A method for establishing a remote module life prediction model and a life prediction method
By acquiring and analyzing the characteristic parameters of the remote module, judging its operating status and establishing a multivariate linear regression model, the shortcomings of the life expectancy of the remote module in the existing technology are solved, and effective prediction of the life expectancy of the remote module of the DC optical measurement system is achieved. , supports operation and maintenance management.
Patent Information
- Application Number
- CN202210317421.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-03-29
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2042-03-29
AI Technical Summary
The prior art lacks research on the life prediction model of the remote module of the DC optical measurement system, especially the lack of methods and status data for predicting the remaining life of the remote module, which has affected the effectiveness of the operation detection of the converter station.
By obtaining the characteristic parameters and output signals of the remote module, judging the operating status, determining the aging and failure thresholds, calculating the average annual rate of change, and establishing a multivariate linear regression model to predict the remaining service life of the remote module.
It realizes the prediction of the remaining service life of the remote module of the DC optical measurement system, supports daily maintenance and maintenance personnel, and solves the technical shortcomings in the management of the full life cycle of the remote module.
Smart Images

Figure CN114970311B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to a method for establishing a remote module life prediction model and a life prediction method, belonging to the technical field of state analysis. Background Art
[0002] The remote module in the DC optical measurement system is the core equipment for the operation detection of the high-voltage DC converter station. At present, the research on remote modules at home and abroad only stays at the analysis of the operation failure of the remote modules, and lacks relevant research on the prediction model of the remote module life, especially the remaining life. Among them, not only is there a lack of methods for life prediction and evaluation, but also a lack of status data of the remote module before the failure. However, many remote modules in the converter station have aged to varying degrees, which seriously affects the effectiveness of the detection of the operating status of the converter station. To achieve real-time prediction of the remaining life of the remote module, many problems need to be solved. This is not only because of the lack of status data of the remote module before the failure, but also because of the lack of the relationship between the remaining service life of the remote module and the status data of the remote module. At present, there is a lack of a method for predicting the remaining service life of the remote module. Summary of the invention
[0003] The purpose of the present invention is to overcome the deficiencies in the prior art and provide a method for establishing a remote module life prediction model and a life prediction method, which can predict the remaining service life of the remote module of a DC optical measurement system. To achieve the above purpose, the present invention is implemented by adopting the following technical solutions:
[0004] In a first aspect, the present invention provides a method for establishing a remote module life prediction model, comprising:
[0005] Obtain characteristic parameters and output signals of each sample remote module;
[0006] Based on the output signal of each sample remote module, the operating state of each sample remote module is judged, and according to the characteristic parameter value of the sample remote module in normal operating state, the aging threshold value and the fault threshold value of each characteristic parameter of the remote module are determined;
[0007] Calculate the average annual change rate of each characteristic parameter of the remote module;
[0008] Calculate the remaining service life of each sample remote module according to the determined aging threshold, failure threshold and calculated annual change rate of each characteristic parameter of the remote module;
[0009] Based on the remaining service life of each sample remote module, a remote module remaining service life prediction model is established.
[0010] In combination with the first aspect, further, the characteristic parameters of each sample remote module include: a rising edge slope, a falling edge slope, a pulse width, a low state level and a low level variance of a pulse signal of the remote module.
[0011] In combination with the first aspect, further, when acquiring the characteristic parameters and output signals of each sample remote module, the service life of each sample remote module is different.
[0012] In combination with the first aspect, further, determining the operating status of each sample remote module includes:
[0013] Initialize a sample set of output signals of each sample remote module;
[0014] Calculate the local outlier factor of each sample point in the sample set;
[0015] If the local outlier factor of a sample point is greater than 1, the sample point is an outlier, and the operating status of the sample remote module corresponding to the sample point is outlier;
[0016] If the local outlier factor of a sample point is less than or equal to 1, the sample point is a normal point, and the operation status of the sample remote module corresponding to the sample point is normal.
[0017] In combination with the first aspect, further, determining an aging threshold and a fault threshold of each characteristic parameter of the remote module includes:
[0018] Calculate the mean value of each characteristic parameter of the sample remote module in normal operation state;
[0019] A half value of the mean value of each characteristic parameter of the remote module is calculated as an aging threshold value of each characteristic parameter of the remote module;
[0020] One third of the aging threshold of each characteristic parameter of the remote module is used as the fault threshold of each characteristic parameter of the remote module.
[0021] In combination with the first aspect, further, the remaining service life of each sample remote module is calculated by the following formula:
[0022]
[0023] In formula (1), σ is the remaining service life of the sample remote module currently calculated, and the remaining service life σ of the sample remote module corresponding to each characteristic parameter is taken as x The minimum value of; x is the index of the 5 characteristic parameters, Δ x is the difference between the characteristic parameters of the currently calculated sample remote module and its fault threshold; δ x It is the average annual change rate of each characteristic parameter of the sample remote module currently calculated.
[0024] In combination with the first aspect, preferably, the average annual change rate of each characteristic parameter of the remote module is obtained according to the characteristic parameter value of each module and the service life value of each module.
[0025] In combination with the first aspect, further, establishing the remote module remaining life prediction model includes:
[0026] The remaining service life of each sample remote module is used as the sample training set of the prediction model, each characteristic parameter is used as the independent variable, and the remaining service life of the sample remote module is used as the dependent variable. The multiple linear regression algorithm is used to establish a multiple linear regression model of the remaining service life of the remote module:
[0027]
[0028] In formula (2), arrive They represent the values of the five characteristic parameters of the i-th group of data, β0 is the intercept of the multiple linear regression model, β1, β2, β3, β4, and β5 are the regression coefficients of the multiple linear regression model, Output the prediction results for group i;
[0029] Based on the least squares method, the true value of the remaining life of the remote module of the ith sample is determined to be y i , by making Minimum, let get:
[0030]
[0031] In formula (3), X b There are q groups of sample training sets, expressed in matrix form:
[0032]
[0033] In formula (4), X b T For X b The transposed matrix of ; and the true value matrix of the remaining life of the remote modules of a total of q groups of samples is
[0034] Y=(y 1 ,y 2 ,...,y q ) T (5)
[0035] Calculated by equations (3), (4) and (5):
[0036] β=(β0,β1,β2,...,β5) T (6)
[0037] The remaining life prediction model of the remote module is obtained by equations (2) and (6).
[0038] In a second aspect, the present invention provides a life prediction method, comprising:
[0039] Get the characteristic parameter value of the remote module to be tested,
[0040] Input the acquired characteristic parameter value into a pre-established remote module remaining life prediction model to obtain the predicted life of the remote module to be tested;
[0041] Wherein, the pre-established remote module remaining life prediction model is generated using the method described in the first aspect.
[0042] The third invention provides a system for establishing a remote module life prediction model, comprising:
[0043] The first acquisition module is used to obtain the characteristic parameter value and output signal of each sample remote module;
[0044] Threshold determination module: used to judge the operating status of each sample remote module based on the output signal of each sample remote module, and determine the aging threshold and fault threshold of each characteristic parameter of the remote module according to the characteristic parameter value of the sample remote module in normal operating status;
[0045] The first calculation module is used to calculate the average annual change rate of each characteristic parameter of the remote module;
[0046] The second calculation module is used to calculate the remaining service life of each sample remote module according to the determined aging threshold, fault threshold and calculated annual change rate of each characteristic parameter of the remote module;
[0047] Model building module: used to build a remote module remaining life prediction model based on the remaining service life of each sample remote module.
[0048] The third invention provides a life prediction system, comprising:
[0049] The second acquisition module is used to obtain the characteristic parameter value of the remote module to be tested.
[0050] Output module: used to input the acquired characteristic parameter value into a pre-established remote module remaining life prediction model to obtain the predicted life of the remote module to be tested; wherein the pre-established remote module remaining life prediction model is generated using the method described in the first aspect.
[0051] Compared with the prior art, the method for establishing a remote module life prediction model and the life prediction method provided by the embodiment of the present invention have the following beneficial effects:
[0052] The present invention provides a method for establishing a remote module life prediction model, including: obtaining characteristic parameters and output signals of each sample remote module; judging the operating state of each sample remote module based on the output signal of each sample remote module, and determining the aging threshold and fault threshold of each characteristic parameter of the remote module according to the characteristic parameter value of the sample remote module in normal operating state; calculating the average annual change rate of each characteristic parameter of the remote module; calculating the remaining service life of each sample remote module according to the determined aging threshold, fault threshold and calculated annual change rate of each characteristic parameter of the remote module; and establishing a remote module remaining service life prediction model based on the remaining service life of each sample remote module. The remote module life prediction model provided by the present invention can predict the remaining service life of the remote module of the DC optical measurement system, facilitates the daily inspection and maintenance of the remote module by the operation and maintenance personnel, and can solve the problem of no technical support for the full life cycle management of the remote module. BRIEF DESCRIPTION OF THE DRAWINGS
[0053] Figure 1 is a flow chart of a method for establishing a remote module life prediction model provided in Example 1 of the present invention;
[0054] Figure 2 It is a result diagram of judging the operating status of each sample remote module in a method for establishing a remote module life prediction model provided in Example 1 of the present invention; DETAILED DESCRIPTION
[0055] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present invention.
[0056] Embodiment 1:
[0057] This embodiment provides a specific application scenario of a method for establishing a remote module life prediction model. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and are not intended to limit the protection scope of the present invention.
[0058] like Figure 1 As shown, a method for establishing a remote module life prediction model includes:
[0059] Obtain characteristic parameter values and output signals of each sample remote module;
[0060] Based on the output signal of each sample remote module, the operating state of each sample remote module is judged, and according to the characteristic parameter value of the sample remote module in normal operating state, the aging threshold value and the fault threshold value of each characteristic parameter of the remote module are determined;
[0061] Calculate the average annual change rate of each characteristic parameter of the remote module;
[0062] Calculate the remaining service life of each sample remote module according to the determined aging threshold, failure threshold and calculated annual change rate of each characteristic parameter of the remote module;
[0063] Based on the remaining service life of each sample remote module, a remote module remaining service life prediction model is established.
[0064] The specific steps include:
[0065] Step 1: Obtain the characteristic parameter values and output signals of each sample remote module.
[0066] Three sample remote modules with different remaining lifespans are selected and numbered X1, X2 and X3. The operating years of the three sample remote modules are shown in Table 1:
[0067] Table 1: Operating years of three sample remote modules
[0068] Module Number X1 X2 X3 Years of operation 0.10 years 8.03 years 11.14 years
[0069] There are five characteristic parameters of the sample remote module, including: rising edge slope, falling edge slope, pulse width, low state level and low level variance of the remote module pulse signal. The device provided by patent 201821642816.4 is used to obtain the characteristic parameters of three sample remote modules.
[0070] Step 2: Based on the output signal of each sample remote module, determine the operating state of each sample remote module; According to the characteristic parameter values of the sample remote modules in normal operating state, determine the aging threshold and fault threshold of each characteristic parameter of the remote module;
[0071] Step 2.1: Based on the output signal of each sample remote module, determine the operating status of each sample remote module
[0072] Step 2.1.1: Initialize the sample set of the output signal of each sample remote module.
[0073] Step 2.1.2: Calculate the local outlier factor of each sample point in the sample set;
[0074] Step 2.1.3: If the local outlier factor of the sample point is greater than 1, the sample point is an outlier, and the operating status of the sample remote module corresponding to the sample point is outlier;
[0075] If the local outlier factor of a sample point is less than or equal to 1, the sample point is a normal point, and the operation status of the sample remote module corresponding to the sample point is normal.
[0076] Steps 2.1.1-2.1.3 were used to test 30 remote modules running on site. The test results are shown in Figure 2. Figure 2 It can be seen that there are 25 normal distal modules and 5 outlier distal modules.
[0077] Step 2.2: According to the characteristic parameter values of the sample remote modules in normal operation, the aging threshold and the fault threshold of each characteristic parameter of the remote modules are determined.
[0078] Step 2.2.1: Calculate the mean of each characteristic parameter of the sample remote module in normal operation.
[0079] Step 2.2.2: half of the calculated mean of each characteristic parameter of the remote module is used as the aging threshold of each characteristic parameter of the remote module. One third of the aging threshold of each characteristic parameter of the remote module is used as the fault threshold of each characteristic parameter of the remote module.
[0080] Half of the mean value of each characteristic parameter of 25 normal remote modules is taken as the aging threshold of each characteristic parameter of the remote module, and one third of the aging threshold of each characteristic parameter of the remote module is taken as the fault threshold of each characteristic parameter of the remote module. The aging threshold and fault threshold results of each characteristic parameter of the remote module are shown in Table 2.
[0081] Table 2: Results of aging threshold and fault threshold of each characteristic parameter of remote module
[0082] Characteristic parameters Aging Threshold Fault Threshold Rising slope (v / us) 7.27 2.42 Falling slope (v / us) 2.6 0.87 Pulse width (ns) 305 265 Low state level (mv) -1.4 -4.2 <![CDATA[Low voltage square difference (mv 2 )]]> 0.054 0.161
[0083] Step 3: Calculate the average annual change rate of each characteristic parameter of the remote module.
[0084] According to the values of the characteristic parameters of each sample remote module and the service life value of each sample remote module, the average annual change rate of each characteristic parameter of the remote module is calculated, and the results are shown in Table 3.
[0085] Table 3: Average annual change rate of each characteristic parameter of the remote module
[0086]
[0087] Step 4: Calculate the remaining service life of each sample remote module based on the determined aging threshold, fault threshold and calculated annual change rate of each characteristic parameter of the remote module.
[0088] Calculate using the following formula:
[0089]
[0090] In formula (1), σ is the remaining service life of the sample remote module currently calculated, and the remaining service life σ of the sample remote module corresponding to each characteristic parameter is taken as x The minimum value of; x is the index of the 5 characteristic parameters, Δ xis the difference between the characteristic parameters of the currently calculated sample remote module and its fault threshold; δ x It is the average annual change rate of each characteristic parameter of the sample remote module currently calculated.
[0091] Step 5: Based on the remaining service life of each sample remote module, a remote module remaining service life prediction model is established.
[0092] Step 5.1: Use the remaining service life of each sample remote module as the sample training set of the prediction model, use each characteristic parameter as the independent variable, and the remaining service life of the sample remote module as the dependent variable, and use the multiple linear regression algorithm to establish a multiple linear regression model of the remaining service life of the remote module:
[0093]
[0094] In formula (2), arrive They represent the values of the five characteristic parameters of the i-th group of data, β0 is the intercept of the multiple linear regression model, β1, β2, β3, β4, and β5 are the regression coefficients of the multiple linear regression model, Output the prediction result for group i.
[0095] Step 5.2: Based on the least squares method, determine the true value of the remaining life of the remote module of the ith sample as y i , by making Minimum, let get:
[0096]
[0097] In formula (3), X b There are q groups of sample training sets, expressed in matrix form:
[0098]
[0099] In formula (4), X b T For X b The transposed matrix of ; and the true value matrix of the remaining life of the remote modules of a total of q groups of samples is
[0100] Y=(y 1 ,y 2 ,...,y q ) T (5)
[0101] Calculated by equations (3), (4) and (5):
[0102] β=(β0,β1,β2,...,β5) T(6)
[0103] The remaining life prediction model of the remote module is obtained by equations (2) and (6).
[0104] Step 5.3: In order to obtain samples of remote modules with different remaining lifespans, high and low temperature cycle accelerated aging tests are performed on the sample remote modules X1-X3 for different periods of time, and 20 sets of data are obtained as sample training sets. The training set data is shown in Table 4.
[0105] Table 4: Training set data
[0106]
[0107]
[0108] The actual remaining life of the sample remote modules X1-X3 is shown in Table 4, and the matrix Y is expressed as:
[0109]
[0110] The regression coefficients of the remote module remaining life prediction model are: β0 = -39.47935923, β1 = 0.49558476, β2 = -1.76224013, β3 = 0.23633589, β4 = 5.39623404, β5 = 0.04145883.
[0111] Then the remaining life prediction model of the remote module is:
[0112]
[0113] In summary, the remote module life prediction model provided by the present invention collects the characteristic parameters of the remote module through the remote module characteristic parameter acquisition system, diagnoses the operating status of the remote module, and determines the operating status threshold of the remote module; based on the multivariate linear regression algorithm, a training data set is used to build a prediction model for the remaining life of the remote module to realize the prediction of the remaining life of the remote module.
[0114] Embodiment 2:
[0115] This embodiment provides a life prediction method, including:
[0116] Get the characteristic parameter value of the remote module to be tested,
[0117] Input the acquired characteristic parameter value into a pre-established remote module remaining life prediction model to obtain the predicted life of the remote module to be tested;
[0118] The pre-established remote module remaining life prediction model is generated using the method described in Example 1.
[0119] Embodiment 3:
[0120] This embodiment provides a system for establishing a remote module life prediction model, including:
[0121] The first acquisition module is used to obtain the characteristic parameter value and output signal of each sample remote module;
[0122] Threshold determination module: used to judge the operating status of each sample remote module based on the output signal of each sample remote module, and determine the aging threshold and fault threshold of each characteristic parameter of the remote module according to the characteristic parameter value of the sample remote module in normal operating status;
[0123] The first calculation module is used to calculate the average annual change rate of each characteristic parameter of the remote module;
[0124] The second calculation module is used to calculate the remaining service life of each sample remote module according to the determined aging threshold, fault threshold and calculated annual change rate of each characteristic parameter of the remote module;
[0125] Model building module: used to build a remote module remaining life prediction model based on the remaining service life of each sample remote module.
[0126] Embodiment 4:
[0127] This embodiment provides a life prediction system, including:
[0128] The second acquisition module is used to obtain the characteristic parameter value of the remote module to be tested.
[0129] Output module: used to input the acquired characteristic parameter value into a pre-established remote module remaining life prediction model to obtain the predicted life of the remote module to be tested; wherein the pre-established remote module remaining life prediction model is generated using the method described in Example 1.
[0130] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0131] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0132] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0133] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.
[0134] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.
Claims
1. A method for establishing a remote module life prediction model, characterized in that: include: Obtain characteristic parameters and output signals of each sample remote module; Based on the output signal of each sample remote module, the operating state of each sample remote module is judged, and according to the characteristic parameter value of the sample remote module in normal operating state, the aging threshold and the fault threshold of each characteristic parameter of the remote module are determined; wherein, the aging threshold and the fault threshold of each characteristic parameter of the remote module are determined, including: Calculate the mean value of each characteristic parameter of the sample remote module in normal operation state; A half value of the mean value of each characteristic parameter of the remote module is calculated as an aging threshold value of each characteristic parameter of the remote module; One third of the aging threshold of each characteristic parameter of the remote module is used as the fault threshold of each characteristic parameter of the remote module; Determine the average annual rate of change of each characteristic parameter of the remote module; According to the determined aging threshold, fault threshold and calculated annual change rate of each characteristic parameter of the remote module, the remaining service life of each sample remote module is calculated; wherein the remaining service life of each sample remote module is calculated by the following formula: In formula (1), σ is the remaining service life of the currently calculated sample remote module, and the remaining service life σ of the currently calculated sample remote module corresponding to each characteristic parameter is taken as x The minimum value of; x is the index of the 5 characteristic parameters, Δ x is the difference between the currently calculated sample remote module characteristic parameter and the fault threshold; δ x is the average annual change rate of each characteristic parameter of the sample remote module currently calculated; Based on the remaining service life of each sample remote module, a remote module remaining service life prediction model is established; wherein the establishing of the remote module remaining service life prediction model includes: The remaining service life of each sample remote module is used as the sample training set of the prediction model, each characteristic parameter is used as the independent variable, and the remaining service life of the sample remote module is used as the dependent variable. The multiple linear regression algorithm is used to establish a multiple linear regression model of the remaining service life of the remote module: In formula (2), arrive They represent the values of the five characteristic parameters of the i-th group of data, β0 is the intercept of the multiple linear regression model, β1, β2, β3, β4, and β5 are the regression coefficients of the multiple linear regression model, Output the prediction result for group i; Based on the least squares method, the true value of the remaining life of the remote module of the ith sample is determined to be y i , by making Minimum, let get: In formula (3), X b There are q groups of sample training sets, expressed in matrix form: In formula (4), X b T For X b The transposed matrix of ; and the true value matrix of the remaining life of the remote modules of a total of q groups of samples is And=(and 1 ,and 2 ,...,and q ) T (5) Calculated by equations (3), (4) and (5): β=(β0,β1,β2,...,β5) T (6) The remaining life prediction model of the remote module is obtained by equations (2) and (6).
2. The method for establishing a remote module life prediction model according to claim 1, characterized in that: The characteristic parameters of each sample remote module include: rising edge slope, falling edge slope, pulse width, low state level and low level variance of the remote module pulse signal.
3. The method for establishing a remote module life prediction model according to claim 1, characterized in that: When obtaining the characteristic parameter value and output signal of each sample remote module, the service life of each sample remote module is different.
4. The method for establishing a remote module life prediction model according to claim 1, characterized in that: The step of determining the operating status of each sample remote module includes: Initialize a sample set of output signals of each sample remote module; Calculate the local outlier factor of each sample point in the sample set; If the local outlier factor of a sample point is greater than 1, the sample point is an outlier, and the operating status of the sample remote module corresponding to the sample point is outlier; If the local outlier factor of a sample point is less than or equal to 1, the sample point is a normal point, and the operation status of the sample remote module corresponding to the sample point is normal.
5. A life prediction method, characterized in that: include: Get the characteristic parameter value of the remote module to be tested, Input the acquired characteristic parameter value into a pre-established remote module remaining life prediction model to obtain the predicted life of the remote module to be tested; Wherein, the pre-established remote module remaining life prediction model is generated by the method described in any one of claims 1 to 4.
6. A system for establishing a remote module life prediction model based on the method for establishing a remote module life prediction model according to claim 1, characterized in that: include: The first acquisition module is used to obtain the characteristic parameter value and output signal of each sample remote module; Threshold determination module: used to judge the operating status of each sample remote module based on the output signal of each sample remote module, and determine the aging threshold and fault threshold of each characteristic parameter of the remote module according to the characteristic parameter value of the sample remote module in normal operating status; The first calculation module is used to calculate the average annual change rate of each characteristic parameter of the remote module; The second calculation module is used to calculate the remaining service life of each sample remote module according to the aging threshold, the fault threshold and the calculated annual change rate of each characteristic parameter of the remote module; Model building module: used to build a remote module remaining life prediction model based on the remaining service life of each sample remote module.
7. A life prediction system, characterized in that: include: The second acquisition module is used to obtain the characteristic parameter value of the remote module to be tested. Output module: used to input the acquired characteristic parameter values into a pre-established remote module remaining life prediction model to obtain the predicted life of the remote module to be tested; wherein the pre-established remote module remaining life prediction model is generated using the method described in any one of claims 1 to 4.
