Control system and control method for intelligent electric locomotive brake device

Abstract

The invention discloses a control system and a control method for an intelligent electric locomotive brake device, relates to the technical field of electric locomotives, and solves the technical problem in the prior art that brake control lags and easily causes current overload and damage to the brake device; the control system comprises: a brake control module collects the working current of the brake device in real time and accurately through a built-in high-performance current sensor; a data verification module is used to verify the validity of the data collected by the brake control module, and if the data abnormality exceeds the tolerance range, it will enter an alarm mode to improve data accuracy; a PLC controller uses a data processing module to quickly process and analyze the working current, cooperates with an industrial-grade communication interface to complete high-speed and lossless transmission of the processing results, and controls the operation of the brake device according to the processing results; a predictive processing module predicts the current trend of the brake device in a short period of time in the future according to the working state of the intelligent electric locomotive, and then gives an early warning to effectively prevent the brake device from being damaged by current overload.

Description

Technical Field

[0001] The present invention relates to the technical field of electric locomotives, and in particular to a control system and a control method for an intelligent electric locomotive brake device. Background Art

[0002] In the existing brake control method, after receiving the brake command, the electric locomotive brake device sends a control signal to the forward and reverse controller after being processed by the PLC program, and the forward and reverse controller controls the action of the brake device; a current transformer is arranged along the power supply line of the brake device to monitor the working current of the brake device, and the PLC program determines whether the working current reaches the preset threshold value, and then controls the brake device to stop;

[0003] However, the prior art has the following problems: the working current fed back by the current transformer is insensitive and has a lag phenomenon, so that the PLC program cannot process the working current in a timely manner, and the sending of the control signal may also be delayed, resulting in the brake device continuing to brake after the working current reaches a preset threshold, making the brake device easy to be damaged and greatly shortening its service life; Based on the above shortcomings, the present invention proposes a control system and a control method for an intelligent electric locomotive brake device. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a control system and a control method for an intelligent electric locomotive brake device, replacing components such as current transformers for collecting and feeding back the working current of the brake device with a brake control module; the brake control module can directly collect the working current and send the working current directly to the PLC program for processing through communication, thereby avoiding the problem of brake control lag in the prior art; the working current is quickly processed and analyzed by a data processing module, a predictive processing module is introduced, and a high-speed, lossless transmission of the processing results is completed in conjunction with an industrial-grade communication interface, and the operation of the brake device is controlled according to the processing results, so as to effectively prevent the brake device from being damaged by current overload.

[0005] To achieve the above-mentioned object, the first aspect of the present invention provides a control system and a control method for an intelligent electric locomotive brake device, including a brake control module, a PLC controller, a data processing module, a data verification module and a predictive processing module;

[0006] The brake control module is equipped with a current sensor for collecting the working current of the brake device in real time, and directly sending the collected working current data to the PLC controller through the wireless communication module;

[0007] The data verification module is connected to the PLC controller and is used to verify the validity of the data collected by the brake control module and calculate the steady measurement deviation value CW; if the steady measurement deviation value CW ≥ the preset deviation threshold, it is determined that the data abnormality exceeds the tolerance range and enters the alarm mode;

[0008] When the measured deviation value CW is less than the preset deviation threshold, the working current collected by the brake control module is determined to be valid data. At this time, the average working current value in the preset time period is obtained by arithmetic averaging, which is the working current of the brake device at a certain moment;

[0009] The PLC controller uses the data processing module to quickly process and analyze the working current, and cooperates with the industrial-grade communication interface to complete the high-speed and lossless transmission of the processing results. Finally, the brake control module controls the operation of the brake device according to the processing results.

[0010] During the analysis and processing of the working current, the predictive processing module is used to predict the current trend of the brake device in the short future time according to the working state of the intelligent electric locomotive; and to determine whether there is a trend exceeding a preset threshold value based on the prediction result, and then provide early warning.

[0011] Furthermore, the specific verification steps of the data verification module are as follows:

[0012] Obtain the working current collected by the brake control module and establish a curve chart of the working current changing over time;

[0013] From the initial moment, the working current data is collected at preset intervals and marked as DLi;

[0014] In a preset time period, the maximum value of the working current is marked as DLmax, and the minimum value of the working current is marked as DLmin; the difference ratio DE is calculated using the formula DE=(DLmax-DLmin) / DLmax;

[0015] Compare adjacent working current data to obtain current discrete value DZ;

[0016] If the current discrete value DZ>the preset discrete threshold value, it indicates that the working current of the brake device is discrete, and the current discrete value DZ is marked as the first discrete value;

[0017] The number of occurrences of the statistical discrete situation is the discrete frequency P1, and all the first discrete values ​​are accumulated to obtain the discrete total value LZ; using the formula The stabilization deviation value CW is calculated, where a1 and a2 are both preset coefficient factors.

[0018] Furthermore, the working principle of the current prediction model is as follows:

[0019] Train the AI ​​model based on historical data to obtain a current prediction model;

[0020] The current prediction model is used to predict the current trend of the brake device in the short term in the future according to the working state of the intelligent electric locomotive;

[0021] Determine whether there is a trend exceeding the preset threshold based on the forecast results, and then provide early warning;

[0022] Adjust the brake action according to the early warning signal, including:

[0023] The control instruction is set according to the early warning signal. Before the control instruction is triggered, it is verified in real time whether the actual current threshold and the predicted current threshold are the same. If they are not the same, it can be determined whether the control instruction needs to be adjusted.

[0024] Furthermore, the specific training steps of the current prediction model are as follows:

[0025] Step 1: sorting and extracting historical data to form input and output data sets; the historical data includes historical working status data of the electric locomotive and historical current trends of the brake device;

[0026] Step 2: Clean the input and output data sets and process missing values; standardize the processed data and divide the data sets into training set, validation set and test set;

[0027] Step 3: Establish an LSTM neural network model and initialize the neural network weights;

[0028] Step 4: Input the training set, validation set, and test set as historical feature values ​​into the LSTM neural network model for model training, and evaluate the model through the loss function to obtain the optimal current prediction model that minimizes the overall error of the training samples.

[0029] Furthermore, the input data refers to the working state data of the electric locomotive and the current trend of the brake device within a certain time period and at a certain time interval; the output data is the current trend of the brake device after a certain period of time lags behind the input data.

[0030] Furthermore, the number of input nodes of the long short-term memory neural network LSTM is specified according to the number of input variables, the number of appropriate hidden layer nodes is set, and the number of output nodes representing the current trend prediction value is set.

[0031] Furthermore, the Nguyen-Widrow method is used to initialize the neural network weights; the neural network weights include at least one of the model's input value, hidden value, number of model layers, neuron discard rate, activation function, feature weight initial value, and bias.

[0032] Furthermore, the root mean square error equation is used as the loss function.

[0033] Furthermore, the wireless communication module is one or more of a Bluetooth module, a WIFI module, a TD-LTE / FDD-LTE module, and a NB-IOT / LoRa module.

[0034] Furthermore, the control method of the intelligent electric locomotive brake device comprises the following steps:

[0035] The first step is that the brake control module uses the built-in high-performance current sensor to collect the working current of the brake device in real time and accurately, and sends the collected data directly to the PLC controller through the wireless communication module;

[0036] In the second step, the PLC controller drives the data verification module to verify the validity of the data collected by the brake control module; if the data abnormality exceeds the tolerance range, it will enter the alarm mode;

[0037] Step 3: The PLC controller uses the data processing module to quickly process and analyze the working current, and cooperates with the industrial-grade communication interface to complete the high-speed and lossless transmission of the processing results. Finally, the brake control module controls the operation of the brake device according to the processing results.

[0038] Step 4. During the analysis and processing of the working current, the predictive processing module is used to predict the current trend of the brake device in the short term in the future according to the working status of the intelligent electric locomotive, and determine whether there is a trend exceeding the preset threshold based on the prediction result, and then provide an early warning.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] 1. The present invention replaces the components such as current transformers that collect and feedback the working current of the brake device with a brake control module; the brake control module can directly collect the working current, and directly send the working current to the PLC program for processing through communication. The PLC controller uses the data processing module to quickly process and analyze the working current, cooperates with the industrial-grade communication interface to complete the high-speed and lossless transmission of the processing results, and controls the operation of the brake device according to the processing results, thereby avoiding the problem of brake control lag in the prior art;

[0041] 2. In the present invention, before the data processing module quickly processes and analyzes the working current, the data verification module is used to verify the validity of the data collected by the brake control module; if the data abnormality exceeds the tolerance range, it will enter the alarm mode, stop the brake device and output alarm information to improve data accuracy; in the process of analyzing and processing the working current, a predictive processing module is introduced, and the predictive processing module is used to predict the current trend of the brake device in the short future time according to the working status of the intelligent electric locomotive; determine whether there is a trend exceeding the preset threshold based on the prediction results, and then give an early warning to effectively prevent the brake device from being damaged by current overload. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 The system block diagram of the control system of the intelligent electric locomotive brake device of the present invention

[0044] Figure 2 The present invention is a flow chart of a control method of an intelligent electric locomotive brake device.

[0045] Figure 3 The figure is a flow chart of the training steps of the current prediction model in the present invention. DETAILED DESCRIPTION

[0046] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] See also Figures 1 to 3 , the first aspect of the present invention provides a control system for an intelligent electric locomotive brake device, including a brake control module, a wireless communication module, a PLC controller, a data processing module, a data verification module and a predictive processing module;

[0048] The brake control module is equipped with a high-performance current sensor for real-time and accurate acquisition of the working current of the brake device. At the same time, the data collected by the brake control module and the corresponding signal are directly sent to the PLC controller for processing through the wireless communication module. The wireless communication module is one or more of the following modules: Bluetooth module, WIFI module, TD-LTE / FDD-LTE module, NB-IOT / LoRa module.

[0049] The PLC controller uses the data processing module to quickly process and analyze the working current, and cooperates with the industrial-grade communication interface to complete the high-speed and lossless transmission of the processing results. Finally, the brake control module controls the operation of the brake device according to the processing results, avoiding the problem of brake control lag in the prior art.

[0050] It should be noted that: before the data processing module quickly processes and analyzes the working current, the data verification module is used to verify the validity of the data collected by the brake control module; if the data abnormality exceeds the tolerance range, it will enter the alarm mode, stop the brake device and output the alarm information;

[0051] The specific verification steps of the data verification module are as follows:

[0052] Obtain the working current collected by the brake control module and establish a curve chart of the working current changing over time; the curve chart includes the working current data collected over a period of time;

[0053] From the initial moment, the working current data is collected at preset intervals and marked as DLi, i = 1, 2, ..., n; for example: detection is performed once every 2ms, 50 sets of working current data are detected in 0.1s, and n is 50;

[0054] In a preset time period (e.g. 0.1s), the maximum working current is marked as DLmax, and the minimum working current is marked as DLmin;

[0055] The difference ratio DE is calculated using the formula DE = (DLmax-DLmin) / DLmax;

[0056] Compare adjacent working current data to obtain a current discrete value DZ; for example: current discrete value DZ = |DLi-DL(i-1)|; compare the current discrete value DZ with a preset discrete threshold;

[0057] If DZ>preset discrete threshold, it indicates that the working current of the brake device is discrete, which may be abnormal. At this time, the current discrete value DZ is marked as the first discrete value;

[0058] The number of occurrences of the statistical discrete situation is the discrete frequency P1, and all the first discrete values ​​are accumulated to obtain the discrete total value LZ; using the formula The stability deviation value CW is calculated, where a1 and a2 are both preset coefficient factors;

[0059] Compare the stable measurement deviation value CW with the preset deviation threshold; if the stable measurement deviation value CW is less than the preset deviation threshold, it is determined that the working current collected by the brake control module is highly stable and is valid data. At this time, the average working current value in the preset time period is obtained by arithmetic averaging, which is the working current of the brake device at a certain moment;

[0060] If the measured deviation value CW ≥ the preset deviation threshold, the working current data collected by the brake control module is judged to be abnormal and exceeds the tolerance range; at this time, the alarm mode is entered, the brake device is stopped and an alarm message is output;

[0061] In this embodiment, a predictive processing module is introduced during the analysis and processing of the working current to effectively prevent the brake device from being damaged by current overload. The working principle of the predictive processing module is as follows:

[0062] Train the AI ​​model based on historical data to obtain a current prediction model;

[0063] Among them, the specific training steps of the current prediction model are as follows:

[0064] Step 1: Sort and extract historical data to form input and output data sets; historical data includes historical working status data of electric locomotives and historical current trends of brake devices;

[0065] The input data refers to the working status data of the electric locomotive and the current trend of the brake device within a certain period of time and at a certain time interval; the output data is the current trend of the brake device after a certain period of time lags behind the input data;

[0066] Step 2: Clean the input and output data sets and process missing values; standardize the processed data and divide the data sets into training set, validation set and test set;

[0067] Step 3: Establish LSTM neural network model; initialize neural network weights;

[0068] Among them, the number of input nodes of the long short-term memory neural network LSTM is specified according to the number of input variables, the number of appropriate hidden layer nodes is set, and the number of output nodes representing the current trend prediction value is set;

[0069] The Nguyen-Widrow method is used to initialize the neural network weights; the neural network weights include at least one of the model input value, hidden value, number of model layers, neuron discard rate, activation function, feature weight initial value, and bias;

[0070] Step 4: Input the training set, validation set, and test set as historical feature values ​​into the LSTM neural network model for model training, and evaluate the model through the loss function to obtain the optimal current prediction model that minimizes the overall error of the training samples; wherein the root mean square error equation is used as the loss function;

[0071] The current prediction model can predict the current trend of the brake device in the short term in the future according to the working status of the intelligent electric locomotive, and determine whether there is a trend exceeding the preset threshold based on the prediction results, so as to provide early warning;

[0072] Adjust the brake action according to the early warning signal to prevent the actual current from being too large and causing damage to the equipment; specifically include:

[0073] Set the control command according to the early warning signal, and verify in real time whether the actual current threshold and the predicted current threshold are the same before the control command is triggered. If they are not the same, it can be determined whether the control command needs to be adjusted.

[0074] A second aspect of the present invention provides a control method for an intelligent electric locomotive brake device, comprising:

[0075] The first step is that the brake control module uses the built-in high-performance current sensor to collect the working current of the brake device in real time and accurately, and sends the collected data directly to the PLC controller through the wireless communication module;

[0076] In the second step, the PLC controller drives the data verification module to verify the validity of the data collected by the brake control module. If the data abnormality exceeds the tolerance range, it will enter the alarm mode;

[0077] Step 3: The PLC controller uses the data processing module to quickly process and analyze the working current, and cooperates with the industrial-grade communication interface to complete the high-speed and lossless transmission of the processing results. Finally, the brake control module controls the operation of the brake device according to the processing results.

[0078] The fourth step is to introduce a predictive processing module in the process of analyzing and processing the working current. The predictive processing module is used to predict the current trend of the brake device in the short term in the future according to the working status of the intelligent electric locomotive, and determine whether there is a trend exceeding the preset threshold based on the prediction results, and then give an early warning.

[0079] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0080] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0081] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. The control system of the intelligent electric locomotive brake device is characterized by: It includes a brake control module, a PLC controller, a data processing module, a data verification module and a predictive processing module; The brake control module is equipped with a current sensor for collecting the working current of the brake device in real time, and directly sending the collected working current data to the PLC controller through the wireless communication module; The data verification module is connected to the PLC controller and is used to verify the validity of the data collected by the brake control module and calculate the stability deviation value CW; The specific verification steps are as follows: Obtain the working current collected by the brake control module and establish a curve chart of the working current changing over time; From the initial moment, the working current data is collected at preset intervals and marked as DLi; In the preset time period, the maximum working current is marked as DLmax, and the minimum working current is marked as DLmin; the difference ratio DE is calculated using the formula DE=(DLmax-DLmin) / DLmax; Compare adjacent working current data to obtain current discrete value DZ; If the current discrete value DZ>the preset discrete threshold value, it indicates that the working current of the brake device is discrete, and the current discrete value DZ is marked as the first discrete value; The number of occurrences of the statistical discrete situation is the discrete frequency P1, and all the first discrete values ​​are accumulated to obtain the discrete total value LZ; using the formula The stability deviation value CW is calculated, where a1 and a2 are both preset coefficient factors; Compare the stabilization deviation value CW with a preset deviation threshold; If the measured stability deviation value CW ≥ the preset deviation threshold, the data is judged to be abnormal and exceeds the tolerance range, and the alarm mode is entered; When the measured deviation value CW is less than the preset deviation threshold, the working current collected by the brake control module is determined to be valid data. At this time, the average working current value in the preset time period is obtained by arithmetic averaging, which is the working current of the brake device at a certain moment; The PLC controller uses the data processing module to quickly process and analyze the working current, and cooperates with the industrial-grade communication interface to complete the high-speed and lossless transmission of the processing results. Finally, the brake control module controls the operation of the brake device according to the processing results. In the process of analyzing and processing the working current, the predictive processing module is used to predict the current trend of the brake device in the short future time according to the working state of the intelligent electric locomotive; Based on the prediction results, determine whether there is a trend that exceeds the preset threshold, and then provide early warning.

2. The control system of the intelligent electric locomotive brake device according to claim 1 is characterized in that: The working principle of the predictive processing module is as follows: Train the AI ​​model based on historical data to obtain a current prediction model; The current prediction model is used to predict the current trend of the brake device in the short term in the future according to the working state of the intelligent electric locomotive; Determine whether there is a trend exceeding the preset threshold based on the forecast results, and then provide early warning; Adjust the brake action according to the early warning signal, including: Set control instructions according to the early warning signals; Before the control instruction is triggered, it is verified in real time whether the actual current threshold and the predicted current threshold are the same; if they are not the same, it is further determined whether the control instruction needs to be adjusted.

3. The control system of the intelligent electric locomotive brake device according to claim 2 is characterized in that: The specific training steps of the current prediction model are as follows: Step 1: sorting and extracting historical data to form input and output data sets; the historical data includes historical working status data of the electric locomotive and historical current trends of the brake device; Step 2: Perform data cleaning and missing value processing on the input and output data sets; Standardize the processed data and divide the data set into training set, validation set and test set; Step 3: Establish an LSTM neural network model and initialize the neural network weights; Step 4: Input the training set, validation set, and test set as historical feature values ​​into the LSTM neural network model for model training, and evaluate the model through the loss function to obtain the optimal current prediction model that minimizes the overall error of the training samples.

4. The control system of the intelligent electric locomotive brake device according to claim 3 is characterized in that: Input data refers to the working status data of the electric locomotive and the current trend of the brake device within a certain period of time and at a certain time interval; The output data is the current trend of the brake device after a certain period of time lagging behind the input data.

5. The control system of the intelligent electric locomotive brake device according to claim 3, characterized in that: in, According to the number of input variables, the number of input nodes of the long short-term memory neural network LSTM is specified, the number of appropriate hidden layer nodes is set, and the number of output nodes representing the current trend prediction value is set.

6. The control system of the intelligent electric locomotive brake device according to claim 3, characterized in that: in, The Nguyen-Widrow method is used to initialize the neural network weights; the neural network weights include at least one of the model's input value, hidden value, number of model layers, neuron discard rate, activation function, feature weight initial value, and bias.

7. The control system of the intelligent electric locomotive brake device according to claim 2, characterized in that: in, The root mean square error equation is used as the loss function.

8. The control system of the intelligent electric locomotive brake device according to claim 1, characterized in that: The wireless communication module is one or more of a Bluetooth module, a WIFI module, a TD-LTE / FDD-LTE module, and a NB-IOT / LoRa module.

9. A control method for an intelligent electric locomotive brake device, applied to the control system of the intelligent electric locomotive brake device according to any one of claims 1 to 8, characterized in that: The steps include: The first step is that the brake control module collects the working current of the brake device in real time through the built-in current sensor, and sends the collected data directly to the PLC controller through the wireless communication module; In the second step, the PLC controller drives the data verification module to verify the validity of the data collected by the brake control module; if the data abnormality exceeds the tolerance range, it will enter the alarm mode; Step 3: The PLC controller uses the data processing module to quickly process and analyze the working current, and completes the transmission of the processing results with the industrial communication interface. Finally, the brake control module controls the operation of the brake device according to the processing results. Step 4. During the analysis and processing of the working current, the predictive processing module is used to predict the current trend of the brake device in the short term in the future according to the working status of the intelligent electric locomotive, and determine whether there is a trend exceeding the preset threshold based on the prediction result, and then provide an early warning.

Images