Train performance evaluation method and device, storage medium and electronic equipment

Abstract

The present invention provides a train performance evaluation method and device, storage medium and electronic device, the method comprising: determining the real-time operation information corresponding to each preset evaluation object according to the current operation information of the target train, determining the historical operation information corresponding to each preset evaluation object according to the historical route operation information of the target train; determining the train operation information corresponding to each preset evaluation object according to the current operation information of multiple running trains currently in driving state; determining the comprehensive performance index value of each preset evaluation object according to the real-time operation information, historical operation information and train operation information corresponding to each preset evaluation object; determining the performance state corresponding to each preset evaluation object according to each of the comprehensive performance index values, and realizing the performance evaluation of the target train. The method of the present invention can realize the automatic train performance evaluation of unified standards, which is conducive to improving the accuracy of performance evaluation.

Description

Technical Field

[0001] The present invention relates to the field of rail transit technology, and in particular to a train performance evaluation method and device, a storage medium and an electronic device. Background Art

[0002] With the development of rail transit technology, railway trains have become one of the important means of transportation in people's daily lives. In order to ensure the safety and stability of train operation, it is necessary to evaluate the train operation performance in railway transportation work, so as to form a rapid response mechanism for early detection, early isolation and early treatment of faults.

[0003] At present, the performance evaluation of trains is usually carried out qualitatively, that is, the staff analyzes the operation data of the trains and judges the performance status of the trains based on experience to achieve train performance evaluation.

[0004] However, in actual railway transportation scenarios, different workers have different experiences. Based on the existing performance evaluation methods, it is impossible to evaluate train performance with unified standards. The accuracy of performance evaluation is poor, which is not conducive to ensuring the safety and stability of train operation. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a train performance evaluation method to solve the problem that the train performance cannot be evaluated according to a unified standard and the evaluation accuracy is poor.

[0006] The embodiment of the present invention also provides a train performance evaluation device to ensure the actual implementation and application of the above method.

[0007] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0008] A train performance evaluation method, comprising:

[0009] When receiving the current running information of the target train in the running state, determining the real-time running information corresponding to each preset evaluation object according to the current running information of the target train, wherein the current running information of the target train includes signal data collected by each onboard sensor of the target train in the current running state;

[0010] Acquire historical route operation information of the target train, and determine historical operation information corresponding to each of the preset evaluation objects based on the historical route operation information;

[0011] Acquire current running information of multiple running trains, wherein the running trains are trains other than the target train that are currently in a running state, and the current running information of each running train includes signal data collected by each onboard sensor of the running train in the current running state;

[0012] Determining the train operation information of the same period corresponding to each of the preset evaluation objects according to the current operation information of the multiple running trains;

[0013] For each of the preset evaluation objects, determine the comprehensive performance index value corresponding to the preset evaluation object according to the real-time operation information, historical operation information and train operation information of the same period corresponding to the preset evaluation object;

[0014] According to the comprehensive performance index value corresponding to each of the preset evaluation objects, the performance status corresponding to each of the preset evaluation objects is determined to achieve performance evaluation of the target train.

[0015] In the above method, optionally, determining the comprehensive performance index value corresponding to the preset evaluation object according to the real-time operation information, historical operation information and train operation information of the same period corresponding to the preset evaluation object includes:

[0016] Determine a performance indicator set corresponding to the preset evaluation object, wherein the performance indicator set includes at least one preset performance indicator;

[0017] For each of the preset performance indicators in the performance indicator set, determine a first deviation degree value and a second deviation degree value corresponding to the preset performance indicator according to the real-time operation information, historical operation information and train operation information of the same period corresponding to the preset evaluation object, and determine the performance indicator value corresponding to the preset performance indicator according to the first deviation degree value and the second deviation degree value;

[0018] According to the performance indicator value corresponding to each of the preset performance indicators in the performance indicator set, the comprehensive performance indicator value corresponding to the preset evaluation object is determined.

[0019] In the above method, optionally, the step of determining the first deviation value corresponding to the preset performance indicator includes:

[0020] Determine, based on the operation data information of multiple historical routes contained in the historical operation information corresponding to the preset evaluation object, multiple groups of historical operation data corresponding to the preset performance indicator, wherein the multiple groups of historical operation data correspond to the multiple historical routes one by one;

[0021] According to the preset multiple statistical features, statistical calculation is performed on each group of the historical operation data to obtain a statistical quantity set corresponding to each group of the historical operation data, wherein the statistical quantity set corresponding to each group of the historical operation data includes a statistical value of the historical data corresponding to each statistical feature;

[0022] Determining a first historical deviation value according to a set of statistics corresponding to each group of the historical operation data;

[0023] Determine the real-time operating data corresponding to the preset performance indicator according to the real-time operating information corresponding to the preset evaluation object;

[0024] According to the multiple statistical features, statistical calculation is performed on the real-time operation data to obtain a set of statistics corresponding to the real-time operation data, wherein the set of statistics corresponding to the real-time operation data includes a real-time data statistical value corresponding to each of the statistical features;

[0025] Determining a second historical deviation value according to a set of statistics corresponding to each group of the historical operation data and a set of statistics corresponding to the real-time operation data;

[0026] A first deviation degree value corresponding to the preset performance indicator is determined according to the first historical deviation value and the second historical deviation value.

[0027] In the above method, optionally, determining the first historical deviation value according to the statistical quantity set corresponding to each group of the historical operation data includes:

[0028] Determine the historical sample standard deviation and the historical sample average corresponding to each statistical feature according to the statistical quantity set corresponding to each group of the historical operation data;

[0029] Determine the historical deviation characteristic value corresponding to each of the statistical features according to the historical sample standard deviation and the historical sample average value corresponding to each of the statistical features;

[0030] A first arithmetic mean is calculated, and the first arithmetic mean is used as the first historical deviation value, where the first arithmetic mean is the arithmetic mean corresponding to each of the historical deviation characteristic values.

[0031] In the above method, optionally, determining the second historical deviation value according to the statistical set corresponding to each group of the historical operation data and the statistical set corresponding to the real-time operation data includes:

[0032] Determining, in each group of the historical operation data, historical operation data to be replaced and a plurality of target historical operation data, wherein the target historical operation data is the historical operation data in each group of the historical operation data except the historical operation data to be replaced;

[0033] Determine the real-time sample standard deviation and the real-time sample average corresponding to each of the statistical features according to the statistical set corresponding to each group of the target historical operation data and the statistical set corresponding to the real-time operation data;

[0034] Determine the real-time offset characteristic value corresponding to each of the statistical features according to the real-time sample standard deviation and the real-time sample average value corresponding to each of the statistical features;

[0035] A second arithmetic mean is calculated, and the second arithmetic mean is used as the second historical deviation value, where the second arithmetic mean is the arithmetic mean corresponding to each of the real-time offset characteristic values.

[0036] In the above method, optionally, determining the first deviation value corresponding to the preset performance indicator according to the first historical deviation value and the second historical deviation value includes:

[0037] A difference operation is performed on the second historical deviation value and the first historical deviation value, and the operation result is used as the first deviation degree value corresponding to the preset performance indicator.

[0038] In the above method, optionally, the determining of the second deviation value corresponding to the preset performance indicator includes:

[0039] Determine, based on the operation data information of each running train contained in the train operation information of the same period corresponding to the preset evaluation object, multiple sets of train operation data corresponding to the preset performance index, wherein the multiple sets of train operation data correspond to each running train one by one;

[0040] According to the multiple statistical features, statistical calculation is performed on each group of the train operation data to obtain a set of statistics corresponding to each group of the train operation data, wherein the set of statistics corresponding to each group of the train operation data includes a train data statistical value corresponding to each statistical feature;

[0041] Determining a first real-time deviation value according to a set of statistics corresponding to each group of train operation data;

[0042] Determining a second real-time deviation value according to a set of statistics corresponding to each group of the train operation data and a set of statistics corresponding to the real-time operation data;

[0043] A second deviation degree value corresponding to the preset performance indicator is determined according to the first real-time deviation value and the second real-time deviation value.

[0044] In the above method, optionally, determining the performance indicator value corresponding to the preset performance indicator according to the first deviation degree value and the second deviation degree value includes:

[0045] Performing a product operation on the first deviation degree value and the first preset weight to obtain a first product;

[0046] Performing a product operation on the second deviation degree value and the second preset weight to obtain a second product;

[0047] A sum operation is performed on the first product and the second product, and a result of the operation is used as a performance indicator value corresponding to the preset performance indicator.

[0048] In the above method, optionally, determining the comprehensive performance indicator value corresponding to the preset evaluation object according to the performance indicator value corresponding to each of the preset performance indicators in the performance indicator set includes:

[0049] Determining whether the performance indicator set includes only one preset performance indicator;

[0050] If the performance indicator set does not include only one preset performance indicator, determining an indicator weight corresponding to each of the preset performance indicators;

[0051] According to the indicator weight corresponding to each of the preset performance indicators, a weighted sum operation is performed on the performance indicator values ​​corresponding to each of the preset performance indicators, and the operation result is used as the comprehensive performance indicator value corresponding to the preset evaluation object.

[0052] In the above method, optionally, determining the indicator weight corresponding to each of the preset performance indicators includes:

[0053] Determine the information entropy corresponding to each of the preset performance indicators according to the performance indicator values ​​corresponding to each of the preset performance indicators;

[0054] According to the information entropy corresponding to each of the preset performance indicators, the indicator weight corresponding to each of the preset performance indicators is calculated.

[0055] The above method may optionally further include:

[0056] If the performance indicator set includes only one preset performance indicator, the performance indicator value corresponding to the preset performance indicator in the performance indicator set is used as the comprehensive performance indicator value corresponding to the preset evaluation object.

[0057] In the above method, optionally, determining the performance status corresponding to each preset evaluation object according to the comprehensive performance indicator value corresponding to each preset evaluation object includes:

[0058] For each of the preset evaluation objects, determining a plurality of indicator value intervals corresponding to the preset evaluation object, wherein the plurality of indicator value intervals correspond one-to-one to a plurality of preset performance states corresponding to the preset evaluation object;

[0059] For each comprehensive performance index value corresponding to the preset evaluation object, the comprehensive performance index value is matched with each index value interval corresponding to the preset evaluation object, the index value interval matching the comprehensive performance index value is determined as the target index value interval, and the preset performance state corresponding to the target index value interval is determined as the performance state corresponding to the preset evaluation object.

[0060] A train performance evaluation device, comprising:

[0061] A first determining unit is used to determine the real-time operating information corresponding to each preset evaluation object according to the current operating information of the target train when receiving the current operating information of the target train in a running state, wherein the current operating information of the target train includes signal data collected by each onboard sensor of the target train in a current operating state;

[0062] A first acquisition unit is used to acquire the historical route operation information of the target train, and determine the historical operation information corresponding to each of the preset evaluation objects according to the historical route operation information;

[0063] A second acquisition unit is used to acquire current operation information of multiple running trains, wherein the running trains are trains other than the target train that are currently in a running state, and the current operation information of each running train includes signal data collected by each onboard sensor of the running train in the current running state;

[0064] A second determining unit is used to determine the train running information of the same period corresponding to each of the preset evaluation objects according to the current running information of the multiple running trains;

[0065] A third determination unit is used to determine, for each of the preset evaluation objects, a comprehensive performance index value corresponding to the preset evaluation object according to the real-time operation information, historical operation information and train operation information of the same period corresponding to the preset evaluation object;

[0066] The evaluation unit is used to determine the performance status corresponding to each preset evaluation object according to the comprehensive performance index value corresponding to each preset evaluation object, so as to realize the performance evaluation of the target train.

[0067] A storage medium includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the train performance evaluation method as described above.

[0068] An electronic device comprises a memory and one or more instructions, wherein the one or more instructions are stored in the memory and configured to be executed by one or more processors to execute the train performance evaluation method as described above.

[0069] A train performance evaluation method provided based on the above embodiment of the present invention includes: when receiving the current operation information of a target train in a running state, determining the real-time operation information corresponding to each preset evaluation object according to the current operation information of the target train, and determining the historical operation information corresponding to each preset evaluation object according to the historical route operation information of the target train; determining the train operation information corresponding to each preset evaluation object according to the current operation information of multiple running trains; for each preset evaluation object, determining the comprehensive performance index value corresponding to the preset evaluation object according to the real-time operation information, historical operation information and train operation information corresponding to the preset evaluation object; determining the performance state corresponding to each preset evaluation object according to the comprehensive performance index value corresponding to each preset evaluation object, and realizing the performance evaluation of the target train. By applying the method provided by the embodiment of the present invention, the performance state of each preset evaluation object corresponding to the target train can be evaluated in combination with the current operation information of the target train, the historical route operation information and the current operation information of other trains running at the same time as the target train, and the train performance can be automatically evaluated according to a unified standard, which is conducive to improving the accuracy of performance evaluation and ensuring the safe and stable operation of the train. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0071] Figure 1 A method flow chart of a train performance evaluation method provided by an embodiment of the present invention;

[0072] Figure 2 An exemplary diagram of a train performance evaluation system provided by an embodiment of the present invention;

[0073] Figure 3 An example diagram of a train performance evaluation process provided by an embodiment of the present invention;

[0074] Figure 4 An example diagram of a performance indicator calculation process provided by an embodiment of the present invention;

[0075] Figure 5 A schematic diagram of the structure of a train performance evaluation device provided by an embodiment of the present invention;

[0076] Figure 6 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0077] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0078] In this application, the terms "comprises", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element.

[0079] As can be seen from the background technology, in the development of railway transportation, the requirements for the safety and stability of train operation are getting higher and higher, and the importance of train performance evaluation is also getting higher and higher. However, how to evaluate train performance is usually still a qualitative evaluation. All parties conduct performance evaluation based on experience, and there is no unified standard, which makes the accuracy of performance evaluation poor, which is not conducive to ensuring the safety of train operation.

[0080] Therefore, an embodiment of the present invention provides a train performance evaluation method, which combines big data to analyze the performance indicators of various evaluation objects to achieve automated performance evaluation with unified standards, which is conducive to improving evaluation accuracy and ensuring train operation safety.

[0081] The embodiment of the present invention provides a train performance evaluation method, which can be applied to a train performance evaluation system, and the execution subject can be a server of the system. The method flow chart of the method is as follows: Figure 1 As shown, including:

[0082] S101: when receiving current running information of a target train in a running state, determining real-time running information corresponding to each preset evaluation object according to the current running information of the target train, the current running information of the target train including signal data collected by each onboard sensor of the target train in the current running state;

[0083] In the method provided by the embodiment of the present invention, during the operation of the train, each on-board sensor on the train will collect relevant signal data in real time, for example, the motor temperature sensor will detect the temperature value of the motor in real time, the total air cylinder pressure sensor will detect the pressure value of the total air cylinder in real time, etc. By setting, the signal data collected by each on-board sensor in the current period can be packaged as current operation information according to a preset time interval, and sent to the server of the train performance evaluation system based on wireless communication technology.

[0084] In the method provided in the embodiment of the present invention, multiple evaluation objects can be preset, and the preset evaluation objects can specifically be some key components or systems on the train, such as the braking system, the pantograph, the traction motor, etc. At the same time, the signal data type associated with each preset evaluation object is set, for example, the signal data type associated with the pantograph can be a pantograph raising state signal, a pantograph main breaking state signal, etc.

[0085] In the method provided by an embodiment of the present invention, when the server receives the current operation information sent by a running target train, it can obtain the respective signal data corresponding to each preset evaluation object in the current operation information of the current train based on the signal data type corresponding to each preset evaluation object, and use the respective signal data corresponding to each preset evaluation object as the real-time operation information corresponding to the preset evaluation object.

[0086] S102: Acquire historical route operation information of the target train, and determine historical operation information corresponding to each of the preset evaluation objects based on the historical route operation information;

[0087] In the method provided by the embodiment of the present invention, the historical route operation information of the target train can be obtained in the database, including the signal data collected by each on-board sensor during the driving process of the current train in multiple historical routes. The route refers to the train route, that is, the fixed turnover section where the train undertakes the transportation task, and the historical route can be understood as the driving range of the train when it undertakes the previous transportation task.

[0088] According to the signal data type corresponding to each preset evaluation object, the signal data corresponding to each preset evaluation object can be obtained from the historical route operation information of the target train as the historical operation information corresponding to each preset evaluation object.

[0089] S103: Acquire current running information of multiple running trains, where the running trains are trains other than the target train that are currently in a running state, and the current running information of each running train includes signal data collected by each onboard sensor of the running train in the current running state;

[0090] In the method provided by the embodiment of the present invention, for each train in motion except the target train in the rail transit system, each on-board sensor will also collect signal data in real time during its motion. Each train will periodically send the current operation information of the train to the server. The server can obtain the current operation information of multiple running trains from the current operation information received in the current time period.

[0091] S104: Determine the train operation information of the same period corresponding to each of the preset evaluation objects according to the current operation information of the multiple running trains;

[0092] In the method provided by an embodiment of the present invention, according to the signal data type corresponding to each preset evaluation object, each signal data corresponding to each preset evaluation object can be obtained in the current operation information of each running train. For each preset evaluation object, the various signal data corresponding to the preset evaluation object obtained from the current operation information of each running train will be used as the train operation information of the same period corresponding to the preset evaluation object.

[0093] S105: for each of the preset evaluation objects, determining a comprehensive performance index value corresponding to the preset evaluation object according to the real-time operation information, historical operation information and train operation information of the same period corresponding to the preset evaluation object;

[0094] In the method provided in an embodiment of the present invention, the comprehensive performance index value corresponding to each preset evaluation object can be calculated based on the real-time operation information, historical operation information and train operation information of the same period corresponding to each preset evaluation object. It can be understood that, in combination with the current signal data of the target train associated with the preset evaluation object, the historical signal data of the target train and the current signal data of other running trains, the preset evaluation object is performance evaluated according to the preset performance indicators to determine the corresponding comprehensive performance index value.

[0095] S106: Determine the performance status corresponding to each of the preset evaluation objects according to the comprehensive performance indicator value corresponding to each of the preset evaluation objects, and implement performance evaluation of the target train.

[0096] In the method provided in the embodiment of the present invention, for each preset evaluation object, the corresponding performance state is determined based on the corresponding comprehensive performance index value. The performance evaluation result of the target train is characterized by the performance state corresponding to each preset evaluation object. The performance state corresponding to the preset evaluation object can be a healthy, early warning or alarm state.

[0097] Based on the method provided by the embodiment of the present invention, the real-time operation information, historical operation information and train operation information of the same period corresponding to each preset evaluation object are determined according to the current operation information of the target train, the historical route operation information and the current operation information of each running train. For each preset evaluation object, the comprehensive performance index value corresponding to the preset evaluation object is determined according to the real-time operation information, historical operation information and train operation information of the same period corresponding to the preset evaluation object; according to the comprehensive performance index value corresponding to each preset evaluation object, the performance state corresponding to each preset evaluation object is determined to perform performance evaluation on the target train. By applying the method provided by the embodiment of the present invention, the operation data corresponding to the preset evaluation object under various driving scenarios can be combined to calculate the comprehensive performance index value corresponding to the preset evaluation object, and then determine its corresponding performance state, and characterize the performance evaluation result of the train with the performance state of each preset evaluation object. The train performance can be automatically evaluated according to a unified standard to achieve quantitative evaluation, which is conducive to improving the accuracy of performance evaluation and ensuring the safe and stable operation of the train. Secondly, the accuracy of performance state evaluation can be further improved by applying big data to analyze performance state.

[0098] Further, in Figure 1 On the basis of the method shown, in the method provided by the embodiment of the present invention, the process of determining the comprehensive performance index value corresponding to the preset evaluation object according to the real-time operation information, historical operation information and train operation information of the same period corresponding to the preset evaluation object mentioned in step S105 includes:

[0099] Determine a performance indicator set corresponding to the preset evaluation object, wherein the performance indicator set includes at least one preset performance indicator;

[0100] In the method provided by the embodiment of the present invention, for the current preset evaluation object, its corresponding performance indicator set can be determined based on pre-configured information, including preset performance indicators for evaluating the preset evaluation object. There can be only one or more preset performance indicators in the performance indicator set, and the number of preset performance indicators is determined by the demand settings in the actual application process, which does not affect the function of the method provided by the embodiment of the present invention.

[0101] For each of the preset performance indicators in the performance indicator set, determine a first deviation degree value and a second deviation degree value corresponding to the preset performance indicator according to the real-time operation information, historical operation information and train operation information of the same period corresponding to the preset evaluation object, and determine the performance indicator value corresponding to the preset performance indicator according to the first deviation degree value and the second deviation degree value;

[0102] In the method provided by the embodiment of the present invention, the first deviation value corresponding to each preset performance indicator and the second deviation value corresponding to each preset performance indicator are determined based on the real-time operation information, historical operation information and train operation information of the same period corresponding to the current preset evaluation object, and the performance indicator value corresponding to each preset performance indicator is calculated based on the first deviation value and the second deviation value corresponding to each preset performance indicator. The first deviation value corresponding to the preset performance indicator can be determined based on the real-time operation information and historical operation information corresponding to the preset evaluation object, and the first deviation value represents the degree of difference between the real-time operation data of the target train associated with the preset performance indicator and the historical operation data. The second deviation value corresponding to the preset performance indicator can be determined based on the real-time operation information and train operation information of the same period corresponding to the preset evaluation object, and the second deviation value represents the degree of difference between the real-time operation data of the target train associated with the preset performance indicator and the real-time operation data of other running trains.

[0103] According to the performance indicator value corresponding to each of the preset performance indicators in the performance indicator set, the comprehensive performance indicator value corresponding to the preset evaluation object is determined.

[0104] In the method provided in the embodiment of the present invention, based on a preset integration strategy and in combination with the performance indicator values ​​corresponding to each preset performance indicator, a comprehensive performance indicator value corresponding to the preset evaluation object can be calculated.

[0105] Further, based on the method provided in the above embodiment, in the method provided in the embodiment of the present invention, the process of determining the first deviation degree value corresponding to the preset performance indicator includes:

[0106] Determine, based on the operation data information of multiple historical routes contained in the historical operation information corresponding to the preset evaluation object, multiple groups of historical operation data corresponding to the preset performance indicator, wherein the multiple groups of historical operation data correspond to the multiple historical routes one by one;

[0107] In the method provided by the embodiment of the present invention, the historical operation information corresponding to the preset evaluation object includes operation data information of multiple historical intersections. From the operation data information of each historical intersection, according to the data type corresponding to the preset performance indicator, the operation data corresponding to the preset performance indicator (i.e., the signal data associated with the preset performance indicator in the operation data information) can be obtained to obtain multiple groups of historical operation data corresponding to the preset performance indicator. Each operation data obtained from the operation data information of a historical intersection constitutes a group of historical operation data, so a group of historical operation data corresponds to a historical intersection. Each group of historical operation data includes multiple operation data values.

[0108] According to the preset multiple statistical features, statistical calculation is performed on each group of the historical operation data to obtain a statistical quantity set corresponding to each group of the historical operation data, wherein the statistical quantity set corresponding to each group of the historical operation data includes a statistical value of the historical data corresponding to each statistical feature;

[0109] In the method provided by the embodiment of the present invention, multiple statistical features for describing the characteristics of the operation data can be pre-set, such as maximum value, minimum value, mean value and other statistical features. Statistical calculations are performed on each set of historical operation data according to each statistical feature to obtain a set of statistics corresponding to each set of historical operation data, that is, for each set of historical operation data, the statistical values ​​of each type of statistical features such as the maximum value, minimum value, mean value and the like of each operation data are calculated respectively. The calculated statistical values ​​are called historical data statistical values, and the statistical values ​​of each historical data calculated according to each statistical feature constitute a set of statistics.

[0110] Determining a first historical deviation value according to a set of statistics corresponding to each group of the historical operation data;

[0111] In the method provided in an embodiment of the present invention, a first historical deviation value can be calculated according to a preset deviation estimation strategy based on a set of statistics corresponding to each group of historical operation data. The first historical deviation value represents the degree of deviation between the statistical values ​​of each historical data in the set of statistics corresponding to each group of historical operation data.

[0112] Determine the real-time operating data corresponding to the preset performance indicator according to the real-time operating information corresponding to the preset evaluation object;

[0113] In the method provided by the embodiment of the present invention, the real-time operation data corresponding to the preset performance indicator can be obtained according to the data type corresponding to the preset performance indicator from each real-time operation data included in the real-time operation information corresponding to the preset evaluation object. The real-time operation data includes multiple operation data values.

[0114] According to the multiple statistical features, statistical calculation is performed on the real-time operation data to obtain a set of statistics corresponding to the real-time operation data, wherein the set of statistics corresponding to the real-time operation data includes a real-time data statistical value corresponding to each of the statistical features;

[0115] In the method provided in the embodiment of the present invention, statistical calculations can be performed on the real-time operation data based on each statistical feature to obtain a set of statistics corresponding to the real-time operation data. The calculation principle is the same as the principle of performing statistical calculations on each group of historical operation data in the above process. Please refer to the above description and will not be repeated here.

[0116] Determining a second historical deviation value according to a set of statistics corresponding to each group of the historical operation data and a set of statistics corresponding to the real-time operation data;

[0117] In the method provided in the embodiment of the present invention, the second historical deviation value can be calculated based on the statistical set corresponding to each group of historical operation data and the statistical set corresponding to the real-time operation data according to the preset deviation estimation strategy. The second historical deviation value represents the degree of deviation between each historical data statistical value and each real-time data statistical value.

[0118] A first deviation degree value corresponding to the preset performance indicator is determined according to the first historical deviation value and the second historical deviation value.

[0119] In the method provided in an embodiment of the present invention, the first historical deviation degree and the second historical deviation degree can be combined to calculate the first deviation degree value corresponding to the current preset performance indicator, that is, the first deviation degree value corresponding to the preset performance indicator is determined based on the deviation degree between the statistical characteristics of each historical operation data and the statistical characteristics of the real-time operation data.

[0120] Further, based on the method provided in the above embodiment, in the method provided in the embodiment of the present invention, the process of determining the first historical deviation value according to the set of statistics corresponding to each group of the historical operation data includes:

[0121] Determine the historical sample standard deviation and the historical sample average corresponding to each statistical feature according to the statistical quantity set corresponding to each group of the historical operation data;

[0122] In the method provided by an embodiment of the present invention, for each statistical feature, the historical data statistical value corresponding to the statistical feature is obtained from the statistical value set corresponding to each group of historical operating data, and based on the various historical data statistical values ​​corresponding to the statistical feature, the sample standard deviation and the sample mean are calculated, and the calculation result of the sample standard deviation is used as the historical sample standard deviation corresponding to the statistical feature, and the calculation result of the sample standard deviation is used as the historical sample mean corresponding to the statistical feature.

[0123] Determine the historical deviation characteristic value corresponding to each of the statistical features according to the historical sample standard deviation and the historical sample average value corresponding to each of the statistical features;

[0124] In the method provided by an embodiment of the present invention, for each statistical feature, its corresponding historical deviation characteristic value can be calculated based on its corresponding historical sample standard deviation and historical sample average value. Specifically, the historical sample standard deviation can be divided by the historical sample average value, and the calculation result can be used as the historical deviation characteristic value.

[0125] A first arithmetic mean is calculated, and the first arithmetic mean is used as the first historical deviation value, where the first arithmetic mean is the arithmetic mean corresponding to each of the historical deviation characteristic values.

[0126] In the method provided by the embodiment of the present invention, an arithmetic mean is calculated for the historical deviation feature values ​​corresponding to each statistical feature to obtain a first arithmetic mean value, and the first arithmetic mean value is used as the first historical deviation value.

[0127] On the basis of the method provided in the above embodiment, in the method provided in the embodiment of the present invention, the process of determining the second historical deviation value according to the statistical set corresponding to each group of the historical operation data and the statistical set corresponding to the real-time operation data includes:

[0128] Determining, in each group of the historical operation data, historical operation data to be replaced and a plurality of target historical operation data, wherein the target historical operation data is the historical operation data in each group of the historical operation data except the historical operation data to be replaced;

[0129] In the method provided by the embodiment of the present invention, a group of historical operation data is selected from each group of historical operation data as the historical operation data to be replaced. Specifically, the historical operation data to be replaced can be selected randomly, or a selection rule can be preset and the historical operation data to be replaced can be selected according to the rule. Each group of historical operation data, except the historical operation data to be replaced, is used as the target historical operation data.

[0130] Determine the real-time sample standard deviation and the real-time sample average corresponding to each of the statistical features according to the statistical set corresponding to each group of the target historical operation data and the statistical set corresponding to the real-time operation data;

[0131] In the method provided by an embodiment of the present invention, for each statistical feature, each historical data statistical value corresponding to the statistical feature is obtained from a statistical set corresponding to each group of target historical operation data, and a real-time data statistical value corresponding to the statistical feature is obtained from a statistical set corresponding to the real-time operation data. Based on the obtained historical data statistical values ​​and real-time data statistical values, the sample standard deviation and the sample mean are calculated, and the calculation result of the sample standard deviation is used as the real-time sample standard deviation corresponding to the statistical feature, and the calculation result of the sample mean is used as the real-time sample mean corresponding to the statistical feature.

[0132] Determine the real-time offset characteristic value corresponding to each of the statistical features according to the real-time sample standard deviation and the real-time sample average value corresponding to each of the statistical features;

[0133] In the method provided by the embodiment of the present invention, the real-time sample standard deviation corresponding to each statistical feature can be divided by its corresponding real-time sample average value, and the calculation result is used as the real-time offset feature value corresponding to the statistical feature.

[0134] A second arithmetic mean is calculated, and the second arithmetic mean is used as the second historical deviation value, where the second arithmetic mean is the arithmetic mean corresponding to each of the real-time offset characteristic values.

[0135] In the method provided by the embodiment of the present invention, an arithmetic mean is calculated for the real-time offset feature values ​​corresponding to each statistical feature to obtain a second arithmetic mean value, and the second arithmetic mean value is used as the second historical deviation value.

[0136] On the basis of the method provided in the above embodiment, in the method provided in the embodiment of the present invention, the process of determining the first deviation degree value corresponding to the preset performance indicator according to the first historical deviation value and the second historical deviation value includes:

[0137] A difference operation is performed on the second historical deviation value and the first historical deviation value, and the operation result is used as the first deviation degree value corresponding to the preset performance indicator.

[0138] In the method provided by the embodiment of the present invention, the difference between the second historical deviation value and the first historical deviation value is used as the first deviation degree value.

[0139] On the basis of the method provided in the above embodiment, in the method provided in the embodiment of the present invention, the process of determining the second deviation degree value corresponding to the preset performance indicator includes:

[0140] Determine, based on the operation data information of each running train contained in the train operation information of the same period corresponding to the preset evaluation object, a plurality of sets of train operation data corresponding to the preset performance index, wherein the plurality of sets of train operation data correspond to each running train one by one;

[0141] In the method provided by the embodiment of the present invention, the train operation information corresponding to the preset evaluation object in the same period includes operation data information of multiple running trains. From the operation data information of each running train, according to the data type corresponding to the current preset performance index, the operation data corresponding to the preset performance index is obtained to obtain multiple groups of train operation data. The individual operation data obtained from the operation data information of a running train constitute a group of train operation data, that is, a group of train operation data corresponds to a running train. Each group of train operation data includes multiple operation data values.

[0142] According to the multiple statistical features, statistical calculation is performed on each group of the train operation data to obtain a set of statistics corresponding to each group of the train operation data, wherein the set of statistics corresponding to each group of the train operation data includes a train data statistical value corresponding to each statistical feature;

[0143] In the method provided by an embodiment of the present invention, statistical calculations are performed on each group of train operation data according to each statistical feature to obtain a set of statistics corresponding to the group of train operation data, which includes a train data statistical value corresponding to each statistical feature. The train data statistical value is the statistical value obtained by performing statistical calculations according to the corresponding statistical feature.

[0144] Determining a first real-time deviation value according to a set of statistics corresponding to each group of train operation data;

[0145] In the method provided in the embodiment of the present invention, a first real-time deviation value can be calculated based on a set of statistics corresponding to each set of train operation data according to a preset deviation estimation strategy, and the first real-time deviation value represents the degree of deviation between the statistical values ​​of each train data in the set of statistics corresponding to each set of train operation data. The calculation principle of the first real-time deviation value is the same as the calculation principle of the first historical deviation value in the above embodiment. For details, please refer to the description of the determination process of the first historical deviation value in the above embodiment, which will not be repeated here.

[0146] Determining a second real-time deviation value according to a set of statistics corresponding to each group of the train operation data and a set of statistics corresponding to the real-time operation data;

[0147] In the method provided by an embodiment of the present invention, according to a preset deviation estimation strategy, a second real-time deviation value is calculated based on a set of statistics corresponding to each group of train operation data and a set of statistics corresponding to real-time operation data, and the second real-time deviation value represents the degree of deviation between each train data statistical value and each real-time data statistical value.

[0148] In the method provided in the embodiment of the present invention, the calculation principle of the second real-time deviation value is similar to the calculation principle of the second historical deviation value in the above embodiment. Please refer to the description of the determination process of the second historical deviation value in the above embodiment, which will not be repeated here. It should be noted that in the method provided in the embodiment of the present invention, the set of statistics involved in the process of determining the second real-time deviation value may be different from the determination method of the set of statistics involved in the process of determining the second historical deviation value. Specifically, in the process of determining the second real-time deviation value, the calculation can be directly based on the set of statistics corresponding to each group of train operation data and the set of statistics corresponding to the real-time operation data, rather than in the process of determining the second historical deviation value, the calculation is based on each target historical operation data in each group of historical operation data combined with the real-time operation data.

[0149] A second deviation degree value corresponding to the preset performance indicator is determined according to the first real-time deviation value and the second real-time deviation value.

[0150] In the method provided in the embodiment of the present invention, the first real-time deviation value and the second real-time deviation value can be combined to calculate the second deviation degree value corresponding to the current preset performance index, that is, the second deviation degree value is determined by the deviation degree between the statistical characteristics of each train operation data and the statistical characteristics of the real-time operation data. The specific calculation principle can be the same as the calculation principle of the first deviation degree value, and the description of the first deviation degree value determination process in the above embodiment can be referred to, which will not be repeated here.

[0151] Further, based on the method provided in the above embodiment, in the method provided in the embodiment of the present invention, the process of determining the performance indicator value corresponding to the preset performance indicator according to the first deviation degree value and the second deviation degree value includes:

[0152] Performing a product operation on the first deviation degree value and the first preset weight to obtain a first product;

[0153] Performing a product operation on the second deviation degree value and the second preset weight to obtain a second product;

[0154] A sum operation is performed on the first product and the second product, and a result of the operation is used as a performance indicator value corresponding to the preset performance indicator.

[0155] In the method provided by the embodiment of the present invention, a first preset weight and a second preset weight can be pre-set according to actual needs, and used to perform a weighted sum operation on two types of deviation degree values, and the sum of the first preset weight and the second preset weight is one. The calculation weight corresponding to the first deviation degree value is the first preset weight, and the calculation weight corresponding to the second deviation degree value is the second preset weight. Based on the first preset weight and the second preset weight, a weighted sum operation is performed on the first deviation degree value and the second deviation degree value, and the operation result is used as the performance indicator value corresponding to the current preset performance indicator.

[0156] Further, based on the method provided in the above embodiment, the process of determining the comprehensive performance indicator value corresponding to the preset evaluation object according to the performance indicator value corresponding to each of the preset performance indicators in the performance indicator set includes:

[0157] Determining whether the performance indicator set includes only one preset performance indicator;

[0158] In the method provided by the embodiment of the present invention, the number of preset performance indicators included in the performance indicator set corresponding to the current preset evaluation object can be determined to judge whether the number of preset performance indicators included in the performance indicator set is one, that is, whether it only includes one preset performance indicator.

[0159] If the performance indicator set does not include only one preset performance indicator, determining an indicator weight corresponding to each of the preset performance indicators;

[0160] In the method provided by the embodiment of the present invention, if the number of preset performance indicators included in the performance indicator set is multiple, the indicator weight corresponding to each preset performance indicator in the performance indicator set is determined according to a preset weight calculation strategy.

[0161] According to the indicator weight corresponding to each of the preset performance indicators, a weighted sum operation is performed on the performance indicator values ​​corresponding to each of the preset performance indicators, and the operation result is used as the comprehensive performance indicator value corresponding to the preset evaluation object.

[0162] In the method provided by the embodiment of the present invention, based on the indicator weights of each preset performance indicator in the performance indicator set, the performance indicator values ​​corresponding to the preset performance indicators are weighted and calculated to obtain the comprehensive performance indicator value corresponding to the current preset evaluation object.

[0163] On the basis of the method provided in the above embodiment, in the method provided in the embodiment of the present invention, the process of determining the indicator weight corresponding to each of the preset performance indicators includes:

[0164] Determine the information entropy corresponding to each of the preset performance indicators according to the performance indicator values ​​corresponding to each of the preset performance indicators;

[0165] In the method provided in the embodiment of the present invention, for each preset performance indicator in the performance indicator set, the information entropy corresponding to the preset performance indicator is calculated based on the performance indicator value corresponding to each preset performance indicator in the performance indicator set. Specifically, the calculation formula for the information entropy corresponding to each preset performance indicator can be as follows:

[0166]

[0167] Among them, E i represents the information entropy of the i-th preset performance indicator, k represents the number of statistical features corresponding to the preset performance indicator, and p d It represents the probability corresponding to the d-th statistical feature corresponding to the preset performance indicator. The probability represents the proportion of the d-th statistical feature in the k statistical features. The probability is the value obtained by normalizing the characteristic value of the d-th statistical feature.

[0168] According to the information entropy corresponding to each of the preset performance indicators, the indicator weight corresponding to each of the preset performance indicators is calculated.

[0169] In the method provided in the embodiment of the present invention, for each preset performance indicator, the corresponding indicator weight can be calculated based on the corresponding information entropy. Specifically, the calculation formula of the indicator weight can be as follows:

[0170]

[0171] Among them, W i represents the indicator weight corresponding to the i-th preset performance indicator, and n represents the number of preset performance indicators in the performance indicator set.

[0172] Furthermore, based on the method provided in the above embodiment, the method provided in the embodiment of the present invention further includes:

[0173] If the performance indicator set includes only one preset performance indicator, the performance indicator value corresponding to the preset performance indicator in the performance indicator set is used as the comprehensive performance indicator value corresponding to the preset evaluation object.

[0174] In the method provided by the embodiment of the present invention, if it is determined that there is only one preset performance indicator in the performance indicator set, the performance indicator value corresponding to the preset performance indicator is used as the comprehensive performance indicator value corresponding to the current preset evaluation object.

[0175] exist Figure 1 On the basis of the method shown, in the method provided by the embodiment of the present invention, the process of determining the performance state corresponding to each preset evaluation object according to the comprehensive performance indicator value corresponding to each preset evaluation object mentioned in step S106 includes:

[0176] For each of the preset evaluation objects, determining a plurality of indicator value intervals corresponding to the preset evaluation object, wherein the plurality of indicator value intervals correspond one-to-one to a plurality of preset performance states corresponding to the preset evaluation object;

[0177] In the method provided in the embodiment of the present invention, multiple preset performance states corresponding to each preset evaluation object and the index value interval corresponding to each preset performance state corresponding to each preset evaluation object can be preset according to actual needs. Based on the pre-configured information, multiple index value intervals corresponding to each preset evaluation object are determined.

[0178] For each comprehensive performance index value corresponding to the preset evaluation object, the comprehensive performance index value is matched with each index value interval corresponding to the preset evaluation object, the index value interval matching the comprehensive performance index value is determined as the target index value interval, and the preset performance state corresponding to the target index value interval is determined as the performance state corresponding to the preset evaluation object.

[0179] In the method provided by an embodiment of the present invention, the comprehensive performance index value corresponding to each preset evaluation object can be matched with each index value interval corresponding to the preset evaluation object to determine in which index value interval the comprehensive performance index value is located, and the index value interval in which the comprehensive performance index value is located (that is, the index value interval that matches the comprehensive performance index value) is used as the target index value interval, and the preset performance state corresponding to the target index value interval is determined as the performance state corresponding to the preset evaluation object.

[0180] In order to better illustrate the method provided by the embodiment of the present invention, the embodiment of the present invention provides another train performance evaluation method in combination with a specific application scenario. The method provided by the embodiment of the present invention can be applied to a train performance evaluation system, and the train performance evaluation system is for Figure 1 An instantiation of the method shown in FIG. 1 may be shown in FIG. Figure 2 As shown, the train performance evaluation system is mainly deployed on the ground server, including a data processing module, a key performance evaluation model and a result display module. The key performance evaluation model includes performance evaluation modules corresponding to each preset evaluation object and a comprehensive analysis module for operating performance, each of which includes a braking system performance evaluation module, a pantograph performance evaluation module, a low-voltage electrical appliance performance evaluation module, a traction motor performance evaluation module and a running gear performance evaluation module. The braking system, pantograph, low-voltage electrical appliance, traction motor and running gear systems and components are the preset evaluation objects in the embodiment of the present invention.

[0181] On-board sensors in the train, such as motor temperature sensors, total air cylinder pressure sensors, etc., can collect signal variable data in real time. The collected signal variable data can be sent to the data processing module of the ground server via WLAN (wireless local area network) to conduct train performance evaluation.

[0182] It should be noted that Figure 2 The structure shown is only a specific embodiment provided by the method provided by the present invention to better illustrate the present invention. In the specific implementation process, the system architecture is not limited to Figure 2 The specific content shown, for example, other performance evaluation modules may be used, and is not limited to WLAN transmission. Other communication methods may be used to transmit data, such as 5G, etc., which does not affect the function of the method provided in the embodiment of the present invention.

[0183] based on Figure 2 The performance evaluation model shown, the train performance evaluation process provided by the embodiment of the present invention mainly includes: signal variable data acquisition, train operation data transmission, train operation data processing, key performance evaluation model evaluation and result display and other processes.

[0184] Signal variable data acquisition;

[0185] In the method provided in the embodiment of the present invention, the train obtains environmental variable data of key components through on-board sensors, such as motor temperature sensors, total air cylinder pressure sensors, and may also include voltage sensors, current sensors, etc.

[0186] Train operation data transmission;

[0187] In the method provided in the embodiment of the present invention, signal variable data such as voltage and current are collected by on-board sensors, and data such as train operation information and vehicle equipment status information are packaged according to a set message format and transmitted to a ground server via WLAN.

[0188] Train operation data processing;

[0189] In the method provided by the embodiment of the present invention, when the ground server receives the transmitted data packet, the data processing module stores the data on the one hand, and parses it according to the set message format on the other hand, and sends the data to each performance evaluation module in the specified format as required.

[0190] Evaluation of key performance evaluation models;

[0191] In the method provided by the embodiment of the present invention, a key performance evaluation model is established based on historical operation data and combined with real-time operation data. The model mainly includes two parts: one is each performance evaluation module, which is used to obtain the key performance indicators (i.e., performance indicator values) of each preset evaluation object. The second is an operation performance comprehensive analysis module, which is used to comprehensively evaluate the performance status of key components of the train (i.e., preset evaluation objects). Each performance evaluation module receives corresponding variable data to calculate key performance indicators. After each performance evaluation module completes the calculation, the obtained key performance indicators are sent to the operation performance comprehensive analysis module. After obtaining the key performance indicators of each component, a comprehensive analysis method is used to evaluate the train operation performance, and the results are sent to the result display module.

[0192] Results display;

[0193] In the method provided by the embodiment of the present invention, after the result display module receives the output result of the key performance evaluation model, it displays it in a visual manner such as a chart.

[0194] Next, the evaluation process of the key performance evaluation model provided by the embodiment of the present invention is further described.

[0195] In the method provided by the embodiment of the present invention, after receiving the train signal variable data, the ground server uses the key performance evaluation model to achieve a quantitative description of the performance of each key component during the train operation process. The schematic diagram of the specific train performance evaluation process can be as follows: Figure 3 shown.

[0196] Each performance evaluation module calculates key performance indicators based on its corresponding variable data to obtain performance indicator values, such as Figure 3 As shown, the key performance indicators can be calculated based on the variable data of the brake system, the pantograph, the low-voltage electrical equipment, the traction motor, and the running gear. The number of key performance indicators that the performance evaluation module needs to calculate can be multiple or only one.

[0197] The operation performance comprehensive analysis module performs comprehensive analysis on the key performance indicators calculated by each performance evaluation module. If the performance evaluation module calculates only one key performance indicator, the performance status of the component or system corresponding to the performance evaluation module is determined based on the indicator value of the key performance indicator. If the performance evaluation module calculates multiple key performance indicators, the indicator value of the component corresponding to the performance evaluation module needs to be adjusted. Specifically, each key performance indicator calculated by the performance evaluation module can be normalized, and the information entropy corresponding to each key performance indicator can be calculated. Based on the information entropy corresponding to each key performance indicator, each key performance indicator can be integrated, and the indicator value of the component or system can be adjusted based on the integration result. Based on the adjusted indicator value, the performance status of the corresponding component or system is determined. Figure 3 As shown, after comprehensive analysis, the performance status of components or systems such as the braking system performance status, pantograph performance status, low-voltage electrical performance status, traction motor performance status and running gear performance status can be obtained to characterize the performance status of the train.

[0198] Next, the calculation of key performance indicators and the comprehensive analysis of operating performance in the method provided in the embodiment of the present invention are further described.

[0199] In the method provided in the embodiment of the present invention, for the calculation of a certain key performance indicator of a certain component or system (preset evaluation object), the process example diagram can be as follows: Figure 4 As shown, it mainly includes the following processes:

[0200] Calculate the same-vehicle deviation degree SE1, by analyzing the operation data of the vehicle's most recent n trips and combining it with the current signal variable data, to obtain the same-vehicle deviation degree SE1 of the current trip;

[0201] Calculate the performance deviation degree SE2 of other vehicles. By analyzing the operation data of train m in the same period and combining the current signal variable data, obtain the deviation degree SE2 of other vehicles in this intersection.

[0202] The key performance indicator SE is calculated by combining SE1 and SE2.

[0203] In the method provided in the embodiment of the present invention, the calculation process of the same-vehicle deviation degree SE1 mainly includes:

[0204] Analyze the running data of the latest n trips of the train currently being evaluated, and calculate the maximum, minimum, mean and other statistics of the running data of each trip as a unit to form a feature vector V = [v1, v2, ..., v k ], and then get the feature matrix R1 = [V1, V2, ..., V n ].

[0205] The deviation degree of R1, i.e. SE1, can be calculated according to the following formula:

[0206]

[0207] in,

[0208] Where i represents the i-th statistical feature, k represents the number of statistical features, j represents the j-th route, and n represents the number of routes. ij Represents the statistical value of the i-th statistical feature of the j-th route.

[0209] In the method provided in the embodiment of the present invention, the calculation process of the same-vehicle deviation degree SE2 mainly includes:

[0210] The running data of m trains in the same period are analyzed. Taking a train running in the same period as a unit, the maximum, minimum, mean and other statistics of its running data are calculated to form a feature vector V'=[v1,v2,...,v k ], and obtain the characteristic matrix R2 = [V'1, V'2, ..., V' m ].

[0211] The degree of deviation of R2, i.e. SE2, can be calculated according to the following formula:

[0212]

[0213] in,

[0214] Among them, i represents the i-th statistical feature, k represents the number of statistical features, j represents the j-th train, and m represents the number of trains in the same period. ij Represents the statistical value of the i-th statistical feature of the j-th train.

[0215] In the method provided in the embodiment of the present invention, the calculation process of the key performance indicator mainly includes:

[0216] For the current running data of the train being evaluated, the maximum, minimum, mean and other statistics of its running data are calculated to form a feature vector V*=[v1,v2,...,v k ].

[0217] For the characteristic matrix R1, replace V1 in R1 with the characteristic vector V*, and then calculate based on formula 3 to obtain SE1'. The first deviation degree value △SE1 can be calculated according to the following formula:

[0218] ΔSE1=SE1'-SE1 (Formula 5)

[0219] For the feature matrix R2, the feature vector V* is added to R2, and then SE2' is calculated based on the following formula:

[0220]

[0221] in,

[0222] The meaning of each parameter is the same as that of the parameter in Formula 4, and can be found in the above description.

[0223] The second deviation value △SE2 is calculated according to the following formula:

[0224] ΔSE2=SE2'-SE2 (Formula 7)

[0225] The key performance indicator SE can be calculated based on the following formula:

[0226] SE=w1ΔSE1+w2ΔSE2 (Formula 8)

[0227] Wherein, w1+w2=1. w1 and w2 are weights preset according to requirements.

[0228] In the method provided in the embodiment of the present invention, the process of comprehensive analysis of train running performance mainly includes:

[0229] For each component or system, each key performance indicator corresponding to the component or system is normalized. According to the information entropy formula (i.e., formula 1), the information entropy of each key performance indicator can be calculated. According to formula 2, the weight of each key performance indicator can be calculated. For the component or system, its final index value Z can be calculated according to the following formula:

[0230]

[0231] Among them, SE i is the SE of the i-th key performance indicator, W i is the weight of the i-th key performance indicator, and n is the number of key performance indicators.

[0232] Determine the performance status of the component or system according to the following rules:

[0233] If Z<r alarm , then the performance status is healthy, if r alarm ≤Z<r warning , the performance status is warning, if Z ≥ r warning , the performance status is alarm status. alarm and r warning , which can be pre-set according to needs.

[0234] The method provided by the embodiment of the present invention transmits the vehicle-borne signal variable data to the ground server through the data transmission module, and then processes and analyzes the train operation data through the data processing module, the key performance evaluation module of each component and the comprehensive analysis module of the operation performance on the server, so as to form a set of intelligent, accurate and fast train key performance evaluation system, which has the function of evaluating the performance status of key components such as the train braking system, pantograph, low-voltage electrical appliances, traction motor, running gear, etc.

[0235] The method provided by the embodiment of the present invention utilizes the historical data of the same vehicle and the operation data of other vehicles to extract the key performance indicators of each component, realizes the comprehensive analysis of the train operation performance through the information entropy theory, and realizes the status evaluation of the operation performance of each key component of the train (such as braking system, pantograph, low-voltage electrical appliance, traction motor, running gear, etc.).

[0236] Based on the method provided by the embodiment of the present invention, quantitative evaluation rules can be established for train operation data to achieve quantitative analysis of train operation performance. The dynamic changes of operation data can be captured in advance, providing prior knowledge for fault diagnosis, and providing a data analysis basis for forming a rapid response mechanism for early detection, early isolation, and early treatment. It can provide strong data support for the establishment of a train performance evaluation system and lay a solid foundation for intelligent railway operation.

[0237] and Figure 1 Corresponding to the train performance evaluation method shown in FIG. 1 , an embodiment of the present invention further provides a train performance evaluation device for evaluating Figure 1 The specific implementation of the method shown in is shown in the structural diagram Figure 5 As shown, including:

[0238] A first determining unit 201 is used to determine the real-time operating information corresponding to each preset evaluation object according to the current operating information of the target train when receiving the current operating information of the target train in the running state, wherein the current operating information of the target train includes signal data collected by each onboard sensor of the target train in the current operating state;

[0239] A first acquisition unit 202 is used to acquire the historical route operation information of the target train, and determine the historical operation information corresponding to each of the preset evaluation objects according to the historical route operation information;

[0240] The second acquisition unit 203 is used to acquire current operation information of multiple running trains, where the running trains are trains other than the target train that are currently in a running state, and the current operation information of each running train includes signal data collected by each onboard sensor of the running train in the current running state;

[0241] A second determining unit 204 is used to determine the train running information of the same period corresponding to each of the preset evaluation objects according to the current running information of the multiple running trains;

[0242] The third determining unit 205 is used to determine, for each of the preset evaluation objects, a comprehensive performance index value corresponding to the preset evaluation object according to the real-time operation information, historical operation information and train operation information of the same period corresponding to the preset evaluation object;

[0243] The evaluation unit 206 is used to determine the performance status corresponding to each of the preset evaluation objects according to the comprehensive performance index value corresponding to each of the preset evaluation objects, so as to realize the performance evaluation of the target train.

[0244] Based on the device provided by the embodiment of the present invention, the real-time operation information, historical operation information and train operation information of the same period corresponding to each preset evaluation object are determined according to the current operation information of the target train, the historical route operation information and the current operation information of each running train. For each preset evaluation object, the comprehensive performance index value corresponding to the preset evaluation object is determined according to the real-time operation information, historical operation information and train operation information of the same period corresponding to the preset evaluation object; according to the comprehensive performance index value corresponding to each preset evaluation object, the performance state corresponding to each preset evaluation object is determined to perform performance evaluation on the target train. By using the device provided by the embodiment of the present invention, the operation data corresponding to the preset evaluation object under various driving scenarios can be combined to calculate the comprehensive performance index value corresponding to the preset evaluation object, and then determine its corresponding performance state, and characterize the performance evaluation result of the train with the performance state of each preset evaluation object. The train performance can be automatically evaluated according to a unified standard to achieve quantitative evaluation, which is conducive to improving the accuracy of performance evaluation and ensuring the safe and stable operation of the train. Secondly, the accuracy of performance state evaluation can be further improved by applying big data to analyze performance state.

[0245] exist Figure 5 On the basis of the device shown, the device provided by the embodiment of the present invention may further include other units. The specific unit functions can refer to the above-mentioned train performance evaluation method, which will not be described in detail here.

[0246] An embodiment of the present invention further provides a storage medium, which includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the train performance evaluation method as described above.

[0247] The embodiment of the present invention further provides an electronic device, the structural diagram of which is shown in FIG. Figure 6 As shown, it specifically includes a memory 301 and one or more instructions 302, wherein the one or more instructions 302 are stored in the memory 301 and are configured to be executed by one or more processors 303 to perform the following operations:

[0248] When receiving the current running information of the target train in the running state, determining the real-time running information corresponding to each preset evaluation object according to the current running information of the target train, wherein the current running information of the target train includes signal data collected by each onboard sensor of the target train in the current running state;

[0249] Acquire historical route operation information of the target train, and determine historical operation information corresponding to each of the preset evaluation objects based on the historical route operation information;

[0250] Acquire current running information of multiple running trains, wherein the running trains are trains other than the target train that are currently in a running state, and the current running information of each running train includes signal data collected by each onboard sensor of the running train in the current running state;

[0251] Determining the train operation information of the same period corresponding to each of the preset evaluation objects according to the current operation information of the multiple running trains;

[0252] For each of the preset evaluation objects, determine the comprehensive performance index value corresponding to the preset evaluation object according to the real-time operation information, historical operation information and train operation information of the same period corresponding to the preset evaluation object;

[0253] According to the comprehensive performance index value corresponding to each of the preset evaluation objects, the performance status corresponding to each of the preset evaluation objects is determined to achieve performance evaluation of the target train.

[0254] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work.

[0255] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0256] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A train performance evaluation method, characterized in that: include: When receiving the current running information of the target train in the running state, determining the real-time running information corresponding to each preset evaluation object according to the current running information of the target train, wherein the current running information of the target train includes signal data collected by each onboard sensor of the target train in the current running state; Acquire historical route operation information of the target train, and determine historical operation information corresponding to each of the preset evaluation objects based on the historical route operation information; Acquire current running information of multiple running trains, wherein the running trains are trains other than the target train that are currently in a running state, and the current running information of each running train includes signal data collected by each onboard sensor of the running train in the current running state; Determining the train operation information of the same period corresponding to each of the preset evaluation objects according to the current operation information of the multiple running trains; For each of the preset evaluation objects, determine the comprehensive performance index value corresponding to the preset evaluation object according to the real-time operation information, historical operation information and train operation information of the same period corresponding to the preset evaluation object; According to the comprehensive performance index value corresponding to each of the preset evaluation objects, the performance status corresponding to each of the preset evaluation objects is determined to achieve performance evaluation of the target train.

2. The method according to claim 1, characterized in that Determining the comprehensive performance index value corresponding to the preset evaluation object according to the real-time operation information, historical operation information and train operation information of the same period corresponding to the preset evaluation object includes: Determine a performance indicator set corresponding to the preset evaluation object, wherein the performance indicator set includes at least one preset performance indicator; For each of the preset performance indicators in the performance indicator set, determine a first deviation degree value and a second deviation degree value corresponding to the preset performance indicator according to the real-time operation information, historical operation information and train operation information of the same period corresponding to the preset evaluation object, and determine the performance indicator value corresponding to the preset performance indicator according to the first deviation degree value and the second deviation degree value; According to the performance indicator value corresponding to each of the preset performance indicators in the performance indicator set, the comprehensive performance indicator value corresponding to the preset evaluation object is determined.

3. The method according to claim 2, characterized in that The determining of the first deviation degree value corresponding to the preset performance indicator includes: Determine, based on the operation data information of multiple historical routes contained in the historical operation information corresponding to the preset evaluation object, multiple groups of historical operation data corresponding to the preset performance indicator, wherein the multiple groups of historical operation data correspond to the multiple historical routes one by one; According to the preset multiple statistical features, statistical calculation is performed on each group of the historical operation data to obtain a statistical quantity set corresponding to each group of the historical operation data, wherein the statistical quantity set corresponding to each group of the historical operation data includes a statistical value of the historical data corresponding to each statistical feature; Determining a first historical deviation value according to a set of statistics corresponding to each group of the historical operation data; Determine the real-time operating data corresponding to the preset performance indicator according to the real-time operating information corresponding to the preset evaluation object; According to the multiple statistical features, statistical calculation is performed on the real-time operation data to obtain a set of statistics corresponding to the real-time operation data, wherein the set of statistics corresponding to the real-time operation data includes a real-time data statistical value corresponding to each of the statistical features; Determining a second historical deviation value according to a set of statistics corresponding to each group of the historical operation data and a set of statistics corresponding to the real-time operation data; A first deviation degree value corresponding to the preset performance indicator is determined according to the first historical deviation value and the second historical deviation value.

4. The method according to claim 3, characterized in that The determining of the first historical deviation value according to the statistical quantity set corresponding to each group of the historical operation data includes: Determine the historical sample standard deviation and the historical sample average corresponding to each statistical feature according to the statistical quantity set corresponding to each group of the historical operation data; Determine the historical deviation characteristic value corresponding to each of the statistical features according to the historical sample standard deviation and the historical sample average value corresponding to each of the statistical features; A first arithmetic mean is calculated, and the first arithmetic mean is used as the first historical deviation value, where the first arithmetic mean is the arithmetic mean corresponding to each of the historical deviation characteristic values.

5. The method according to claim 3, characterized in that: The determining of the second historical deviation value according to the statistical set corresponding to each group of the historical operation data and the statistical set corresponding to the real-time operation data includes: Determining, in each group of the historical operation data, historical operation data to be replaced and a plurality of target historical operation data, wherein the target historical operation data is the historical operation data in each group of the historical operation data except the historical operation data to be replaced; Determine the real-time sample standard deviation and the real-time sample average corresponding to each of the statistical features according to the statistical set corresponding to each group of the target historical operation data and the statistical set corresponding to the real-time operation data; Determine the real-time offset characteristic value corresponding to each of the statistical features according to the real-time sample standard deviation and the real-time sample average value corresponding to each of the statistical features; A second arithmetic mean is calculated, and the second arithmetic mean is used as the second historical deviation value, where the second arithmetic mean is the arithmetic mean corresponding to each of the real-time offset characteristic values.

6. The method according to claim 3, characterized in that Determining a first deviation degree value corresponding to the preset performance indicator according to the first historical deviation value and the second historical deviation value includes: A difference operation is performed on the second historical deviation value and the first historical deviation value, and the operation result is used as the first deviation degree value corresponding to the preset performance indicator.

7. The method according to claim 3, characterized in that The determining of the second deviation degree value corresponding to the preset performance indicator includes: Determine, based on the operation data information of each running train contained in the train operation information of the same period corresponding to the preset evaluation object, multiple sets of train operation data corresponding to the preset performance index, wherein the multiple sets of train operation data correspond to each running train one by one; According to the multiple statistical features, statistical calculation is performed on each group of the train operation data to obtain a set of statistics corresponding to each group of the train operation data, wherein the set of statistics corresponding to each group of the train operation data includes a train data statistical value corresponding to each statistical feature; Determining a first real-time deviation value according to a set of statistics corresponding to each group of train operation data; Determining a second real-time deviation value according to a set of statistics corresponding to each group of the train operation data and a set of statistics corresponding to the real-time operation data; A second deviation degree value corresponding to the preset performance indicator is determined according to the first real-time deviation value and the second real-time deviation value.

8. The method according to claim 2, characterized in that: Determining the performance indicator value corresponding to the preset performance indicator according to the first deviation degree value and the second deviation degree value includes: Performing a product operation on the first deviation degree value and the first preset weight to obtain a first product; Performing a product operation on the second deviation degree value and the second preset weight to obtain a second product; A sum operation is performed on the first product and the second product, and a result of the operation is used as a performance indicator value corresponding to the preset performance indicator.

9. The method according to claim 2, characterized in that: Determining the comprehensive performance indicator value corresponding to the preset evaluation object according to the performance indicator value corresponding to each of the preset performance indicators in the performance indicator set includes: Determining whether the performance indicator set includes only one preset performance indicator; If the performance indicator set does not include only one preset performance indicator, determining an indicator weight corresponding to each of the preset performance indicators; According to the indicator weight corresponding to each of the preset performance indicators, a weighted sum operation is performed on the performance indicator values ​​corresponding to each of the preset performance indicators, and the operation result is used as the comprehensive performance indicator value corresponding to the preset evaluation object.

10. The method according to claim 9, characterized in that The determining of the indicator weight corresponding to each of the preset performance indicators includes: Determine the information entropy corresponding to each of the preset performance indicators according to the performance indicator values ​​corresponding to each of the preset performance indicators; According to the information entropy corresponding to each of the preset performance indicators, the indicator weight corresponding to each of the preset performance indicators is calculated.

11. The method according to claim 9, characterized in that Also includes: If the performance indicator set includes only one preset performance indicator, the performance indicator value corresponding to the preset performance indicator in the performance indicator set is used as the comprehensive performance indicator value corresponding to the preset evaluation object.

12. The method according to claim 1, characterized in that Determining the performance status corresponding to each preset evaluation object according to the comprehensive performance indicator value corresponding to each preset evaluation object includes: For each of the preset evaluation objects, determining a plurality of indicator value intervals corresponding to the preset evaluation object, wherein the plurality of indicator value intervals correspond one-to-one to a plurality of preset performance states corresponding to the preset evaluation object; For each comprehensive performance index value corresponding to the preset evaluation object, the comprehensive performance index value is matched with each index value interval corresponding to the preset evaluation object, the index value interval matching the comprehensive performance index value is determined as the target index value interval, and the preset performance state corresponding to the target index value interval is determined as the performance state corresponding to the preset evaluation object.

13. A train performance evaluation device, characterized in that: include: A first determining unit is used to determine the real-time operating information corresponding to each preset evaluation object according to the current operating information of the target train when receiving the current operating information of the target train in a running state, wherein the current operating information of the target train includes signal data collected by each onboard sensor of the target train in a current operating state; A first acquisition unit is used to acquire the historical route operation information of the target train, and determine the historical operation information corresponding to each of the preset evaluation objects according to the historical route operation information; A second acquisition unit is used to acquire current operation information of multiple running trains, wherein the running trains are trains other than the target train that are currently in a running state, and the current operation information of each running train includes signal data collected by each onboard sensor of the running train in the current running state; A second determining unit is used to determine the train running information of the same period corresponding to each of the preset evaluation objects according to the current running information of the multiple running trains; A third determination unit is used to determine, for each of the preset evaluation objects, a comprehensive performance index value corresponding to the preset evaluation object according to the real-time operation information, historical operation information and train operation information of the same period corresponding to the preset evaluation object; The evaluation unit is used to determine the performance status corresponding to each preset evaluation object according to the comprehensive performance index value corresponding to each preset evaluation object, so as to realize the performance evaluation of the target train.

14. A storage medium, characterized in that: The storage medium includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the train performance evaluation method according to any one of claims 1 to 12.

15. An electronic device, characterized in that: The system comprises a memory and one or more instructions, wherein the one or more instructions are stored in the memory and configured to be executed by one or more processors to perform the train performance evaluation method according to any one of claims 1 to 12.

Images