A construction process monitoring method for a railway hump decelerator device

Abstract

The present application relates to a kind of existing railway hump decelerator equipment construction process monitoring method, belong to construction monitoring technical field, the present application is by constructing construction abnormal data identification model, by training to construction abnormal data identification model, and the training process of construction abnormal area identification model is adjusted, according to the construction requirement data of existing railway hump decelerator equipment the drawing of existing railway hump decelerator equipment is analyzed in construction area, points out the abnormal area in the drawing of existing railway hump decelerator equipment, and by combining the construction investigation data of target construction area to optimize the construction process of existing railway hump decelerator equipment, by combining the construction investigation data of target construction area to optimize the construction process of existing railway hump decelerator equipment, before point positioning, early pre-arrangement, one forming method reduces the quantity of secondary adjustment, maximum guarantee construction quality.

Description

TECHNICAL FIELD

[0001] The present application relates to the construction process monitoring technical field, and particularly relates to a construction process flow monitoring method for existing railway hump retarder equipment. BACKGROUND

[0002] The hump is a shunting line equipment for disassembling and assembling of freight trains in a railway marshalling station, and is named after its longitudinal section shape like the back of a camel. In the process of vehicle sliding through the "hump", in order to ensure that the sliding speed is just right without colliding with the car body, the vehicle needs to be appropriately decelerated by the hump retarder equipment. The hump retarder is a device for controlling the sliding speed of the vehicle, and is usually installed at the entrance and exit of the sliding line and at the key positions. The new retarder is configured with a noise reduction brake beam, which greatly reduces the noise and makes the braking effect more effective. However, when the design drawings of the existing railway hump retarder equipment do not meet the relevant specifications, standards or technical conditions, the quality of the construction does not meet the established requirements, resulting in low work efficiency. SUMMARY

[0003] The present application overcomes the deficiencies of the prior art and provides a construction process flow monitoring method for existing railway hump retarder equipment.

[0004] To achieve the above purpose, the technical solution adopted by the present application is as follows:

[0005] The present application provides a construction process flow monitoring method for existing railway hump retarder equipment, which specifically includes the following steps:

[0006] Obtain the construction requirement data of the existing railway hump retarder equipment, and construct a construction abnormal data identification model according to the construction requirement data of the existing railway hump retarder equipment;

[0007] Train the construction abnormal data identification model, and adjust the training process of the construction abnormal area identification model;

[0008] Identify abnormal data of the construction requirement data of the existing railway hump retarder equipment based on the construction abnormal area identification model, and perform secondary analysis in combination with the construction investigation data of the target construction area;

[0009] Optimize the construction process of the existing railway hump retarder equipment according to the secondary analysis result.

[0010] Further, in the construction process flow monitoring method for existing railway hump retarder equipment, the construction abnormal data identification model is constructed according to the construction requirement data of the existing railway hump retarder equipment, and specifically includes:

[0011] extracting construction drawing data in construction requirement data of the existing railway hump retarder equipment, and constructing a historical case data set according to the construction drawing data, obtaining construction abnormal data and non-abnormal data in the construction drawing data from the historical case data set, and constructing a training set;

[0012] constructing a construction abnormal data identification model based on a deep neural network, initializing a network parameter data set of the construction abnormal data identification model, introducing a whale optimization algorithm and a snake optimization algorithm, inputting the training set into the construction abnormal data identification model, and initializing training by randomly selecting network parameters from the network parameter data set of the construction abnormal data identification model;

[0013] obtaining the convergence speed and prediction accuracy of the construction abnormal data identification model, and when the convergence speed and prediction accuracy of the construction abnormal data identification model are lower than a preset evaluation index, performing global search on the network parameter data set of the construction abnormal data identification model through the whale optimization algorithm to obtain a global network parameter data set;

[0014] inputting the global network parameter data set into the snake optimization algorithm for local search to obtain a local network parameter data set, and training the construction abnormal data identification model according to the network parameters in the local network parameter data set.

[0015] Further, in the existing railway hump retarder equipment construction process monitoring method, the construction abnormal data identification model is trained, and the training process of the construction abnormal area identification model is adjusted, specifically as follows:

[0016] statistically contributing data of each construction abnormal data and non-abnormal data type in the prediction process of the construction abnormal data identification model, and setting a contribution data threshold;

[0017] judging whether there is construction abnormal data and non-abnormal data type corresponding to the contribution data threshold in the training data;

[0018] when there is construction abnormal data and non-abnormal data type corresponding to the contribution data threshold in the training data, the corresponding construction abnormal data and non-abnormal data type is deleted until there is no construction abnormal data and non-abnormal data type corresponding to the contribution data threshold;

[0019] when there is construction abnormal data and non-abnormal data type corresponding to the contribution data threshold in the training data, the construction abnormal area identification model is trained according to the current training data.

[0020] Further, in the construction process flow monitoring method of the existing railway hump retarder equipment, the construction requirement data of the existing railway hump retarder equipment is subjected to abnormal data identification based on the construction abnormal area identification model, and secondary analysis is performed in combination with the construction investigation data of the target construction area, specifically including:

[0021] The construction requirement data of the existing railway hump retarder equipment is input into the construction abnormal area identification model for verification;

[0022] Through verification, the drawing abnormal area in the construction requirement data of the existing railway hump retarder equipment is obtained, and the construction investigation data of the target construction area is obtained, and the work interference data within a preset range of the existing railway hump retarder equipment is obtained according to the construction investigation data of the target construction area;

[0023] According to the work interference data within a preset range of the existing railway hump retarder equipment and the drawing abnormal area in the construction requirement data of the existing railway hump retarder equipment, actual construction interference data of the existing railway hump retarder equipment during construction is generated;

[0024] According to the actual construction interference data of the existing railway hump retarder equipment during construction, a secondary analysis result is generated.

[0025] Further, in the construction process flow monitoring method of the existing railway hump retarder equipment, the construction process of the existing railway hump retarder equipment is optimized according to the secondary analysis result, specifically including:

[0026] According to the secondary analysis result, construction interference data of the existing railway hump retarder equipment during construction is determined, and geographical position information of each construction auxiliary equipment is initialized, and work range information of the construction auxiliary equipment is obtained;

[0027] According to the geographical position information of each construction auxiliary equipment and the work range information of the construction auxiliary equipment, actual construction range information of each construction auxiliary equipment is obtained, and it is judged whether the actual construction range information of each construction auxiliary equipment overlaps with the construction interference data of the existing railway hump retarder equipment during construction;

[0028] A reset number threshold is set, and when the actual construction range information of the construction auxiliary equipment overlaps with the construction interference data of the existing railway hump retarder equipment during construction, the geographical position information of the construction auxiliary equipment is reset based on the reset number, until there is no overlap;

[0029] When the actual construction range information of the construction auxiliary equipment does not overlap with the construction interference data of the existing railway hump retarder equipment during construction, the geographic location information of the construction auxiliary equipment is taken as the recommended construction position.

[0030] Further, in the existing railway hump retarder equipment construction process monitoring method, the following steps are further included:

[0031] When the number of resets reaches the maximum value of the reset number threshold, the construction drawing data in the construction requirement data of the existing railway hump retarder equipment is obtained, and the layout position of the existing railway hump retarder equipment is reselected from the construction drawing data in the construction requirement data of the existing railway hump retarder equipment;

[0032] According to the construction interference confirmation of the reselected layout position of the existing railway hump retarder equipment, the frequency data of the construction interference items is confirmed, a frequency data threshold is set, and it is judged whether the frequency data of the construction interference items is greater than the frequency data threshold;

[0033] When the frequency data of the construction interference items is greater than the frequency data threshold, the layout position of the existing railway hump retarder equipment is continuously reset;

[0034] When the frequency data of the construction interference items is not greater than the frequency data threshold, the layout position of the existing railway hump retarder equipment is taken as the recommended layout position, and the recommended layout position of the existing railway hump retarder equipment is displayed in a preset manner.

[0035] The second aspect of the present application provides an existing railway hump retarder equipment construction process monitoring system, including a memory and a processor, the memory includes an existing railway hump retarder equipment construction process monitoring method program, and the existing railway hump retarder equipment construction process monitoring method program is executed by the processor to realize the steps of any one of the existing railway hump retarder equipment construction process monitoring method.

[0036] The third aspect of the present application provides a computer readable storage medium, including an existing railway hump retarder equipment construction process monitoring method program, and the existing railway hump retarder equipment construction process monitoring method program is executed by the processor to realize the steps of any one of the existing railway hump retarder equipment construction process monitoring method.

[0037] The present application solves the defects in the background art, and has the following beneficial effects:

[0038] The application obtains construction requirement data of the existing railway hump retarder equipment and construction investigation data of a target construction area, analyzes each construction area according to the construction requirement data and drawings of the existing railway hump retarder equipment through artificial intelligence technology, such as whether the equipment layout is reasonable and correct, the line path meets the regulations and the actual situation, and if there is a conflict, the abnormal area in the drawings of the existing railway hump retarder equipment is pointed out, and the construction process of the existing railway hump retarder equipment is optimized through artificial intelligence technology combined with the construction investigation data of the target construction area. The application optimizes the construction process of the existing railway hump retarder equipment through artificial intelligence technology combined with the construction investigation data of the target construction area, and reduces the number of secondary adjustments through the method of positioning in advance, pre-arrangement in advance and one-time forming, which maximizes the construction quality. Moreover, the construction drawings of the target area are analyzed in advance, so that part of the construction content in the sky window is transferred to the outside, reducing the labor intensity of the construction personnel in the point, improving the work efficiency, protecting the personal safety of the construction operation, and reducing the safety risk. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, other drawings of other embodiments can be obtained without creative labor on the basis of these drawings.

[0040] Figure 1 The overall flowchart of a construction process flow monitoring method of an existing railway hump retarder equipment is shown;

[0041] Figure 2 The system block diagram of a construction process flow monitoring system of an existing railway hump retarder equipment is shown. DETAILED DESCRIPTION

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, other drawings of other embodiments can be obtained without creative labor on the basis of these drawings.

[0043] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, however, the present application can also be implemented in other ways different from those described herein, therefore, the scope of protection of the present application is not limited by the specific embodiments disclosed below.

[0044] As Figure 1As shown, the first aspect of the present application provides a construction process monitoring method for existing railway hump decelerator equipment, specifically comprising the following steps:

[0045] Obtain the construction requirement data of the existing railway hump decelerator equipment, and construct a construction abnormal data identification model according to the construction requirement data of the existing railway hump decelerator equipment;

[0046] Train the construction abnormal data identification model, and adjust the training process of the construction abnormal area identification model;

[0047] Based on the construction abnormal area identification model, the construction requirement data of the existing railway hump decelerator equipment is identified for abnormal data, and secondary analysis is performed in combination with the construction investigation data of the target construction area;

[0048] According to the secondary analysis result, the construction process of the existing railway hump decelerator equipment is optimized.

[0049] It should be noted that the present application optimizes the construction process of the existing railway hump decelerator equipment by combining the construction investigation data of the target construction area with artificial intelligence technology, and reduces the number of secondary adjustments by using the method of point positioning, advance preparation and one-time forming, thereby maximizing the construction quality. Moreover, the construction drawings of the target area are analyzed in advance, so that part of the construction content that needs to be opened in the sky is transferred to outside the point to complete, reducing the labor intensity of the construction personnel inside the point, improving the work efficiency, ensuring the personal safety of the construction operation, and reducing the safety risk.

[0050] Further, in the construction process monitoring method for the existing railway hump decelerator equipment, the construction abnormal data identification model is constructed according to the construction requirement data of the existing railway hump decelerator equipment, specifically as follows:

[0051] Extract the construction drawing data in the construction requirement data of the existing railway hump decelerator equipment, and construct a historical case data set according to the construction drawing data, obtain the construction abnormal data and non-abnormal data in the construction drawing data from the historical case data set, and construct a training set;

[0052] Based on the deep neural network, the construction abnormal data identification model is constructed, and the network parameter data set of the construction abnormal data identification model is initialized, the whale optimization algorithm and the snake optimization algorithm are introduced, the training set is input into the construction abnormal data identification model, and the network parameters are randomly selected from the network parameter data set of the construction abnormal data identification model for initialization training;

[0053] The convergence speed and prediction accuracy of the construction abnormal data identification model are acquired, and when the convergence speed and prediction accuracy of the construction abnormal data identification model are lower than preset evaluation indexes, the global search of the network parameter data set of the construction abnormal data identification model is performed through the whale optimization algorithm to acquire the global network parameter data set;

[0054] The global network parameter data set is input into the snake optimization algorithm for local search to acquire the local network parameter data set, and the construction abnormal data identification model is trained according to the network parameters in the local network parameter data set.

[0055] It should be noted that the construction requirement data of the existing railway hump retarder equipment includes construction drawing data, construction size deviation of the existing railway hump retarder equipment, construction flatness deviation of the existing railway hump retarder equipment and the like, the global search capability of WOA (whale optimization algorithm) and the local optimization characteristic of SO (snake optimization algorithm) are combined, the neural network parameters are dynamically adjusted, and the identification accuracy of the construction abnormal data identification model can be further improved. The historical case data includes construction abnormal data and non-abnormal data in the construction drawing data, so as to identify the construction drawing data in the construction requirement data of the existing railway hump retarder equipment.

[0056] Further, in the existing railway hump retarder equipment construction process flow monitoring method, the construction abnormal data identification model is trained, and the training process of the construction abnormal area identification model is adjusted, specifically:

[0057] The contribution degree data of each construction abnormal data and non-abnormal data type in the prediction process of the construction abnormal data identification model is counted, and the contribution degree data threshold is set;

[0058] It is judged whether the construction abnormal data and non-abnormal data type corresponding to the contribution degree data lower than the contribution degree data threshold exist in the training data;

[0059] When the construction abnormal data and non-abnormal data type corresponding to the contribution degree data lower than the contribution degree data threshold exist in the training data, the corresponding construction abnormal data and non-abnormal data type are deleted until there is no construction abnormal data and non-abnormal data type corresponding to the contribution degree data lower than the contribution degree data threshold;

[0060] When the construction abnormal data and non-abnormal data type corresponding to the contribution degree data lower than the contribution degree data threshold exist in the training data, the construction abnormal area identification model is trained according to the current training data.

[0061] It should be noted that when the contribution data in the training data is lower than the construction abnormal data corresponding to the contribution data threshold and the non-abnormal data type, the corresponding construction abnormal data and non-abnormal data type are deleted, which reduces the interference of data with low contribution to model training, thereby improving the prediction accuracy and training amount of the model, so as to identify the abnormal area in the drawing, including whether the equipment layout is reasonable and correct, whether the line and path meet the regulations and actual conditions, whether there is contradiction and mutual interference, whether the equipment installation size is incorrect or improper, and whether the plan and installation drawing is correct, missing, etc.

[0062] Further, in the existing railway hump retarder equipment construction process monitoring method, the construction requirement data of the existing railway hump retarder equipment is identified based on the construction abnormal area identification model, and the construction investigation data of the target construction area is analyzed again, specifically including:

[0063] The construction requirement data of the existing railway hump retarder equipment is input into the construction abnormal area identification model for verification;

[0064] Through verification, the drawing abnormal area in the construction requirement data of the existing railway hump retarder equipment is obtained, and the construction investigation data of the target construction area is obtained, and the operation interference data within the preset range of the existing railway hump retarder equipment is obtained according to the construction investigation data of the target construction area;

[0065] According to the operation interference data within the preset range of the existing railway hump retarder equipment and the drawing abnormal area in the construction requirement data of the existing railway hump retarder equipment, the actual construction interference data of the existing railway hump retarder equipment during construction is generated;

[0066] According to the actual construction interference data of the existing railway hump retarder equipment during construction, a secondary analysis result is generated.

[0067] It should be noted that the construction investigation data of the target construction area includes on-site construction environment data, engineering overview, construction materials and equipment, construction work plan and other data, and the construction interference data includes on-site construction obstacles, active interference: also known as electronic interference or background noise, which will have different degrees of influence on positioning equipment. Most electronic devices will emit interference signals, which will reduce the ability of accurate tracking sensors to position, or affect the accuracy of angle / tilt angle measurement readings, and also includes transportation factors: transportation problems often cause delays in the construction period, involving transportation mode selection, contract negotiation, customs duties and restrictions, special transportation requirements, etc.

[0068] Further, in the existing railway hump decelerator equipment construction process monitoring method, the construction process of the existing railway hump decelerator equipment is optimized according to the secondary analysis results, specifically:

[0069] According to the secondary analysis results, the construction interference data of the existing railway hump decelerator equipment during construction is determined, and the geographic location information of each construction auxiliary equipment is initialized to obtain the working range information of the construction auxiliary equipment;

[0070] According to the geographic location information of each construction auxiliary equipment and the working range information of the construction auxiliary equipment, the actual construction range information of each construction auxiliary equipment is obtained, and it is judged whether the actual construction range information of each construction auxiliary equipment overlaps with the construction interference data of the existing railway hump decelerator equipment during construction;

[0071] A reset number threshold (such as setting the maximum number to 100) is set, and when the actual construction range information of the construction auxiliary equipment overlaps with the construction interference data of the existing railway hump decelerator equipment during construction, the geographic location information of the construction auxiliary equipment is reset based on the reset number until there is no overlap;

[0072] When the actual construction range information of the construction auxiliary equipment does not overlap with the construction interference data of the existing railway hump decelerator equipment during construction, the geographic location information of the construction auxiliary equipment is taken as the recommended construction position.

[0073] It should be noted that the construction auxiliary equipment mainly includes a crane. Through the method, when the actual construction range information of the construction auxiliary equipment overlaps with the construction interference data of the existing railway hump decelerator equipment during construction, the geographic location information of the construction auxiliary equipment is reset based on the reset number until there is no overlap, and when the actual construction range information of the construction auxiliary equipment does not overlap with the construction interference data of the existing railway hump decelerator equipment during construction, the geographic location information of the construction auxiliary equipment is taken as the recommended construction position, which can reduce conflicts in the construction process.

[0074] Further, in the existing railway hump decelerator equipment construction process monitoring method, the following steps are further included:

[0075] When the reset number reaches the maximum value of the reset number threshold, the construction drawing data in the construction requirement data of the existing railway hump decelerator equipment is obtained, and the layout position of the existing railway hump decelerator equipment is reselected from the construction drawing data in the construction requirement data of the existing railway hump decelerator equipment;

[0076] According to the construction interference confirmation of the reselected layout position of the existing railway hump retarder equipment, the frequency data of the construction interference project is confirmed, the frequency data threshold is set, and whether the frequency data of the construction interference project is greater than the frequency data threshold is judged;

[0077] When the frequency data of the construction interference project is greater than the frequency data threshold, the layout position of the existing railway hump retarder equipment is reset;

[0078] When the frequency data of the construction interference project is not greater than the frequency data threshold, the layout of the existing railway hump retarder equipment is recommended as the position, and the layout of the existing railway hump retarder equipment is displayed in a preset manner.

[0079] It should be noted that when the frequency data of the construction interference project is greater than the frequency data threshold, the layout position of the existing railway hump retarder equipment is reset, and when the frequency data of the construction interference project is not greater than the frequency data threshold, the layout of the existing railway hump retarder equipment is recommended as the position, and the layout of the existing railway hump retarder equipment is displayed in a preset manner. In this way, the construction process of the existing railway hump retarder equipment can be optimized, so that part of the construction content that needs to be performed during the day can be transferred to the point outside, reducing the labor intensity of the construction personnel inside the point, improving the work efficiency, ensuring the personal safety of the construction operation, and reducing the safety risk. Moreover, the method of positioning in advance, pre-arranging and one-time forming reduces the number of secondary adjustments, and maximizes the construction quality.

[0080] In addition, the method further comprises:

[0081] A digital twin of the construction process of the existing railway hump retarder equipment is constructed, and the structural mechanics and acoustic propagation characteristics of the construction process of the existing railway hump retarder equipment in the construction process are integrated;

[0082] Based on the structural mechanics and acoustic propagation characteristics of the construction process of the existing railway hump retarder equipment in the construction process, the digital twin of the construction process of the existing railway hump retarder equipment is simulated by using finite element analysis and fluid dynamics to simulate the propagation path of vibration and noise in each topography;

[0083] Through simulation, the construction interference noise intensity data of each existing railway hump retarder equipment arrangement point within a preset range is predicted, and a construction interference noise intensity data threshold is set;

[0084] Obtaining a region area corresponding to the construction interference noise intensity data being greater than the construction interference noise intensity data threshold value, if the region area is greater than a preset region area threshold value, when the existing railway hump retarder equipment arrangement point is within a preset range, a preset target site is provided, and a blasting operation time with the least noise influence is selected.

[0085] It should be noted that the target site includes residential areas, commercial areas, etc. Since certain construction interference may be caused during the construction process, the method simulates the propagation path of vibration and noise in each terrain based on the structural mechanics and acoustic propagation characteristics of the existing railway hump retarder equipment construction process during the construction process, using finite element analysis and fluid dynamics on the digital twin of the existing railway hump retarder equipment construction process, thereby selecting a blasting operation time with the least noise influence and reducing the influence on the target area.

[0086] In addition, the method further comprises:

[0087] Real-time collection of construction interference data of the existing railway hump retarder equipment construction site by Internet of Things sensors, analysis of the construction interference source according to the construction interference data of the existing railway hump retarder equipment construction site, and acquisition of the interference source and the propagation law information of the interference source;

[0088] Obtaining the working parameter information of the interference source, performing interference simulation according to the working parameter information of the interference source, the interference source, and the propagation law information of the interference source, and acquiring noise intensity characteristic data of the interference source within a preset range;

[0089] Judging whether the noise intensity characteristic data of the interference source within the preset range is greater than a preset noise intensity characteristic data threshold value;

[0090] When the noise intensity characteristic data of the interference source within the preset range is greater than the preset noise intensity characteristic data threshold value, the working parameter information of the interference source is reduced or a noise reduction device is started until it is not greater than the preset noise intensity characteristic data threshold value;

[0091] When the noise intensity characteristic data of the interference source within the preset range is not greater than the preset noise intensity characteristic data threshold value, the working parameter information of the interference source is maintained unchanged.

[0092] It should be noted that the method can automatically adjust the construction equipment operation parameters (such as tower crane operation time, piling machine frequency) or start the noise reduction device (such as intelligent fog gun machine, soundproof barrier) according to the interference prediction result, thereby improving the construction rationality of the existing railway hump retarder equipment construction site.

[0093] For example, Figure 2As shown, the second aspect of the present application provides a construction process flow monitoring system 4 of the existing railway hump decelerator device, comprising a memory 41 and a processor 42, the memory 41 comprises a construction process flow monitoring method program of the existing railway hump decelerator device, and the construction process flow monitoring method program of the existing railway hump decelerator device is executed by the processor 42 to realize the steps of any one of the construction process flow monitoring method of the existing railway hump decelerator device.

[0094] The third aspect of the present application provides a computer readable storage medium comprising a construction process flow monitoring method program of the existing railway hump decelerator device, and the construction process flow monitoring method program of the existing railway hump decelerator device is executed by the processor to realize the steps of any one of the construction process flow monitoring method of the existing railway hump decelerator device.

[0095] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the various components shown or discussed can be through some interface, indirect coupling or communication connection between the devices or units can be electrical, mechanical or other forms.

[0096] The units described above as separate components can or can not be physically separated, and the components shown as units can or can not be physical units; they can be located in one place or distributed on multiple network units; and some or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0097] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be realized in the form of hardware or in the form of hardware plus software functional unit.

[0098] Those skilled in the art can understand that all or part of the steps of the above-mentioned method embodiments can be completed by program instruction related hardware, the foregoing program can be stored in a computer readable storage medium, and the program executes the steps of the method embodiments when executed; and the foregoing storage medium includes a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disc or an optical disc, and various storage medium capable of storing program codes.

[0099] Alternatively, the integrated unit of the present application can be stored in a computer readable storage medium if it is realized in the form of a software function module and sold or used as an independent product. Based on such understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product, and the computer software product is stored in a storage medium, includes several instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the embodiments of the method of the present application. The foregoing storage medium includes a mobile storage device, a ROM, a RAM, a magnetic disc or an optical disc, and various storage medium capable of storing program codes.

[0100] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for monitoring the construction process of a railway hump retarder device, characterized in that, Specifically comprising the following steps: Obtain construction requirement data of the existing railway hump retarder equipment, and construct a construction abnormal data identification model according to the construction requirement data of the existing railway hump retarder equipment; Train the construction abnormal data identification model, and adjust the training process of the construction abnormal data identification model; Identify abnormal data of the construction requirement data of the existing railway hump retarder equipment based on the construction abnormal data identification model, and perform secondary analysis in combination with construction investigation data of a target construction area; Optimize the construction process of the existing railway hump retarder equipment according to the secondary analysis result; Construct a construction abnormal data identification model according to the construction requirement data of the existing railway hump retarder equipment, specifically as follows: Extract construction drawing data in the construction requirement data of the existing railway hump retarder equipment, and construct a historical case data set according to the construction drawing data, obtain construction abnormal data and non-abnormal data in the construction drawing data from the historical case data set, and construct a training set; Construct a construction abnormal data identification model based on a deep neural network, initialize a network parameter data set of the construction abnormal data identification model, introduce a whale optimization algorithm and a snake optimization algorithm, input the training set into the construction abnormal data identification model, and randomly select network parameters from the network parameter data set of the construction abnormal data identification model for initialization training; Obtain the convergence speed and prediction accuracy of the construction abnormal data identification model, and when the convergence speed and prediction accuracy of the construction abnormal data identification model are lower than a preset evaluation index, perform global search on the network parameter data set of the construction abnormal data identification model through the whale optimization algorithm to obtain a global network parameter data set; Input the global network parameter data set into the snake optimization algorithm for local search to obtain a local network parameter data set, and train the construction abnormal data identification model according to the network parameters in the local network parameter data set; Train the construction abnormal data identification model, and adjust the training process of the construction abnormal data identification model, specifically as follows: Statistically analyze the contribution degree data of each construction abnormal data and non-abnormal data type in the prediction process of the construction abnormal data identification model, and set a contribution degree data threshold; Determine whether there is construction abnormal data and non-abnormal data type corresponding to the contribution degree data lower than the contribution degree data threshold in the training data; When there is construction abnormal data and non-abnormal data type corresponding to the contribution degree data lower than the contribution degree data threshold in the training data, delete the corresponding construction abnormal data and non-abnormal data type until there is no construction abnormal data and non-abnormal data type corresponding to the contribution degree data lower than the contribution degree data threshold; When there is construction abnormal data and non-abnormal data type corresponding to the contribution degree data lower than the contribution degree data threshold in the training data, train the construction abnormal data identification model according to the current training data.

2. The method according to claim 1, wherein the method is characterized by, The construction abnormal data identification model is used to identify abnormal data in the construction requirement data of the existing railway hump retarder equipment, and secondary analysis is performed in combination with the construction investigation data of the target construction area, specifically including: The construction requirement data of the existing railway hump retarder equipment is input into the construction abnormal data identification model for verification. Through verification, the drawing abnormal area in the construction requirement data of the existing railway hump retarder equipment is obtained, and the construction investigation data of the target construction area is obtained. The work interference data within a preset range of the existing railway hump retarder equipment is obtained according to the construction investigation data of the target construction area. The actual construction interference data of the existing railway hump retarder equipment during construction is generated according to the work interference data within a preset range of the existing railway hump retarder equipment and the drawing abnormal area in the construction requirement data of the existing railway hump retarder equipment. The secondary analysis result is generated according to the actual construction interference data of the existing railway hump retarder equipment during construction.

3. The method according to claim 1, wherein the method is characterized by, According to the secondary analysis result, the construction process of the existing railway hump retarder equipment is optimized, specifically including: According to the secondary analysis result, the construction interference data of the existing railway hump retarder equipment during construction is determined, and the geographic location information of each construction auxiliary equipment is initialized to obtain the working range information of the construction auxiliary equipment. According to the geographic location information of each construction auxiliary equipment and the working range information of the construction auxiliary equipment, the actual construction range information of each construction auxiliary equipment is obtained, and it is judged whether the actual construction range information of each construction auxiliary equipment overlaps with the construction interference data of the existing railway hump retarder equipment during construction. A reset frequency threshold is set, and when the actual construction range information of the construction auxiliary equipment overlaps with the construction interference data of the existing railway hump retarder equipment during construction, the geographic location information of the construction auxiliary equipment is reset based on the reset frequency until there is no overlap. When the actual construction range information of the construction auxiliary equipment does not overlap with the construction interference data of the existing railway hump retarder equipment during construction, the geographic location information of the construction auxiliary equipment is taken as the recommended construction position.

4. The method for monitoring the construction process of existing railway humpback reducer equipment according to claim 3, characterized in that, The following steps are also included: When the reset frequency reaches the maximum value of the reset frequency threshold, the construction drawing data in the construction requirement data of the existing railway hump retarder equipment is obtained, and the layout position of the existing railway hump retarder equipment is reselected from the construction drawing data in the construction requirement data of the existing railway hump retarder equipment. According to the reselected layout position of the existing railway hump retarder equipment, the construction interference project frequency data is confirmed, a frequency data threshold is set, and it is judged whether the frequency data of the construction interference project is greater than the frequency data threshold. When the frequency data of the construction interference project is greater than the frequency data threshold, the layout position of the existing railway hump retarder equipment is continued to be reset. When the frequency data of the construction interference project is not greater than the frequency data threshold, a layout recommended position of the existing railway hump retarder equipment is obtained, and the layout recommended position of the existing railway hump retarder equipment is displayed in a preset mode.

5. A system for monitoring the construction process of a railway hump retarder device, characterized in that, The memory comprises a program of the existing railway hump retarder equipment construction process monitoring method, and the processor executes the program of the existing railway hump retarder equipment construction process monitoring method to realize the steps of the existing railway hump retarder equipment construction process monitoring method according to any one of claims 1-4.

6. A computer-readable storage medium, characterized in that, The memory comprises a program of the existing railway hump retarder equipment construction process monitoring method, and the processor executes the program of the existing railway hump retarder equipment construction process monitoring method to realize the steps of the existing railway hump retarder equipment construction process monitoring method according to any one of claims 1-4.

Images