Shunting locomotive working condition model construction method and device, program product and electronic equipment

Abstract

The invention provides a shunting locomotive working condition model construction method and device, a program product and electronic equipment, and relates to the technical field of rail transit. The method comprises the following steps: determining operation data of various traction working conditions of the shunting locomotive of which the working conditions are to be constructed; performing the following operations on the operation data of each type of traction working conditions: dividing the operation data into a plurality of driving units, and performing clustering processing on the plurality of driving units to obtain at least one driving unit set, each driving unit set corresponding to one type of driving working conditions; and constructing a working condition model of the shunting locomotive according to the at least one driving unit set corresponding to each type of traction working condition. According to the method and the device, the actual working condition of the shunting locomotive can be accurately reflected through the working condition model constructed by processing the operation data of the various traction working conditions of the shunting locomotive, so that the working condition model with relatively high precision is obtained, and the evaluation accuracy of the working condition of the shunting locomotive is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of rail transit technology, and in particular to a method, device, program product and electronic equipment for constructing a shunting locomotive operating condition model. Background Art

[0002] A shunting locomotive is a locomotive used for marshaling and dismantling operations at marshaling yards or shunting yards. Since the number of freight cars and load weights pulled by shunting locomotives vary when performing different operations, their operating conditions are highly complex and diverse. The operating conditions of shunting locomotives are important basic standards for locomotive endurance, energy consumption evaluation and durability assessment, and are also important design inputs in the development of locomotive power systems.

[0003] Therefore, how to construct a driving condition curve that can reflect the actual operating characteristics of the shunting locomotive has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] The present disclosure provides a method for constructing a shunting locomotive operating condition model, a shunting locomotive operating condition model construction device, a computer program product and an electronic device, so as to at least to some extent solve the problem of constructing a driving condition curve that can reflect the actual operating characteristics of a shunting locomotive.

[0005] According to a first aspect of the present disclosure, a method for constructing a shunting locomotive operating condition model is provided, the method comprising:

[0006] Determine the operation data of multiple types of traction working conditions of the shunting locomotive for which the working condition model is to be constructed;

[0007] For each type of the operating data of the traction working condition, the following operations are performed respectively: the operating data is divided into a plurality of driving units, and the plurality of driving units are clustered to obtain at least one driving unit set, each of the driving unit sets corresponding to a type of driving working condition;

[0008] According to the obtained at least one travel unit set corresponding to each type of traction operating condition, a working condition model of the shunting locomotive is constructed.

[0009] In one embodiment, determining the operating data of multiple types of traction operating conditions of a shunting locomotive for which an operating condition model is to be constructed includes:

[0010] Performing data preprocessing on the original operating data of each type of traction working condition to obtain operating data corresponding to each type of traction working condition;

[0011] The data preprocessing includes at least one of missing data processing, abnormal data processing, and filtered data processing.

[0012] In one embodiment, for each type of the operating data of the traction condition, the following operations are performed respectively: the operating data is divided into a plurality of driving units, and the plurality of driving units are clustered to obtain at least one driving unit set, including:

[0013] Determining M characteristic parameters for describing each of the travel units according to the processed operating data;

[0014] Performing principal component analysis on the M characteristic parameters of the plurality of driving units to obtain N principal component characteristic parameters for describing each of the driving units; wherein M and N are positive integers, and M is greater than N;

[0015] The plurality of driving units are clustered according to the N principal component characteristic parameters to obtain at least one driving unit set.

[0016] In one embodiment, constructing the operating condition model of the shunting locomotive according to the obtained at least one travel unit set corresponding to each type of the traction operating condition includes:

[0017] Constructing a working condition curve corresponding to each type of the traction working condition according to the obtained at least one driving unit set corresponding to each type of the traction working condition;

[0018] According to the operating condition curve corresponding to each type of traction operating condition, an operating condition model of the shunting locomotive is constructed.

[0019] In one embodiment, constructing a working condition curve corresponding to each type of the traction working condition according to the obtained at least one driving unit set corresponding to each type of the traction working condition includes:

[0020] Determine the duration of each driving unit set in the plurality of driving unit sets corresponding to each type of the traction working condition;

[0021] According to the duration of each driving unit set and the operating condition curve corresponding to each driving unit set, a working condition model corresponding to each type of traction working condition is constructed.

[0022] In one embodiment, constructing the operating condition model of the shunting locomotive according to the operating condition curve corresponding to each type of the traction operating condition includes:

[0023] Determining the duration of each type of traction condition;

[0024] According to the duration of each type of traction working condition and the corresponding working condition curve, a working condition model of the shunting locomotive is constructed.

[0025] In one embodiment, the operating data of the multiple types of traction conditions include: the condition where the shunting locomotive is not pulling a freight car, the condition where the shunting locomotive is pulling a freight car and the load is within a first preset range, and the condition where the shunting locomotive is pulling a freight car and the load is within a second preset range; the upper limit value within the first preset range is not greater than the lower limit value within the second preset range.

[0026] According to a second aspect of the present disclosure, a device for constructing a shunting locomotive operating condition model is provided, the device comprising:

[0027] A determination unit, used to determine the operation data of multiple types of traction conditions of the shunting locomotive of the working condition to be constructed;

[0028] A processing unit, for performing the following operations on the operating data of each type of traction working condition: dividing the operating data into a plurality of driving units, and performing clustering processing on the plurality of driving units to obtain at least one driving unit set, each of the driving unit sets corresponding to a type of driving working condition;

[0029] A construction unit is used to construct a working condition model of the shunting locomotive according to the at least one travel unit set corresponding to each type of traction working condition obtained.

[0030] In one implementation, the determining unit is configured to:

[0031] Performing data preprocessing on the original operating data of each type of traction working condition to obtain operating data corresponding to each type of traction working condition;

[0032] The data preprocessing includes at least one of missing data processing, abnormal data processing, and filtered data processing.

[0033] In one embodiment, the processing unit is used to:

[0034] Determining M characteristic parameters for describing each of the travel units according to the processed operating data;

[0035] Performing principal component analysis on the M characteristic parameters of the plurality of driving units to obtain N principal component characteristic parameters for describing each of the driving units; wherein M and N are positive integers, and M is greater than N;

[0036] The plurality of driving units are clustered according to the N principal component characteristic parameters to obtain at least one driving unit set.

[0037] In one embodiment, the building block is used to:

[0038] Constructing a working condition curve corresponding to each type of the traction working condition according to the obtained at least one driving unit set corresponding to each type of the traction working condition;

[0039] According to the operating condition curve corresponding to each type of traction operating condition, an operating condition model of the shunting locomotive is constructed.

[0040] In one embodiment, the building block is used to:

[0041] Determine the duration of each driving unit set in the plurality of driving unit sets corresponding to each type of the traction working condition;

[0042] According to the duration of each driving unit set and the operating condition curve corresponding to each driving unit set, a working condition model corresponding to each type of traction working condition is constructed.

[0043] In one embodiment, the building block is used to:

[0044] Determining the duration of each type of traction condition;

[0045] According to the duration of each type of traction working condition and the corresponding working condition curve, the working condition model of the shunting locomotive is constructed.

[0046] In one embodiment, the operating data of the multiple types of traction conditions include: the condition where the shunting locomotive is not pulling a freight car, the condition where the shunting locomotive is pulling a freight car and the load is within a first preset range, and the condition where the shunting locomotive is pulling a freight car and the load is within a second preset range; the upper limit value within the first preset range is not greater than the lower limit value within the second preset range.

[0047] According to a third aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the method of the first aspect and possible implementations thereof are implemented.

[0048] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the method of the above-mentioned first aspect and its possible implementation methods by executing the executable instructions.

[0049] The technical solution disclosed in this disclosure has the following beneficial effects:

[0050] In the embodiment of the present disclosure, the operating data of multiple types of traction conditions of the shunting locomotive for the working condition to be constructed can be determined; for the operating data of each type of traction condition, the following operations are performed respectively: the operating data is divided into multiple driving units, and the multiple driving units are clustered to obtain at least one driving unit set, each driving unit set corresponds to a type of driving condition; according to the obtained at least one driving unit set corresponding to each type of traction condition, a working condition model of the shunting locomotive is constructed. The working condition model constructed by processing the operating data of multiple types of traction conditions of the shunting locomotive in the present disclosure can more accurately reflect the actual working condition of the shunting locomotive, thereby obtaining a working condition model with higher accuracy, and further improving the accuracy of the evaluation of the working condition of the shunting locomotive.

[0051] Other features and advantages of the present disclosure will be described in the following description, and partly become apparent from the description, or be understood by practicing the present disclosure. The purpose and other advantages of the present disclosure can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the embodiments of the present disclosure will be briefly introduced below. Obviously, the drawings introduced below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 A schematic diagram of an application scenario in this exemplary embodiment is shown;

[0054] Figure 2 A system architecture diagram in this exemplary embodiment is shown;

[0055] Figure 3 A flow chart showing a method for constructing a shunting locomotive operating condition model in this exemplary embodiment;

[0056] Figure 4 A schematic diagram showing a kind of original operation data in the present exemplary embodiment;

[0057] Figure 5A A schematic diagram showing another type of original operation data in this exemplary embodiment;

[0058] Figure 5B A schematic diagram showing operation data after another type of original operation data is compressed in this exemplary embodiment;

[0059] Fig. 6A A schematic diagram showing another type of original operation data in this exemplary embodiment;

[0060] Figure 6B A schematic diagram showing operation data after removing idle data from another type of original operation data in this example embodiment;

[0061] Figure 7 A comparison schematic diagram of processing noise data in this example implementation is shown;

[0062] Figure 8 A schematic diagram showing a division of the travel unit in this example implementation mode is shown;

[0063] Fig. 9 A flowchart showing a method of dividing a travel unit in this example implementation is shown;

[0064] Fig.10 A schematic diagram showing the mean and standard deviation of the silhouette coefficients for different numbers of clusters under a type of traction conditions in this example implementation;

[0065] Fig.11 A schematic diagram showing the clustering effect of the travel units in a type of traction condition in this example implementation mode;

[0066] Fig.12 A schematic diagram showing a working condition model of a travel unit in a type of traction working condition in this example implementation manner;

[0067] Fig.13 A schematic diagram showing a working condition model of a type of traction working condition in this example implementation mode;

[0068] Fig.14 A schematic diagram showing an operating condition model of another type of traction operating condition in this example embodiment;

[0069] Fig.15 A schematic structural diagram of a shunting locomotive operating condition model building device in this exemplary embodiment is shown;

[0070] Fig.16 A schematic structural diagram of an electronic device in this exemplary embodiment is shown. DETAILED DESCRIPTION

[0071] In order to make the purpose, technical solutions and advantages of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present disclosure. In the absence of conflict, the embodiments in the present disclosure and the features in the embodiments can be arbitrarily combined with each other. In addition, although the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in an order different from that here.

[0072] The term "comprising" and any variations thereof in the specification and claims of the present disclosure are intended to cover non-exclusive protection. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.

[0073] In the embodiments of the present disclosure, one or more, "many" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or plural.

[0074] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order, sequence, size and priority. For example, the first driving unit set and the second driving unit set in the embodiment of the present disclosure are only used to distinguish different driving unit sets. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0075] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, which are schematic diagrams of the present disclosure and are not necessarily drawn to scale. Some of the block diagrams shown in the accompanying drawings may be functional entities, which do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in hardware modules or integrated circuits, or in networks, processors or microcontrollers. The implementation method can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein. The features, structures or characteristics described in the present disclosure may be combined in one or more implementations in any suitable manner. In the following description, many specific details are provided to provide a full description of the implementation methods of the present disclosure. However, those skilled in the art should be aware that one or more specific details may be omitted when implementing the technical solution of the present disclosure, or one or more specific details may be replaced by other methods, components, devices, steps, etc.

[0076] It should be noted that in the embodiments of the present disclosure, some existing solutions in the industry such as software, components, models, etc. may be mentioned, which should be considered as exemplary, and their purpose is only to illustrate the feasibility of implementing the technical solution of the present disclosure, but it does not mean that the applicant has or will necessarily use the solution. In the technical solution of the present disclosure, the collection, dissemination, and use of casting data are in compliance with relevant national laws and regulations.

[0077] In the relevant technology, the shunting locomotive undertakes the key tasks of shunting locomotive formation, adjustment and parking in the station, and its operating characteristics are characterized by frequent starts and stops and variable operating conditions. Since the number of freight cars and load weights pulled by the shunting locomotives when performing different operations are different, its operating conditions are highly complex and diverse. In the process of locomotive system design and energy management strategy optimization, it is crucial to construct a set of typical driving condition models that can accurately reflect the actual operating characteristics of the locomotive. The typical operating conditions of the locomotive are an important basic standard for locomotive endurance, energy consumption evaluation and durability assessment, and are also an important design input in the development of the locomotive power system. The accuracy of the construction of typical operating conditions has a decisive influence on ensuring the rationality of the system design and the effectiveness of the energy management strategy.

[0078] The current solution is based on the standard operating curve, which uses the standard operating curve to manage the energy and evaluate the performance of shunting locomotives. However, this method has the following disadvantages: (1) It cannot accurately reflect the actual driving characteristics: The standard operating curve usually cannot reflect the actual driving characteristics of different regions and lines, resulting in differences between design parameters and actual applications. (2) Poor applicability: Due to the different driving conditions of different lines, a single standard operating curve is difficult to meet the diverse actual needs.

[0079] In view of one or more of the above problems, an exemplary embodiment of the present disclosure provides a method for constructing a shunting locomotive operating condition model, through which the operating data of multiple types of traction conditions of a shunting locomotive whose operating condition is to be constructed can be determined; for the operating data of each type of traction condition, the following operations are performed respectively: the operating data is divided into multiple driving units, and the multiple driving units are clustered to obtain at least one driving unit set, each driving unit set corresponding to a type of driving condition; based on the obtained at least one driving unit set corresponding to each type of traction condition, a working condition model of the shunting locomotive is constructed. The working condition model constructed by processing the operating data of multiple types of traction conditions of the shunting locomotive in the present disclosure can more accurately reflect the actual working condition of the shunting locomotive, thereby obtaining a working condition model with higher accuracy, thereby improving the accuracy of the evaluation of the working condition of the shunting locomotive.

[0080] In order to better understand the technical solutions provided by the embodiments of the present disclosure, the following briefly introduces the application scenarios to which the technical solutions provided by the embodiments of the present disclosure are applicable. It should be noted that the application scenarios introduced below are only used to illustrate the embodiments of the present disclosure and are not intended to limit the present disclosure. In specific implementation, the technical solutions provided by the embodiments of the present disclosure can be flexibly applied according to actual needs.

[0081] See also Figure 1 As shown, Figure 1 This is an application scenario to which the technical solution of the embodiment of the present disclosure can be applied. In the scenario diagram, multiple acquisition devices 101 and electronic devices 102 are included. Among them, acquisition device 101-1, acquisition device 101-2, ..., acquisition device 101-n can be used by different users, and n is a positive integer, so that the driving condition data of different shunting locomotives can be collected, or the driving condition data of shunting locomotives with different traction conditions can be collected, or the driving condition data of shunting locomotives in different regions can be collected.

[0082] It can be seen that in the embodiments of the present disclosure, multiple acquisition devices 101 can be set on the same line in the same area to collect driving condition data of the shunting locomotive on the line under different traction conditions; multiple acquisition devices can also be set on different lines in different areas to collect driving condition data of different shunting locomotives under different traction conditions, which is not limited in the embodiments of the present disclosure. For example, if it is necessary to construct a working condition model for shunting locomotive 1, all acquisition devices 101 can be set to collect relevant driving conditions of shunting locomotive 1; if it is necessary to construct working condition models for multiple shunting locomotives, all acquisition devices 101 can be set to collect relevant driving conditions of multiple shunting locomotives.

[0083] Optionally, the collection device 101 is, for example, any electronic device that supports collecting driving condition data, which is not limited in the embodiments of the present disclosure. The collection device 101 and the electronic device 102, as well as each collection device 101, can be directly or indirectly connected to each other through one or more networks 103.

[0084] In the disclosed embodiment, a user can determine a shunting locomotive for which an operating condition model is to be constructed, and control the acquisition device 101 to collect operating data of multiple types of traction conditions of the locomotive, so that the acquisition device 101 can send the collected operating data of multiple types of traction conditions to the electronic device 102, and the electronic device 102 can perform the following operations on the operating data of each type of traction condition: divide the operating data into multiple driving units, and cluster the multiple driving units to obtain at least one driving unit set, each driving unit set corresponding to a type of driving condition; and construct the operating condition model of the shunting locomotive based on the at least one driving unit set corresponding to each type of traction condition obtained.

[0085] in, Figure 1 The electronic device 102 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It may also be a cloud server or cloud server cluster that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), as well as big data and artificial intelligence platforms, but is not limited to these.

[0086] Of course, the method provided in the embodiment of the present disclosure is not limited to Figure 1 The application scenario shown can also be used in other possible application scenarios, such as an application scenario of a method for constructing a shunting locomotive operating condition model that is implemented only by electronic equipment, and the embodiments of the present disclosure are not limited thereto.

[0087] See also Figure 2 As shown, Figure 2 The system architecture diagram of the operating environment of this exemplary embodiment is shown. The system architecture may include a collection device 201 and a server 202. The collection device 201 includes a collection unit 2011. The server 202 includes a raw data preprocessing unit 2021, a unit division and parameter calculation unit 2022, a driving unit clustering analysis unit 2023, and a typical working condition synthesis and verification unit 2024.

[0088] In the disclosed embodiment, the raw data preprocessing unit 2021 is used to receive the raw operating data collected by the acquisition unit 2011 included in the acquisition device 201 from the actual shunting locomotive test. These raw operating data will serve as the basis for subsequent working condition analysis and research. This step is the starting point for building the working condition model. Since the acquisition unit 2011 included in the acquisition device 201 is the raw operating data collected from the actual shunting locomotive test, the authenticity and reliability of the data are ensured. Furthermore, the raw data preprocessing unit 2021 performs necessary data cleaning and preprocessing on the received raw operating data. Preprocessing includes eliminating abnormal data generated during driving due to equipment failure or other reasons, and reasonably completing the missing values ​​in the raw operating data, so as to create a complete historical driving condition database.

[0089] In the disclosed embodiment, the raw data preprocessing unit 2021 can also classify the traction condition in the driving condition database. Specifically, the classification of the traction condition depends on the key information collected by the locomotive during the actual operation, including but not limited to the number and load weight of the traction trucks, so as to classify and confirm the locomotive condition.

[0090] In one implementation, according to the operating characteristics of the shunting locomotive, the number and load of the freight cars pulled during each operation are different. Based on the actual daily operation report of the shunting locomotive, the working condition data of the locomotive can be finely divided into the following three categories:

[0091] (1) Single-unit operating condition: refers to the condition in which the shunting locomotive operates alone without towing any freight cars.

[0092] (2) Low load condition: refers to the condition where a shunting locomotive is pulling a number of freight cars, but the total traction tonnage does not exceed 2,000 tons.

[0093] (3) High load condition: refers to the condition where a shunting locomotive is pulling freight cars and the total traction tonnage exceeds 2,000 tons.

[0094] Through the above classification method, the locomotive operating condition data is divided in detail, and the specific division results are shown in Table 1.

[0095]

[0096] Table 1

[0097] In the disclosed embodiment, the unit division and parameter calculation unit 2022 can use the definition of the driving unit to perform detailed division of the pre-processed operating condition data, i.e., the historical driving condition database, so as to establish a driving unit library of driving conditions. On the basis of the driving unit library, a certain number of key characteristic parameters are selected, which can accurately describe the driving laws of each driving unit. By calculating these characteristic parameters, the dynamic characteristics of each driving unit can be more deeply understood. In addition, considering that the operating condition characteristic parameter data is usually high-dimensional, in order to reduce the calculation complexity and reduce the impact of redundant information on the operating condition construction, it is necessary to effectively reduce the dimensionality of the original characteristic parameters.

[0098] In the disclosed embodiment, the driving unit clustering analysis unit 2023 can cluster the driving units based on the feature parameters after dimensionality reduction, and can also evaluate the clustering results by calculating the silhouette coefficient of each unit, thereby determining the appropriate number of working condition categories and building a candidate driving unit library.

[0099] In the disclosed embodiment, the typical operating condition synthesis and verification unit 2024 can combine and splice the driving units obtained by cluster analysis to construct a working condition model based on the actual shunting locomotive driving data. In addition, the constructed working condition model needs to be verified for validity to ensure that the working condition model can truly reflect the actual driving characteristics of the shunting locomotive.

[0100] To further illustrate the technical solution provided by the embodiments of the present disclosure, this is described in detail below in conjunction with the accompanying drawings and specific implementation methods. Although the embodiments of the present disclosure provide method operation steps as shown in the following embodiments or drawings, more or fewer operation steps may be included in the method based on routine or no creative labor. In the steps where there is no necessary causal relationship logically, the execution order of these steps is not limited to the execution order provided by the embodiments of the present disclosure. The method may be executed in the order of the method shown in the embodiments or drawings or in parallel during the actual processing process or when the device is executed.

[0101] See also Figure 3 , Figure 3 FIG. 1 is a flow chart of a method for constructing a shunting locomotive operating condition model in an embodiment of the present disclosure. The method flow chart may be executed by an electronic device, for example, and the electronic device may be Figure 1 The electronic device 102 or Figure 2 The specific implementation process of the method is as follows:

[0102] Step 301: Determine the operating data of multiple types of traction operating conditions of a shunting locomotive for which an operating condition model is to be constructed.

[0103] In the embodiment of the present disclosure, the electronic device can determine the operating data of multiple types of traction working conditions of the shunting locomotive for which the working condition model is to be constructed. The operating data of multiple types of traction working conditions of the shunting locomotive can be the original operating data obtained by directly classifying the traction working conditions after the acquisition device collects the data, or it can be the operating data obtained after the acquisition device collects the data and pre-classifies the data and classifies the traction working conditions, which is not limited in the embodiment of the present disclosure.

[0104] In an embodiment of the present disclosure, the electronic device can perform data preprocessing on the original operating data of each type of traction condition to obtain processed operating data corresponding to each type of traction condition; wherein the data preprocessing includes: at least one of missing data processing, abnormal data processing, and filtered data processing.

[0105] In the disclosed embodiment, the electronic device can obtain the original operation data of the shunting locomotive for which the working condition model is to be constructed, which is sent by the acquisition device. Optionally, the acquisition frequency of the original operation data is 50 Hz. The data size is 1.35 GB. For example, see Figure 4 , Figure 4 The schematic diagram of part of the original operation data is shown as an exemplary embodiment of the present disclosure, wherein the horizontal axis in the figure is time, and the vertical axis is the shunting locomotive speed of the shunting locomotive.

[0106] In the embodiment of the present disclosure, in view of the huge amount of original data, the original operation data can be compressed and merged in the embodiment of the present disclosure to reduce the amount of data for subsequent analysis and processing. Optionally, the original operation data can be compressed and merged by adopting the mean method, for example, see Figure 5A and Figure 5B ,exist Figure 5B In this paper, the average speed of shunting locomotives per second is calculated to reduce the size of the data while maintaining the integrity and accuracy of the data.

[0107] In the disclosed embodiment, it is considered that in the process of collecting the original operation data, since the collection equipment starts to record in real time from the power-on, the driving process of the shunting locomotive on the real route is a typical non-stationary random process. This process is affected by many factors, including but not limited to the driver's operating behavior, the measurement accuracy of the on-board sensor, the accuracy of the data collection equipment, and the sudden situation of the route traffic, etc., which inevitably leads to the collected original operation data containing some invalid or bad data information. These data information include but are not limited to long-term parking state, too long idling time, abnormal fluctuations in low-speed section speed, and frequent sudden changes in speed. The existence of these bad data seriously affects the quality of the data and the accuracy of the subsequent construction of the working condition model of the shunting locomotive. Therefore, it is necessary to pre-process these original operation data to ensure the reliability and validity of the data.

[0108] In one embodiment, considering that signal loss may occur from time to time due to technical limitations during data collection, this is manifested as temporal discontinuity in the recording of the original operation data. To address this problem, the embodiments of the present disclosure may adopt but are not limited to the following two processing strategies:

[0109] The first processing strategy: When the data is missing for too long, the traditional interpolation method cannot accurately reflect the actual driving conditions due to the large amount of missing data. Therefore, all recorded data of the vehicle during this period is eliminated.

[0110] Optionally, a first threshold may be set, and based on the first threshold, it is determined whether the data missing time is too long or too short. The threshold may be, for example, 3 seconds or 5 seconds, etc., which is not limited in the embodiments of the present disclosure.

[0111] For example, assuming that the first threshold is 5 seconds and the missing time is 6 seconds, data within 1 minute including the data will be deleted.

[0112] The second processing strategy: When the data missing time is short, that is, does not exceed the set threshold of the data missing time, the Lagrange interpolation method is used to fill in the missing data to ensure the continuity and integrity of the data.

[0113] In one embodiment, in order to handle abnormal acceleration data or deceleration data, the second threshold and the third threshold can be set based on the actual implementation of the corresponding settings in the embodiment of the present disclosure. Among them, the second threshold is the threshold corresponding to the acceleration, the third threshold is the threshold corresponding to the deceleration, and the second threshold and the third threshold can be set based on the actual implementation. Specifically, for data exceeding the second threshold and the third threshold, it can be corrected based on the second threshold and the third threshold, and adjusted to the maximum acceleration of the shunting locomotive under normal driving conditions and the maximum deceleration during braking, so as to ensure the rationality and accuracy of the data.

[0114] In one embodiment, when the shunting locomotive stops or runs at a low speed for a long time, the data collected by the collection device is called idle data. In order to effectively process these idle data, the maximum idle time can be set in the embodiment of the present disclosure, for example, the maximum idle time is set to 180 seconds. If the idle time in the collected original running data exceeds this maximum idle time, the idle data of this section is deleted. For example, see Fig. 6A and Figure 6B ,Obviously, the amount of data after processing the idle data is reduced by an order of magnitude.

[0115] In one embodiment, considering that the data may fluctuate due to the collection equipment, railway traffic conditions, and the vibration of the vehicle itself, the original operation data may contain noise interference, usually including high-frequency noise and impulse noise. Therefore, it is necessary to filter and reduce the noise of the original operation data. In the embodiment of the present disclosure, a sliding recursive filtering algorithm is used to filter the collected operating condition data. For example, see Figure 7 , Figure 7 This is a comparative schematic diagram of processing noise data in an embodiment of the present disclosure. Obviously, there are some peaks in the original data before filtering, and the data obtained after filtering, transformation and noise reduction is smoother.

[0116] Optionally, in order to avoid data distortion caused by noise filtering of the original operating data, a data error evaluation method may be used in the embodiment of the present disclosure to perform error analysis on the denoised data, thereby determining whether the noise filtered data is distorted.

[0117] For example, the mean absolute error (MAE) and the root mean square error (RSME) can be selected to evaluate the rationality and accuracy of the denoised data. The calculation formula 1 of MAE and the calculation formula 2 of RSME are as follows:

[0118]

[0119] Among them, xi is the denoised running data, and yi is the original running data.

[0120] If the MAE value between the noise-reduced operation data and the original operation data is calculated to be 0.023km / h, and the RSME value is 0.032km / h, and the comparison value is assumed to be 0.30, it can be determined that the error of the operation data before and after noise reduction is small, the noise-reduced operation data can truly reflect the actual working conditions of the shunting locomotive, and the accuracy of the noise-reduced operation data meets the requirements of subsequent working condition analysis and construction.

[0121] In the embodiments of the present disclosure, the electronic device may first perform data preprocessing on the original operating data, and then classify the traction conditions on the preprocessed operating data; or it may first classify the traction conditions on the original operating data, and then perform data preprocessing on each type of traction conditions after classification, which is not limited in the embodiments of the present disclosure.

[0122] In the disclosed embodiment, the operating data of multiple types of traction conditions include: the condition where the shunting locomotive is not pulling a freight car, the condition where the shunting locomotive is pulling a freight car and the load is within a first preset range, and the condition where the shunting locomotive is pulling a freight car and the load is within a second preset range; the upper limit value within the first preset range is not greater than the lower limit value within the second preset range.

[0123] In the embodiment of the present disclosure, the first preset range and the second preset range may be set based on the actual operating conditions of the shunting locomotive, which is not limited in the embodiment of the present disclosure.

[0124] For example, as shown in the above Table 1, the operating condition in which the shunting locomotive is not pulling a freight car can be called a single-machine operating condition, the operating condition in which the shunting locomotive is pulling a freight car and the load is within the first preset range can be called a low-load operating condition, and the operating condition in which the shunting locomotive is pulling a freight car and the load is within the second preset range can be called a high-load operating condition. The upper limit value of the first preset range is, for example, 1999 tons, and the lower limit value of the second preset range is, for example, 2000 tons.

[0125] Step 302: For the operation data of each type of traction condition, perform the following operations respectively: divide the operation data into multiple driving units, and cluster the multiple driving units to obtain at least one driving unit set, each driving unit set corresponding to a type of driving condition.

[0126] In the disclosed embodiment, after the electronic device obtains the operation data of multiple types of traction conditions of the shunting locomotive, it can process the operation data of each type of traction condition. Optionally, the electronic device can determine M characteristic parameters for describing each travel unit based on the operation data; perform principal component analysis on the M characteristic parameters of multiple travel units to obtain N principal component characteristic parameters for describing each travel unit; wherein M and N are positive integers, and M is greater than N; perform clustering on multiple travel units based on the N principal component characteristic parameters to obtain at least one travel unit set.

[0127] In the embodiments of the present disclosure, in order to better introduce the scheme for determining at least one driving unit set corresponding to each type of traction condition provided by the present disclosure, the processing of traction conditions in which a shunting locomotive is not pulling a freight car is taken as an example to introduce the processing of low-load conditions and high-load conditions. The processing of low-load conditions and high-load conditions can be executed accordingly with reference to this process and will not be repeated here.

[0128] In the disclosed embodiment, the running data can be divided into a plurality of driving units with different characteristics. A driving unit consists of an idle segment and a moving segment. For example, see Figure 8 , Figure 8 A schematic diagram of an exemplary division of driving units shown in an embodiment of the present disclosure. Figure 8 Two driving units are shown in the figure. The motion segments are further subdivided into acceleration, constant speed and deceleration processes. In other words, the division of driving units is based on the operating interval of the shunting locomotive from one idle state to the next idle state. Specifically, a complete driving unit can be defined as the vehicle driving process of the shunting locomotive between two adjacent zero speeds.

[0129] In one embodiment, see Fig. 9 , Fig. 9 A flow chart showing the division of a driving unit according to an embodiment of the present disclosure.

[0130] Step 901: Find the first point where the vehicle speed drops to 0, and use the first point as the starting point.

[0131] Step 902: Find a second point where the vehicle speed drops to 0, and take the second point as the end point.

[0132] Among them, the time corresponding to the second point is later than the time corresponding to the first point.

[0133] Step 903: Calculate the segment lengths of the start point and the end point.

[0134] Step 904: Determine whether the length of the segment is within the limit. If the length is not within the limit, execute step 905; if the length is within the limit, execute step 906.

[0135] Step 905: Discard the segment information corresponding to the segment length.

[0136] Step 906: Record the segment information corresponding to the segment length as a driving unit.

[0137] Step 907: Update the end point to the start point corresponding to the next segment information.

[0138] Step 908: Determine whether the termination condition is met. If the termination condition is met, then stop and end this process; if the termination condition is not met, then execute step 902.

[0139] In the embodiments of the present disclosure, the termination condition is, for example, that the end point is the end point of the operation data record, or the end point is the end point of the data quantity corresponding to the traction condition such as the single-machine condition, or other conditions, which are not limited in the embodiments of the present disclosure.

[0140] In the disclosed embodiment, the above division method can divide the entire shunting locomotive travel into multiple independent travel units, and each travel unit has specific motion characteristics. In other words, this division method can decompose the shunting travel process into units that are easy to analyze and manage.

[0141] In the disclosed embodiment, after the electronic device obtains the driving unit, the operating data of each driving unit can be analyzed and processed. Optionally, when performing feature analysis of the driving condition data of the shunting locomotive, in order to comprehensively evaluate the feature differences between different driving units and accurately reflect their travel characteristics, a certain number of feature parameters must be carefully selected. These parameters can describe the driving unit, i.e., the time-speed curve, in detail. Considering that there are many feature parameters describing the motion condition, such as average vehicle speed, working distance, deceleration time ratio, etc., but they each have different meanings, the screened working condition characteristics will also be different. And, although increasing the number of feature parameters can improve the accuracy of the description of the working condition characteristics, there is a certain correlation between the feature parameters. Too many feature parameters will not only lead to information redundancy, but also increase the complexity of statistical analysis. Therefore, it is crucial to select the right number and type of feature parameters. This can not only ensure the accurate description of the working condition characteristics, but also effectively reduce unnecessary calculations, thereby saving time and resources.

[0142] In the embodiment of the present disclosure, 16 characteristic parameters are selected to describe each driving unit, and the specific parameters are shown in Table 2.

[0143] This choice aims to ensure description accuracy while minimizing computational complexity and information redundancy.

[0144]

[0145] Table 2

[0146] In the disclosed embodiment, the above 16 characteristic parameters are calculated for the divided traveling units under the single-machine working condition of the shunting locomotive respectively, and the characteristic parameters of each traveling unit are shown in Table 3.

[0147]

[0148] Table 3

[0149] In the disclosed embodiment, considering the 16 characteristic parameters selected above, if a comprehensive statistical analysis is performed on all characteristic parameters, the problem of too high data dimension will inevitably be faced. Due to the large number of driving units, there may be data redundancy between the characteristic parameters, which will lead to a significant increase in the amount of calculation.

[0150] In view of this, in order to improve the computational efficiency and reduce the dimension of the original operation data, the present invention adopts the screening strategy of principal component analysis (PCA). Through this screening strategy, multiple indicators that may be interrelated can be converted into a few comprehensive indicators through dimensionality reduction technology.

[0151] In one embodiment, it is assumed that there are m indicator variables for principal component analysis and n evaluation objects in total. Where m is the number of characteristic parameters, i.e., m=16; n is the number of extracted driving units, i.e., n=144. Let the value of the jth characteristic parameter of the i-th driving unit be xij, then the matrix X representing the actual operation data is (x ij ) m×n It can be expressed as:

[0152]

[0153] Once you have a matrix representing the actual run data, you can perform the following steps:

[0154] Step (1): Non-dimensionalize the original eigenvalue matrix.

[0155] Specifically, in order to eliminate the impact of dimension on the actual driving condition analysis results, each index value xij is converted into a standardized index Please refer to Formula 3 for details:

[0156]

[0157] In formula three, It can be understood as the sample mean of the jth indicator, which can be determined based on formula 4; s j It can be understood as the standard deviation of the jth indicator, which can be determined based on the following formula 5:

[0158]

[0159] Step (2): Solve the correlation coefficient matrix of the dimensionless eigenvalue matrix.

[0160] Specifically, the correlation coefficient matrix R = +r is needed when performing principal component analysis. ij ) m×m , specifically:

[0161]

[0162] Among them, the correlation coefficient rij between the i-th indicator and the j-th indicator can be determined based on the following formula 6:

[0163]

[0164] And there are rii=1, rij=rji.

[0165] Step (3): Solve for eigenvalues ​​and eigenvectors.

[0166] Specifically, according to the correlation coefficient matrix R, the m non-negative eigenvalues ​​of the matrix R can be obtained by solving the characteristic equation |λI-R|=0: m ≥0 and the corresponding eigenvectors u1,u2,…,u m , where u j =(u 1j ,u 2j ,…u nj ) 9 , which is composed of m new indicator variables by eigenvectors. Among them, I can be understood as the unit matrix.

[0167] Step (4): Calculate the principal component contribution rate.

[0168] Specifically, p (p≤m) principal components can be selected from the m principal components obtained above to screen the driving condition characteristic parameters. First, the characteristic value λ can be calculated based on Formula 7: j (j=1,2,…,m) information contribution rate bj to principal component yj:

[0169]

[0170] And, the principal components y1, y2, ..., y can also be calculated based on formula 8 A The cumulative contribution rate α A :

[0171]

[0172] In formula 8, when α A When it is close to 1, it means that the p principal components selected at this time can represent most of the information of the driving condition. Select the first p indicator variables y1, y2, ..., y A The p principal components are used to replace the original m indicator variables, so that a comprehensive analysis can be performed on the p principal components.

[0173] In the disclosed embodiment, by performing principal component analysis on the 16 characteristic parameters of the driving unit, the characteristic value, information contribution rate and cumulative contribution rate of each principal component are obtained. The specific data are shown in Table 4.

[0174] principal component Eigenvalue Information contribution rate (%) Cumulative contribution rate (%) Y1 5.56 34.76 34.76 Y2 3.82 23.88 58.64 Y3 2.40 15.00 73.64 Y4 1.46 9.16 82.80 Y5 1.37 8.56 91.35 Y6 0.61 3.82 95.18 Y7 0.33 2.03 97.21 Y8 0.20 1.22 98.43 Y9 0.13 0.79 99.23 Y10 0.05 0.32 99.55 Y11 0.03 0.19 99.74 Y12 0.02 0.11 99.85 Y13 0.01 0.07 99.92 Y14 0.01 0.06 99.97 Y15 0.00 0.03 100.00 Y16 0.00 0.00 100.00

[0175] Table 4

[0176] In the embodiment of the present disclosure, considering that the cumulative contribution rate is an indicator for measuring the importance of the principal component, the principal component can be screened based on the cumulative contribution rate.

[0177] For example, when the cumulative contribution rate reaches more than 80%, it is generally believed that the selected principal components can represent most of the information of the original data. Please continue to refer to Table 4. According to the data in Table 4, it is found that the cumulative contribution rate of the first four principal components has reached 82.8%. In other words, by selecting the first four principal components, most of the key information of the original operating data can be retained. For another example, when the cumulative contribution rate reaches more than 90%, it is generally believed that the selected principal components can represent most of the information of the original data. Please continue to refer to Table 4. According to the data in Table 4, it is found that the cumulative contribution rate of the first five principal components has reached 91.35%.

[0178] It can be seen that by adopting the aforementioned principal component analysis screening strategy, in the embodiment of the present disclosure, the dimension of the original operation data can be successfully reduced from 16 dimensions to 4 dimensions. This dimensionality reduction not only significantly reduces the complexity of subsequent calculations, but also effectively simplifies the feature parameters while ensuring the integrity of the data information.

[0179] In the disclosed embodiment, after obtaining the filtered principal component characteristic parameters, the correlation between the filtered principal component characteristic parameters and the characteristic parameters of the original 16 dimensions can also be calculated.

[0180] For example, see Table 5, which shows the correlation coefficient matrix of the first four principal components. The absolute value of the coefficients in this matrix is ​​a key indicator for measuring the weight of the characteristic parameters in each principal component. By analyzing these coefficients, the degree of correlation between each principal component and the characteristic parameter can be clearly determined.

[0181]

[0182]

[0183] Table 5

[0184] Specifically, the correlation coefficient matrix of the principal component Y1 shows that the coefficients of average speed, maximum speed, average value of speed multiplied by negative acceleration, standard deviation of speed, and mileage are relatively large in absolute value. This indicates that Y1 mainly reflects the information of these characteristic parameters. Further analysis shows that the correlation coefficient matrix of the principal component Y2 reveals that the coefficients of average acceleration, maximum acceleration, maximum deceleration, standard deviation of acceleration, and average value of speed multiplied by positive acceleration are relatively large in absolute value, so Y2 mainly reflects the information of these characteristic parameters.

[0185] For Y3, the correlation coefficient matrix shows that the absolute values ​​of the coefficients of average deceleration, acceleration time ratio, and uniform speed time ratio are large, indicating that Y3 mainly reflects the information of these characteristic parameters. Finally, the correlation coefficient matrix of principal component Y4 shows that the absolute values ​​of the coefficients of average deceleration and deceleration time ratio are high, so it can be inferred that Y4 mainly reflects the information of these two characteristic parameters.

[0186] In the embodiment of the present disclosure, after obtaining the principal component correlation coefficient matrix, the principal component score of each driving unit can also be calculated based on Formula 9, and the calculation formula is as follows:

[0187]

[0188] Among them, y1 in Formula 9 is the first principal component, y2 is the second principal component, and so on, ym is the mth principal component.

[0189] For example, please refer to Table 6, which shows the first four principal component scores of all driving units. The first four principal component scores of all driving units will be used as new eigenvalues ​​to replace the original 16 characteristic parameters for subsequent research and analysis.

[0190] Serial number Y1 Y2 Y3 Y4 1 -3.34 0.73 -1.05 0.45 2 1.37 -0.41 0.49 -1.51 3 -3.88 0.15 -1.81 -0.79 4 1.40 -0.10 -1.76 -1.00 …… …… …… …… …… 141 1.08 2.58 0.63 0.20 142 1.36 1.51 0.06 -1.13 143 2.20 0.08 -0.64 0.70 144 0.71 -0.27 0.01 1.08

[0191] Table 6

[0192] In the disclosed embodiment, it is considered that during the driving process of the shunting locomotive, due to the diversity of road conditions, the characteristic parameters show significant differences in different driving stages. Therefore, in order to build an accurate driving condition model, the driving units must be systematically classified according to established rules. On this basis, representative condition fragments are selected from each driving condition category, and then these fragments are integrated to form a complete driving condition model.

[0193] In the disclosed embodiment, a cluster analysis method is used to systematically classify all driving units based on the principal component characteristic parameters obtained after dimensionality reduction through principal component analysis.

[0194] In one embodiment, the operation data can be decomposed and reconstructed using wavelet analysis to extract characteristic parameters of kinematic segments (such as speed, acceleration, energy consumption, etc.). Other clustering algorithms (such as hierarchical clustering, DBSCAN, etc.) are further used to replace K-means clustering to perform cluster analysis on the extracted characteristic parameters, and similar segments are grouped together to obtain clustering results.

[0195] In one embodiment, a deep learning model (such as Long Short-Term Memory Networks (LSTM), Convolutional Neural Network (CNN), etc.) can be used to automatically extract feature parameters in driving data, and complex time series features can be learned and extracted through the deep learning model. A deep clustering method (such as deep embedding clustering, variational autoencoder, etc.) is used to perform cluster analysis on the extracted features to obtain a clustering result.

[0196] In one implementation, a K-means clustering algorithm may be used to cluster the operating condition characteristic parameters obtained after dimensionality reduction through principal component analysis.

[0197] Optionally, the calculation process of the K-means clustering algorithm may adopt but is not limited to the following steps:

[0198] Step a: Determine the number of categories K according to the needs of the research, and specify an initial cluster center point for each category;

[0199] Step b: Calculate the Euclidean distance between each sample point and the initial cluster center, and classify each sample point into the class where the initial cluster center is located according to the minimum distance principle. The distance can be calculated using the following formula 11:

[0200]

[0201] Step c: After the first clustering is completed, each cluster center point can be updated based on the following formula:

[0202]

[0203] In Formula 12, is the updated cluster center point, and n is the number of samples.

[0204] Step d: Re-cluster according to the cluster center points calculated in step c, repeat steps b and c, and iterate continuously until the cluster center points tend to be stable.

[0205] It should be noted that if all driving units are classified according to the steps of K-means cluster analysis, it is first necessary to assume that the number of initial cluster centers is 3, 4, 5, 6, 7, and 8, and then use the silhouette coefficient to judge the rationality of different cluster numbers. Specifically, the silhouette coefficient method (Silhoiette Coefficient, SC) is a commonly used evaluation method for clustering effects. It can combine the two factors of cohesion and separation, and is used to evaluate the impact of different algorithms or different operation modes of algorithms on clustering results based on the same original data. Optionally, the silhouette coefficient can be calculated based on the following formula 13:

[0206]

[0207] In Formula 13, i is the number of the working condition sample, ai is the average distance between sample i and the samples in its class, representing the cohesion of the sample points; bi is the minimum average distance between sample i and the sample points outside its class, representing the separation of the sample points, and both are calculated using Euclidean distance. The silhouette coefficient is used to evaluate the clustering results. It characterizes the similarity between the working condition sample and the overall characteristics of its class, and its value is between [-1,1]. When the silhouette value reaches 0.6 or above, it indicates that the clustering result is reasonable; the closer the silhouette value is to -1, the more unreasonable the clustering result is; if it is close to 0, the sample has similar characteristics to both types of working conditions.

[0208] For example, see Fig.10 , Fig.10 The figure shows the mean and standard deviation of the silhouette coefficient under different numbers of clusters under single machine conditions. Fig.10 It can be seen that when the number of clusters is 4, the cohesion of different clusters is the highest and the dispersion is the lowest.

[0209] It can be seen that in the embodiment of the present disclosure, the cluster analysis method is used to process the first four principal components of the driving unit in order to achieve the classification of different driving conditions. When the selected number of clusters is 4, please refer to Table 7, and the cluster center positions of various driving conditions and the number of segments contained in each driving condition are obtained through analysis.

[0210]

[0211] Table 7

[0212] As shown in Table 7, when the driving condition is cluster condition 1, the corresponding driving unit set includes 40 driving units, when the driving condition is cluster condition 2, the corresponding driving unit set includes 36 driving units, when the driving condition is cluster condition 3, the corresponding driving unit set includes 50 driving units, and when the driving condition is cluster condition 4, the corresponding driving unit set includes 18 driving units. Optionally, when dividing the driving units, each driving unit corresponds to a unique identifier, and based on the unique identifier corresponding to each driving unit, the driving units corresponding to each driving unit set can be screened out from the driving unit library.

[0213] In one implementation, it is difficult to directly display the clustering results on a two-dimensional plane because the dimensions of the selected principal components are high. In order to more intuitively display the clustering results, a three-dimensional scatter plot of the principal components can be drawn. For example, see Fig.11 , Fig.11 A three-dimensional scatter plot based on the first, second, and third principal components was drawn. Fig.11It can be seen that the driving units are divided into four categories relatively evenly, namely cluster condition 1, cluster condition 2, cluster condition 3 and cluster condition 4, and the cluster center of each cluster condition is shown, so as to ensure that there is a clear distinction between each type of fragment.

[0214] In one implementation, after each driving unit set under a single-machine operating condition is obtained, information on 16 characteristic parameters corresponding to the driving units in each driving unit set may also be determined.

[0215] For example, the characteristic parameters of the driving unit under each clustering condition of the single machine condition are shown in Table 8.

[0216]

[0217]

[0218] Table 8

[0219] In one embodiment, after obtaining each driving unit set under a single machine working condition, the working condition model of the driving working condition corresponding to each driving unit set can also be determined. Fig.12 , Fig.12 is the driving curve corresponding to the typical driving unit of each driving condition under single machine condition. Fig.12 Four driving conditions are shown in Fig.12 The time-speed curves of working conditions one, two, three and four are the working condition models.

[0220] Step 303: constructing a working condition model of the shunting locomotive according to at least one travel unit set corresponding to each type of traction working condition obtained.

[0221] In the embodiment of the present disclosure, after the electronic device obtains at least one driving unit set corresponding to each type of traction operating condition, it can construct a working condition curve corresponding to each type of traction operating condition based on the obtained at least one driving unit set corresponding to each type of traction operating condition; and construct a working condition model of the shunting locomotive based on the working condition curve corresponding to each type of traction operating condition.

[0222] In one embodiment, the electronic device can determine the duration of each driving unit set among multiple driving unit sets corresponding to each type of traction condition; and construct a working condition model corresponding to each type of traction condition based on the duration of each driving unit set and the working condition curve corresponding to each driving unit set.

[0223] Optionally, after clustering the original operating data to obtain the clustering results, a working condition model suitable for the shunting locomotive in the traction condition of the single-machine condition can be constructed. According to the results of the cluster analysis, the Euclidean distance between each unit in the class and the cluster center of the corresponding working condition category is solved, and the fragment with the smallest distance from the cluster center in each type of driving unit library is extracted to represent the class, and finally a complete working condition curve is synthesized. In order to ensure the characteristics of the original driving condition and take into account the current typical driving cycle conditions, the duration of each driving unit set in the working condition model corresponding to each type of traction condition is determined according to the following formula 14:

[0224]

[0225] In Formula 14, ti is the duration of the i-th driving condition in the constructed condition model, Ti is the total duration of the i-th condition in all driving units, Ttot is the total duration of the driving unit, and ttot is the target duration for constructing the condition model.

[0226] For example, a working condition model of a traction working condition such as a single-machine working condition finally constructed based on the above method, that is, a speed-time curve is as follows: Fig.13 As shown in the figure, a working condition model of a type of traction working condition such as a single-machine working condition finally constructed based on the above method, that is, the acceleration-time curve is as follows Fig.14 shown.

[0227] In a possible implementation, in order to verify the accuracy of the constructed single-machine working condition model of a traction working condition, an error analysis is performed on the original working condition and the constructed single-machine working condition model of a traction working condition. In the disclosed embodiment, twelve characteristic parameters are selected for comparison, and the results are shown in Table 9, that is, the parameter errors of the two working conditions are less than 5%, indicating that the single-machine working condition model of a traction working condition synthesized by the working condition model construction method proposed in the disclosed embodiment can better reflect the driving condition characteristics of the shunting locomotive under the condition of traction of freight cars.

[0228]

[0229]

[0230] Table 9

[0231] In the disclosed embodiment, after the operating condition model corresponding to the operating condition when the shunting locomotive is not pulling a freight car is constructed, the same method is used to construct the operating condition model corresponding to the operating condition when the shunting locomotive is pulling a freight car and the load is within a first preset range, and the operating condition model corresponding to the operating condition when the shunting locomotive is pulling a freight car and the load is within a second preset range.

[0232] In one implementation, the electronic device may determine the duration of each type of traction operating condition, and then construct a working condition model of the shunting locomotive according to the duration of each type of traction operating condition and the corresponding working condition curve.

[0233] Optionally, in order to ensure that a complete working condition model that can effectively characterize the original driving route characteristics of the vehicle is constructed, the working condition models of the three traction working condition types of the shunting locomotive can be synthesized. Specifically, the duration of different types of working condition models in the complete working condition model of the shunting locomotive can be determined based on the following formula 15:

[0234]

[0235] In Formula 15, ttype is used to indicate the duration of different types of traction conditions in the complete operating condition model, Ttype is used to indicate the total duration of different types of traction conditions, Ttotal is used to indicate the total duration of all original operating data, and ttotal is used to indicate the target duration for building a complete operating condition model.

[0236] The exemplary embodiment of the present disclosure also provides a device for constructing a shunting locomotive operating condition model. Fig.15 As shown, the shunting locomotive operating condition model building device 1500 includes the following program modules:

[0237] A determination unit 1501 is used to determine the operation data of multiple types of traction conditions of the shunting locomotive of the working condition to be constructed;

[0238] The processing unit 1502 is used to perform the following operations on the operation data of each type of traction working condition: divide the operation data into multiple driving units, and perform clustering processing on the multiple driving units to obtain at least one driving unit set, each of which corresponds to a type of driving working condition;

[0239] The construction unit 1503 is used to construct the operating condition model of the shunting locomotive according to the at least one travel unit set corresponding to each type of the traction operating condition.

[0240] In one implementation, the determining unit 1501 is configured to:

[0241] Performing data preprocessing on the original operating data of each type of traction working condition to obtain operating data corresponding to each type of traction working condition;

[0242] The data preprocessing includes at least one of missing data processing, abnormal data processing, and filtered data processing.

[0243] In one implementation, the processing unit 1502 is configured to:

[0244] Determining M characteristic parameters for describing each of the travel units according to the processed operating data;

[0245] Performing principal component analysis on the M characteristic parameters of the plurality of driving units to obtain N principal component characteristic parameters for describing each of the driving units; wherein M and N are positive integers, and M is greater than N;

[0246] The plurality of driving units are clustered according to the N principal component characteristic parameters to obtain at least one driving unit set.

[0247] In one embodiment, the construction unit 1502 is used to:

[0248] Constructing a working condition curve corresponding to each type of the traction working condition according to the obtained at least one driving unit set corresponding to each type of the traction working condition;

[0249] According to the operating condition curve corresponding to each type of traction operating condition, an operating condition model of the shunting locomotive is constructed.

[0250] In one embodiment, the construction unit 1502 is used to:

[0251] Determine the duration of each driving unit set in the plurality of driving unit sets corresponding to each type of the traction working condition;

[0252] According to the duration of each driving unit set and the operating condition curve corresponding to each driving unit set, a working condition model corresponding to each type of traction working condition is constructed.

[0253] In one embodiment, the construction unit 1502 is used to:

[0254] Determining the duration of each type of traction condition;

[0255] According to the duration of each type of traction working condition and the corresponding working condition curve, a working condition model of the shunting locomotive is constructed.

[0256] In one embodiment, the operating data of the multiple types of traction conditions include: the condition where the shunting locomotive is not pulling a freight car, the condition where the shunting locomotive is pulling a freight car and the load is within a first preset range, and the condition where the shunting locomotive is pulling a freight car and the load is within a second preset range; the upper limit value within the first preset range is not greater than the lower limit value within the second preset range.

[0257] The specific details of each part of the above-mentioned device have been described in detail in the implementation method of the method part. The undisclosed details can be found in the implementation method of the method part, so they will not be repeated here.

[0258] It should be noted that Figure 2 The raw data preprocessing unit 2021 and Fig.15 The functions performed by the determining unit 1501 in may be the same. Figure 2 The unit division and parameter calculation unit 2022 and the driving unit cluster analysis unit 2023 are Fig.15 The functions performed by the processing unit 1502 in may be the same. Figure 2 Typical working condition synthesis and verification unit in Fig.15 The functions performed by the construction unit 1503 in may be the same.

[0259] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the exemplary embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0260] The exemplary embodiments of the present disclosure also provide a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the above-mentioned method for constructing a shunting locomotive operating condition model is implemented.

[0261] In one embodiment, the computer program product may be a tangible product containing a computer program, such as a computer-readable storage medium storing a computer program. The readable storage medium may be a storage medium based on electrical, magnetic, optical, electromagnetic, infrared, or other signals, including but not limited to: random access memory (RAM), read-only memory (ROM), magnetic tape, floppy disk, flash memory (Flash), mechanical hard disk (HDD), solid-state drive (SSD), and the like. Exemplarily, the computer program product may be implemented as a non-volatile storage medium storing a computer program, such as a read-only memory, a NAND flash memory, and the like.

[0262] In one embodiment, the computer program product may be an intangible product including a computer program. Exemplarily, the computer program product may be implemented as a virtual digital product, such as a digital file storing an executable file, an installation package, etc. of the computer program.

[0263] The code of the computer program can be written in one or more programming languages. Programming languages ​​such as C language, Java, C++, etc. The program code can be executed entirely on the user computing device, or partially on the user computing device, or as a separate software package, or partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, such as a local area network (LAN), a wide area network (WAN), etc., or can be connected to an external computing device (e.g., an Internet connection provided by an operator).

[0264] Computer programs can be carried or transmitted through electrical, magnetic, optical, electromagnetic, infrared and other signals. Electronic devices can convert signals carrying computer programs into digital signals, thereby running computer programs. When a computer program runs on an electronic device, its code is used to enable the electronic device to execute (more specifically, it can enable the processor of the electronic device to execute) the method steps of various exemplary embodiments of the present disclosure, such as the above-mentioned shunting locomotive operating condition model construction method, which includes the following steps: Step 301: Determine the operating data of multiple types of traction conditions of the shunting locomotive for which the operating condition model is to be constructed; Step 302: For the operating data of each type of traction condition, perform the following operations respectively: Divide the operating data into multiple driving units, and cluster the multiple driving units to obtain at least one driving unit set, each driving unit set corresponding to a type of driving condition; Step 303: Construct a shunting locomotive operating condition model based on the at least one driving unit set corresponding to each type of traction condition obtained.

[0265] By implementing the above method steps through a computer program, the operating data of multiple types of traction conditions of the shunting locomotive for the working condition to be constructed can be determined; for the operating data of each type of traction condition, the following operations are performed respectively: the operating data is divided into multiple driving units, and the multiple driving units are clustered to obtain at least one driving unit set, each driving unit set corresponds to a type of driving condition; based on the at least one driving unit set corresponding to each type of traction condition obtained, the working condition model of the shunting locomotive is constructed. The working condition model constructed by processing the operating data of multiple types of traction conditions of the shunting locomotive disclosed in the present invention can more accurately reflect the actual working condition of the shunting locomotive, thereby obtaining a working condition model with higher accuracy, thereby improving the accuracy of the evaluation of the working condition of the shunting locomotive.

[0266] The exemplary embodiments of the present disclosure also provide an electronic device, which may include a processor and a memory. The memory stores executable instructions of the processor, such as a computer program. The processor executes the method steps of various exemplary embodiments of the present disclosure by executing the executable instructions.

[0267] Reference below Fig.16 , the electronic device is exemplified in the form of a general-purpose computing device. It should be understood that Fig.16 The electronic device 1600 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0268] like Fig.16 As shown, the electronic device 1600 may include: a processor 1610 , a memory 1620 , a bus 1630 , an I / O (input / output) interface 1640 , a network adapter 1650 , and a display 1680 .

[0269] The memory 1620 may include a volatile memory, such as a RAM 1621, a cache unit 1622, and may also include a non-volatile memory, such as a ROM 1623. The memory 1620 may also include one or more program modules 1624, such program modules 1624 include but are not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or a combination thereof may include the implementation of a network environment. For example, the program module 1624 may include each module in the above-mentioned device.

[0270] Processor 1610 may include one or more processing units. For example, processor 1610 may include an AP (Application Processor), a modem processor, a GPU (Graphics Processing Unit), an ISP (Image Signal Processor), a controller, an encoder, a decoder, a DSP (Digital Signal Processor), a baseband processor and / or an NPU (Neural-Network Processing Unit), etc.

[0271] Processor 1610 can be used to execute executable instructions stored in memory 1620, such as the above-mentioned method for constructing a shunting locomotive operating condition model, which includes the following steps: Step 301: Determine the operating data of multiple types of traction conditions of the shunting locomotive for which the operating condition model is to be constructed; Step 302: For the operating data of each type of traction condition, perform the following operations respectively: divide the operating data into multiple driving units, and cluster the multiple driving units to obtain at least one driving unit set, each driving unit set corresponding to a type of driving condition; Step 303: Construct a working condition model of the shunting locomotive based on the at least one driving unit set corresponding to each type of traction condition obtained.

[0272] By executing the above method steps through the processor 810, the operating data of multiple types of traction conditions of the shunting locomotive for the working condition to be constructed can be determined; for the operating data of each type of traction condition, the following operations are performed respectively: the operating data is divided into multiple driving units, and the multiple driving units are clustered to obtain at least one driving unit set, each driving unit set corresponds to a type of driving condition; according to the at least one driving unit set corresponding to each type of traction condition obtained, the working condition model of the shunting locomotive is constructed. The working condition model constructed by processing the operating data of multiple types of traction conditions of the shunting locomotive in the present disclosure can more accurately reflect the actual working condition of the shunting locomotive, thereby obtaining a working condition model with higher accuracy, thereby improving the accuracy of the evaluation of the working condition of the shunting locomotive.

[0273] The bus 1630 is used to realize the connection between different components of the electronic device 1600, and may include a data bus, an address bus, and a control bus.

[0274] The electronic device 1600 can communicate with one or more external devices 1700 (eg, a keyboard, a mouse, an external controller, etc.) through the I / O interface 1640 .

[0275] The electronic device 1600 can communicate with one or more networks through the network adapter 1650. For example, the network adapter 1650 can provide mobile communication solutions such as 3G / 4G / 5G, or provide wireless communication solutions such as wireless LAN, Bluetooth, near field communication, etc. The network adapter 1650 can communicate with other modules of the electronic device 1600 through the bus 1630.

[0276] The electronic device 1600 may display a graphical user interface, such as an operating condition model, through the display 1680 .

[0277] although Fig.16 Not shown, other hardware and / or software modules may also be provided in the electronic device 1600, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0278] As can be seen from the above, the technical solution of the present disclosure can be implemented as a method, an apparatus, a system, a computer program product, a storage medium, an electronic device, etc. Those skilled in the art can understand that various aspects of the present disclosure can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software, such as being respectively referred to as a "circuit", "module" or "system".

[0279] It should be understood that the present disclosure is not limited to the specific method steps or structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from the scope thereof. Those skilled in the art will easily think of other embodiments based on the specific embodiments provided by the present disclosure. Therefore, the specific embodiments provided by the present disclosure are only exemplary, and the scope and spirit of the present disclosure are indicated by the claims, and any variations, uses or adaptive changes of the present disclosure should be covered, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the technical field that are not disclosed in the present disclosure.

Claims

1. A method for constructing a shunting locomotive operating condition model, characterized in that: The method comprises: Determine the operation data of multiple types of traction working conditions of the shunting locomotive for which the working condition model is to be constructed; For each type of the operating data of the traction working condition, the following operations are performed respectively: the operating data is divided into a plurality of driving units, and the plurality of driving units are clustered to obtain at least one driving unit set, each of the driving unit sets corresponding to a type of driving working condition; According to the obtained at least one travel unit set corresponding to each type of traction operating condition, a working condition model of the shunting locomotive is constructed.

2. The method according to claim 1, characterized in that Determine the operating data of multiple types of traction conditions of the shunting locomotive for which the operating condition model is to be constructed, including: Performing data preprocessing on the original operating data of each type of traction working condition to obtain operating data corresponding to each type of traction working condition; The data preprocessing includes at least one of missing data processing, abnormal data processing, and filtered data processing.

3. The method according to claim 2, characterized in that For each type of the operating data of the traction condition, the following operations are performed respectively: the operating data is divided into a plurality of driving units, and the plurality of driving units are clustered to obtain at least one driving unit set, including: Determining M characteristic parameters for describing each of the travel units according to the processed operating data; Performing principal component analysis on the M characteristic parameters of the plurality of driving units to obtain N principal component characteristic parameters for describing each of the driving units; wherein M and N are positive integers, and M is greater than N; The plurality of driving units are clustered according to the N principal component characteristic parameters to obtain at least one driving unit set.

4. The method according to any one of claims 1 to 3, characterized in that: According to the obtained at least one travel unit set corresponding to each type of the traction working condition, a working condition model of the shunting locomotive is constructed, including: Constructing a working condition curve corresponding to each type of the traction working condition according to the obtained at least one driving unit set corresponding to each type of the traction working condition; According to the operating condition curve corresponding to each type of traction operating condition, an operating condition model of the shunting locomotive is constructed.

5. The method according to claim 4, characterized in that According to the obtained at least one driving unit set corresponding to each type of the traction working condition, a working condition curve corresponding to each type of the traction working condition is constructed, including: Determine the duration of each driving unit set in the plurality of driving unit sets corresponding to each type of the traction working condition; According to the duration of each driving unit set and the operating condition curve corresponding to each driving unit set, a working condition model corresponding to each type of traction working condition is constructed.

6. The method according to claim 5, characterized in that According to the operating condition curve corresponding to each type of traction operating condition, a working condition model of the shunting locomotive is constructed, including: Determining the duration of each type of traction condition; According to the duration of each type of traction working condition and the corresponding working condition curve, a working condition model of the shunting locomotive is constructed.

7. The method according to claim 1, characterized in that The operating data of the multiple types of traction conditions include: the condition where the shunting locomotive is not pulling a freight car, the condition where the shunting locomotive is pulling a freight car and the load is within a first preset range, and the condition where the shunting locomotive is pulling a freight car and the load is within a second preset range; the upper limit value within the first preset range is not greater than the lower limit value within the second preset range.

8. A shunting locomotive operating condition model building device, characterized in that: The device comprises: A determination unit, used to determine the operation data of multiple types of traction conditions of the shunting locomotive of the working condition to be constructed; A processing unit is used to perform the following operations on the operation data of each type of traction working condition: divide the operation data into a plurality of driving units, and perform clustering processing on the plurality of driving units to obtain at least one driving unit set, each of the driving unit sets corresponding to a type of driving working condition; A construction unit is used to construct a working condition model of the shunting locomotive according to the at least one travel unit set corresponding to each type of traction working condition obtained.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: processor; A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 7 by executing the executable instructions.

Images