Hydraulic pressure sensor fault detection method, device, storage medium and traction system

Abstract

The application discloses a kind of water pressure sensor fault detection method, device, storage medium and traction system, including the acquisition for multiple entrance water pressure sensor entrance pressure value and with each entrance water pressure sensor corresponding outlet water pressure sensor outlet pressure value;According to multiple entrance pressure value and multiple outlet pressure value, residual error that characterizes fault state is constructed;According to the expression of preset detection statistical quantity, the detection statistical quantity corresponding to residual error is determined;According to detection statistical quantity and detection threshold, the decision value corresponding to residual error is determined;According to decision value and preset fault threshold, whether the fault of entrance water pressure sensor and outlet water pressure sensor occurs, so, based on the time sequence characteristics of each water pressure sensor and the data correlation between each water pressure sensor are designed, and fault feature matrix is calculated to carry out fault decision, and then realize the accurate fault positioning of water pressure sensor, improve the reliability of water pressure sensor fault diagnosis result.

Description

Technical Field

[0001] This invention belongs to the field of fault detection technology, specifically relating to a fault detection method, device, storage medium, and traction system for a water pressure sensor. Background Technology

[0002] In train traction drive systems, water pressure is a crucial indicator of the equipment's operating environment and condition. It indirectly reflects system abnormalities in the traction converter cabinet's cooling system, such as loose water pipes, coolant leaks, burst pipes, changes in pipe resistance or flow, and clogged filters. Both excessively high and low water pressure necessitate appropriate protective measures to ensure safe equipment operation. However, due to the harsh operating environment of traction drive systems, sensor malfunctions are frequent. In such cases, the water pressure sensor's sampled values ​​may not reflect the true values, potentially leading to malfunctions or delayed protection in the control system. Frequent malfunctions reduce train availability, while delayed protection against abnormal water pressure can escalate the fault, impacting train safety. Therefore, researching effective methods for water pressure sensor fault diagnosis is of significant practical importance.

[0003] Currently, the most common method for diagnosing water pressure sensors in engineering is the threshold exceedance judgment method. This means that if the collected water pressure sensor signal value exceeds the normal hardware sampling range, it is considered a water pressure sensor fault. This method has a serious risk of false negatives. For example, if the water pressure sensor experiences a decrease in accuracy or drift, but the sampled value is still within the effective hardware sampling range, the water pressure sensor fault cannot be diagnosed, posing a serious safety hazard.

[0004] Therefore, how to improve the reliability of water pressure sensor fault diagnosis results is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] The main objective of this invention is to provide a fault detection method, device, storage medium, and traction system for water pressure sensors, in order to solve the problem of low reliability of fault diagnosis results of existing water pressure sensors.

[0006] To address the above problems, the present invention provides a fault detection method for a water pressure sensor, comprising:

[0007] Collect the inlet pressure values ​​of multiple inlet water pressure sensors used to detect the water pressure of the target device and the outlet pressure value of the outlet water pressure sensor corresponding to each inlet water pressure sensor;

[0008] Based on multiple inlet pressure values ​​and multiple outlet pressure values, a residual characterizing the fault state is constructed;

[0009] Based on the preset detection statistic expression, the detection statistic corresponding to the residual is determined;

[0010] Based on the detection statistics and detection threshold, determine the decision value corresponding to the residual;

[0011] Based on the decision value and the preset fault threshold, it is determined whether the inlet water pressure sensor and the outlet water pressure sensor have malfunctioned.

[0012] Furthermore, in the above-described fault detection method for water pressure sensors, a residual characterizing the fault state is constructed based on multiple inlet pressure values ​​and multiple outlet pressure values, including:

[0013] Determine the inlet residual between any two inlet pressure values;

[0014] Determine the export residual between any two outlets based on any two outlet pressure values;

[0015] Based on any given inlet pressure value and its corresponding outlet pressure value, determine the inlet / outlet residual between the inlet and the corresponding outlet.

[0016] Based on the residuals of any two entrances and exits, determine the inter-path residuals between the corresponding two paths.

[0017] Furthermore, in the above-described fault detection method for the water pressure sensor, the preset expression is as follows:

[0018]

[0019] Among them, T i 2 Let r represent the detection statistic for the i-th residual. i (j) Let represent the sampled value of the i-th residual in the j-th sampling period, N represent the number of samples per period, and μ0 represent the average value under normal operating conditions. This represents the standard deviation under normal operating conditions.

[0020] Furthermore, in the above-described method for fault detection of a water pressure sensor, the process of obtaining the detection threshold includes:

[0021] The detection threshold is determined based on the preset confidence level and the number of periodic samples.

[0022] Furthermore, in the above-described fault detection method for the water pressure sensor, determining the decision value corresponding to the residual based on the detection statistics and detection threshold includes:

[0023] Substitute the detection statistics and detection threshold into the preset decision value expression to determine the decision value corresponding to the residual;

[0024] The decision value expression is as follows:

[0025]

[0026] Among them, g i (k) represents the decision value of the i-th residual at time k, g i (k-1) represents the decision value of the i-th residual at time k-1, T αi This represents the detection threshold for the i-th residual.

[0027] The present invention also provides a fault detection device for a water pressure sensor, comprising:

[0028] The acquisition module is used to acquire the inlet pressure values ​​of multiple inlet water pressure sensors used to detect the water pressure of the target device and the outlet pressure values ​​of the outlet water pressure sensor corresponding to each inlet water pressure sensor.

[0029] A construction module is used to construct residuals characterizing the fault state based on multiple inlet pressure values ​​and multiple outlet pressure values;

[0030] The first determining module is used to determine the detection statistic corresponding to the residual based on a preset detection statistic expression;

[0031] The second determining module is used to determine the decision value corresponding to the residual based on the detection statistics and the detection threshold.

[0032] The third determining module is used to determine whether the inlet water pressure sensor and the outlet water pressure sensor have failed based on the decision value and the preset fault threshold.

[0033] Furthermore, in the aforementioned fault detection device for the water pressure sensor, the building module is specifically used for:

[0034] Determine the inlet residual between any two inlet pressure values;

[0035] Determine the export residual between any two outlets based on any two outlet pressure values;

[0036] Based on any given inlet pressure value and its corresponding outlet pressure value, determine the inlet / outlet residual between the inlet and the corresponding outlet.

[0037] Based on the residuals of any two entrances and exits, determine the inter-path residuals between the corresponding two paths.

[0038] Furthermore, in the aforementioned fault detection device for the water pressure sensor, the preset expression is as follows:

[0039]

[0040] Among them, Ti 2 Let r represent the detection statistic for the i-th residual. i (j) Let represent the sampled value of the i-th residual in the j-th sampling period, N represent the number of samples per period, and μ0 represent the average value under normal operating conditions. This represents the standard deviation under normal operating conditions.

[0041] The present invention also provides a traction system, including a memory and a controller, wherein the memory stores a computer program, and when the computer program is executed by the controller, it implements the fault detection method of the water pressure sensor described in any one of the above.

[0042] The present invention also provides a storage medium storing a computer program, which, when executed by a controller, implements the fault detection method for the water pressure sensor described in any of the above claims.

[0043] Compared with the prior art, one or more embodiments of the above solutions may have the following advantages or beneficial effects:

[0044] The present invention discloses a fault detection method, apparatus, storage medium, and traction system for water pressure sensors. This method collects inlet pressure values ​​from multiple inlet water pressure sensors used to detect water pressure in a target device and outlet pressure values ​​from an outlet water pressure sensor corresponding to each inlet water pressure sensor. Based on these inlet and outlet pressure values, a residual characterizing the fault state is constructed. A detection statistic corresponding to the residual is determined according to a preset detection statistic expression. A decision value corresponding to the residual is determined based on the detection statistic and a detection threshold. Finally, based on the decision value and a preset fault threshold, it determines whether the inlet and outlet water pressure sensors have failed. This method achieves design based on the temporal characteristics of each water pressure sensor and the data correlation between them. It also integrates signals from multiple water pressure sensors to calculate a fault feature matrix for fault decision-making, thereby achieving accurate fault location of the water pressure sensor and improving the reliability of the water pressure sensor fault diagnosis results.

[0045] Other features and advantages of the invention will be set forth in the description which follows, and will become apparent in part from the adjustments made thereto, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the description, claims, and drawings. Attached Figure Description

[0046] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with the embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0047] Figure 1 This is a schematic diagram of the composite cooling system principle of the traction system;

[0048] Figure 2 This is a flowchart illustrating an embodiment of the water pressure sensor fault detection method of the present invention;

[0049] Figure 3 This is a schematic diagram of the structure of an embodiment of the water pressure sensor fault detection device of the present invention;

[0050] Figure 4 This is a schematic diagram of the structure of an embodiment of the traction system of the present invention. Detailed Implementation

[0051] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings and examples, so that the process of how the present invention uses technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly. It should be noted that, as long as there is no conflict, the various embodiments and features in the various embodiments of the present invention can be combined with each other, and the resulting technical solutions are all within the protection scope of the present invention.

[0052] To ensure the normal operation of major components of locomotives / trains and to provide effective protection under abnormal conditions, water pressure sensors are installed in key components of the locomotive / train traction system, such as the traction transformer, traction converter, and traction motor. Traction motors are typically cooled by forced air cooling, using independent traction fans and ventilation ducts. The traction converter and traction transformer are cooled by water and oil respectively, using a combined oil-water cooling system.

[0053] Taking a certain type of EMU traction system as an example, Figure 1 This is a schematic diagram of the composite cooling system for the traction system. Figure 1 As shown, the composite radiator 12 is the heat exchange device of the oil-water cooling system of the composite cooling tower. Cooling water from the traction converter 10 enters the upper layer of the radiator, and oil from the traction transformer 11 enters the lower layer of the composite radiator 12. The heat from the traction converter 10 and the traction transformer 11 is exchanged with the air in the composite radiator 12, cooling the water and oil to the required temperature. The cooled water and oil then enter the traction converter 10 and the traction transformer 11 respectively to further cool them. The composite radiator 12 of the cooling tower is connected to the traction converter 10 and the transformer via pipelines. The composite radiator 12 consists of two separate fluid branches. Through the action of a fan, an oil pump, and a water pump, oil, water, and air exchange heat in the composite radiator 12.

[0054] The water pressure sensors of the traction converter 10 are installed at the inlet and outlet of the water pipe to measure the water pressure at the inlet and outlet. Each traction drive system typically includes four water pressure sensors. The control system collects these water pressure values ​​in real time and performs timely diagnosis and protection against water pressure anomalies.

[0055] However, in related technologies, after the control system collects these water pressure values ​​in real time, it only determines whether the water pressure sensor has malfunctioned by checking whether the water pressure reading exceeds the normal sampling range of the hardware. This method has a serious risk of false negatives. For example, if the water pressure sensor experiences a decrease in accuracy or drift failure, but the sampled value is still within the effective sampling range of the hardware, the water pressure sensor malfunction cannot be diagnosed, posing a serious safety hazard.

[0056] Therefore, in order to solve the above-mentioned technical problems, the present invention provides the following embodiments.

[0057] Figure 2 This is a flowchart of an embodiment of the water pressure sensor fault detection method of the present invention, as shown below. Figure 2 As shown, the fault detection of the water pressure sensor in this embodiment may specifically include the following steps:

[0058] 200. Collect the inlet pressure values ​​of multiple inlet water pressure sensors used to detect the water pressure of the target device and the outlet pressure value of the outlet water pressure sensor corresponding to each inlet water pressure sensor;

[0059] 201. Based on multiple inlet pressure values ​​and multiple outlet pressure values, construct residuals that characterize the fault state;

[0060] In a specific implementation process, the inlet residual between any two inlets can be determined based on any two inlet pressure values; the outlet residual between any two outlets can be determined based on any two outlet pressure values; the inlet-outlet residual between any inlet pressure value and its corresponding outlet pressure value can be determined based on any inlet pressure value and its corresponding outlet pressure value; and the inter-path residual between any two corresponding paths can be determined based on any two inlet-outlet residuals.

[0061] Specifically, with Figure 1 For example, Figure 1 The sampled values ​​of the four water pressure sensors (two inlet water pressure sensors and two outlet water pressure sensors) of the traction drive system shown are respectively represented as the first inlet pressure value P. i1 Second inlet pressure value P i2 First outlet pressure value P o1 Second outlet pressure value P o2 Under normal circumstances, the first inlet pressure value P i1 With the second inlet pressure value P i2 Approaching, first inlet pressure value P i1 With the second inlet pressure value Pi2 The pressure values ​​are close, and the first inlet pressure value P is... i1 With the first outlet pressure value P o1 Interval difference, second inlet pressure value P i2 With the second outlet pressure value P o2 The differences between them are positively correlated.

[0062] In a specific implementation process, the residuals constructed in this embodiment are as follows: (1)-(5):

[0063] r1 = P i1 -P i2 (1)

[0064] r2=P o1 -P o2 (2)

[0065] r3=P i1 -P o1 (3)

[0066] r4 = P i2 -P o2 (4)

[0067] r5=(P i1 -P o1 )-(P i2 -P o2 (5)

[0068] Where r1 represents the inlet residual between the first inlet and the second inlet, r2 represents the outlet residual between the first outlet and the second outlet, r3 represents the inlet / outlet residual between the first inlet and the first outlet, r4 represents the inlet / outlet residual between the second inlet and the second outlet, and r5 represents the inter-channel residual between the first passage and the second passage.

[0069] After constructing the residuals characterizing the fault states, the fault feature matrix can be further obtained, as shown in Table 1. In Table 1, F1 to F4 represent the faults of the first inlet water pressure sensor, the second inlet water pressure sensor, the first outlet water pressure sensor, and the second outlet water pressure sensor, respectively; the symbol "X" indicates that the fault is detectable, and blank spaces indicate that the fault is not detectable. For example, r1 can detect two faults (the first inlet water pressure sensor and the second inlet water pressure sensor), but cannot detect faults of other water pressure sensors.

[0070] Table 1

[0071]

[0072]

[0073] 202. Determine the detection statistic corresponding to the residual based on the preset detection statistic expression;

[0074] In a specific implementation, after constructing the residuals, the next step is to construct a suitable detection statistic for fault detection. During normal operation, if the traction system is fault-free, the residual r... i Satisfies a normal distribution Where μ0 represents the average value under normal operating conditions. This represents the standard deviation under normal operating conditions, and its value can be obtained by learning from normal historical data. Let R be... i ={r i (1) ,r i (2) ,…,r i (N)} for r i The periodic sample values, where N is the number of periodic samples for calculation.

[0075] A preset expression for the detection statistic can be defined as shown in equation (6).

[0076]

[0077] Among them, T i 2 Let r represent the detection statistic for the i-th residual. i (j) Let N represent the sampled value of the i-th residual in the j-th sampling period, and N represent the number of sampling periods.

[0078] In one specific implementation, the process of obtaining the detection threshold includes: determining the detection threshold based on a preset confidence level and the number of periodic samples.

[0079] The detection statistic satisfies the χ² value with N-1 degrees of freedom. 2 Standard distribution, and In the formula The measured quantity T represents the quantity detected under the fault-free assumption H0. i 2 Greater than The probability of.

[0080] This embodiment uses this method for fault detection. The threshold is obtained by approximating the chi-square distribution, referring to expression (7):

[0081]

[0082] In the formula, T α Indicates the threshold. χ represents the number of degrees of freedom N and the confidence level α. 2The chi-square distribution of the critical value is usually understood as the allowable probability of false detections.

[0083] 203. Determine the decision value corresponding to the residual based on the detection statistics and detection threshold;

[0084] Specifically, the detection statistics and detection threshold can be substituted into a preset decision value expression to determine the decision value corresponding to the residual.

[0085] Because the sampling data in practice has significant noise, and the residuals under fault conditions contain apparent oscillations, we apply the one-sided CUSUM (cumulative sum) algorithm for residual decision-making. The decision value expression is given by equation (9).

[0086]

[0087] Among them, g i (k) represents the decision value of the i-th residual at time k, g i (k-1) represents the decision value of the i-th residual at time k-1, T αi This represents the detection threshold for the i-th residual.

[0088] 204. Based on the decision value and the preset fault threshold, determine whether the inlet water pressure sensor and the outlet water pressure sensor have failed.

[0089] In a specific implementation process, the residual decision logic is as follows: if g i (k)≤h i Accepting H0 indicates no fault; if g i (k)>h i If H1 is received, then there is a fault. Where h... i The preset fault threshold can be derived from the experience of application engineers.

[0090] In a specific implementation process, let the residual r i The decision functions corresponding to (i = 1, ..., 5) are g1(k) to g5(k) respectively, and the fault thresholds are h1 to h5 respectively. Based on the fault feature matrix described in Table 1, the fault diagnosis rules for each water pressure sensor fault are shown in Table 2. Based on Table 2, effective detection and isolation of each fault can be achieved.

[0091] Table 2

[0092]

[0093] The fault detection method for water pressure sensors in this embodiment collects the inlet pressure values ​​of multiple inlet water pressure sensors used to detect the water pressure of the target device and the outlet pressure values ​​of the corresponding outlet water pressure sensors. Based on the multiple inlet and outlet pressure values, a residual characterizing the fault state is constructed. According to a preset detection statistic expression, the detection statistic corresponding to the residual is determined. Based on the detection statistic and a detection threshold, a decision value corresponding to the residual is determined. Based on the decision value and a preset fault threshold, it is determined whether the inlet and outlet water pressure sensors have failed. This method is designed based on the temporal characteristics of each water pressure sensor and the data correlation between them. By integrating multiple water pressure sensor signals, a fault feature matrix is ​​calculated for fault decision-making, thereby achieving accurate fault location of the water pressure sensor and improving the reliability of the water pressure sensor fault diagnosis results.

[0094] It should be noted that the method of this embodiment can be executed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method of this embodiment, and the multiple devices will interact with each other to complete the method.

[0095] Figure 3 This is a schematic diagram of an embodiment of the fault detection device for the water pressure sensor of the present invention, as shown below. Figure 3 As shown, the fault detection device for the water pressure sensor in this embodiment may include a data acquisition module 30, a data construction module 31, a first determination module 32, a second determination module 33, and a third determination module 34.

[0096] The acquisition module 30 is used to acquire the inlet pressure values ​​of multiple inlet water pressure sensors used to detect the water pressure of the target device and the outlet pressure values ​​of the outlet water pressure sensor corresponding to each inlet water pressure sensor.

[0097] Module 31 is used to construct residuals characterizing the fault state based on multiple inlet pressure values ​​and multiple outlet pressure values;

[0098] Specifically, the inlet residual between any two inlets can be determined based on any two inlet pressure values; the outlet residual between any two outlets can be determined based on any two outlet pressure values; the inlet-outlet residual between any inlet pressure value and its corresponding outlet pressure value can be determined based on any inlet pressure value and its corresponding outlet pressure value; and the inter-path residual between any two corresponding paths can be determined based on any two inlet-outlet residuals.

[0099] The first determining module 32 is used to determine the detection statistic corresponding to the residual based on a preset detection statistic expression;

[0100] In a specific implementation process, the preset expression can refer to expression (6).

[0101] The second determining module 33 is used to determine the decision value corresponding to the residual based on the detection statistics and the detection threshold.

[0102] In one specific implementation, the process of obtaining the detection threshold includes determining the detection threshold based on a preset confidence level and the number of periodic samples.

[0103] In a specific implementation process, the detection statistics and detection threshold can be substituted into a preset decision value expression to determine the decision value corresponding to the residual;

[0104] The decision value expression can be found in the aforementioned expression (9).

[0105] The third determining module 34 is used to determine whether the inlet water pressure sensor and the outlet water pressure sensor have failed based on the decision value and the preset fault threshold.

[0106] The fault detection device for water pressure sensors in this embodiment collects the inlet pressure values ​​of multiple inlet water pressure sensors used to detect the water pressure of the target device and the outlet pressure values ​​of the corresponding outlet water pressure sensors. Based on the multiple inlet and outlet pressure values, a residual characterizing the fault state is constructed. According to a preset detection statistic expression, the detection statistic corresponding to the residual is determined. Based on the detection statistic and a detection threshold, a decision value corresponding to the residual is determined. Based on the decision value and a preset fault threshold, it is determined whether the inlet and outlet water pressure sensors have failed. This device is designed based on the temporal characteristics of each water pressure sensor and the data correlation between them. It integrates signals from multiple water pressure sensors to calculate a fault feature matrix for fault decision-making, thereby achieving accurate fault location of the water pressure sensor and improving the reliability of the water pressure sensor fault diagnosis results.

[0107] The apparatus in the above embodiments is used to implement the corresponding methods in the foregoing embodiments. The specific implementation scheme can be found in the methods described in the foregoing embodiments and the relevant descriptions in the method embodiments. It also has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0108] Figure 4 This is a schematic diagram of the structure of an embodiment of the traction system of the present invention, as shown below. Figure 4As shown, the traction system includes a memory 40 and a controller 41. The memory 40 stores a computer program, which, when executed by the controller 41, implements the fault detection method for the water pressure sensor described in the above embodiment.

[0109] The present invention also provides a storage medium storing a computer program, which, when executed by a controller, implements the fault detection method for the water pressure sensor described in the above embodiments.

[0110] It is understood that the same or similar parts in the above embodiments can be referred to each other, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0111] It should be noted that in the description of this invention, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this invention, unless otherwise stated, "a plurality of" means at least two.

[0112] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0113] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0114] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0115] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0116] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0117] The storage media mentioned above can be read-only memory, disk, or optical disk, etc.

[0118] While the embodiments disclosed in this invention are as described above, the content is merely for the purpose of facilitating understanding of the invention and is not intended to limit the invention. Any person skilled in the art to which this invention pertains may make any modifications and changes in form and detail of the implementation without departing from the spirit and scope disclosed herein; however, the scope of protection of this invention shall still be determined by the scope defined in the appended claims.

Claims

1. A fault detection method for a water pressure sensor, characterized in that, include: Collect the inlet pressure values ​​of multiple inlet water pressure sensors used to detect the water pressure of the target device and the outlet pressure value of the outlet water pressure sensor corresponding to each inlet water pressure sensor; Based on multiple inlet pressure values ​​and multiple outlet pressure values, a residual characterizing the fault state is constructed; Based on the preset detection statistic expression, the detection statistic corresponding to the residual is determined; Based on the detection statistics and detection threshold, determine the decision value corresponding to the residual; Based on the decision value and the preset fault threshold, determine whether the inlet water pressure sensor and the outlet water pressure sensor have failed; Among them, residuals characterizing the fault state are constructed based on multiple inlet pressure values ​​and multiple outlet pressure values, including: Determine the inlet residual between any two inlet pressure values; Determine the export residual between any two outlets based on any two outlet pressure values; Based on any given inlet pressure value and its corresponding outlet pressure value, determine the inlet / outlet residual between the inlet and the corresponding outlet. Based on the residuals of any two entrances and exits, determine the inter-path residuals between the corresponding two paths.

2. The fault detection method for a water pressure sensor according to claim 1, characterized in that, The preset expression is as follows: in, Indicates the first The detection statistic for each residual. Indicates the first The first residual The sampled values ​​for each sampling period, Indicates the number of periodic samples. This represents the average value under normal operating conditions. This represents the standard deviation under normal operating conditions.

3. The fault detection method for a water pressure sensor according to claim 2, characterized in that, The process of obtaining the detection threshold includes: The detection threshold is determined based on the preset confidence level and the number of periodic samples.

4. The fault detection method for a water pressure sensor according to claim 3, characterized in that, Based on the detection statistics and detection threshold, the decision value corresponding to the residual is determined, including: Substitute the detection statistics and detection threshold into the preset decision value expression to determine the decision value corresponding to the residual; The decision value expression is as follows: in, Indicates the first The residual is The decision value at any given moment. Indicates the first The residual is The decision value at any given moment. Indicates the first The detection threshold for each residual.

5. A fault detection device for a water pressure sensor, characterized in that, include: The acquisition module is used to acquire the inlet pressure values ​​of multiple inlet water pressure sensors used to detect the water pressure of the target device and the outlet pressure values ​​of the outlet water pressure sensor corresponding to each inlet water pressure sensor. A construction module is used to construct residuals characterizing the fault state based on multiple inlet pressure values ​​and multiple outlet pressure values; The first determining module is used to determine the detection statistic corresponding to the residual based on a preset detection statistic expression; The second determining module is used to determine the decision value corresponding to the residual based on the detection statistics and the detection threshold. The third determining module is used to determine whether the inlet water pressure sensor and the outlet water pressure sensor have failed based on the decision value and the preset fault threshold. Specifically, the construction module is used for: Determine the inlet residual between any two inlet pressure values; Determine the export residual between any two outlets based on any two outlet pressure values; Based on any given inlet pressure value and its corresponding outlet pressure value, determine the inlet / outlet residual between the inlet and the corresponding outlet. Based on the residuals of any two entrances and exits, determine the inter-path residuals between the corresponding two paths.

6. The fault detection device for a water pressure sensor according to claim 5, characterized in that, The preset expression is as follows: in, Indicates the first The detection statistic for each residual. Indicates the first The first residual The sampled values ​​for each sampling period, Indicates the number of periodic samples. This represents the average value under normal operating conditions. This represents the standard deviation under normal operating conditions.

7. A traction system, characterized in that, The device includes a memory and a controller, wherein the memory stores a computer program that, when executed by the controller, implements the fault detection method for the water pressure sensor according to any one of claims 1 to 4.

8. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by the controller, implements the fault detection method for the water pressure sensor according to any one of claims 1 to 4.

Images