A method and system for monitoring and managing the internal environment of a high-speed rail electrical cabinet

Abstract

The present invention discloses a method and system for monitoring and managing the internal environment of a high-speed rail electrical cabinet, relating to the technical field of temperature monitoring. By statistically analyzing the correlation between each electrical device and the high-speed rail travel status, and based on the correlation, all electrical devices are divided into relevant devices and irrelevant devices. For relevant devices, a first temperature prediction model is trained based on high-speed rail travel history data, device operation history data, and device temperature history data; for irrelevant devices, a second temperature prediction model is trained based on device operation history data and device temperature history data. During the real-time travel of the high-speed rail, the expected temperature of each electrical device is obtained based on the real-time device operation data, real-time travel data, the first temperature prediction model, and the second temperature prediction model. Based on the expected temperature and the real-time temperature, the abnormal situation of each electrical device is judged, thereby achieving more accurate temperature prediction and anomaly detection.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature monitoring, and in particular to a method and system for monitoring and managing the internal environment of a high-speed railway electrical cabinet. Background Art

[0002] As a vital component of modern transportation, the safe and stable operation of high-speed rail is crucial. Electrical cabinets, core components of high-speed rail vehicles, house numerous critical electrical devices, whose proper operation is directly related to the safety and reliability of the train. However, during high-speed operation, the equipment within these cabinets generates significant heat. If this accumulated heat is not dissipated promptly, it can lead to equipment overheating, performance degradation, and even failure.

[0003] On the one hand, during the operation of high-speed rail, there will be acceleration, braking, and long-term high-speed driving. The acceleration behavior will increase the power demand of the traction system, resulting in an increase in the load of the traction system and a rapid increase in temperature. During braking, the energy recovery system will work, and the temperature of related braking equipment will increase. During long-term high-speed driving, the electrical equipment will continue to operate under high load.

[0004] Traditional temperature monitoring methods often use fixed thresholds or simple statistical models, which are difficult to adapt to the complex and changeable operating environment of high-speed rail and the differences in characteristics of different equipment, and are prone to false alarms or missed alarms.

[0005] To this end, the present invention proposes a method and system for monitoring and managing the internal environment of a high-speed railway electrical cabinet. Summary of the Invention

[0006] 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 method and system for monitoring and managing the internal environment of a high-speed rail electrical cabinet, which achieves more accurate temperature prediction and anomaly detection.

[0007] To achieve the above objectives, a method for monitoring and managing the internal environment of a high-speed rail electrical cabinet is proposed, comprising the following steps:

[0008] Step 1: Collect cabinet layout information in advance;

[0009] Step 2: Collect the high-speed rail travel history data generated during the high-speed rail's historical operation, as well as the equipment operation history data and equipment temperature history data of each electrical equipment in the electrical cabinet;

[0010] Step 3: Based on the historical data of high-speed rail travel and equipment temperature, the correlation between each electrical device and the high-speed rail travel status is calculated, and based on the correlation, all electrical devices are divided into relevant devices and unrelated devices;

[0011] Step 4: For relevant equipment, a first temperature prediction model is trained based on the high-speed rail travel history data, equipment operation history data, and equipment temperature history data; for unrelated equipment, a second temperature prediction model is trained based on the equipment operation history data and equipment temperature history data;

[0012] Step 5: During the high-speed train's real-time operation, the temperature distribution information inside the electrical cabinet is collected in real time. Based on the temperature distribution information and the cabinet layout information, the real-time temperature of each electrical device is obtained;

[0013] Step 6: Collect real-time equipment operation data of each electrical device and real-time high-speed rail travel data, and obtain the expected temperature of each electrical device based on the real-time equipment operation data, real-time travel data, the first temperature prediction model, and the second temperature prediction model; and determine the abnormality of each electrical device based on the expected temperature and the real-time temperature;

[0014] The method of pre-collecting the cabinet layout information is as follows:

[0015] Collect CAD designs of the interior of the electrical cabinet;

[0016] Collect a detailed inventory of all electrical equipment in the electrical cabinet;

[0017] Create 3D models of electrical cabinets based on 2D drawings and field measurement data;

[0018] Locate each piece of electrical equipment in the 3D model and assign a unique identifier to each piece of electrical equipment;

[0019] The position relationship and identifier of each device in the 3D model are combined into the cabinet layout information;

[0020] The method for collecting the high-speed rail travel history data generated during the high-speed rail historical operation, as well as the equipment operation history data and equipment temperature history data of each electrical equipment in the electrical cabinet is:

[0021] The speed time series and acceleration time series of the high-speed rail historical driving process are collected from the historical driving records of the high-speed rail to form the high-speed rail driving history data;

[0022] From the historical operation records of the electrical cabinet, the electrical parameter time series of each electrical equipment are collected to form the equipment operation history data;

[0023] Collect the temperature-time curve of each electrical device during high-speed rail operation as the device temperature history data;

[0024] The method of calculating the correlation between each electrical device and the high-speed rail travel status based on the high-speed rail travel history data and the equipment temperature history data is as follows:

[0025] The speed time series of the high-speed rail travel history data is marked as V;

[0026] Mark each moment as T, and the speed at the Tth moment in the speed time series V is marked as v_T;

[0027] The temperature time series of the i-th electrical equipment is marked as Wi, and the parameter value at the T-th moment in the temperature time series Wi is wi_T;

[0028] For the i-th electrical equipment:

[0029] Calculate the correlation ri between the velocity time series and the temperature time series;

[0030] The correlation ri is calculated as follows:

[0031]

[0032] Among them, vm is the average value of the velocity time series, wim is the average value of the temperature time series Wi;

[0033] Calculate the T statistic Ts_i of the i-th electrical equipment. Specifically, the T statistic Where n is the length of the velocity time series;

[0034] Then, under the T distribution with n-2 degrees of freedom, find the corresponding critical value in is the critical value, and α is the preset significance level;

[0035] If |ts_i| is greater than the critical value, the i-th electrical equipment is classified as related equipment; otherwise, the i-th electrical equipment is classified as irrelevant equipment;

[0036] For the relevant equipment, the method of training the first temperature prediction model based on the high-speed rail travel history data, equipment operation history data, and equipment temperature history data is as follows:

[0037] For each relevant device:

[0038] Set the input sequence length L and the sliding window step size S;

[0039] The acceleration time series is marked as A, and the acceleration at the Tth moment in the acceleration time series is marked as a_T;

[0040] Assuming the initial moment of the historical operation process is T0, for the velocity time series and acceleration time series, construct the velocity sequence segment [v_T0,v_(T0+1),...v_(T0+L-1)] and the acceleration sequence segment [a_T0,a_(T0+1),a_(T0+L-1)] respectively;

[0041] The electrical parameter time series of the j-th electrical parameter of the relevant device is marked as Dj, and the j-th electrical parameter value at the T-th time is marked as dj_T;

[0042] Construct an electrical parameter sequence segment of [dj_T0, dj_(T0+1), dj_(T0+L-1)] for the jth electrical parameter;

[0043] The velocity sequence segment, acceleration sequence segment and all electrical parameter sequence segments at time T0 are combined into the first input feature at time T0;

[0044] The temperature of the relevant device at time T0+1 is used as the first temperature label at time T0;

[0045] The first input feature and the first temperature label at time T0 form a set of first samples;

[0046] Using the sliding window method, continue to construct the first sample at time T0+k×S;

[0047] The first input feature at any time T is used as the input of a first temperature prediction model. The first temperature prediction model uses the temperature prediction value at a time after time T as the output, uses the first temperature label corresponding to time T as the prediction target, uses the difference between the temperature prediction value and the first temperature label as the first prediction error, and minimizes the sum of the first prediction errors as the training objective. The first temperature prediction model is trained until the sum of the first prediction errors reaches convergence. The first temperature prediction model is a time series prediction model.

[0048] For the unrelated devices, the second temperature prediction model is trained based on the device operation history data and the device temperature history data as follows:

[0049] For each unrelated device:

[0050] All electrical parameter sequence segments of the unrelated device at time T0 are combined into a second input feature at time T0;

[0051] The temperature of the unrelated device at time T0+1 is used as the second temperature tag at time T0;

[0052] The second input feature and the second temperature label at time T0 are combined into a set of second samples;

[0053] Using the sliding window method, continue to construct the second sample at time T0+k×S;

[0054] The second input feature at any time T is used as the input of the second temperature prediction model. The second temperature prediction model uses the temperature prediction value at a time after time T as the output, uses the second temperature label corresponding to time T as the prediction target, uses the difference between the temperature prediction value and the second temperature label as the second prediction error, and minimizes the sum of the second prediction errors as the training goal. The second temperature prediction model is trained until the sum of the second prediction errors reaches convergence. The second temperature prediction model is a time series prediction model.

[0055] The method based on real-time device operation data, real-time driving data, the first temperature prediction model and the second temperature prediction model is:

[0056] For relevant equipment, construct a set of first samples based on real-time equipment operation data and real-time driving data, and obtain expected temperatures of the relevant equipment based on the first samples and a first temperature prediction model;

[0057] For the unrelated equipment, a set of second samples is constructed based on the real-time equipment operation data, and the expected temperature of the unrelated equipment is obtained based on the second samples and the second temperature prediction model;

[0058] The method for determining the abnormality of each electrical device based on the expected temperature and the real-time temperature is as follows:

[0059] For the i-th electrical equipment, the over-temperature threshold ratio bi is preset;

[0060] The expected temperature of the i-th electrical equipment is marked as Yi, and the real-time temperature of the i-th electrical equipment is marked as Xi;

[0061] like If the temperature is abnormal, it is judged as normal.

[0062] Example 2

[0063] like Figure 2 As shown, an internal environment monitoring and management system for a high-speed rail electrical cabinet includes a layout information collection module, a training data collection module, an equipment division module, a model training module, and a temperature monitoring module; wherein each module is electrically connected;

[0064] The layout information collection module collects the cabinet layout information in advance and sends the cabinet layout information to the temperature monitoring module;

[0065] The training data collection module collects the high-speed rail travel history data generated during the high-speed rail's historical operation, as well as the equipment operation history data and equipment temperature history data of each electrical equipment in the electrical cabinet, and sends the high-speed rail travel history data, equipment operation history data, and equipment temperature history data to the equipment classification module and the model training module;

[0066] The equipment classification module calculates the correlation between each electrical device and the high-speed rail driving status based on the high-speed rail driving history data and equipment temperature history data. Based on the correlation, all electrical devices are divided into relevant devices and irrelevant devices, and the results of the classification of relevant and irrelevant devices are sent to the model training module.

[0067] The model training module trains a first temperature prediction model for relevant equipment based on the high-speed rail travel history data, equipment operation history data, and equipment temperature history data; and trains a second temperature prediction model for unrelated equipment based on the equipment operation history data and equipment temperature history data, and sends the first temperature prediction model and the second temperature prediction model to the temperature monitoring module;

[0068] The temperature monitoring module collects the temperature distribution information in the electrical cabinet in real time during the real-time operation of the high-speed rail, obtains the real-time temperature of each electrical device based on the temperature distribution information and the layout information in the cabinet, collects the real-time equipment operation data of each electrical device and the real-time operation data of the high-speed rail, and obtains the expected temperature of each electrical device based on the real-time equipment operation data, real-time operation data, the first temperature prediction model and the second temperature prediction model; and judges the abnormal conditions of each electrical device based on the expected temperature and the real-time temperature.

[0069] An electronic device comprises: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the above-mentioned method and system for monitoring and managing the internal environment of a high-speed railway electrical cabinet by calling the computer program stored in the memory.

[0070] A computer-readable storage medium stores instructions. When the instructions are run on a computer, the computer executes the above-mentioned method and system for monitoring and managing the internal environment of a high-speed railway electrical cabinet.

[0071] Compared with the prior art, the present invention has the following beneficial effects:

[0072] The present invention divides electrical equipment into related equipment and unrelated equipment through correlation analysis between electrical equipment and high-speed rail travel status. For related equipment, the high-speed rail travel data, equipment operation data and historical temperature data are combined to construct a corresponding temperature prediction model. For unrelated equipment, the focus is on the equipment's own operating characteristics and temperature change rules to construct a corresponding temperature prediction model. Based on the temperature prediction model and the real-time temperature of each device, it is judged whether the real-time temperature is abnormal. The method of dividing related equipment into unrelated equipment takes into account the degree of influence of the high-speed rail operation status on the temperature changes of different equipment, so that the characteristics of the equipment temperature changes can be captured more accurately. This differentiated modeling strategy not only improves the accuracy of temperature prediction, but also better adapts to the characteristics of different types of equipment, provides a more reliable basis for anomaly detection, and realizes more accurate temperature prediction and anomaly detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 This is a flow chart of a method for monitoring and managing the internal environment of a high-speed railway electrical cabinet in Example 1 of the present invention;

[0074] Figure 2 This is a module connection diagram of an internal environment monitoring and management system for a high-speed railway electrical cabinet in Example 2 of the present invention;

[0075] Figure 3 This is a schematic diagram of the structure of an electronic device in Example 3 of the present invention;

[0076] Figure 4 This is a schematic diagram of the computer-readable storage medium structure in Example 4 of the present invention. DETAILED DESCRIPTION

[0077] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0078] Example 1

[0079] like Figure 1 As shown, a method for monitoring and managing the internal environment of a high-speed railway electrical cabinet includes the following steps:

[0080] Step 1: Collect cabinet layout information in advance;

[0081] Step 2: Collect the high-speed rail travel history data generated during the high-speed rail's historical operation, as well as the equipment operation history data and equipment temperature history data of each electrical equipment in the electrical cabinet;

[0082] Step 3: Based on the historical data of high-speed rail travel and equipment temperature, the correlation between each electrical device and the high-speed rail travel status is calculated, and based on the correlation, all electrical devices are divided into relevant devices and unrelated devices;

[0083] Step 4: For relevant equipment, a first temperature prediction model is trained based on the high-speed rail travel history data, equipment operation history data, and equipment temperature history data; for unrelated equipment, a second temperature prediction model is trained based on the equipment operation history data and equipment temperature history data;

[0084] Step 5: During the high-speed train's real-time operation, the temperature distribution information inside the electrical cabinet is collected in real time. Based on the temperature distribution information and the cabinet layout information, the real-time temperature of each electrical device is obtained;

[0085] Step 6: Collect real-time equipment operation data of each electrical device and real-time high-speed rail travel data, and obtain the expected temperature of each electrical device based on the real-time equipment operation data, real-time travel data, the first temperature prediction model, and the second temperature prediction model; and determine the abnormality of each electrical device based on the expected temperature and the real-time temperature;

[0086] The method of pre-collecting the cabinet layout information is as follows:

[0087] Collect CAD designs of the interior of the electrical cabinet;

[0088] Collect a detailed inventory of all electrical equipment in the electrical cabinet;

[0089] Create 3D models of electrical cabinets based on 2D drawings and field measurement data;

[0090] Locate each piece of electrical equipment in the 3D model and assign a unique identifier to each piece of electrical equipment;

[0091] The position relationship and identifier of each device in the 3D model are combined into the cabinet layout information;

[0092] Further preferably, a structured database of electrical equipment may be created to record information such as the location coordinates, size, type, etc. of each electrical equipment;

[0093] Furthermore, the method of collecting the high-speed rail travel history data generated during the high-speed rail historical operation, as well as the equipment operation history data and equipment temperature history data of each electrical equipment in the electrical cabinet is:

[0094] The speed time series and acceleration time series of the high-speed rail's historical driving process are collected from the high-speed rail's historical driving records to form the high-speed rail driving history data. It can be understood that the speed time series stores the high-speed rail's driving speed at each moment, and the acceleration time series stores the high-speed rail's acceleration at each moment.

[0095] From the historical operation records of the electrical cabinet, the electrical parameter time series of each electrical parameter of each electrical device is collected to form the equipment operation history data; it can be understood that the electrical parameter time series stores the parameter value of the corresponding electrical parameter at each moment;

[0096] Specifically, the electrical parameters include but are not limited to current parameters, voltage parameters, power parameters, frequency parameters, impedance parameters, efficiency parameters, electromagnetic compatibility parameters, vibration and noise parameters, etc.; the current parameters include but are not limited to operating current, peak current, current fluctuation rate, and harmonic content; the voltage parameters include but are not limited to operating voltage, voltage fluctuation rate, voltage stability, overvoltage / undervoltage conditions; the power parameters include but are not limited to active power, reactive power, power factor, and power fluctuation; the frequency parameters include but are not limited to operating frequency, frequency stability, and frequency response; the impedance parameters include but are not limited to insulation resistance, contact resistance, and impedance change trend; the efficiency parameters include but are not limited to energy conversion efficiency and loss; the electromagnetic compatibility parameters include but are not limited to electromagnetic interference level and radiation intensity; the vibration and noise parameters include but are not limited to vibration frequency and amplitude, noise level, and resonance characteristics; by integrating these electrical parameters, a comprehensive and accurate anomaly detection and diagnosis system can be constructed, which can not only improve the accuracy of anomaly detection, but also provide richer information for anomaly cause analysis;

[0097] Collect the temperature-time curve of each electrical device during the high-speed rail operation as the device temperature history data; it can be understood that the temperature-time curve saves the temperature of each electrical device at every moment;

[0098] It is understandable that the electrical equipment affected by high-speed rail during acceleration, braking, and long periods of high-speed travel varies. Furthermore, some electrical equipment in the electrical cabinet is not affected by the travel state, such as lighting equipment. Therefore, the travel state of the high-speed rail can affect some electrical equipment in the electrical cabinet. Therefore, it is necessary to differentiate the electrical equipment.

[0099] Specifically, the method of calculating the correlation between each electrical device and the high-speed rail travel status based on the high-speed rail travel history data and the equipment temperature history data is as follows:

[0100] The speed time series of the high-speed rail travel history data is marked as V;

[0101] Mark each moment as T, and the velocity at the Tth moment in the velocity time series V is marked as v_T;

[0102] The temperature time series of the i-th electrical equipment is marked as Wi, and the parameter value at the T-th moment in the temperature time series Wi is wi_T;

[0103] For the i-th electrical equipment:

[0104] Calculate the correlation ri between the velocity time series and the temperature time series;

[0105] The correlation ri is calculated as follows:

[0106]

[0107] Among them, vm is the average value of the velocity time series, wim is the average value of the temperature time series Wi;

[0108] It can be understood that the value range of ri is [-1,1], ri>0 indicates positive correlation, ri<0 indicates negative correlation, and the larger the absolute value, the higher the correlation.

[0109] Calculate the t statistic ts_i of the i-th electrical equipment. Specifically, the t statistic Where n is the length of the velocity time series;

[0110] Then, under the t distribution with n-2 degrees of freedom, find the corresponding critical value in, is the critical value, and α is the preset significance level; the significance level is usually 0.05 or 0.1;

[0111] If |ts_i| is greater than the critical value, the i-th electrical equipment is classified as related equipment; otherwise, the i-th electrical equipment is classified as irrelevant equipment;

[0112] The physical meaning of the critical value is: under the t-distribution with n-2 degrees of freedom, when the absolute value |ts_i| is greater than the critical value, the probability of rejecting the null hypothesis "the two are correlated" is α; the t-distribution is the Student distribution, which belongs to the conventional mathematical model and will not be elaborated here;

[0113] For example, when there are 50 time points of sample data on speed and temperature, the calculated sample correlation coefficient is 0.37, and the significance level is set to 0.05; then the critical value ts_0.05 / 2 corresponds to the 97.5% quantile of the ts_i distribution with 48 degrees of freedom (because it is a two-sided test, it is 0.05 / 2). By consulting the t distribution table or using software, it can be found that when the degrees of freedom are 48, the 97.5% quantile t_0.05 / 2 = 2.011; the t statistic is It is believed that the sample correlation coefficient r = 0.37 is statistically significantly different from 0, that is, there is a significant positive correlation between the high-speed rail speed and the temperature of the electrical equipment;

[0114] It is understandable that for relevant equipment, due to the different operating conditions of high-speed trains, the normal temperature benchmarks of various electrical equipment are different under different operating conditions of high-speed trains. For example, when a high-speed train is accelerating, the temperature of the relevant equipment will normally exceed the temperature when it is running at a constant speed. Therefore, the same set of comparison standards cannot be used;

[0115] Furthermore, for the related equipment, based on the high-speed rail travel history data, equipment operation history data, and equipment temperature history data, the method of training the first temperature prediction model is as follows:

[0116] For each relevant device:

[0117] Set the input sequence length L and the sliding window step size S;

[0118] The acceleration time series is marked as A, and the acceleration at the Tth moment in the acceleration time series is marked as a_T;

[0119] Assuming the initial moment of the historical operation process is T0, for the velocity time series and acceleration time series, construct the velocity sequence segment [v_T0,v_(T0+1),...v_(T0+L-1)] and the acceleration sequence segment [a_T0,a_(T0+1),a_(T0+L-1)] respectively;

[0120] The electrical parameter time series of the j-th electrical parameter of the relevant device is marked as Dj, and the j-th electrical parameter value at the T-th time is marked as dj_T;

[0121] Construct an electrical parameter sequence segment of [dj_T0, dj_(T0+1), dj_(T0+L-1)] for the jth electrical parameter;

[0122] The velocity sequence segment, acceleration sequence segment and all electrical parameter sequence segments at time T0 are combined into the first input feature at time T0;

[0123] The temperature of the relevant device at time T0+1 is used as the first temperature label at time T0;

[0124] The first input feature and the first temperature label at time T0 form a set of first samples;

[0125] Using the sliding window method, continue to construct the first sample at time T0+k×S;

[0126] The first input feature at each moment is used as the input of a first temperature prediction model. The first temperature prediction model uses the temperature prediction value at a moment after the moment as the output, uses the first temperature label corresponding to the moment as the prediction target, uses the difference between the temperature prediction value and the first temperature label as the first prediction error, and minimizes the sum of the first prediction errors as the training objective. The first temperature prediction model is trained until the sum of the first prediction errors reaches convergence. The first temperature prediction model is a time series prediction model. The time series prediction model is either an RNN model or an LSTM model.

[0127] Furthermore, for the unrelated devices, the second temperature prediction model is trained based on the device operation history data and the device temperature history data as follows:

[0128] For each unrelated device:

[0129] All electrical parameter sequence segments of the unrelated device at time T0 are combined into a second input feature at time T0;

[0130] The temperature of the unrelated device at time T0+1 is used as the second temperature tag at time T0;

[0131] The second input feature and the second temperature label at time T0 are combined into a set of second samples;

[0132] Using the sliding window method, continue to construct the second sample at time T0+k×S;

[0133] The second input feature at any time T is used as the input of the second temperature prediction model. The second temperature prediction model uses the temperature prediction value at a time after time T as the output, uses the second temperature label corresponding to time T as the prediction target, uses the difference between the temperature prediction value and the second temperature label as the second prediction error, and minimizes the sum of the second prediction errors as the training goal. The second temperature prediction model is trained until the sum of the second prediction errors reaches convergence. The second temperature prediction model is a time series prediction model.

[0134] Firstly, the method of collecting the temperature distribution information in the electrical cabinet in real time may be:

[0135] Install one or more thermal imaging cameras on the inside of the cabinet door or on the top of the cabinet to provide a temperature distribution map of the entire cabinet space;

[0136] Second, the method of collecting the temperature distribution information in the electrical cabinet in real time may also be:

[0137] Install multiple small temperature sensors in the electrical cabinet, covering key areas and hot spots;

[0138] Furthermore, the method for obtaining the real-time temperature of each electrical device based on the temperature distribution information and the cabinet layout information is as follows:

[0139] Map temperature distribution information to the 3D model of the electrical cabinet;

[0140] Using the equipment location coordinates in the cabinet layout information, the location of each device is matched with the temperature distribution one by one to obtain the real-time temperature of each electrical device;

[0141] The real-time equipment operation data includes parameter values ​​of various electrical parameters of each electrical equipment;

[0142] The real-time driving data includes the speed and acceleration of each electrical device;

[0143] Furthermore, the method based on the real-time device operation data, the real-time driving data, the first temperature prediction model and the second temperature prediction model is:

[0144] For relevant equipment, construct a set of first samples based on real-time equipment operation data and real-time driving data, and obtain expected temperatures of the relevant equipment based on the first samples and a first temperature prediction model;

[0145] For the unrelated equipment, a set of second samples is constructed based on the real-time equipment operation data, and the expected temperature of the unrelated equipment is obtained based on the second samples and the second temperature prediction model;

[0146] Furthermore, the method of judging the abnormality of each electrical device based on the expected temperature and the real-time temperature is as follows:

[0147] For the i-th electrical equipment, the over-temperature threshold ratio bi is preset;

[0148] The expected temperature of the i-th electrical equipment is marked as Yi, and the real-time temperature of the i-th electrical equipment is marked as Xi;

[0149] like If the temperature is abnormal, it is judged as normal.

[0150] Example 2

[0151] like Figure 2 As shown, an internal environment monitoring and management system for a high-speed rail electrical cabinet includes a layout information collection module, a training data collection module, an equipment division module, a model training module, and a temperature monitoring module; wherein each module is electrically connected;

[0152] The layout information collection module collects the cabinet layout information in advance and sends the cabinet layout information to the temperature monitoring module;

[0153] The training data collection module collects the high-speed rail travel history data generated during the high-speed rail's historical operation, as well as the equipment operation history data and equipment temperature history data of each electrical equipment in the electrical cabinet, and sends the high-speed rail travel history data, equipment operation history data, and equipment temperature history data to the equipment classification module and the model training module;

[0154] The equipment classification module calculates the correlation between each electrical device and the high-speed rail driving status based on the high-speed rail driving history data and equipment temperature history data. Based on the correlation, all electrical devices are divided into relevant devices and irrelevant devices, and the results of the classification of relevant and irrelevant devices are sent to the model training module.

[0155] The model training module trains a first temperature prediction model for relevant equipment based on the high-speed rail travel history data, equipment operation history data, and equipment temperature history data; and trains a second temperature prediction model for unrelated equipment based on the equipment operation history data and equipment temperature history data, and sends the first temperature prediction model and the second temperature prediction model to the temperature monitoring module;

[0156] The temperature monitoring module collects the temperature distribution information in the electrical cabinet in real time during the real-time operation of the high-speed rail, obtains the real-time temperature of each electrical device based on the temperature distribution information and the layout information in the cabinet, collects the real-time equipment operation data of each electrical device and the real-time operation data of the high-speed rail, and obtains the expected temperature of each electrical device based on the real-time equipment operation data, real-time operation data, the first temperature prediction model and the second temperature prediction model; and judges the abnormal conditions of each electrical device based on the expected temperature and the real-time temperature.

[0157] Example 3

[0158] See also Figure 3 According to another aspect of the present application, an electronic device 500 is provided. The electronic device 500 may include one or more processors and one or more memories. The memories may store computer-readable code that, when executed by the one or more processors, may execute the aforementioned method and system for monitoring and managing the internal environment of a high-speed rail electrical cabinet.

[0159] The method or system according to the embodiment of the present application can also be used by Figure 3 The electronic device architecture shown in FIG. Figure 3As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a read-only memory (ROM) 503, a random access memory (RAM) 504, a communication port 505 connected to a network, an input / output component 506, a hard disk 507, etc. The storage device in the electronic device 500, such as the ROM 503 or the hard disk 507, may store the internal environment monitoring and management method and system of a high-speed railway electrical cabinet provided in this application. Furthermore, the electronic device 500 may also include a user interface 508. Of course, Figure 3 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 3 One or more components of an electronic device are shown.

[0160] Example 4

[0161] See also Figure 4 As shown, a computer-readable storage medium 600 according to one embodiment of the present application is shown. Computer-readable instructions are stored on the computer-readable storage medium 600. When the computer-readable instructions are executed by a processor, the method and system for monitoring and managing the internal environment of a high-speed rail electrical cabinet according to an embodiment of the present application described with reference to the above figures can be executed. The storage medium 600 includes, but is not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory. Non-volatile memory may include, for example, read-only memory (ROM), a hard disk, flash memory, etc.

[0162] In addition, according to embodiments of the present application, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, the present application provides a non-transitory machine-readable storage medium storing machine-readable instructions capable of being executed by a processor to perform instructions corresponding to the method steps provided in the present application;

[0163] The above embodiments can be implemented in whole or in part through software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via a wired or wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, or a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0164] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0165] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0166] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a method and system for monitoring and managing the internal environment of a high-speed rail electrical cabinet. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0167] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0168] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0169] The above embodiments are only used to illustrate the technical method of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A method for monitoring and managing the internal environment of a high-speed rail electrical cabinet, characterized in that: The following steps are involved: Step 1: Collect cabinet layout information in advance; Step 2: Collect the high-speed rail travel history data generated during the high-speed rail's historical operation, as well as the equipment operation history data and equipment temperature history data of each electrical equipment in the electrical cabinet; Step 3: Based on the historical data of high-speed rail travel and equipment temperature, the correlation between each electrical device and the high-speed rail travel status is calculated, and based on the correlation, all electrical devices are divided into relevant devices and unrelated devices; Step 4: For relevant equipment, a first temperature prediction model is trained based on the high-speed rail travel history data, equipment operation history data, and equipment temperature history data; for unrelated equipment, a second temperature prediction model is trained based on the equipment operation history data and equipment temperature history data; Step 5: During the high-speed train's real-time operation, the temperature distribution information inside the electrical cabinet is collected in real time. Based on the temperature distribution information and the cabinet layout information, the real-time temperature of each electrical device is obtained; Step 6: Collect the real-time equipment operation data of each electrical device and the real-time travel data of the high-speed rail, and obtain the expected temperature of each electrical device based on the real-time equipment operation data, real-time travel data, the first temperature prediction model and the second temperature prediction model; based on the expected temperature and the real-time temperature, determine the abnormality of each electrical device.

2. The method for monitoring and managing the internal environment of a high-speed railway electrical cabinet according to claim 1, characterized in that: The method of pre-collecting the cabinet layout information is as follows: Collect CAD designs of the interior of the electrical cabinet; Collect a detailed inventory of all electrical equipment in the electrical cabinet; Create 3D models of electrical cabinets based on 2D drawings and field measurement data; Locate each piece of electrical equipment in the 3D model and assign a unique identifier to each piece of electrical equipment; The position relationship and identifier of each device in the 3D model are combined into the cabinet layout information.

3. The method for monitoring and managing the internal environment of a high-speed railway electrical cabinet according to claim 2, characterized in that: The method for collecting the high-speed rail travel history data generated during the high-speed rail historical operation, as well as the equipment operation history data and equipment temperature history data of each electrical equipment in the electrical cabinet is: The speed time series and acceleration time series of the high-speed rail historical driving process are collected from the historical driving records of the high-speed rail to form the high-speed rail driving history data; From the historical operation records of the electrical cabinet, the electrical parameter time series of each electrical equipment are collected to form the equipment operation history data; The temperature-time curve of each electrical equipment during high-speed rail operation is collected as equipment temperature history data.

4. The method for monitoring and managing the internal environment of a high-speed railway electrical cabinet according to claim 3, characterized in that: The method of calculating the correlation between each electrical device and the high-speed rail travel status based on the high-speed rail travel history data and the equipment temperature history data is as follows: The speed time series of the high-speed rail travel history data is marked as V; Mark each moment as T, and the speed at the Tth moment in the speed time series V is marked as v_T; The temperature time series of the i-th electrical equipment is marked as Wi, and the parameter value at the T-th moment in the temperature time series Wi is wi_T; For the i-th electrical equipment: Calculate the correlation ri of the velocity time series and the temperature time series based on the velocity time series and the temperature time series; Calculate the t-statistic ts_i of the i-th electrical equipment based on the correlation ri and the length of the temperature time series; Then, under the t distribution with n-2 degrees of freedom, find the corresponding critical value ,in is the preset significance level; n is the length of the velocity time series; If | If | is greater than the critical value, the i-th electrical equipment is classified as related equipment; otherwise, the i-th electrical equipment is classified as irrelevant equipment.

5. The method for monitoring and managing the internal environment of a high-speed railway electrical cabinet according to claim 4, characterized in that: For the relevant equipment, the method of training the first temperature prediction model based on the high-speed rail travel history data, equipment operation history data, and equipment temperature history data is as follows: For each relevant device: Set the input sequence length L and the sliding window step size S; The acceleration time series is marked as A, and the acceleration at the Tth moment in the acceleration time series is marked as a_T; Assuming the initial moment of the historical operation process is T0, for the velocity time series and acceleration time series, construct the velocity sequence segment [v_T0,v_(T0+1),...v_(T0+L-1)] and the acceleration sequence segment [a_T0,a_(T0+1),...a_(T0+L-1)] respectively; The electrical parameter time series of the j-th electrical parameter of the related device is marked as Dj, and the j-th electrical parameter value at the T-th moment is marked as dj_T; Construct an electrical parameter sequence segment of [dj_T0, dj_(T0+1), ... dj_(T0+L-1)] for the jth electrical parameter; The velocity sequence segment, acceleration sequence segment and all electrical parameter sequence segments at time T0 are combined into the first input feature at time T0; The temperature of the relevant device at time T0+1 is used as the first temperature label at time T0; The first input feature and the first temperature label at time T0 form a set of first samples; Continue to construct T0+k through the sliding window method The first sample at time S; k=1,2,... ; The first input feature at any time T is used as the input of the first temperature prediction model. The first temperature prediction model uses the temperature prediction value at a time after time T as the output, the first temperature label corresponding to time T as the prediction target, the difference between the temperature prediction value and the first temperature label as the first prediction error, and minimizing the sum of the first prediction errors as the training goal; the first temperature prediction model is trained until the sum of the first prediction errors reaches convergence and the training is stopped; the first temperature prediction model is a time series prediction model.

6. The method for monitoring and managing the internal environment of a high-speed railway electrical cabinet according to claim 5, characterized in that: For the unrelated devices, the second temperature prediction model is trained based on the device operation history data and the device temperature history data as follows: For each unrelated device: All electrical parameter sequence segments of the unrelated device at time T0 are combined into a second input feature at time T0; The temperature of the unrelated device at time T0+1 is used as the second temperature tag at time T0; The second input feature and the second temperature label at time T0 are combined into a set of second samples; Continue to construct T0+k through the sliding window method The second sample at time S; The second input feature at any time T is used as the input of the second temperature prediction model. The second temperature prediction model uses the temperature prediction value at a time after time T as the output, the second temperature label corresponding to time T as the prediction target, the difference between the temperature prediction value and the second temperature label as the second prediction error, and minimizing the sum of the second prediction errors as the training goal; The second temperature prediction model is trained until the sum of the second prediction errors reaches convergence and the training is stopped; the second temperature prediction model is a time series prediction model.

7. The method for monitoring and managing the internal environment of a high-speed railway electrical cabinet according to claim 6, characterized in that: The method for determining the abnormality of each electrical device based on the expected temperature and the real-time temperature is as follows: For the i-th electrical equipment, the over-temperature threshold ratio bi is preset; The expected temperature of the i-th electrical equipment is marked as Yi, and the real-time temperature of the i-th electrical equipment is marked as Xi; like , it is judged that the temperature is abnormal, otherwise, it is judged that the temperature is normal.

8. A high-speed railway electrical cabinet internal environment monitoring and management system, which is used to implement the high-speed railway electrical cabinet internal environment monitoring and management method according to any one of claims 1 to 7, characterized in that: It includes a layout information collection module, a training data collection module, a device partitioning module, a model training module, and a temperature monitoring module; wherein each module is electrically connected; The layout information collection module collects the cabinet layout information in advance and sends the cabinet layout information to the temperature monitoring module; The training data collection module collects the high-speed rail travel history data generated during the high-speed rail's historical operation, as well as the equipment operation history data and equipment temperature history data of each electrical equipment in the electrical cabinet, and sends the high-speed rail travel history data, equipment operation history data, and equipment temperature history data to the equipment classification module and the model training module; The equipment classification module calculates the correlation between each electrical device and the high-speed rail driving status based on the high-speed rail driving history data and equipment temperature history data. Based on the correlation, all electrical devices are divided into relevant devices and irrelevant devices, and the results of the classification of relevant and irrelevant devices are sent to the model training module. The model training module trains a first temperature prediction model for relevant equipment based on the high-speed rail travel history data, equipment operation history data, and equipment temperature history data; and trains a second temperature prediction model for unrelated equipment based on the equipment operation history data and equipment temperature history data, and sends the first temperature prediction model and the second temperature prediction model to the temperature monitoring module; The temperature monitoring module collects the temperature distribution information in the electrical cabinet in real time during the real-time operation of the high-speed rail, obtains the real-time temperature of each electrical device based on the temperature distribution information and the layout information in the cabinet, collects the real-time equipment operation data of each electrical device and the real-time operation data of the high-speed rail, and obtains the expected temperature of each electrical device based on the real-time equipment operation data, real-time operation data, the first temperature prediction model and the second temperature prediction model; and judges the abnormal conditions of each electrical device based on the expected temperature and the real-time temperature.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the internal environment monitoring and management method of a high-speed railway electrical cabinet according to any one of claims 1 to 7 by calling the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are run on a computer, the computer is caused to execute the internal environment monitoring and management method of a high-speed railway electrical cabinet as described in any one of claims 1 to 7.

Images