CN113375777A - Overload detection method and overload detection system for train - Google Patents
Overload detection method and overload detection system for train Download PDFInfo
- Publication number
- CN113375777A CN113375777A CN202110934180.0A CN202110934180A CN113375777A CN 113375777 A CN113375777 A CN 113375777A CN 202110934180 A CN202110934180 A CN 202110934180A CN 113375777 A CN113375777 A CN 113375777A
- Authority
- CN
- China
- Prior art keywords
- basis function
- radial basis
- neural network
- data
- target train
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01G—WEIGHING
- G01G19/00—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups
- G01G19/02—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups for weighing wheeled or rolling bodies, e.g. vehicles
- G01G19/04—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups for weighing wheeled or rolling bodies, e.g. vehicles for weighing railway vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The application provides an overload detection method and an overload detection system of a train, relates to the field of industrial detection, and specifically comprises the following steps: when the target train is detected, the metering data of the target train is obtained by using the metering instrument; inputting the metering data into an input layer of a radial basis function neural network metering data model, and obtaining dynamic weighing data of the target train on an output layer; the radial basis function neural network metering data model comprises an input layer, a hidden layer and an output layer; and if the dynamic weighing data is larger than the approved load data of the target train, determining that the target train is overloaded. According to the method and the device, the metering data of the target train is obtained and input to the radial basis function neural network metering data model for calculation and statistics, so that the dynamic weighing data of the target train is obtained, whether the carriage is overloaded or not can be automatically judged, and powerful guarantee is provided for safety management of the railway freight train.
Description
Technical Field
The application relates to the field of industrial detection, in particular to an overload detection method and an overload detection system of a train.
Background
In recent years, with the continuous increase of the speed of freight trains, railway safety accidents happen occasionally, and overload and unbalance loading of freight trains are important factors causing vehicle derailment and influencing railway traffic safety, so that railway freight transportation safety is directly endangered. At present, the overload and unbalance loading detection is mainly carried out by means of a Radio Frequency Identification (RFID) system and a dynamic rail weighbridge system, and the following problems exist: on one hand, weighing data of the dynamic rail weighbridge is influenced by factors such as vehicle speed, vibration and rail unevenness, and the precision is poor; on the other hand, the problems that the number of the read carriage information is dropped, the carriage chip is easy to damage and lose, the carriage information cannot be updated in time and the like exist in the radio frequency identification, and in addition, the electronic tag is not installed on the non-state railway vehicle, so that a lot of problems are brought to overload and unbalanced load detection.
Disclosure of Invention
The application aims to provide an overload detection method and an overload detection system of a train, which can improve the overload detection precision.
In order to solve the technical problem, the application provides an overload detection method for a train, which has the following specific technical scheme:
when a target train is detected, acquiring metering data of the target train by using a metering instrument;
inputting the metering data into an input layer of a radial basis function neural network metering data model, and obtaining dynamic weighing data of the target train on an output layer; the radial basis function neural network metering data model comprises an input layer, a hidden layer and an output layer;
and if the dynamic weighing data is larger than the approved load data of the target train, determining that the target train is overloaded.
Optionally, the method further includes:
acquiring video information on a rail weighbridge;
analyzing the video information to obtain the carriage information of the target train;
and determining the approved load data according to the carriage information.
Optionally, the method further includes:
taking a radial basis function as a hidden unit, and generating a hidden layer space containing the hidden unit;
determining a radial basis function center point and a mapping relation of input quantity to the hidden layer space; and the hidden layer space is used for mapping the input quantity from low dimensionality to high dimensionality to obtain the radial basis function neural network.
Optionally, the method further includes:
and training the radial basis function neural network to obtain the radial basis function neural network metering data model.
Optionally, training the radial basis function neural network to obtain the radial basis function neural network measurement data model includes:
inputting the average value of wheel weight data and the vehicle speed into the radial basis function neural network;
taking the static weighing value of the vehicle as a desired output;
obtaining the output of each unit of the hidden layer and the output layer through one-time learning calculation to obtain the deviation between the expected output and the actual output;
if the deviation is larger than a preset value, calculating a hidden layer error, and updating the weight to learn again;
if the deviation is smaller than the preset value, verifying whether the deviation of all expected outputs and actual outputs is smaller than the preset value; and if not, updating the weight to learn again, and obtaining the radial basis function neural network metering data model when all the deviations are smaller than the preset value.
Optionally, when the radial basis function neural network is trained to obtain the radial basis function neural network measurement data model, the method further includes:
and determining the function parameters of the radial basis function neural network by utilizing a K-means clustering algorithm.
The present application further provides an overload detection system of a train, including:
the data acquisition module is used for acquiring the metering data of the target train by using a metering instrument when the target train is detected;
the data input module is used for inputting the metering data into an input layer of a radial basis function neural network metering data model and obtaining dynamic weighing data of the target train on an output layer; the radial basis function neural network metering data model comprises an input layer, a hidden layer and an output layer;
and the overload detection module is used for determining that the target train is overloaded if the dynamic weighing data is larger than the approved load data of the target train.
Optionally, the method further includes:
the load data acquisition module is used for acquiring video information on the rail weighbridge; analyzing the video information to obtain the carriage information of the target train; and determining the approved load data according to the carriage information.
The application provides an overload detection method of a train, which comprises the following steps: when a target train is detected, acquiring metering data of the target train by using a metering instrument; inputting the metering data into an input layer of a radial basis function neural network metering data model, and obtaining dynamic weighing data of the target train on an output layer; the radial basis function neural network metering data model comprises an input layer, a hidden layer and an output layer; and if the dynamic weighing data is larger than the approved load data of the target train, determining that the target train is overloaded.
According to the method and the device, the metering data of the target train is obtained and input to the radial basis function neural network metering data model for calculation and statistics, so that the dynamic weighing data of the target train is obtained, whether the carriage is overloaded or not can be automatically judged, and powerful guarantee is provided for safety management of the railway freight train.
This application still provides an overload detection system of train, has above-mentioned beneficial effect, and this is no longer repeated here.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of an overload detection method for a train according to an embodiment of the present disclosure;
fig. 2 is a schematic wheel diagram of a train during unbalanced load detection according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram illustrating an application of a method for detecting an overload of a train according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an overload detection system for a train according to an embodiment of the present disclosure.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, fig. 1 is a flowchart of a method for detecting an overload of a train according to an embodiment of the present application, where the method includes:
s101: when a target train is detected, acquiring metering data of the target train by using a metering instrument;
the method aims to acquire the metering data of the target train by using the metering instrument. The metering data mainly refers to dynamic metering data of a carriage wheel pair, and also can comprise a real-time speed value, wherein a specifically adopted metering instrument is not limited, and the metering data can comprise a weight acquisition device or a weight acquisition sensor arranged on a track scale, and a corresponding speed sensor or a corresponding speed acquisition device if the speed of a target train needs to be detected. Specifically, the system reads the data of the metering instrument through an RS232/485 interface, obtains the weight data of four train wheel pairs of the rail weighbridge, calculates the total weight of the current carriage, and can also calculate the unbalance loading value. It is easily understood that the number of train wheel pairs obtained in the present embodiment is only one preferred reference value provided by the present embodiment, and those skilled in the art may choose to obtain weight data of more train wheel pairs on the basis of the present embodiment, for example, eight train wheel pairs, which is not limited herein by way of example.
In addition, in the step, whether a train passes through or not can be detected by a camera near the track, and the train is not identified in an empty rail state. When the train is detected to pass, the photoelectric switch is triggered, so that the video camera acquires the video signal of the train on the dynamic track scale, and the train compartment information is obtained. Specifically, the photoelectric switch triggering can be realized by capturing the rising edge of the photoelectric switch, data of four wheel pairs of the track scale are read simultaneously, and when the front frame weight data and the rear frame weight data exceed a set threshold value, the situation that a carriage passes through is judged, and the carriage is just located at the track scale position. Of course, the threshold value set here is not limited, and may be set to 1/3 where the lightest car is empty.
S102: inputting the metering data into an input layer of a radial basis function neural network metering data model, and obtaining dynamic weighing data of the target train on an output layer;
this step is directed to inputting metrology data into a radial basis function neural network metrology data model, the model comprising an input layer, a hidden layer, and an output layer. It should be noted that, in this embodiment, how to obtain the radial basis function neural network metric data model is not specifically limited, in this embodiment, only the radial basis function neural network metric data model is required to be able to receive input metric data and output corresponding dynamic weighing data, and any model capable of implementing the process may be used as the radial basis function neural network metric data model in this embodiment.
S103: and if the dynamic weighing data is larger than the approved load data of the target train, determining that the target train is overloaded.
And when the dynamic weighing data is larger than the approved load data of the target train, determining that the target train is overloaded.
The approved load data can be obtained by comparing the carriage information obtained in the above steps, that is, the carriage information is obtained by analyzing the video information obtained by the camera, and then the approved load data corresponding to the carriage information is confirmed. It is easily understood that the car information may include car types, numbers, and the like, and the settled load data of the target train is actually the sum of the settled load data of the cars due to differences in the settled loads of the different car types and numbers. Therefore, it is necessary to acquire the approved load data of the target train before the step is performed, so as to perform the weight data comparison process of the step.
According to the embodiment of the application, the metering data of the target train is obtained and input into the radial basis function neural network metering data model for calculation and statistics, so that the dynamic weighing data of the target train is obtained, whether the carriage is overloaded or not can be automatically judged, and powerful guarantee is provided for safety management of the railway freight train.
The following description is directed to how to obtain a radial basis function neural network metric data model, and it should be noted that the process of obtaining a radial basis function neural network metric data model disclosed below is only one preferred process disclosed in the present application:
taking a radial basis function as a hidden unit, and generating a hidden layer space containing the hidden unit;
determining a radial basis function center point and a mapping relation of input quantity to the hidden layer space; and the hidden layer space is used for mapping the input quantity from low dimensionality to high dimensionality to obtain the radial basis function neural network.
A Radial Basis Function (RBF) neural network is a three-layer neural network comprising an input layer, a hidden layer, and an output layer. The transformation from the input space of the input layer to the hidden layer space of the hidden layer is non-linear, while the transformation from the hidden layer space to the output layer space is linear. The hidden layer space is formed by taking a Radial Basis Function (RBF) as the 'base' of a hidden unit, so that an input vector can be directly mapped to the hidden space without being connected through a weight. When the Radial Basis Function (RBF) center point is determined, the mapping relationship is determined. The mapping from the hidden layer space to the output space is linear, that is, the output of the network is the linear weighted sum of the hidden unit outputs, and the weight here is the network adjustable parameter. Wherein the role of the hidden layer is to map the vector from p of low dimension to h of high dimension, so that the inseparable linear case of low dimension becomes highly dimensionable. Thus, the mapping of the network from input to output is non-linear, whereas the network output is linear for the adjustable parameters. The weight of the network can be directly solved by a linear equation system, thereby greatly accelerating the learning speed and avoiding the local minimum problem.
The activation function of the radial basis function neural network can be expressed as:
wherein
For the p-th input sample,
is the ith center point, h is the node number of the hidden layer, and n is the number of samples or classifications output. The structure of the radial basis function neural network yields the output of the network as:
wherein
The synaptic weight between the ith node of the hidden layer and the jth node of the output layer.
Of course, d is the expected output value of the sample, expressed as a loss function of least squares:
the above is a description of the activation function and related structure of the radial basis function neural network.
The process of obtaining the radial basis function neural network metric data model based on the Radial Basis Function (RBF) neural network may be as follows:
firstly, inputting the average value of wheel weight data and vehicle speed into the radial basis function neural network;
secondly, taking the static weighing value of the vehicle as expected output;
thirdly, obtaining the output of each unit of the hidden layer and the output layer through one-time learning calculation to obtain the deviation between the expected output and the actual output;
fourthly, if the deviation is larger than a preset value, calculating a hidden layer error, and updating the weight to learn again;
fifthly, if the deviation is smaller than a preset value, verifying whether all the deviations of the expected output and the actual output are smaller than the preset value; and if not, updating the weight to learn again, and obtaining the radial basis function neural network metering data model when all the deviations are smaller than the preset value.
Since the metering data obtained by the metering instrument includes the weight data of the train wheel sets, and each wheel set includes the left wheel weight data and the right wheel weight data, the average value of the left wheel weight data and the right wheel weight data can be used as the average value of the wheel weight data.
In addition, when the radial basis function neural network is trained to obtain the radial basis function neural network measurement data model, the function parameters of the radial basis function neural network can be determined by utilizing a K-means clustering algorithm.
I. And (5) initializing the network. Given the initial center of the hidden unit i
；
Calculating the distance
；
And III, solving the minimum distance,
；
IV, adjusting the center of the device,
；
and V, judging. If it is not
The iteration is terminated, otherwise II is carried out.
Learning of the weight W adopts supervised learning and least square method (LMS) algorithm, specifically: is provided with N groups of input samples
An error function is defined.
Initializing a weight: (
）。
Calculating an output error:
adjusting the network weight:
get
。
And repeatedly training the Radial Basis Function (RBF) model for N rounds by using a plurality of groups of data collected in advance to obtain the final Radial Basis Function (RBF) neural network metering data model.
The relative error of weighing and metering is verified to be less than 3 percent, and the requirement of weighing precision can be met. Of course, other values may be used by those skilled in the art as the relative error accuracy, and are not limited herein.
Based on the above embodiment, as a preferred embodiment, referring to fig. 2, this embodiment may also detect the car unbalance loading condition on the basis of detecting the overload, and the specific process may be as follows:
total weight calculating method
Front frame weight WQ = first front right wheel 1+ second front right wheel 2+ first front left wheel 3+ second front left wheel 4;
the rear frame weight WH = the first rear right wheel 5+ the second rear right wheel 6+ the first rear left wheel 7+ the second rear left wheel 8;
total weight G = front frame weight WQ + rear frame weight WH.
② front and back deviation calculating method
Front frame weight WQ = first front right wheel 1+ second front right wheel 2+ first front left wheel 3+ second front left wheel 4;
the rear frame weight WH = the first rear right wheel 5+ the second rear right wheel 6+ the first rear left wheel 7+ the second rear left wheel 8;
front-rear unbalance Δ W = front frame weight WQ — rear frame weight WH.
Method for calculating left and right deviation
The offset weight difference Δ W of the longitudinal offset load = front frame weight WQ — rear frame weight WH;
front left-right unbalance rate rQ = [ (first front left wheel 3 weight + second front left wheel 4 weight) - (first front right wheel 1 weight + second front right wheel 2 weight) ]/[ (first front left wheel 3 weight + second front left wheel 4 weight) + (first front right wheel 1 weight + second front right wheel 2 weight) ];
a rear left-right unbalance rate rH = [ (first rear left wheel 7 weight + second rear left wheel 8 weight) - (first rear right wheel 5 weight + second rear right wheel 6 weight) ]/[ (first rear left wheel 7 weight + second rear left wheel 8 weight) + (first rear right wheel 5 weight + second rear right wheel 6 weight) ];
if the load ZG of the carriage is less than the total weight G-empty weight KG, judging the carriage is overloaded;
if the front-rear unbalance loading limit LB is smaller than the front-rear unbalance loading value delta W, the front-rear unbalance loading state is judged;
if the front unbalance loading rate limit value rF is less than the front unbalance loading rate rQ, the front unbalance loading is judged to be front left and right unbalance loading, rQ is greater than 0 and is the front left unbalance loading, and rQ is less than 0 and is the front right unbalance loading;
if the front offset ratio limit value rB is less than the rear offset ratio rH, the rear left and right offset load is determined, wherein rH > 0 is the left rear offset load, and rH < 0 is the right rear offset load.
In order to achieve the above object, a specific application process of the train overload detection method is provided, and referring to fig. 3, fig. 3 is a schematic structural diagram of an application of the train overload detection provided by an embodiment of the present application, and includes: photoelectric switch 1, high definition camera 2, image processor 3, host computer 4, can also include the client, and it can be connected with host computer 4 (not shown in fig. 3), wherein:
the photoelectric switch 1 is used for triggering the system to read the metering data measured by the metering instrument, specifically including the rail balance data, and triggering the high-definition camera 2 to collect images.
And the image processor 3 is used for analyzing and identifying the received high-definition video signals to obtain the current carriage number, the load and the empty weight information of the freight train.
The upper computer 4 is used for receiving the metering data, inputting the Radial Basis Function (RBF) neural network metering model for calculation, and outputting dynamic weighing values of the four wheel pairs. Of course, the Radial Basis Function (RBF) neural network needs to be learned and trained in advance, and the weights between the hidden layer and the input layer of the metering model can be trained by an unsupervised clustering method, such as a k-mean method. And training the weight between the output layer and the hidden layer by adopting a method with a guide. After determining the weights between the hidden layer and the input layer, the static weighing measurement data is substituted as an ideal output into a Radial Basis Function (RBF) network, thereby deriving the weights between the neurons of each output layer and the hidden layer. Adopting a linear least square method and a gradient method condition full matrix, and finally converging the gradient algorithm to a global optimal solution;
weighing information of each carriage of the freight train is integrated and summarized into an overload and unbalance loading and weighing information configuration table of the freight train, and the overload and unbalance loading and weighing information configuration table is output to the client 5, so that automatic overload and unbalance loading detection metering management is realized.
In addition, the carriage information identified by the image processor can be read, calculation and comparison are carried out, whether the carriage is overloaded and unbalanced load is judged, and automatic alarm of the overloaded and unbalanced load is carried out.
In the following, a train overload detection system provided by an embodiment of the present application is introduced, and the below-described overload detection system and the above-described train overload detection method may be referred to correspondingly.
Fig. 4 is a schematic structural diagram of an overload detection system of a train according to an embodiment of the present application, and the present application further provides an overload detection system of a train, including:
the data acquisition module 100 is configured to acquire metering data of a target train by using a metering device when the target train is detected;
the data input module 200 is used for inputting the metering data into an input layer of a radial basis function neural network metering data model and obtaining dynamic weighing data of the target train on an output layer; the radial basis function neural network metering data model comprises an input layer, a hidden layer and an output layer;
and an overload detection module 300, configured to determine that the target train is overloaded if the dynamic weighing data is greater than the approved load data of the target train.
Based on the above embodiment, as a preferred embodiment, the method may further include:
the load data acquisition module is used for acquiring video information on the rail weighbridge; analyzing the video information to obtain the carriage information of the target train; and determining the approved load data according to the carriage information.
The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system provided by the embodiment, the description is relatively simple because the system corresponds to the method provided by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present application are explained herein using specific examples, which are provided only to help understand the method and the core idea of the present application. It should be noted that, for those skilled in the art, it is possible to make several improvements and modifications to the present application without departing from the principle of the present application, and such improvements and modifications also fall within the scope of the claims of the present application.
It is further noted that, in the present specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Claims (8)
1. An overload detection method for a train, comprising:
when a target train is detected, acquiring metering data of the target train by using a metering instrument;
inputting the metering data into an input layer of a radial basis function neural network metering data model, and obtaining dynamic weighing data of the target train on an output layer; the radial basis function neural network metering data model comprises an input layer, a hidden layer and an output layer;
and if the dynamic weighing data is larger than the approved load data of the target train, determining that the target train is overloaded.
2. The overload detection method of claim 1, further comprising:
acquiring video information on a rail weighbridge;
analyzing the video information to obtain the carriage information of the target train;
and determining the approved load data according to the carriage information.
3. The overload detection method of claim 1, further comprising:
taking a radial basis function as a hidden unit, and generating a hidden layer space containing the hidden unit;
determining a radial basis function center point and a mapping relation of input quantity to the hidden layer space; and the hidden layer space is used for mapping the input quantity from low dimensionality to high dimensionality to obtain the radial basis function neural network.
4. The overload detection method of claim 3, further comprising:
and training the radial basis function neural network to obtain the radial basis function neural network metering data model.
5. The overload detection method of claim 4, wherein training a radial basis function neural network to obtain the radial basis function neural network metric data model comprises:
inputting the average value of wheel weight data and the vehicle speed into the radial basis function neural network;
taking the static weighing value of the vehicle as a desired output;
obtaining the output of each unit of the hidden layer and the output layer through one-time learning calculation to obtain the deviation between the expected output and the actual output;
if the deviation is larger than a preset value, calculating a hidden layer error, and updating the weight to learn again;
if the deviation is smaller than the preset value, verifying whether the deviation of all expected outputs and actual outputs is smaller than the preset value; and if not, updating the weight to learn again, and obtaining the radial basis function neural network metering data model when all the deviations are smaller than the preset value.
6. The overload detection method according to claim 5, wherein when the radial basis function neural network is trained to obtain the radial basis function neural network metric data model, the method further comprises:
and determining the function parameters of the radial basis function neural network by utilizing a K-means clustering algorithm.
7. An overload detection system for a train, comprising:
the data acquisition module is used for acquiring the metering data of the target train by using a metering instrument when the target train is detected;
the data input module is used for inputting the metering data into an input layer of a radial basis function neural network metering data model and obtaining dynamic weighing data of the target train on an output layer; the radial basis function neural network metering data model comprises an input layer, a hidden layer and an output layer;
and the overload detection module is used for determining that the target train is overloaded if the dynamic weighing data is larger than the approved load data of the target train.
8. The overload detection system of claim 7, further comprising:
the load data acquisition module is used for acquiring video information on the rail weighbridge; analyzing the video information to obtain the carriage information of the target train; and determining the approved load data according to the carriage information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110934180.0A CN113375777A (en) | 2021-08-16 | 2021-08-16 | Overload detection method and overload detection system for train |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110934180.0A CN113375777A (en) | 2021-08-16 | 2021-08-16 | Overload detection method and overload detection system for train |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113375777A true CN113375777A (en) | 2021-09-10 |
Family
ID=77577181
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110934180.0A Pending CN113375777A (en) | 2021-08-16 | 2021-08-16 | Overload detection method and overload detection system for train |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113375777A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116152757A (en) * | 2023-04-18 | 2023-05-23 | 深圳亿维锐创科技股份有限公司 | Weighing data analysis method and related device based on multiple points |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1061093A (en) * | 1990-10-31 | 1992-05-13 | 柳州铁路局科学技术研究所 | Dynamic weighing device for goods train |
| WO2005008191A1 (en) * | 2003-07-22 | 2005-01-27 | Chengdu Huoan Measure Technical Center | New apparatus for examining the over loading and bias loading of railcars |
| CN102564546A (en) * | 2010-12-14 | 2012-07-11 | 金基太 | Method and system for detecting overload and unlawful measurement of vehicle |
| CN202770517U (en) * | 2012-09-20 | 2013-03-06 | 南车南京浦镇车辆有限公司 | Humanized motor train unit overload early warning system |
| CN104036321B (en) * | 2014-06-06 | 2017-05-17 | 陕西科技大学 | Icing information detection method |
-
2021
- 2021-08-16 CN CN202110934180.0A patent/CN113375777A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1061093A (en) * | 1990-10-31 | 1992-05-13 | 柳州铁路局科学技术研究所 | Dynamic weighing device for goods train |
| WO2005008191A1 (en) * | 2003-07-22 | 2005-01-27 | Chengdu Huoan Measure Technical Center | New apparatus for examining the over loading and bias loading of railcars |
| CN102564546A (en) * | 2010-12-14 | 2012-07-11 | 金基太 | Method and system for detecting overload and unlawful measurement of vehicle |
| CN202770517U (en) * | 2012-09-20 | 2013-03-06 | 南车南京浦镇车辆有限公司 | Humanized motor train unit overload early warning system |
| CN104036321B (en) * | 2014-06-06 | 2017-05-17 | 陕西科技大学 | Icing information detection method |
Non-Patent Citations (2)
| Title |
|---|
| 付研宇: "轨道车辆动态称重数据处理算法研究", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》 * |
| 程武山: "《智能控制理论与应用》", 30 November 2006 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116152757A (en) * | 2023-04-18 | 2023-05-23 | 深圳亿维锐创科技股份有限公司 | Weighing data analysis method and related device based on multiple points |
| CN116152757B (en) * | 2023-04-18 | 2023-07-07 | 深圳亿维锐创科技股份有限公司 | Weighing data analysis method and related device based on multiple points |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109641603B (en) | Abnormality detection device, abnormality detection method, and computer program | |
| US6198987B1 (en) | Method and a multi-functional apparatus for determining the class of a vehicle | |
| US9121747B2 (en) | Object evaluation accounting for motion-related dynamic forces | |
| JP6750967B2 (en) | Vehicle type identification device and vehicle type identification method | |
| CN111524365B (en) | Method for classifying vehicle types by using multiple geomagnetic sensors | |
| CN109839175B (en) | Bridge live load optimizing and recognizing system | |
| CN114076631A (en) | Overload vehicle identification method, system and equipment | |
| CN113375777A (en) | Overload detection method and overload detection system for train | |
| CN114822029B (en) | Bridge deck traffic flow load space-time distribution reconstruction method, system and device | |
| JP2012059058A (en) | Risk estimation device and program | |
| CN112781702B (en) | Method and system for weighing vehicle | |
| CN107204118A (en) | Weighing information matching process, device and server | |
| CN104165676A (en) | Dynamic vehicle high-accuracy weighing method achieved in axle dynamic monitoring mode and axle set weighing mode | |
| JP7424945B2 (en) | Failure detection device, toll collection system, failure detection method, and program | |
| CN107491786B (en) | Automatic visual detection and identification method for repeated weighing behaviors of tobacco purchase | |
| Balid et al. | Real-time magnetic length-based vehicle classification: Case study for inductive loops and wireless magnetometer sensors in Oklahoma state | |
| KR100794591B1 (en) | Automatic measuring system for vehicle information | |
| RU2448331C1 (en) | Method and system for increasing accuracy of weighing motor vehicle in motion | |
| Fanthony et al. | Yolo algorithm-based surrounding object identification on autonomous electric vehicle | |
| JP6864734B2 (en) | Billing system, billing method and program | |
| JP6986584B2 (en) | Information processing device, information processing method, and information processing program, and vehicle arrival time estimation device | |
| CN113112061A (en) | Method and device for predicting vehicle oil consumption | |
| CN114255452A (en) | Target ranging method and device | |
| CN107368460B (en) | Train shaking factor detection device and method | |
| US11703374B2 (en) | Onboard system, charging system, charging method, and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210910 |