Equipment platform sensor data collection accuracy verification method and verification system

Abstract

The present invention provides a method for verifying the accuracy of data collected by sensors of an equipment platform. The specific steps include determining the type of sensor: screening from data of different objects according to different requirements, and obtaining the number, type and requirements of the required sensors by merging the types. Verifying the correctness of the data collected by the sensor: placing a certain number of sensors at positions that can characterize the performance parameters of the function and performance degradation of the object through simulation analysis and experimental analysis; evaluating whether the position and number of sensors are reasonable through closed-loop analysis of the sensor test data and the actual state of the object. Verifying the accuracy of the sensor sampling data using three sensors at different levels in the object or a mathematical derivation model of the system in the object. The present invention verifies the accuracy of the data collected by the sensor through different methods such as functional inheritance, cross-validation, redundant verification and system modeling between sensors, thereby avoiding the impact caused by errors or false alarms.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial Internet of Things applications, and in particular to a method and system for verifying the accuracy of data collected by a sensor on an equipment platform. Background Art

[0002] A sensor is a detection device that can sense the information being measured and convert it into electrical signals or other signals through certain rules to transmit, store and display the collected data. The sensor has a data collection function. When the sensor drifts, is not in a working state or other faults occur, the collected data cannot be used correctly and effectively, and may also mislead operators and maintenance personnel.

[0003] The accurate and effective data collected by the sensor provides a good basis for monitoring the status and controlling the equipment. If the collected data has a large deviation, it will have a greater impact on the control algorithm of the equipment, thereby affecting the automatic control of the equipment, and will also give wrong instructions. Therefore, a method is needed to more effectively ensure that the sensor data is correct and accurate. The correctness and accuracy of the method of the present invention refers to that the data measurement of the sensor is within the error range set by the sensor. Summary of the invention

[0004] In view of the problems existing in the prior art, the present invention provides a method for verifying the accuracy of data collected by sensors of an equipment platform. By verifying the correctness of the data collected by sensors on different objects, the sensors can better characterize the performance parameters of the functions and performance degradation of the objects at more specific locations. By utilizing a function inheritance method, a cross-validation method, a redundant verification method or a mathematical derivation model of the system, the accuracy of the collected data by sensors at different locations is verified to avoid the impact caused by errors or false alarms in sensor data, so that the system can develop in the direction of what is collected is what is believed and what is collected is what is used.

[0005] The present invention provides a method for verifying the accuracy of data collected by equipment platform sensors, and the specific implementation steps are as follows:

[0006] S1. Determine the type of sensor: filter the data of different objects of units, systems and equipment platforms, and obtain the number, type and requirements of the required sensors by combining the types;

[0007] S2. Verify the correctness of the data collected by the sensor, which specifically includes the following sub-steps:

[0008] S21. Through simulation analysis and experimental analysis, a certain number of sensors are placed at positions that can characterize performance parameters of object function and performance degradation;

[0009] S22. Under the monitoring, diagnosis and prediction functions of different objects, a closed-loop analysis is performed based on the sensor test data and the state of the object response to evaluate whether the location and number of sensors are reasonable:

[0010] If the data collected by the sensor is within a reasonable range but the object fails to function or the object has performance degradation and needs to be downgraded, the position and number of sensors need to be rearranged, and the process returns to and repeats step S21;

[0011] If the sensor's test data is consistent with the state of the object's response, the sensor's position and quantity are reasonably arranged, and step S3 is performed;

[0012] S3. Verify the accuracy of sensor data collected using multiple sensors at different levels in the object, including the following sub-steps:

[0013] S31. If there are less than or equal to 3 systems in the object, and the function of each system is characterized separately, and there is no feature of functional feedback, the function inheritance method is used to verify the accuracy of the sensor collected data;

[0014] S32. If there are more than 3 systems in the object, and the functions of each system are intricately interconnected and the functions of each system affect each other, a cross-validation method is used to verify the accuracy of the data collected by the sensor;

[0015] S33. If there is a many-to-one or one-to-many relationship in the object, and different systems have independent sensors collecting the characteristics that affect the function data for function transfer, a redundant verification method is used to verify the accuracy of the sensor collection data;

[0016] S4. Verify the accuracy of the sensor sampling data based on the mathematical model of the system in the object:

[0017] The input parameter x of the system 1 and x 2 They are respectively input into the mathematical model of the system to obtain the output parameter or feedback parameter Y. The expression of the mathematical model is:

[0018]

[0019] In the formula, k 1 , k 2 and k 3 are the parameters of the mathematical model;

[0020] The obtained output parameter or feedback parameter is subtracted from the value collected by the sensor. If the difference is within the range of the sensor collection error, the sensor collected data is accurate. If the difference exceeds the range of the sensor collection error, the sensor collected data is incorrect.

[0021] Preferably, in step S1, the different objects include units, systems and equipment platforms, the different requirements include monitoring, diagnosis and health management, and the screening conditions are based on the functional data and performance data required by different objects.

[0022] Preferably, in step S21, the simulation analysis includes circuit simulation analysis and stress simulation analysis.

[0023] Preferably, the accuracy of the sensor sampling data depends on the accuracy of the sensor and the sudden failure of the sensor.

[0024] Preferably, in step S3, the function inheritance method and the cross-validation method both verify that the data collected by the third sensor is incorrect by verifying that the data collected by two of the three sensors are accurate. The specific process is as follows:

[0025] If the data collected by the third sensor deviates from the data collected by the first sensor and the second sensor respectively, the accuracy of the third sensor is abnormal and the data collected by the third sensor is incorrect;

[0026] If the third sensor alarms due to its own fault, and the comparison results of the first sensor and the second sensor show that the third sensor is normal, then re-power on the third sensor and observe the fault;

[0027] If the third sensor does not give an alarm due to its own fault, and the comparison result between the first sensor and the second sensor shows that the third sensor is abnormal, then the third sensor is faulty.

[0028] Preferably, the step S3 and the step S4 respectively use different methods to verify the accuracy of the data collected by the sensor, which are in a parallel relationship.

[0029] Another aspect of the present invention further provides a verification system for the above-mentioned equipment platform sensor data acquisition accuracy verification method,

[0030] The system comprises a sensor type analysis module, a first sensor data verification module, a second sensor data verification module and a sensor data verification module, wherein the sensor type analysis module, the first sensor data verification module, the second sensor data verification module and the sensor data verification module are sequentially communicatively connected;

[0031] The sensor type analysis module is used to obtain the quantity, type and requirements of the required sensors based on the data in the database;

[0032] The first sensor data verification module is used to evaluate whether the position and quantity of sensors are reasonable;

[0033] The second sensor data verification module is used to verify the accuracy of sensor data collected by using multiple sensors at different levels in the object;

[0034] The sensor data verification module is used to verify the accuracy of the sensor sampling data according to the mathematical derivation model of the system in the object.

[0035] Preferably, the sensor data verification module uses multiple sensors at different levels in the object to verify the accuracy of the sensor data collected. The specific method is as follows: the input parameter x of the system 1 and x 2 They are respectively input into the mathematical model of the system to obtain output parameters or feedback parameters. The expression of the mathematical model is:

[0036]

[0037] In the formula, k 1 , k 2 and k 3 are the parameters of the mathematical model;

[0038] The obtained output parameter or feedback parameter is subtracted from the value collected by the sensor. If the difference is within the range of the sensor collection error, the sensor collected data is accurate. If the difference exceeds the range of the sensor collection error, the sensor collected data is incorrect.

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

[0040] The present invention obtains a clear mechanism of the sensor, that is, one that can be expressed by a mathematical model, through a function inheritance method, a cross-validation method, and a redundant validation method among different sensors, and verifies the accuracy of the sensor data by way of system modeling, thereby avoiding the impact caused by errors in sensor data or false alarms, and developing in the direction of believing what is collected, using what is collected, being more intelligent, and having stronger automatic control capabilities, ultimately improving work efficiency, shortening debugging time, and reducing the occurrence of misleading situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a flow chart of the method for verifying the accuracy of data collected by the equipment platform sensor of the present invention;

[0042] Figure 2 It is a flow chart for verifying the correctness of sensor collected data in the accuracy verification method of the equipment platform sensor collected data of the present invention;

[0043] Figure 3 It is a flow chart for verifying the accuracy of sensor collected data in the method for verifying the accuracy of sensor collected data of the equipment platform of the present invention;

[0044] Figure 4 It is a schematic diagram of the function inheritance method in the accuracy verification method of the equipment platform sensor data collected by the present invention;

[0045] Figure 5 It is a schematic diagram of the cross-validation method in the accuracy verification method of the data collected by the equipment platform sensor of the present invention;

[0046] Figure 6 It is a schematic diagram of a redundancy verification method in the accuracy verification method of data collected by the equipment platform sensor of the present invention;

[0047] Figure 7 It is a schematic diagram of a model of a method for verifying the accuracy of data collected by sensors on an equipment platform of the present invention;

[0048] Figure 8 It is a schematic block diagram of the structure of the verification system of the present invention. DETAILED DESCRIPTION

[0049] In order to fully describe the technical content, objectives and effects of the present invention, the following will be described in detail with reference to the accompanying drawings.

[0050] The accuracy verification method of the equipment platform sensor data collected by the present invention is implemented as follows: Figure 1 As shown, it includes the following steps:

[0051] S1. Determine the type of sensor.

[0052] S2. Verify the correctness of the data collected by the sensor.

[0053] S3. Use three sensors at different levels in the object to verify the accuracy of the sensor data collected.

[0054] Specifically, the accuracy of sensor sampling data depends on the accuracy of the sensor and the sudden failure of the sensor.

[0055] S4. Verify the accuracy of the sensor sampling data based on the mathematical derivation model of the system in the object.

[0056] Specifically, step S3 and step S4 respectively use different methods to verify the accuracy of the data collected by the sensor, and are in a parallel relationship.

[0057] Furthermore, in step S1, the method for determining the sensor type is as follows: screening from the data of different objects according to different requirements, and obtaining the number, type and requirements of the required sensors by combining the types. Specifically, different objects include units, systems and equipment platforms, and different requirements include monitoring, diagnosis and health management. The screening conditions are based on the functional data and performance data required by different objects.

[0058] Further, such as Figure 2 As shown, the method for verifying the correctness of the sensor collected data in step S2 includes:

[0059] S21. Through simulation analysis and experimental analysis, a certain number of sensors are placed at locations that can characterize the performance parameters of the object's function and performance degradation.

[0060] Preferably, the simulation analysis includes circuit simulation analysis and stress simulation analysis, with circuit simulation analysis being performed on electronic products and stress simulation analysis being performed on structural products.

[0061] S22. Under the monitoring, diagnosis and prediction functions of different objects, a closed-loop analysis is performed through the sensor test data and the state of the object response to evaluate whether the location and number of sensors are reasonable:

[0062] If the function of the object fails but the sensor data is within a reasonable range, the position and number of sensors need to be rearranged and step S21 is repeated;

[0063] If the object has performance degradation and needs to be downgraded, but the performance parameters of the sensor are within a reasonable range, the position and number of the sensors need to be rearranged, and step S21 is repeated;

[0064] If the test data of the sensor is consistent with the state of the object response, the position and quantity of the sensors are arranged reasonably, and step S3 is performed.

[0065] Further, such as Figure 3 As shown, the specific steps for verifying the accuracy of the sensor collected data in step S3 are as follows:

[0066] S31. If there are less than or equal to 3 systems in the object, and the functions of each system are characterized separately, the function transfer relationship of the devices in the system is simple, and there is no closed-loop transfer feature of functional feedback, then the function inheritance method is used to verify the accuracy of the data collected by the sensor.

[0067] S32. If there are more than three systems in the object and they cannot be represented by the function of one system alone, the functions of each system are intricately interconnected and the functions of each system affect each other, then the cross-validation method is used to verify the accuracy of the data collected by the sensor.

[0068] S33. If there are multiple systems corresponding to one system or one system corresponding to multiple systems in the object, and whether it is one-to-many or many-to-one, different systems have independent sensors collecting data for function transmission that affects the function data, then a redundant verification method is used to verify the accuracy of the sensor collection data.

[0069] Further, such as Figure 7 As shown, the specific steps for verifying the accuracy of the sensor collected data in step S4 are as follows:

[0070] The input parameter x of the system 1 and x 2 Input them into the mathematical model of the system respectively to obtain the output parameters or feedback parameters. The expression of the mathematical model is:

[0071]

[0072] In the formula, k 1 , k 2 and k 3 are the parameters of the mathematical model.

[0073] The obtained output parameter or feedback parameter is subtracted from the value collected by the sensor. If the difference is within the range of the sensor collection error, the sensor collected data is accurate. If the difference exceeds the range of the sensor collection error, the sensor collected data is incorrect.

[0074] In a preferred embodiment of the present invention, both the function inheritance method and the cross-validation method verify that the data collected by the third sensor is incorrect by verifying that the data collected by two of the three sensors is accurate. The specific process is as follows:

[0075] If the data collected by the third sensor deviates from the data collected by the first sensor and the second sensor respectively, the accuracy of the third sensor is abnormal and the data collected by the third sensor is incorrect;

[0076] If the third sensor alarms due to its own fault, and the comparison results of the first sensor and the second sensor show that the third sensor is normal, then re-power on the third sensor and observe the fault;

[0077] If the third sensor does not give an alarm due to its own fault, and the comparison result between the first sensor and the second sensor shows that the third sensor is abnormal, then the third sensor is faulty.

[0078] Specifically, two sensors of the same type are added near the measurement location. If any one of them has a large data deviation from the other two sensors, it proves that the sensor with the larger deviation is faulty. Although this type of method is effective within a certain range, it will increase the cost and complexity of the test system. Therefore, this method cannot be widely used to analyze and evaluate data accuracy.

[0079] Another aspect of the present invention also provides a verification system for the above-mentioned equipment platform sensor data acquisition accuracy verification method, such as Figure 8As shown, the system includes a sensor type analysis module 1, a first sensor data verification module 2, a second sensor data verification module 3 and a sensor data verification module 4, and the sensor type analysis module 1, the first sensor data verification module 2, the second sensor data verification module 3 and the sensor data verification module 4 are communicatively connected in sequence; the sensor type analysis module 1 is used to obtain the number, type and requirements of the required sensors according to the data in the database; the first sensor data verification module 2 is used to evaluate whether the location and number of sensors are reasonable; the second sensor data verification module 3 is used to verify the accuracy of the sensor collected data using multiple sensors at different levels in the object; the sensor data verification module 4 is used to verify the accuracy of the sensor sampling data according to the mathematical derivation model of the system in the object.

[0080] The following is a further description of a method for verifying the accuracy of data collected by a sensor on an equipment platform of the present invention in conjunction with an embodiment:

[0081] S1. Determine the type of sensor: Consider different objects such as units, systems and equipment platforms, screen the functional data and performance data required by different objects according to the requirements of monitoring, diagnosis and health management, select different data sets that meet the different levels and requirements of the objects, and determine the number, types and requirements of the required sensors by merging types.

[0082] S2. Verify the correctness of the data collected by the sensors. Specifically, correctness refers to whether the installation position and quantity of the sensors for the functional data and performance data collected by the unit, system, and equipment platform are correct.

[0083] S21. Based on past experience or through simulation analysis and experimental analysis, a certain number of sensors are placed at locations that can characterize the performance parameters of the object's function and performance degradation.

[0084] S22. Based on step S21, according to the monitoring, diagnosis and prediction functions of different objects, the location and quantity of sensors are evaluated to see whether they are reasonable through closed-loop analysis of the sensor test data and the actual state of the object:

[0085] If the function of the object fails but the sensor data is within a reasonable range, the position and quantity of the sensors are unreasonable and need to be readjusted. Unreasonable means that the test data cannot truly reflect the state of the object and cannot be used for fault diagnosis and health management. Repeat step S21.

[0086] If the object has performance degradation and needs to be downgraded, but the performance parameters of the sensor are within a reasonable range, the position and quantity of the sensor are unreasonable and need to be readjusted, and step S21 is repeated.

[0087] If the test data of the sensor is consistent with the state of the object response, the position and quantity of the sensor are reasonable, and step S3 is performed.

[0088] S3. When a sensor has a problem, the data collected must be wrong. Incorrect data can greatly mislead subsequent data applications, leading to wrong directions and thus wrong decisions. Therefore, after completing the steps of determining the sensor type and verifying the correctness of the data, it is necessary to verify the accuracy of the data collected by the sensor; use three sensors at different levels in the object to verify the accuracy of the sensor data collected. The accuracy of the sensor sampling data depends on the accuracy of the sensor, the selection problem does not meet the actual requirements and the sudden failure of the sensor, such as common failures such as non-working state and drift.

[0089] S31. If there are less than or equal to 3 systems in the object, and the functions of each system are characterized separately, the function transfer relationship of the devices in the system is simple, and there is no closed-loop transfer feature of functional feedback, then the function inheritance method is used to verify the accuracy of the data collected by the sensor.

[0090] In a preferred embodiment of the present invention, as shown in Table 1, the equipment platform function inherits the system function, and the parameters of the equipment platform function are acquired by the first sensor. The system function inherits the device function, and the parameters of the system function are acquired by the second sensor, and the parameters of the device function are acquired by the third sensor. Through the inheritance relationship and the logical relationship between the sensors, the inaccuracy of the data of each sensor can be judged, thereby verifying the accuracy of the other two sensors.

[0091] Table 1 Function inheritance relationship and logical relationship

[0092]

[0093]

[0094] The formula of the logical relationship can be further expressed in the form of a correlation matrix:

[0095] Table 2 Function inheritance expression

[0096]

[0097] In this implementation, it is assumed that two sensors will not fail at the same time. By comparing the sensors, it is possible to determine which sensor among the first sensor, the second sensor, and the third sensor fails. Combined with the sensor's own fault report, considering that the sensor sometimes falsely reports a fault, the relationship between the equipment function, the system function, and the device function is as follows: Figure 4 shown.

[0098] The equipment platform function is not only related to the system function, but also to the functions of multiple systems. At the same time, the system function may not only be related to the device function. In the subsequent equipment platform design process, it is necessary to sort out such associations and form a mapping table between functions to provide data support for the accuracy evaluation of sensor data.

[0099] If the data collected by the third sensor deviates from the data collected by the first sensor and the second sensor respectively, the accuracy of the third sensor is abnormal, the data collected by the third sensor is inaccurate, and cannot be used as input for subsequent data applications.

[0100] If the third sensor alarms due to its own fault, and the comparison result of the first sensor and the second sensor shows that the third sensor is normal, the fault reported by the third sensor may be a false alarm. Repower the third sensor and observe whether the fault report is eliminated.

[0101] If the third sensor does not alarm due to its own fault, and the comparison result of the first sensor and the second sensor shows that the third sensor is abnormal, the third sensor is faulty, indicating that the data of the third sensor is inaccurate and cannot be used as input for subsequent data.

[0102] S32. If there are more than three systems in the object and they cannot be represented by the function of one system alone, the functions of each system are intricately interconnected and the functions of each system affect each other, then the cross-validation method is used to verify the accuracy of the data collected by the sensor.

[0103] In a preferred embodiment of the present invention, the cross-validation method has cross-relationships between sensor data in different systems and different devices, and the cross-relationships are relationships such as transformation, weak correlation, and non-mathematical model construction. If the function of a certain system is normal and has a cross-relationship with the function of another system, it can be understood that when the function of the first system fails, the function of the second system also fails, and when the function of the first system fails, the function of the third system also fails. Through the influence and discrimination between the transmission of multiple functions, it can be analyzed whether the functions of the first system, the second system, and the third system are similar to those of the first system, the second system, and the third system are invalid. The cross-relationships and logical relationships are shown in Table 3.

[0104] Table 3 System function cross-relationship

[0105]

[0106]

[0107] The formula of the logical relationship can be further expressed in the form of a correlation matrix:

[0108] Table 4 System function cross expression

[0109]

[0110] The functional cross-relationships between systems are generally complex. To clearly describe the logical relationships between the functional transfer and functional cross-relationships between systems, Figure 5 As shown, the function of the first system will affect whether the function of the second system is normal, and will also affect whether the function of the third system is normal. All functions can be measured by corresponding sensors. When any two functions conflict with the implementation information of another function, it can be concluded that the conflicting sensor data is unreliable and inaccurate.

[0111] S33. If there are multiple systems corresponding to one system or one system corresponding to multiple systems in the object, and whether it is one-to-many or many-to-one, different systems have independent sensors collecting data for function transmission that affects the function data, then a redundant verification method is used to verify the accuracy of the sensor collection data.

[0112] In a preferred embodiment of the present invention, the redundancy verification method uses the redundant relationship of the sensor to infer whether the data of the redundant sensor is accurate and whether a fault occurs that causes abnormal data collection. This embodiment takes the input and output voltage as an example, and the sensor function redundancy relationship and logical relationship are shown in Table 5.

[0113] Table 5 Functional redundancy method verification data table

[0114]

[0115]

[0116] The formula of the logical relationship can be further expressed in the form of a correlation matrix:

[0117] Table 6 Functional redundancy expressions

[0118]

[0119] The first input voltage test of the converter is obtained by testing the first voltage sensor, and the second, third and fourth input voltage tests of the converter are obtained by the second, third and fourth voltage sensors respectively. The data accuracy of the sensors can be verified by the second, third and fourth input voltages and the first input voltage. Since the tests of the second, third and fourth input voltages are redundant, the logical relationship is shown in Table 3, and the specific redundant schematic diagram is shown in Figure 6 shown.

[0120] S4. Verify the accuracy of the sensor sampling data based on the mathematical derivation model of the system in the object, and characterize and observe the data to be measured through the mathematical derivation model.

[0121] The input parameter x of the system1 and x 2 Input them into the mathematical model of the system respectively to obtain the output parameters or feedback parameters. The expression of the mathematical model is:

[0122]

[0123] In the formula, k 1 , k 2 and k 3 are the parameters of the mathematical model.

[0124] The obtained output parameter or feedback parameter is subtracted from the value collected by the sensor. If the difference is within the range of the sensor collection error, the sensor collected data is accurate. If the difference exceeds the range of the sensor collection error, the sensor collected data is incorrect.

[0125] The embodiments described above are only descriptions of the preferred implementation modes of the present invention, and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A method for verifying the accuracy of data collected by equipment platform sensors, It is characterized in that The following steps are involved: S1. Determine the type of sensor: filter the data of different objects of units, systems and equipment platforms, and obtain the number, type and requirements of the required sensors by combining the types; S2. Verify the correctness of the data collected by the sensor, which specifically includes the following sub-steps: S21. Through simulation analysis and experimental analysis, a certain number of sensors are placed at positions that can characterize performance parameters of object function and performance degradation; S22. Under the monitoring, diagnosis and prediction functions of different objects, a closed-loop analysis is performed based on the sensor test data and the state of the object response to evaluate whether the location and number of sensors are reasonable: If the data collected by the sensor is within a reasonable range but the object fails to function or the object has performance degradation and needs to be downgraded, the position and number of sensors need to be rearranged, and the process returns to and repeats step S21; If the sensor's test data is consistent with the state of the object's response, the sensor's position and quantity are reasonably arranged, and step S3 is performed; S3. Verify the accuracy of sensor data collected using multiple sensors at different levels in the object, including the following sub-steps: S31. If there are less than or equal to 3 systems in the object, and the function of each system is characterized separately, and there is no feature of functional feedback, the function inheritance method is used to verify the accuracy of the sensor collected data; S32. If there are more than 3 systems in the object, and the functions of each system are intricately interconnected and the functions of each system affect each other, a cross-validation method is used to verify the accuracy of the data collected by the sensor; S33. If there is a many-to-one or one-to-many relationship in the object, and different systems have independent sensors collecting the characteristics that affect the function data for function transfer, a redundant verification method is used to verify the accuracy of the sensor collection data; S4. Verify the accuracy of the sensor sampling data based on the mathematical model of the system in the object: The input parameter x of the system 1 and x 2 They are respectively input into the mathematical model of the system to obtain the output parameter or feedback parameter Y. The expression of the mathematical model is: ； In the formula, k 1 , k 2 and k 3 are the parameters of the mathematical model; The obtained output parameter or feedback parameter is subtracted from the value collected by the sensor. If the difference is within the range of the sensor collection error, the sensor collected data is accurate. If the difference exceeds the range of the sensor collection error, the sensor collected data is incorrect.

2. The method for verifying the accuracy of data collected by the equipment platform sensor according to claim 1, It is characterized in that In step S1, the requirements include monitoring, diagnosis and health management, and the screening conditions are determined according to the functional data and performance data required by different objects.

3. The method for verifying the accuracy of data collected by the equipment platform sensor according to claim 1, It is characterized in that In step S21, the simulation analysis includes circuit simulation analysis and stress simulation analysis.

4. The method for verifying the accuracy of data collected by the equipment platform sensor according to claim 1, It is characterized in that The accuracy of the sensor sampling data depends on the accuracy of the sensor and the sudden failure of the sensor.

5. The method for verifying the accuracy of data collected by the equipment platform sensor according to claim 1 or 4, It is characterized in that In step S3, both the function inheritance method and the cross-validation method verify that the data collected by the third sensor is incorrect by verifying that the data collected by two of the three sensors are accurate. The specific process is as follows: If the data collected by the third sensor deviates from the data collected by the first sensor and the second sensor respectively, the accuracy of the third sensor is abnormal and the data collected by the third sensor is incorrect; If the third sensor alarms due to its own fault, and the comparison results of the first sensor and the second sensor show that the third sensor is normal, then re-power on the third sensor and observe the fault; If the third sensor does not give an alarm due to its own fault, and the comparison result between the first sensor and the second sensor shows that the third sensor is abnormal, then the third sensor is faulty.

6. The method for verifying the accuracy of data collected by the equipment platform sensor according to claim 1, It is characterized in that The step S3 and the step S4 respectively use different methods to verify the accuracy of the data collected by the sensor, and are in a parallel relationship.

7. A verification system for the accuracy verification method of data collected by the equipment platform sensor according to claim 1, It is characterized in that It includes the following modules: a sensor type analysis module, a first sensor data verification module, a second sensor data verification module and a sensor data verification module, wherein the sensor type analysis module, the first sensor data verification module, the second sensor data verification module and the sensor data verification module are sequentially communicatively connected; The sensor type analysis module is used to obtain the quantity, type and requirements of the required sensors based on the data in the database; The first sensor data verification module is used to evaluate whether the position and quantity of sensors are reasonable; The second sensor data verification module is used to verify the accuracy of sensor data collected by using multiple sensors at different levels in the object; The sensor data verification module is used to verify the accuracy of the sensor sampling data according to the mathematical model of the system in the object.

8. The verification system according to claim 7, It is characterized in that The specific method of the sensor data verification module using multiple sensors at different levels in the object to verify the accuracy of the sensor data is as follows: 1 and x 2 They are respectively input into the mathematical model of the system to obtain output parameters or feedback parameters. The expression of the mathematical model is: ； In the formula, k 1 , k 2 and k 3 are the parameters of the mathematical model; The obtained output parameter or feedback parameter is subtracted from the value collected by the sensor. If the difference is within the range of the sensor collection error, the sensor collected data is accurate. If the difference exceeds the range of the sensor collection error, the sensor collected data is incorrect.

Images