A method for identifying and repairing faults in a rail vehicle cooling system
By analyzing sensor data and parts working curve charts and combining historical data, the problem of failure of track vehicle cooling system in the prior art cannot be identified and positioned, the fault is accurately positioned and the cause identification is realized, and the maintenance process is simplified.
Patent Information
- Application Number
- CN202411051273.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-01
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-08-01
AI Technical Summary
The prior art cannot effectively identify and locate the faults in the cooling system of rail vehicles during operation, resulting in inconvenience in maintenance.
By acquiring sensor data, a monitoring and analysis signal and fault warning signal are generated, combined with the working curve of the components and the health status curve chart, analyze historical data to determine the cause of the failure, and realize fault positioning of the cooling system.
It realizes accurate positioning and cause identification of cooling system failures, facilitates subsequent maintenance work and saves maintenance time.
Smart Images

Figure CN118579119B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of cooling system fault identification, and in particular to a rail vehicle cooling system fault identification and repair method. Background Art
[0002] The cooling system is an essential component in vehicle equipment and is often used to reduce the temperature of the traction motor to ensure the safety of vehicle operation. The existing cooling system includes a water pump, pipelines, fans and heat exchangers. During operation, the water medium is driven by the water pump to circulate in the traction motor, pipeline system and heat exchanger. After the water medium takes out the heat of the traction motor, it exchanges heat with the external cooling air blown by the fan in the heat exchanger to cool the traction motor and ensure the normal operation of the traction motor.
[0003] According to the application number CN202310425052.2, a vehicle cooling system, cooling method and fault identification and repair method are disclosed. In the vehicle cooling system, a water pump and a heat exchanger are both arranged on a pipeline. In the water flow direction along the pipeline, a traction motor is arranged between the water pump and the heat exchanger, and its water inlet and outlet are both connected to the pipeline; a driver is connected to a fan; the fan and the heat exchanger are arranged correspondingly; a temperature sensor is arranged at the water outlet of the traction motor and connected to the driver; the water pump is connected to the direct current on the vehicle; and a control component is arranged on the vehicle. This cooling method can not only make the traction motor work in a suitable temperature range, but also reduce the noise and energy consumption of the vehicle cooling system.
[0004] The above patent ensures the overall working stability by adjusting the parameters of the driver, but the above patent cannot determine the faults that occur during the working process, and cannot directly determine the cause of subsequent faults, which is not convenient for subsequent maintenance work. Summary of the invention
[0005] In view of the deficiencies in the prior art, the present invention provides a method for identifying and repairing faults in a rail vehicle cooling system, which solves the problem that a fault occurring during operation cannot be located, the specific cause of the fault cannot be identified, and subsequent maintenance is inconvenient.
[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A method for identifying and repairing a rail vehicle cooling system fault, comprising the following steps:
[0007] Step 1: acquiring sensor data in the rail vehicle, and comparing sensor parameters according to first predetermined parameters, and generating a monitoring analysis signal or a cause analysis signal;
[0008] Step 2: Analyze and process the generated monitoring and analysis signals, draw corresponding working curves according to the periodic working parameters of different components, and compare them with the health status curves to determine the working status of the components, and generate normal monitoring signals and fault warning signals at the same time;
[0009] Step 3: Analyze the components that are judged to generate fault warning signals, obtain the same changes in historical data, and perform comprehensive analysis based on the abnormal characteristics corresponding to the components to generate normal monitoring signals and fault warning signals;
[0010] Step 4: Analyze and process the generated cause analysis signal, compare the sensor data corresponding to the cause analysis signal with the size of the second predetermined parameter and generate an abnormal analysis signal and a normal monitoring signal, process the abnormal analysis signal, periodically monitor the working parameters of the components, and determine the corresponding working parameter changes to generate a normal monitoring signal and an unstable analysis signal;
[0011] Step 5: Analyze the generated unstable signal by analyzing the number of unstable changes and the peak value within the time period, and generate an amplification analysis signal and a normal monitoring signal according to the change of the peak value. For the amplification analysis signal, generate a normal monitoring signal and a fault signal by combining historical data for analysis.
[0012] As a further solution of the present invention: the specific method of generating the monitoring analysis signal or the cause analysis signal in step 1 is:
[0013] All sensor data are obtained, and at the same time, the first predetermined parameter corresponding to the cooling system is obtained, and the first predetermined parameter is set by the operator. Then the two are compared and judged to be the same. If the sensor data is the same as the first predetermined parameter, a monitoring and analysis signal is generated. If the sensor data is different from the first predetermined parameter, a cause analysis signal is generated.
[0014] As a further solution of the present invention: the specific method of generating the normal monitoring signal and the fault signal in step 2 is:
[0015] Obtain all components i, where i=1, 2, ..., j, where j is the number of components, and plot the working parameters of the components in the time period t to obtain a working curve graph, and simultaneously obtain the health status curve graph corresponding to the components, and compare and match the obtained working curve graph with the health status curve graph;
[0016] If the working curve diagram matches the health status curve diagram, it means that the working status of the component is normal and a normal monitoring signal is generated. If the working curve diagram does not match the health status curve diagram, it means that the working status of the component is abnormal and a fault warning signal is generated.
[0017] As a further solution of the present invention: the specific method of analyzing the components that generate the fault warning signal in step 3 is:
[0018] The components corresponding to the fault warning signal are obtained and recorded as abnormal components. At the same time, the historical records with the same changes as the abnormal components in the historical data are screened to determine the component status corresponding to the historical records. If the component status is normal, a feature analysis signal is generated. If the component status is abnormal, a fault signal is generated.
[0019] As a further solution of the present invention: the specific method of analyzing the generated characteristic analysis signal in step 3 is:
[0020] The current abnormal features of the abnormal parts are obtained, and the corresponding historical features in the historical records are obtained and compared with the current abnormal features. If the current abnormal features are the same as the historical features, it means that the abnormal parts are normal and a normal monitoring signal is generated. If the current abnormal features are different from the historical features, the current abnormal features are analyzed at the same time, and the specific analysis method is as follows:
[0021] According to the current abnormal feature, the number of abnormalities in the corresponding historical data within the time T is obtained, recorded as C, and the abnormal number ratio of the current abnormal feature is calculated and recorded as a. Then, the abnormal number ratio a is compared with the preset value. When the abnormal number ratio a is greater than the preset value, a fault signal is generated. Conversely, when the abnormal number ratio a is less than the preset value, a normal monitoring signal is generated.
[0022] As a further solution of the present invention: the specific method of analyzing and processing the generated cause analysis signal in step 4 is:
[0023] The sensor data and the second predetermined parameter corresponding to the abnormal cause signal are obtained, and the parameter sizes of the two are compared and judged. If the sensor parameter does not exist within the second predetermined parameter, an abnormal analysis signal is generated. If the sensor parameter exists within the second predetermined parameter, a normal monitoring signal is generated, and the second predetermined parameter is a range value, and the abnormal analysis signal is analyzed.
[0024] As a further solution of the present invention: the specific method of analyzing the abnormal analysis signal in step 4 is:
[0025] Obtaining component operating parameters corresponding to corresponding sensor data, and comparing the component operating parameters with preset values, if the component operating parameters are different from the preset values, generating a fault signal, if the component operating parameters are the same as the preset values, generating a periodic monitoring signal, and analyzing the periodic monitoring signal;
[0026] Obtain the changes in the working parameters of the corresponding components within the time period t1, and establish a relationship diagram of the working parameters of the components. At the same time, judge the changes based on the relationship diagram. If the changes are stable, no processing will be done and a normal monitoring signal will be generated. Otherwise, if the changes are unstable, an unstable signal will be generated.
[0027] As a further solution of the present invention: the specific method of analyzing the generated unstable signal in step 5 is:
[0028] The number of unstable changes corresponding to the working parameters of the components within the time period t1 is obtained, recorded as n, and the change peak value corresponding to the unstable change number n is obtained, recorded as Kn, and the change of the change peak value is analyzed. If the change peak value is an increasing change, an increasing analysis signal is generated. Otherwise, if the change peak value is a decreasing change, a normal monitoring signal is generated, and the increasing analysis signal is analyzed at the same time.
[0029] As a further solution of the present invention: the specific method of analyzing the amplified analysis signal in step 5 is:
[0030] The maximum change peak value corresponding to the component is obtained, and the maximum change peak value is compared with the threshold. When the maximum change peak value is greater than the threshold, a fault signal is generated. Otherwise, when the maximum change peak value is less than the threshold, historical data is obtained for comprehensive analysis to determine whether there is similar abnormal data in the historical data. If so, a fault signal is generated. Otherwise, a normal monitoring signal is generated.
[0031] The present invention provides a method for identifying and repairing faults in a rail vehicle cooling system. Compared with the prior art, it has the following beneficial effects:
[0032] The present invention determines whether the current cooling system has any working abnormality according to the corresponding sensor parameters. For the abnormal working state, the working parameters are periodically analyzed, and it is determined whether there is a potential problem according to the corresponding curve graph. Further, for the more abnormal situation, a specific analysis is performed in combination with historical data, and analysis is performed according to the corresponding component parameters to locate the fault of the working abnormality and determine the cause of the fault, which is convenient for maintenance personnel to view intuitively and save time for subsequent maintenance. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] Figure 1 It is a method diagram of the present invention;
[0034] Figure 2 It is a flow chart of the present invention. DETAILED DESCRIPTION
[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not 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.
[0036] See also Figure 1 and Figure 2 The present application provides a method for identifying and repairing a rail vehicle cooling system fault, the method specifically comprising the following steps:
[0037] Step 1: Acquire sensor data in the rail vehicle, compare sensor parameters according to first predetermined parameters, and generate a monitoring analysis signal or a cause analysis signal. The specific method of generating the monitoring analysis signal or the cause analysis signal is:
[0038] All sensor data are obtained, and the sensor data includes various data corresponding to the cooling system in the rail vehicle, and at the same time, a first predetermined parameter corresponding to the cooling system is obtained, and the first predetermined parameter is set by an operator, and then the two are compared and judged to be identical;
[0039] If the sensor data is the same as the first predetermined parameter, and the same means that the difference between the sensor data and the first predetermined parameter is within the allowable range, the difference is calculated by subtracting the first predetermined parameter from the sensor data, and the specific value of the allowable range is set by the operator, then a monitoring and analysis signal is generated; if the sensor data is not the same as the first predetermined parameter, and the difference between the two exceeds the allowable range, then a cause analysis signal is generated;
[0040] Step 2: Analyze and process the generated monitoring and analysis signals, draw corresponding working curves according to the periodic working parameters of different components, and compare them with the health status curves to determine the working status of the components. At the same time, generate normal monitoring signals and fault warning signals. The specific methods for generating normal monitoring signals and fault signals are as follows:
[0041] All components are labeled as i, and i=1, 2, ..., j, where j is the number of components. Then, the working parameters of the components are obtained with time t as a period, and the working parameters of the components within the time period t are plotted to obtain a working curve graph, and the health state curve graph corresponding to the components is obtained at the same time, and the health state curve graph is represented as a parameter change curve graph corresponding to the corresponding component under normal working conditions;
[0042] The obtained working curve graph is compared and matched with the health status curve graph, and the comparison and matching here is judged by comparing the working parameters corresponding to different time points, and analyzing by calculating the parameter difference corresponding to the same time point. If the working curve graph matches the health status curve graph, it means that the working state of the component is normal, and a normal monitoring signal is generated, and the generated normal monitoring signal is not processed. If the working curve graph does not match the health status curve graph, it means that the working state of the component is abnormal, and a fault warning signal is generated, and the match and mismatch are respectively represented by the parameter difference being within the allowable range or the parameter difference being not within the allowable range.
[0043] Step 3: Analyze the components that are judged to generate fault warning signals, obtain the same changes in historical data, and perform comprehensive analysis based on the abnormal characteristics corresponding to the components to generate normal monitoring signals and fault signals. The specific methods for generating normal monitoring signals and fault signals are as follows:
[0044] The components corresponding to the fault warning signal are obtained and recorded as abnormal components, and historical data are obtained. At the same time, the historical records with the same changes as the abnormal components in the historical data are screened, and the same changes here are represented by the same corresponding working parameters. Then, the corresponding situations in the historical records are analyzed to determine the component status corresponding to the historical records. If the component status is normal, a characteristic analysis signal is generated. If the component status is abnormal, a fault signal is generated, and the corresponding component fault information is further generated;
[0045] For example, suppose a sensor in the cooling system of a rail vehicle sends a fault warning signal. The system first marks the sensor as an abnormal component and obtains historical data. By analyzing the historical data, it is found that in the past few months, the operating parameters of the sensor were the same as the parameters when the current warning signal was issued. Further analysis of these historical records found that in these cases, the sensor status was normal. Therefore, the system generates a characteristic analysis signal to prompt the operator to pay attention to this changing trend, but no immediate maintenance is required. On the contrary, if a situation similar to the current warning signal and corresponding to the abnormal component status is found in the historical records, the system will generate a fault signal and prompt the operator to check or replace the sensor to prevent potential failures.
[0046] With respect to the generated characteristic analysis signal, the current abnormal characteristic of the abnormal component is obtained. The current abnormal characteristic can be expressed as the condition of the component itself, such as the temperature rise of the component, the defect of the component, etc. At the same time, the corresponding historical characteristics in the historical records are obtained, and the historical characteristics here are expressed as the corresponding component characteristics under normal working conditions, and the current abnormal characteristic is compared with the historical characteristics. If the current abnormal characteristic is the same as the historical characteristic, it means that the abnormal component is normal, and a normal monitoring signal is generated. If the current abnormal characteristic is different from the historical characteristic, the current abnormal characteristic is further analyzed;
[0047] According to the current abnormal feature, the number of abnormalities in the corresponding historical data within the time T is obtained, which is recorded as C. At the same time, the total number of times corresponding to the current abnormal feature is obtained, which is recorded as Z. The total number of times obtained here includes the normal number of times and the abnormal number of times. The abnormal number ratio of the current abnormal feature is calculated and recorded as a. Then, the abnormal number ratio a is compared with the preset value, and the specific value of the preset value is set by the operator. When the abnormal number ratio a is greater than the preset value, a fault signal is generated. Conversely, when the abnormal number ratio a is less than the preset value, a normal monitoring signal is generated.
[0048] For example, in the cooling system of a rail vehicle, we observe that the number of temperature anomalies of a certain sensor within time T is C, and the total number of monitoring times of the sensor in the same time period is Z. Assume that the abnormal number ratio a we calculated is 40%. If the operator sets the preset value of 30% based on experience, then since a is greater than the preset value, the system will generate a fault signal, prompting the operator to pay attention to the operating status of the sensor. On the contrary, if the preset value is 50%, then a is less than the preset value, and the system will generate a normal monitoring signal, indicating that the operating status of the sensor is still normal.
[0049] Step 4: Analyze and process the generated cause analysis signal, compare the sensor data corresponding to the cause analysis signal with the size of the second predetermined parameter and generate an abnormal analysis signal and a normal monitoring signal, process the abnormal analysis signal, periodically monitor the working parameters of the parts, and determine the corresponding working parameter changes to generate a normal monitoring signal and an unstable analysis signal, and the specific method of generating the normal monitoring signal and the unstable analysis signal is:
[0050] The sensor data and the second predetermined parameter are obtained, and the parameter sizes of the two are compared and judged. If the sensor parameter does not exist within the second predetermined parameter, an abnormal analysis signal is generated. If the sensor parameter exists within the second predetermined parameter, a normal monitoring signal is generated. The second predetermined parameter here is a range value. Within this range value, it means that the corresponding measured data is normal.
[0051] For example, in the cooling system of rail vehicles, we set the coolant temperature range to 30°C to 40°C. When the coolant temperature detected by the sensor is within this range, the system will generate a normal monitoring signal. However, if the temperature detected by the sensor exceeds this range, such as reaching 45°C, the system will generate an abnormal analysis signal, prompting the operator that there may be an overheating problem that needs to be dealt with in a timely manner.
[0052] Then, the generated abnormal analysis signal is processed to obtain the component working parameters corresponding to the corresponding sensor data, and the component working parameters are compared with the preset values, and the specific values of the preset values are set by the operator. If the component working parameters are different from the preset values, a fault signal is generated, and component fault information is further generated. If the component working parameters are the same as the preset values, a periodic monitoring signal is generated and the periodic monitoring signal is analyzed;
[0053] Obtain the changes in the working parameters of the corresponding parts within the time period t1, and establish a relationship diagram of the working parameters of the parts. At the same time, judge the changes based on the relationship diagram. If the changes are stable, no processing will be done and a normal monitoring signal will be generated. Otherwise, if the changes are unstable, an unstable signal will be generated. The specific criteria for judging stability or instability are to compare the parameter differences corresponding to different time points within the time period t1. If the overall parameter difference is within the allowable range of changes, it is stable, otherwise it is unstable. The range of changes is an interval composed of specific values, which is set by the operator according to the actual situation.
[0054] Step 5: Analyze the generated unstable signal, analyze the number of unstable changes and the change peak value within the time period, generate the large analysis signal and the normal monitoring signal according to the change of the change peak value, and analyze the large analysis signal, generate the normal monitoring signal and the fault signal by combining the historical data for analysis, and the specific analysis method is:
[0055] The number of unstable changes corresponding to the working parameters of the components in the time period t1 is obtained, which is recorded as n. At the same time, the change peak value corresponding to the number of unstable changes n is obtained, which is recorded as Kn. The change peak value here is represented by a value exceeding the value corresponding to the normal working parameters. The change of the change peak value is analyzed. If the change peak value is an increasing change, an increasing analysis signal is generated. On the contrary, if the change peak value is a decreasing change, a normal monitoring signal is generated.
[0056] Then, the generated amplification analysis signal is processed to obtain the maximum change peak value corresponding to the component, and the maximum change peak value is compared with the threshold. When the maximum change peak value is greater than the threshold, a fault signal is generated. On the contrary, when the maximum change peak value is less than the threshold, the historical data is obtained for comprehensive analysis to determine whether there is similar abnormal data in the historical data. If so, a fault signal is generated. On the contrary, if not, a normal monitoring signal is generated. Specifically, the similar abnormal data here refers to abnormal records similar to the current situation that appear in the historical data. When the maximum change peak value is less than the threshold, we need to further obtain historical data for comprehensive analysis. This is because some faults may not immediately lead to obvious parameter changes, but by analyzing similar abnormal data in historical data, we can still find potential signs of faults. If there is similar abnormal data in the historical data, we will generate a fault signal; on the contrary, if there is no similar abnormal data, a normal monitoring signal is generated.
[0057] For example, in the cooling system of a rail vehicle, we detected that the temperature change rate of a certain sensor exceeded the predetermined range and generated a large analysis signal. Assume that the maximum change peak value corresponding to the sensor is 50°C, and the preset threshold is 45°C. Since the maximum change peak value is greater than the threshold, the system will generate a fault signal to prompt the operator to pay attention to the operating status of the sensor. Subsequently, the operator can further check the working status of the sensor and repair or replace it as needed.
[0058] In conclusion, by processing and comprehensively analyzing the generated amplified analysis signals, we can timely detect potential faults in the cooling system of rail vehicles and take corresponding preventive measures.
[0059] Some of the data in the above formulas are dimensionless and numerically calculated. Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.
[0060] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. 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 identifying and repairing faults in a rail vehicle cooling system, characterized in that: The following steps are involved: Step 1: Acquire sensor data in the rail vehicle, and compare the sensor parameters according to the first predetermined parameter to generate a monitoring analysis signal or a cause analysis signal. The specific method of generating the monitoring analysis signal or the cause analysis signal is: All sensor data are obtained, and at the same time, a first predetermined parameter corresponding to the cooling system is obtained, and the first predetermined parameter is set by an operator, and then the two are compared and judged to be the same. If the sensor data is the same as the first predetermined parameter, a monitoring and analysis signal is generated; if the sensor data is not the same as the first predetermined parameter, a cause analysis signal is generated; Step 2: Analyze and process the generated monitoring and analysis signals, draw corresponding working curves according to the periodic working parameters of different components, and compare them with the health status curves to determine the working status of the components, and generate normal monitoring signals and fault warning signals at the same time; Step 3: Analyze the components that are judged to generate fault warning signals, obtain the same changes in historical data, and perform comprehensive analysis based on the abnormal characteristics corresponding to the components to generate normal monitoring signals and fault signals; Step 4: Analyze and process the generated cause analysis signal, compare the sensor data corresponding to the cause analysis signal with the size of the second predetermined parameter and generate an abnormal analysis signal and a normal monitoring signal, process the abnormal analysis signal, periodically monitor the working parameters of the components, and determine the corresponding working parameter changes to generate a normal monitoring signal and an unstable analysis signal, and the specific method of analyzing and processing the generated cause analysis signal is: The sensor data and the second predetermined parameter corresponding to the cause analysis signal are obtained, and the parameter sizes of the two are compared and judged. If the sensor parameter does not exist within the second predetermined parameter, an abnormal analysis signal is generated. If the sensor parameter exists within the second predetermined parameter, a normal monitoring signal is generated, and the second predetermined parameter is a range value, and the abnormal analysis signal is analyzed; Step 5: Analyze the generated unstable signal. By analyzing the number of unstable changes and the change peak value within the time period, generate an increased analysis signal and a normal monitoring signal according to the change of the change peak value. The specific method of analyzing the generated unstable signal is as follows: The number of unstable changes corresponding to the working parameters of the components within the time period t1 is obtained, recorded as n, and the change peak value corresponding to the number of unstable changes n is obtained, recorded as Kn, and the change of the change peak value is analyzed. If the change peak value is an increasing change, an increasing analysis signal is generated. On the contrary, if the change peak value is a decreasing change, a normal monitoring signal is generated, and the increasing analysis signal is analyzed at the same time; For the amplified analysis signal, the normal monitoring signal and the fault signal are generated by combining the historical data for analysis. The specific method is as follows: The maximum change peak value corresponding to the component is obtained, and the maximum change peak value is compared with the threshold. When the maximum change peak value is greater than the threshold, a fault signal is generated. Otherwise, when the maximum change peak value is less than the threshold, historical data is obtained for comprehensive analysis to determine whether there is similar abnormal data in the historical data. If so, a fault signal is generated. Otherwise, a normal monitoring signal is generated.
2. A rail vehicle cooling system fault identification and repair method according to claim 1, characterized in that: The specific method of generating the normal monitoring signal and the fault signal in step 2 is: Obtain all components i, where i=1, 2, ..., j, where j is the number of components, and plot the working parameters of the components in the time period t to obtain a working curve graph, and simultaneously obtain the health status curve graph corresponding to the components, and compare and match the obtained working curve graph with the health status curve graph; If the working curve diagram matches the health status curve diagram, it means that the working status of the component is normal and a normal monitoring signal is generated. If the working curve diagram does not match the health status curve diagram, it means that the working status of the component is abnormal and a fault warning signal is generated.
3. A rail vehicle cooling system fault identification and repair method according to claim 1, characterized in that: The specific method of analyzing the components that generate the fault warning signal in step 3 is: The components corresponding to the fault warning signal are obtained and recorded as abnormal components. At the same time, the historical records with the same changes as the abnormal components in the historical data are screened to determine the component status corresponding to the historical records. If the component status is normal, a feature analysis signal is generated. If the component status is abnormal, a fault signal is generated.
4. A rail vehicle cooling system fault identification and repair method according to claim 3, characterized in that: The specific method of analyzing the generated characteristic analysis signal in step 3 is: The current abnormal features of the abnormal parts are obtained, and the corresponding historical features in the historical records are obtained and compared with the current abnormal features. If the current abnormal features are the same as the historical features, it means that the abnormal parts are normal and a normal monitoring signal is generated. If the current abnormal features are different from the historical features, the current abnormal features are analyzed at the same time, and the specific analysis method is as follows: According to the current abnormal feature, the number of abnormalities in the corresponding historical data within the time T is obtained, recorded as C, and the abnormal number ratio of the current abnormal feature is calculated and recorded as a. Then, the abnormal number ratio a is compared with the preset value. When the abnormal number ratio a is greater than the preset value, a fault signal is generated. Conversely, when the abnormal number ratio a is less than the preset value, a normal monitoring signal is generated.
5. A rail vehicle cooling system fault identification and repair method according to claim 1, characterized in that: The specific method of analyzing the abnormal analysis signal in step 4 is: Obtaining component operating parameters corresponding to corresponding sensor data, and comparing the component operating parameters with preset values, if the component operating parameters are different from the preset values, generating a fault signal, if the component operating parameters are the same as the preset values, generating a periodic monitoring signal, and analyzing the periodic monitoring signal; Obtain the changes in the working parameters of the corresponding components within the time period t1, and establish a relationship diagram of the working parameters of the components. At the same time, judge the changes based on the relationship diagram. If the changes are stable, no processing will be done and a normal monitoring signal will be generated. Otherwise, if the changes are unstable, an unstable signal will be generated.
