical solution, the database server collects the incoming and outgoing, up and down track, maintenance operation conditions and equipment failure information of the equipment for analysis and transmits the results to the life cycle management platform;

[0010] The system further includes monitoring sensors, the monitoring sensors are installed on the equipment and communicatively connected to the monitoring and acquisition server, and the monitoring and acquisition server obtains information on the rotation ability, action circuit electrical characteristics and maintenance conditions of the equipment according to the data of the monitoring sensors and transmits it to the whole life cycle management platform.

[0011] As a preferred technical solution, the system further includes a station warehouse and a supply station warehouse, both the station warehouse and the supply station warehouse include handheld terminals, the handheld terminals are used to record the incoming and outgoing, up and down track, maintenance operation conditions and equipment failure information of the equipment, and the handheld terminals are communicatively connected to the database server.

[0012] As a preferred technical solution, the system further includes an operation and maintenance center and an information computer room, the whole life cycle management platform is installed in the operation and maintenance center, and the database server and the monitoring and acquisition server are installed in the information computer room.

[0013] As a preferred technical solution, the whole life cycle management platform includes a display module, and the display module is used to display the device health result and the device alarm information.

[0014] As a preferred technical solution, the display module is refreshed every predetermined time.

[0015] According to another aspect of the present invention, there is provided a method for a whole life cycle management system of rail transit equipment as described in any one of the above, characterized in that the method includes the following steps:

[0016] S1. The database server and the monitoring and acquisition server respectively perform real-time data collection;

[0017] S2. The database server displays according to the collected data through the whole life cycle management platform;

[0018] S3. The whole life cycle management platform calculates the final score through the collected data of the monitoring and acquisition server and combines the objective weight, subjective weight and probability distribution, determines the health result according to the final score and displays it on the whole life cycle management platform;

[0019] S4. The historical database establishes a device health trend model based on the historical data of the database server and the monitoring and acquisition server to predict the device health life.

[0020] As a preferred technical solution, the health results are respectively four grades: excellent, good, medium, and poor.

[0021] As a preferred technical solution, the objective weight and the subjective weight respectively form an objective weight vector and a subjective weight vector. The combined weight vector is formed according to the objective weight vector and the subjective weight vector, and the probability distribution is calculated. Finally, the final score is calculated, and the health result is determined according to the final score.

[0022] The objective weight vector has the following formula:

[0023] ω (1) =(ω 1 , ω 2 , …, ω n )

[0024] ω 1 , ω 2 , …, ω n are the objective weight values of different devices in sequence.

[0025] The subjective weight vector has the following formula:

[0026] λ (1) =(λ 1 , λ 2 , …, λ n )

[0027] λ 1 , λ 2 , …, λ n are the subjective weight values of different devices in sequence.

[0028] The combined weight vector has the following formula:

[0029] ω=(θ 1 ω (1) +θ 2 λ (1) )

[0030] θ 1 is the proportion of the objective weight vector, and θ 2 is the proportion of the subjective weight vector.

[0031] The probability distribution has the following formula:

[0032] μ i =(μ i1 , μ i2 , μ i3 , μ i4 )

[0033] τ = ω × μ

[0034] μ i1 ~μ i4 represent the probabilities of the i-th index being excellent, good, medium, and poor, τ 1 ~τ 4 are the probabilities of the evaluation target being excellent, good, medium, and poor;

[0035] The final score has the following formula:

[0036] f = [X 1 , X 2 , X 3 , X 4 · [τ 1 , τ 2 , τ 3 , τ 4 T

[0037] X 1 ~X 4 are the benchmark scores for excellent, good, medium, and poor respectively, and the benchmark scores are 90, 80, 60, and 30 in sequence.

[0038] As a preferred technical solution, the S4 specifically includes:

[0039] S41. Collect the daily health results of the equipment within one year, as well as the equipment rotation ability, electrical characteristics of the action circuit, maintenance status, alarm status, equipment inbound and outbound, equipment on and off the production line, and equipment inspection and repair data for the previous 1 day, 5 days, 30 days, 60 days, and 180 days;

[0040] S42. Calculate the average equipment health results for the previous 1 day, 5 days, 30 days, 60 days, and 180 days as the data set;

[0041] S43. Use 80% of the data in the data set as the training set and the remaining 20% of the data set as the test set for training;

[0042] S44. Push the predicted equipment health trend and the real-time equipment trend to the full life cycle management platform and display them, and at the same time give maintenance suggestions.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] 1. By setting the objective weight and the subjective weight, the existing state evaluation of rail transit equipment basically adopts the analytic hierarchy process mainly based on subjective evaluation or the entropy weight method based on data mining. However, in actual applications, there are problems such as distorted evaluation results or lack of credibility. The combination of subjective and objective evaluation methods is used to ensure that the evaluation results are more reasonable.​

[0045] 2. The present invention calculates the probability distribution and obtains the health result. Since it is difficult to quantify the quality of the equipment, probability converts quantitative evaluation into qualitative evaluation, which can well solve the problems that are fuzzy and difficult to quantify.

[0046] 3. The present invention sets up a database server and a monitoring and acquisition server, analyzes the data collected in real time by the database server and the monitoring and acquisition server, obtains the health result of the equipment and displays it, which is convenient for managing the life cycle management of the equipment.

[0047] 4. The database server of the present invention collects the information of the equipment's inbound and outbound, up and down tracks, maintenance operations and equipment failures, realizing the full life cycle management of the equipment; at the same time, there are many types of collected data, and the judgment and setting of the health result are more accurate.

[0048] 5. The present invention sets up a display module, with comprehensive information display, showing information such as the equipment quality report, the number of in-use equipment, the number of spare equipment, the number of in-use indoor and outdoor equipment, the quantity of inventory materials, the equipment excellent rate, the equipment health degree, and the equipment status of each station. The information content is large and the coverage is wide, which can improve the efficient and safe operation ability of rail transit equipment throughout the life cycle.

[0049] 6. On the basis of the conventional prediction of the equipment health trend according to the monitoring equipment status, the present invention adds the prediction of the health trend by fusing multi-source information such as the equipment's inbound and outbound, up and down tracks, maintenance operations, and equipment failures, improving the accuracy of the health trend prediction and enhancing the maintenance efficiency and safety of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a schematic diagram of the system structure framework of the present invention;

[0051] Figure 2 It is a working flow chart of the present invention;

[0052] Figure 3 It is an effect diagram of the display interface of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0054] With the acceleration of the urbanization process, people's demand for convenient and efficient public transportation is increasing day by day. Rail transit has become an important part of urban transportation due to its characteristics such as large capacity, high speed, and high punctuality rate. The number of rail transit lines is increasing, and the speed of trains is getting faster. It includes many complex devices and subsystems, such as vehicles, signals, communications, power supply, etc. The management and maintenance of these devices have become increasingly complex.

[0055] The full life cycle management system of rail transit equipment refers to the comprehensive management throughout the entire process of rail transit equipment from procurement, installation, operation, maintenance to scrapping. It relies on high-precision and low-cost sensor technology to collect the real-time status of equipment, and uses information technologies such as cloud computing, big data, Internet of Things, and artificial intelligence to make advance judgments for preventive maintenance and repair, which can significantly reduce the repair and replacement costs of equipment, extend the service life of equipment, reduce unexpected downtime, and improve overall economic benefits.

[0056] The present invention provides a full life cycle management system and method for rail transit equipment; by setting objective weights and subjective weights, the existing state evaluation of rail transit equipment basically adopts the analytic hierarchy process mainly based on subjective evaluation or the entropy weight method based on data mining. However, in practical applications, there are problems such as distorted evaluation results or lack of credibility. The combination of subjective and objective evaluation methods is used to ensure that the evaluation results are more reasonable. By calculating the probability distribution and obtaining the health result, since it is difficult to quantify the quality of equipment, probability converts quantitative evaluation into qualitative evaluation, which can well solve the problems of fuzziness and difficulty in quantification. By setting a database server and a monitoring and acquisition server, through analyzing the data collected in real time by the database server and the monitoring and acquisition server, the health result of the equipment is obtained and displayed, which is convenient for managing the life cycle management of the equipment. The database server of the present invention collects the incoming and outgoing, on and off track, maintenance operation conditions and equipment failure information of the equipment, realizing the full life cycle management of the equipment; at the same time, a large variety of data is collected, and the judgment of setting the health result is more accurate. By setting a display module, the information display is comprehensive, showing information such as equipment quality reports, the number of in-use equipment, the number of spare equipment, the number of in-use indoor and outdoor equipment, the quantity of inventory materials, equipment excellent rate, equipment health degree, and the equipment status of each station. The information content is large and the coverage is wide, which can improve the efficient and safe operation ability of rail transit equipment throughout its life cycle. On the basis of routinely predicting the health trend of equipment according to the monitored equipment status, the present invention adds the prediction of the health trend by fusing multi-source information such as the incoming and outgoing, on and off track, maintenance operation conditions, and equipment failures of the equipment, improving the accuracy of the health trend prediction and enhancing the maintenance efficiency and safety of the equipment.

[0057] Embodiment 1

[0058] As Figure 1As shown in the figure, a full life cycle management system for rail transit equipment includes a full life cycle management platform, a historical database, a database server, and a monitoring and acquisition server. The full life cycle management platform is communicatively connected to the database server and the monitoring and acquisition server respectively. The full life cycle management platform receives and analyzes the data of the database server and the monitoring and acquisition server, obtains the health result and displays it, and is used to monitor the life cycle of the equipment;

[0059] The health result is obtained by calculating the final score through objective weight, subjective weight, and probability distribution. The full life cycle management platform is communicatively connected to the historical database. The historical database receives the acquisition data of the database server and the monitoring and acquisition server as historical data, and establishes an equipment health trend model for predicting the health life of the equipment.

[0060] The database server collects the information on the storage in and out, on and off the track, maintenance operations, and equipment failures of the equipment, analyzes it, and transmits the results to the life cycle management platform;

[0061] The system further includes monitoring sensors. The monitoring sensors are installed on the equipment and communicatively connected to the monitoring and acquisition server. The monitoring and acquisition server obtains the information on the rotation ability, electrical characteristics of the action circuit, and maintenance status of the equipment based on the data of the monitoring sensors and transmits it to the full life cycle management platform.

[0062] The system further includes a station warehouse and a supply station warehouse. Both the station warehouse and the supply station warehouse include handheld terminals. The handheld terminals are used to record the information on the storage in and out, on and off the track, maintenance operations, and equipment failures of the equipment. The handheld terminals are communicatively connected to the database server.

[0063] The system further includes an operation and maintenance center and an information computer room. The full life cycle management platform is installed in the operation and maintenance center, and the database server and the monitoring and acquisition server are installed in the information computer room.

[0064] The full life cycle management platform includes a display module. The display module is used to display the equipment health result and the equipment alarm information. The display module is refreshed every predetermined time.

[0065] In this embodiment, an equipment life cycle management platform is deployed in the operation and maintenance center. The platform includes an equipment quality management module, an in-use equipment management module, a spare parts management module, an equipment guarantee module, and a spare parts plan management module.

[0066] The administrator of the station warehouse is equipped with a handheld terminal, and the administrator of the supply station warehouse is equipped with a handheld terminal and a label printer. The handheld terminal is installed with a full life cycle management APP, including modules such as material warehousing, material outbound, device on-track, device off-track, material coding management, problem management, equipment maintenance, etc. The equipment purchased by the supply station is pasted with labels, and the equipment is associated and outbound through scanning the code with the handheld terminal. The administrator of the station warehouse performs the inbound and outbound operations of the equipment.

[0067] The system also includes an equipment management platform server. A database server, an equipment management platform server, and a monitoring and acquisition server are deployed in the information computer room, and monitoring sensors are deployed on indoor and outdoor equipment.

[0068] Real-time monitoring data is collected through the sensors arranged on the equipment, and the obtained data is transmitted to the monitoring and acquisition server and intelligently analyzed through deep learning methods to obtain data such as the rotation ability of the equipment, the electrical characteristics of the action circuit, and the maintenance status.

[0069] The information data such as the inbound and outbound of equipment, on-track and off-track, maintenance operation status, and equipment failures on the full life cycle management APP are stored in the database server. After data analysis, information such as equipment quality reports, the number of in-use equipment, the number of spare equipment, the number of in-use indoor and outdoor equipment, and the quantity of inventory materials is displayed on the full life cycle management platform.

[0070] The data such as the rotation ability of the equipment, the electrical characteristics of the action circuit, and the maintenance status are stored in the database server. After the equipment health evaluation through the analytic hierarchy process, information such as the excellent rate and health degree of the equipment is displayed on the full life cycle management platform. The full life cycle management platform includes a display module, and a display screen is set in the display module. The display screen is refreshed regularly to display the latest equipment health data. The collected equipment alarm information data is stored in the database server, and at the same time, the equipment alarm information data is pushed to the full life cycle management platform through WebSocket technology.

[0071] According to the obtained equipment health data, a WebGIS scenario is built to display the equipment status of each station in real time through the display screen, and the locations of each station and the number of excellent, good, medium, and poor equipment are displayed. The relevant data collected by the database server and the monitoring and acquisition server every day are stored in the historical database as historical data, and model training and prediction are carried out based on the historical data.

[0072] Embodiment 2

[0073] As Figure 2 shown, a method for a full life cycle management system of rail transit equipment, the method includes the following steps:

[0074] S1. The database server and the monitoring and acquisition server respectively perform real-time data acquisition;

[0075] S2. The database server displays according to the acquired data through the whole life cycle management platform;

[0076] S3. The whole life cycle management platform calculates the final score by combining the acquired data of the monitoring and acquisition server with the objective weight, subjective weight and probability distribution, determines the health result according to the final score and displays it on the whole life cycle management platform;

[0077] S4. The historical database establishes an equipment health trend model based on the historical data of the database server and the monitoring and acquisition server to predict the equipment health life.

[0078] 8. The method according to claim 7, wherein the health results are respectively four grades of excellent, good, medium and poor.

[0079] 9. The method according to claim 8, wherein the objective weight and the subjective weight respectively form an objective weight vector and a subjective weight vector, a combined weight vector is formed according to the objective weight vector and the subjective weight vector and the probability distribution is calculated, and finally the final score is calculated, and the health result is determined according to the final score;

[0080] The objective weight vector has the following formula:

[0081] ω (1) =(ω 1 ,ω 2 ,…,ω n )

[0082] ω 1 ,ω 2 ,…,ω n are the objective weight values of different devices in sequence;

[0083] The subjective weight vector has the following formula:

[0084] λ (1) =(λ 1 ,λ 2 ,…,λ n )

[0085] λ 1 ,λ 2 ,…,λ n are the subjective weight values of different devices in sequence;

[0086] The combined weight vector has the following formula:

[0087] ω=(θ 1 ω (1) +θ2 λ (1) )

[0088] θ 1 is the proportion of the objective weight vector, and θ 2 is the proportion of the subjective weight vector;

[0089] The probability distribution has the following formula:

[0090] μ i =(μ i1 , μ i2 , μ i3 , μ i4 )

[0091] τ = ω × μ

[0092] μ i1 ~μ i4 represents the probabilities that the i-th index is excellent, good, medium, and poor, and τ 1 ~τ 4 are the probabilities that the evaluation objective is excellent, good, medium, and poor;

[0093] The final score has the following formula:

[0094] f = [X 1 , X 2 , X 3 , X 4 ·[τ 1 , τ 2 , τ 3 , τ 4 T

[0095] X 1 ~X 4 are the benchmark scores for excellent, good, medium, and poor respectively, and the benchmark scores are 90, 80, 60, and 30 in sequence.

[0096] Specifically, S4 includes:

[0097] S41. Collect the health results of the equipment every day within one year, as well as the equipment rotation ability, electrical characteristics of the action circuit, maintenance situation, alarm situation, equipment inbound and outbound, equipment up and down the line, and equipment inspection and repair data for the previous 1 day, previous 5 days, previous 30 days, previous 60 days, and previous 180 days;

[0098] S42. Calculate the average equipment health results for the previous 1 day, previous 5 days, previous 30 days, previous 60 days, and previous 180 days as the data set;

[0099] S43. Use 80% of the data in the data set as the training set and 20% of the data set as the test set for training;

[0100] ​S44. Push the predicted device health trend and the real-time device trend to the full-life cycle management platform for display, and give maintenance suggestions at the same time.

[0101] In this embodiment, the device information data in the historical database is trained through multi-source information fusion and the LSTM neural network to predict the short-term and long-term health trends of the device. The device health structure is collected every day within one year, and data such as the device rotation ability, the electrical characteristics of the action circuit, the maintenance situation, the alarm situation, the device inbound and outbound, the device up and down the line, and the device inspection and repair in the previous 1 day, 5 days, 30 days, 60 days, and 180 days are collected. Data such as the average device health results in the previous 1 day, 5 days, 30 days, 60 days, and 180 days are calculated as the data set. 80% of the previous data is used as the training set, and the latter 20% of the data set is used as the test set for training. Push the predicted device health trend and the real-time device trend to the interface of the device full-life cycle management platform, and give maintenance suggestions.

[0102] The entire evaluation index system is divided into three layers. The top layer is the device health degree target layer, which is used to reflect the overall health status of the device; the middle layer is the dimension layer, which includes three dimensions: rotation ability, electrical characteristics, and maintenance situation; the bottom layer is the index layer, and the state score of the upper-level object is evaluated through index information. The evaluation indicators corresponding to the rotation ability are current curve unlocking (fixed to reverse), current curve unlocking (reverse to fixed), current curve conversion (fixed to reverse), current curve conversion (reverse to fixed), current curve locking (fixed to reverse), current curve locking (reverse to fixed), conversion duration (fixed to reverse), and conversion duration (reverse to fixed). The evaluation indicators corresponding to the electrical characteristics are starting current peak value and voltage curve change rate, voltage (shunt residual voltage). The evaluation indicators corresponding to the maintenance situation are periodic inspection, dynamic monitoring results of the dynamic inspection vehicle, and the combination of engineering and electricity. Fixed to reverse means from the fixed position to the reverse position, and reverse to fixed means from the reverse position to the fixed position.

[0103] The specific process of the health assessment result includes the following steps:

[0104] 1. Collect historical data and obtain the objective weight vector of each index by using the entropy weight method; then detect the current current value through the monitoring sensor. For example: obtain the weight of current curve unlocking (fixed to reverse) as 0.1, the weight of current curve unlocking (reverse to fixed) as 0.2, the weight of current curve conversion (fixed to reverse) as 0.1, the weight of current curve conversion (reverse to fixed) as 0.2, the weight of current curve locking (fixed to reverse) as 0.1, the weight of current curve locking (reverse to fixed) as 0.1, the weight of conversion duration (fixed to reverse) as 0.1, and the weight of conversion duration (reverse to fixed) as 0.1, then ω (1) =(0.1, 0.2, 0.1, 0.2, 0.1, 0.1, 0.1, 0.1).

[0105] 2. Obtain the scores of each index from experienced experts through questionnaire surveys, and use the analytic hierarchy process to obtain the subjective weight vector of each index. For example: Through experts, obtain the weight of current curve unlocking (from fixed to reverse) as 0.2, the weight of current curve unlocking (from reverse to fixed) as 0.1, the weight of current curve conversion (from fixed to reverse) as 0.1, the weight of current curve conversion (from reverse to fixed) as 0.2, the weight of current curve locking (from fixed to reverse) as 0.1, the weight of current curve locking (from reverse to fixed) as 0.1, the weight of conversion duration (from fixed to reverse) as 0.1, and the weight of conversion duration (from reverse to fixed) as 0.1. Then λ (1) =(0.2, 0.1, 0.1, 0.2, 0.1, 0.1, 0.1, 0.1).

[0106] 3. Use the linear weighted method to aggregate the subjective weight and the objective weight to obtain the final combined weight vector.

[0107] ω=(θ 1 ω (1) +θ 2 λ (1) ), where θ 1 +θ 2 =1 represents the measure of the importance of the two evaluation methods by the decision maker. For example: In the case of detailed and balanced data information, θ 1 =0.7, θ 2 =0.3, then ω=(0.13, 0.17, 0.1, 0.2, 0.1, 0.1, 0.1, 0.1). In the case of detailed and balanced data information, the proportion of the objective evaluation weight is greater than that of the subjective evaluation weight; when the data is unbalanced, the subjective evaluation weight will dominate and can be adjusted according to the situation.

[0108] 4. Divide each index into four grade intervals of excellent, good, medium, and poor within its numerical range, and use the fuzzy algorithm to calculate the membership matrix μ i =(μ i1 , μ i2 , μ i3 , μ i4 ), where μ i is the membership matrix of the i-th index, and μ i1 ~μ i4 represents the probability of the i-th index belonging to excellent, good, medium, and poor. For example: For the current curve rate, divide it into four grade intervals, 0.92~1.07 is poor, 1.02~1.22 is medium, 1.2~1.38 is good, 1.38~1.53 is excellent. Then the probability that the value 1.52 is excellent within the range of 1.38~1.53 is (1.52 - 1.38) / (1.53 - 1.38), and the probabilities of being good, medium, and poor are 0. Then μ 1=(0.93, 0, 0, 0), and u2, u3, u4... and so on.

[0109] 5. Calculate the membership function τ = ω × μ, where μ = (μ 1 , μ 2 , …, μ i ), τ = (τ 1 , τ 2 , …, τ i ), and τ 1 ~τ 4 are the probabilities of the evaluation target being excellent, good, medium, and poor. For example: in the above example, τ 1 =(0.12, 0, 0, 0), and T2, T3, T4... and so on.

[0110] 6. The final score of the target f = [s 1 , s 2 , s 3 , s 4 · [τ 1 , τ 2 , τ 3 , τ 4 T , and s 1 ~s 4 are the benchmark scores for excellent, good, medium, and poor respectively, defined as 90, 80, 60, and 30.

[0111] The health result being poor corresponds to the final score of 0 - 30; the health result is medium when the score is between 30 - 60, good when the score is between 60 - 80, and excellent when the score is above 80.

[0112] As Figure 3 shown, on the whole - life cycle platform, display the different health results of the devices and the number of devices with different health results, and give key prompts for the devices with poor health results (i.e., the health results are medium and poor).

[0113] The historical database stores the historical data of the devices, including the daily health results of the devices within one year, as well as the data of the device rotation ability, the electrical characteristics of the action circuit, the maintenance situation, the alarm situation, the device inbound and outbound, the device up and down the line, the device inspection and repair, etc. for the previous 1 day, 5 days, 30 days, 60 days, and 180 days. Calculate the average device health results and other data for the previous 1 day, 5 days, 30 days, 60 days, and 180 days as the data set, use 80% of the previous data as the training set, and the latter 20% of the data set as the test set for training and prediction. Push the health trend and real - time device trend of the device to the whole - life cycle management platform, and give maintenance suggestions, including repair or replacement.

[0114] ​As described above, it is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A full life cycle management system for rail transit equipment, characterized in that: It includes a full life cycle management platform, a historical database, a database server and a monitoring and acquisition server. The full life cycle management platform is respectively connected to the database server and the monitoring and acquisition server for communication. The full life cycle management platform receives and analyzes the data from the database server and the monitoring and acquisition server, obtains and displays health results, and is used to monitor the life cycle of the equipment. The health result is obtained by calculating the final score through objective weights, subjective weights and probability distribution; the full life cycle management platform is communicated with the historical database, the historical database receives the collected data from the database server and the monitoring and collection server as historical data, and establishes an equipment health trend model for predicting the healthy life of the equipment.

2. A full life cycle management system for rail transit equipment according to claim 1, characterized in that: The database server collects the equipment's in-and-out storage, loading and unloading, maintenance operation status and equipment failure information for analysis and transmits the results to the lifecycle management platform; The system also includes a monitoring sensor, which is installed on the equipment and communicates with a monitoring and acquisition server. The monitoring and acquisition server obtains the equipment's rotation capacity, electrical characteristics of the action circuit, and maintenance status information based on the data from the monitoring sensor and transmits it to the full life cycle management platform.

3. The full life cycle management system of rail transit equipment according to claim 2 is characterized in that: The system also includes a station warehouse and a supply station warehouse, and both the station warehouse and the supply station warehouse include a handheld terminal, which is used to record the equipment's entry and exit, entry and exit, maintenance operation status and equipment failure information. The handheld terminal is communicatively connected to the database server.

4. The full life cycle management system of rail transit equipment according to claim 1, characterized in that: The system also includes an operation and maintenance center and an information room. The full life cycle management platform is installed in the operation and maintenance center, and the database server and the monitoring and acquisition server are installed in the information room.

5. The full life cycle management system of rail transit equipment according to claim 1, characterized in that: The full life cycle management platform includes a display module, which is used to display equipment health results and equipment alarm information.

6. A full life cycle management system for rail transit equipment according to claim 5, characterized in that: The display module is refreshed at predetermined intervals.

7. A method for the full life cycle management system of rail transit equipment according to any one of claims 1 to 6, characterized in that: The method comprises the following steps: S1, the database server and the monitoring and collection server respectively collect data in real time; S2, the database server displays the collected data through the full life cycle management platform; S3, the life cycle management platform calculates the final score by monitoring the collected data of the collection server and combining the objective weight, subjective weight and probability distribution, determines the health result according to the final score and displays it on the life cycle management platform; S4. The historical database establishes an equipment health trend model based on the historical data of the database server and the monitoring and acquisition server to predict the healthy life of the equipment.

8. The method according to claim 7, characterized in that The health results are divided into four levels: excellent, good, fair and poor.

9. The method according to claim 8, characterized in that The objective weight and the subjective weight respectively form an objective weight vector and a subjective weight vector, and a combined weight vector is formed according to the objective weight vector and the subjective weight vector, and the probability distribution is calculated, and finally the final score is calculated, and the health result is determined according to the final score; The objective weight vector has the following formula: oh (1) =(ω1,ω2,…,ω n ) ω1,ω2,…,ω n These are the objective weight values ​​of different devices in turn; The subjective weight vector has the following formula: l (1) =(λ1,λ2,…,λ n ) λ1,λ2,…,λ n These are the subjective weight values ​​of different devices in turn; The combined weight vector has the following formula: ω=(θ1ω (1) +θ2λ (1) ) θ1 is the proportion of objective weight vector, θ2 is the proportion of subjective weight vector; The probability distribution has the following formula: m i =(μ i1 ,m i2 ,m i3 ,m i4 ) τ=ω×μ μ i1 ~μ i4 represents the probability of the ith indicator being excellent, good, medium and poor, τ1~τ4 are the probabilities of the evaluation targets being excellent, good, medium and poor; The final score has the following formula: f=[X1,X2,X3,X4]·[τ1,τ2,τ3,τ4] T X1 to X4 are benchmark scores of excellent, good, fair, and poor, which are 90, 80, 60, and 30, respectively.

10. The method according to claim 7, characterized in that The S4 specifically includes: S41. Collect the health results of the equipment every day within one year, as well as the equipment rotation capacity, action circuit electrical characteristics, maintenance status, alarm status, equipment in and out of the warehouse, equipment loading and unloading, and equipment inspection and maintenance data of the previous 1 day, 5 days, 30 days, 60 days, and 180 days; S42, calculating the average equipment health results of the previous day, the previous five days, the previous 30 days, the previous 60 days, and the previous 180 days as a data set; S43, use the first 80% of the data in the data set as the training set, and the last 20% of the data set as the test set for training; S44. Push the predicted equipment health trend and real-time equipment trend to the full life cycle management platform and display them, and provide maintenance suggestions.

Images