Device and method for testing information monitoring system

Abstract

The invention discloses a device and a method for testing an information monitoring system. The method comprises the following steps of: initializing each functional module of the information monitoring system; acquiring a test index Ai of each functional module; calculating a function risk value Ri of each function module based on the test index Ai; performing priority ranking based on the function risk value Ri, and identifying a function module which needs to be tested preferentially; dynamically adjusting the test frequency based on the function risk value Ri; executing a built-in test, monitoring the state of each functional module in real time, and identifying a potential fault; and generating a test report. The method has the functions of dynamic threshold adjustment, multilevel fault detection and the like, and has the advantages of improving the accuracy of fault detection, reducing the maintenance cost, enhancing the expandability of the system and the like.

Description

Technical Field

[0001] The invention belongs to the field of computer system engineering, and in particular relates to a testing device and method for an information monitoring system. Background Art

[0002] In modern industrial and engineering systems, the reliability and safety of equipment are of vital importance. With the rapid development of technology, complex mechanical and electronic systems are widely used in various fields, such as aerospace, automobile manufacturing, energy production, etc. These systems are usually composed of multiple modules, and each module may fail during operation, resulting in performance degradation of the equipment and even safety accidents. Therefore, timely and accurate detection and identification of faults and preventive maintenance have become important tasks in modern equipment management.

[0003] Traditional fault detection methods usually rely on manual inspection and regular maintenance, which is not only inefficient but also difficult to deal with multiple potential faults in complex systems. In addition, the results of manual inspection are often affected by the operator's experience and subjective judgment, which can easily lead to missed detection or misjudgment. Therefore, a more efficient, objective and automated fault detection method is urgently needed.

[0004] As a common fault detection method, the threshold detection algorithm has been widely used in various industrial systems. The algorithm compares the real-time monitoring data by setting predetermined upper and lower thresholds. Once the monitoring value exceeds the threshold range, the system will issue a fault alarm. The setting of the threshold is usually based on the historical operating data of the equipment, and the normal operating range is determined by statistical analysis. This method is simple and intuitive, easy to implement, and therefore has been widely recognized in practical applications. However, the threshold detection algorithm also has certain limitations. First, the setting of the threshold needs to be personalized for each specific module, and its applicability is poor. Second, threshold detection can only identify obvious faults, and some potential and progressive faults may not be discovered in time. In addition, relying solely on threshold detection may lead to a certain false alarm rate, thereby increasing maintenance costs and workload.

[0005] In order to solve these technical problems, researchers began to explore comprehensive fault detection solutions that combine multiple detection methods. For example, threshold detection is combined with model-based fault detection, and the physical model and operating data of the system are used for comprehensive analysis. This method can improve the accuracy of fault detection and reduce the false alarm rate. At the same time, using machine learning and artificial intelligence technology to analyze and learn historical data, automatically adjust thresholds and detection strategies, and achieve more intelligent fault detection. Summary of the invention

[0006] In view of the defects existing in the above-mentioned prior art, the present invention provides a testing method of an information monitoring system, comprising the following steps:

[0007] Step S101, initializing each functional module of the information monitoring system;

[0008] Step S103: Obtain the test index A of each functional module i ;

[0009] Step S105: Based on the test indicator A i Calculate the functional risk value R of each functional module i ;

[0010] Step S107: Based on the functional risk value R i Perform prioritization and identify functional modules that need to be tested first;

[0011] Step S109: Based on the functional risk value R i , dynamically adjust the test frequency;

[0012] Step S1011, perform in-machine testing, monitor the status of each functional module in real time, and identify potential faults;

[0013] Step S1013: Generate a test report.

[0014] Among them, the test index A i Defined as:

[0015] A i =f(D i )+g(F impact ), where D i is the fault detection value set of the i-th module;

[0016] D ij is the fault detection value of the i-th module in the j-th detection: is the variance of the fault detection value, ∈ is a very small positive number to prevent the denominator from being zero, α and β are adjustment parameters, is the fault impact function of the ith module, F impact is the fault impact parameter of the i-th module, τ is the time constant of the fault impact, δ and θ are adjustment parameters used to adjust the response speed of the function.

[0017] Among them, the functional risk value R i The following formula is used for calculation: R i =W i ·A i , where W i is the weight of the i-th module.

[0018] Wherein, based on the collected working parameters for each functional module, the fault detection value set D is calculated.i , the operating parameters include voltage, current, temperature and time.

[0019] The priority sorting in step S107 adopts a machine learning algorithm to identify the module most likely to fail by analyzing the historical data and monitoring data of each functional module, and allocates priority testing resources to it.

[0020] Wherein, in step S109, based on the functional risk value R i By comparing with the preset threshold T, the test frequency of the corresponding functional module is adjusted.

[0021] Wherein, the functional risk value R i Compare with the preset threshold T and adjust the test frequency of the corresponding functional module, including:

[0022] Set the risk preset threshold T, when R i >T, it means that module i needs to be tested first;

[0023] Calculate the adjustment factor K for each module i , used to determine the increase or decrease of test frequency:

[0024]

[0025] Set the initial test frequency F i0 , the new test frequency F i The adjustment factor is calculated using the following formula: i =F i0 ·K i where F i0 is the initial test frequency.

[0026] The in-machine test collects data in real time through an embedded system and uses an improved neural network model to perform fault detection.

[0027] Among them, the temperature change rate, voltage fluctuation amplitude, current fluctuation amplitude and response time are extracted based on the working parameters, and the extracted features are analyzed by threshold detection, machine learning classifier or statistical method to output the fault detection value D ij , by the fault detection value D ij Construct the fault detection value set D i .

[0028] The present invention also proposes a testing device for an information monitoring system, comprising:

[0029] An initialization module, which is used to initialize various functional modules of the information monitoring system;

[0030] The test indicator acquisition module is used to obtain the test indicator A of each functional module. i ;

[0031] Functional risk value calculation module, based on the test indicator A i Calculate the functional risk value R of each functional module i ;

[0032] A ranking module is used to sort the risk value R based on the function i Perform prioritization and identify functional modules that need to be tested first;

[0033] A test frequency adjustment module is used to adjust the function risk value R based on the function risk value R i , dynamically adjust the test frequency;

[0034] Potential fault identification module, which is used to perform in-machine testing, monitor the status of each functional module in real time, and identify potential faults;

[0035] The report generation module is used to generate a test report.

[0036] Compared with the prior art, the present invention has the following advantages:

[0037] By combining real-time monitoring data with the threshold detection algorithm, the fault status of the equipment can be identified more accurately. The improved fault detection value function can handle the volatility in the data, reduce false positives and false negatives, and thus improve the reliability of detection.

[0038] Existing threshold settings usually rely on static historical data and may not be able to adapt to changes in the operating status of the equipment. By introducing a dynamic adjustment mechanism, the technical solution can update the threshold in real time, adapt to different operating conditions, and improve the flexibility and adaptability of fault detection.

[0039] Combining machine learning algorithms and data analysis technology, it can automatically identify fault modes and learn and adjust based on historical and real-time data. This intelligent processing method enables the fault detection system to self-optimize, reduce manual intervention, and improve work efficiency.

[0040] The comprehensive fault detection method adopted in the scheme not only relies on simple threshold detection, but also can be combined with other detection technologies (such as model-based detection). This multi-level detection mechanism enables the system to comprehensively monitor the equipment status and detect potential faults in a timely manner, especially progressive faults.

[0041] By improving the timeliness and accuracy of fault detection, the downtime caused by equipment failure can be effectively reduced. Identifying and handling faults in advance reduces the high maintenance costs caused by sudden failures and improves equipment availability and production efficiency.

[0042] The fault detection system with modular design can be easily integrated into the existing industrial environment and is suitable for different types of equipment and application scenarios. This scalability enables the technical solution to be widely used in various industries and improve the overall equipment management level.

[0043] Real-time monitoring of each module status and updating of fault detection values, combined with a feedback mechanism, can quickly respond to changes in equipment status. This real-time nature ensures that the system can respond as soon as a fault occurs, reducing the risk of accidents.

[0044] By taking advantage of big data technology and the Internet of Things, we can conduct in-depth analysis of large amounts of monitoring data and identify potential failure modes. This data-driven decision-making method enables fault detection to not only be limited to the current state, but also to predict future failure trends.

[0045] Timely and accurate fault detection can effectively prevent safety accidents caused by equipment failures and ensure the safety of operators and equipment. This is especially important for high-risk industries and can significantly reduce the probability of accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present disclosure will become readily understood. In the accompanying drawings, several embodiments of the present disclosure are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0047] Figure 1 The flowchart of the testing method of the information monitoring system according to the embodiment of the present invention is shown. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings, and "multiple" generally includes at least two.

[0050] It should be understood that although the terms first, second, third, etc. may be used to describe ... in the embodiments of the present invention, these ... should not be limited to these terms. These terms are only used to distinguish .... For example, without departing from the scope of the embodiments of the present invention, the first ... may also be referred to as the second ..., and similarly, the second ... may also be referred to as the first ....

[0051] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0052] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0053] It should also be noted that the term "includes", "comprising" or any other variation thereof is intended to cover non-exclusive inclusion, so that a commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprising a ..." do not exclude the existence of other identical elements in the commodity or device including the elements.

[0054] The optional embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0055] Embodiment 1

[0056] like Figure 1 As shown, the present invention discloses a testing and evaluation method for an information monitoring system, comprising the following steps:

[0057] Step S101, initializing each functional module of the information monitoring system;

[0058] Step S103: Obtain the test index A of each functional module i ;

[0059] Step S105: Based on the test indicator A i Calculate the functional risk value R of each functional module i ;

[0060] Step S107: Based on the functional risk value R i Perform prioritization and identify functional modules that need to be tested first;

[0061] Step S109: Based on the functional risk value R i , dynamically adjust the test frequency;

[0062] Step S1011, perform in-machine testing, monitor the status of each functional module in real time, and identify potential faults;

[0063] Step S1013: Generate a test report.

[0064] Embodiment 2

[0065] The present invention provides a method for testing an information monitoring system, comprising the following steps:

[0066] Step S101, initializing each functional module of the information monitoring system;

[0067] Step S103: Obtain the test index A of each functional module i ;

[0068] Step S105: Based on the test indicator A i Calculate the functional risk value R of each functional module i ;

[0069] Step S107: Based on the functional risk value R i Perform prioritization and identify functional modules that need to be tested first;

[0070] Step S109: Based on the functional risk value R i , dynamically adjust the test frequency;

[0071] Step S1011, perform in-machine testing, monitor the status of each functional module in real time, and identify potential faults;

[0072] Step S1013: Generate a test report.

[0073] Among them, the test index A i Defined as:

[0074] A i =f(D i )+g(F impact ), where D i is the fault detection value set of the i-th module; D ij is the fault detection value of the i-th module in the j-th detection: is the variance of the fault detection value, ∈ is a very small positive number to prevent the denominator from being zero, α and β are adjustment parameters, is the fault impact function of the ith module, F impact is the fault impact parameter of the i-th module, τ is the time constant of the fault impact, δ and θ are adjustment parameters used to adjust the response speed of the function.

[0075] Where D is a set containing all module fault detection values, which can be expressed as: D = {D 1 , D 2 , ..., D n}, where n is the total number of modules. Di is the fault detection value of the i-th module, expressed as a set containing all the detection values ​​of the module in multiple tests, which can be expressed as: i ={D i1 , D i2 , ..., D iN}Where N is the number of detections performed by the module. D is a set containing the fault detection values ​​of all modules. i is a subset of D, specifically for the detection value of the i-th module; D ij Yes D i The elements of represent the specific value of the i-th module in the j-th detection.

[0076] In one embodiment, the variance It is used to measure the volatility of fault detection values ​​and is usually calculated by the following steps:

[0077] Calculate the mean of the detection values ​​of the i-th module: Calculate the variance:

[0078]

[0079] Among them, the estimation through fault history data and real-time monitoring data usually depends on the following factors: the type and frequency of faults, the working environment of the module, load conditions, etc. impact , which can be determined by weighted average or other statistical methods:

[0080] Where M is the number of fault types, w k is the weight of the kth fault type, and the fault index k is the rated value of the kth fault type. Among them, α, β, δ, and θ can all be obtained in advance through statistics or experiments.

[0081] Among them, the functional risk value R i The following formula is used for calculation: R i =W i ·A i, where W i is the weight of the i-th module.

[0082] Wherein, based on the collected working parameters for each functional module, the fault detection value set D is calculated. i , the operating parameters include voltage, current, temperature and time.

[0083] The priority sorting in step S107 adopts a machine learning algorithm to identify the module most likely to fail by analyzing the historical data and monitoring data of each functional module, and allocates priority testing resources to it.

[0084] Wherein, in step S109, based on the functional risk value R i By comparing with the preset threshold T, the test frequency of the corresponding functional module is adjusted.

[0085] Wherein, the functional risk value R i Compare with the preset threshold T and adjust the test frequency of the corresponding functional module, including:

[0086] Set the risk preset threshold T, when R i >T, it means that module i needs to be tested first;

[0087] Calculate the adjustment factor K for each module i , used to determine the increase or decrease of test frequency:

[0088]

[0089] Set the initial test frequency F i0 , the new test frequency F i The adjustment factor is calculated using the following formula: i =F i0 ·K i , where F i0 It is the initial test frequency, which is set by analyzing historical data, combining the system's monitoring requirements and module importance. The initial frequency can be determined by empirical values, such as every hour, every day, etc.

[0090] In one embodiment, during the test, the status of each module is monitored in real time, and Di and the fault impact parameter F are updated. impact .

[0091] Adjust the weight Di and fault impact parameter F according to the test results impact , updated by the following formula: W i =α w ·W i +(1-α w )·New weights, where α wRepresents the learning rate, which can be obtained in advance by analyzing historical data. Use machine learning models (such as decision trees, random forests, etc.) to analyze historical data and optimize the settings of weights and fault impact parameters.

[0092] Initial settings:

[0093] Assume there are three modules and the initial test frequency is F 10 = 1 time / hour, where weight W 1 =0.4,W 2 =0.3,W 3 =0.3, assuming that after calculation, we get, R 1 =1.2, R 2 =0.6, R 3 =0.8, set the threshold T=1.0, and calculate the adjustment factor: Then dynamically adjust the test frequency:

[0094] The in-machine test collects data in real time through an embedded system and uses an improved neural network model to perform fault detection.

[0095] In one embodiment, the goal of performing built-in testing is to monitor the status of each module in real time, identify potential faults and record relevant data to ensure the reliability of the information monitoring system.

[0096] Test execution steps:

[0097] Initialize the test environment, start the monitoring system, and ensure that all modules are in a testable state; determine the test parameters, including the indicators to be monitored (such as temperature, voltage, running time, etc.), and configure relevant sensors;

[0098] Configure the test protocol, formulate a specific test protocol, and define the test content, frequency, and execution time. For example: each module performs a status check once an hour, and key modules perform a detailed check every 15 minutes;

[0099] Data acquisition, using sensors and data acquisition systems to collect real-time operating data of each module. These data include: temperature, monitoring module temperature changes under different working conditions; voltage, monitoring module power supply stability; processing load, recording module processing capacity and load conditions; fault detection value, real-time fault detection value calculated through the above steps.

[0100] Real-time monitoring of module status, real-time data monitoring, using embedded systems or industrial control systems (such as PLC) for data collection and real-time monitoring. Use time series databases (such as InfluxDB) to store real-time data for quick retrieval and analysis;

[0101] Status indicator setting: each module sets key performance indicators (KPIs), such as temperature threshold (too high or too low temperature), voltage fluctuation amplitude (exceeding the set range), and response time (whether it exceeds the normal range).

[0102] Real-time data visualization, using data visualization tools (such as Grafana) to display real-time monitoring data, making it easier for operators or engineers to quickly identify abnormal situations.

[0103] Identify potential faults, implement fault detection algorithms, and use machine learning models (such as decision trees, neural networks) to analyze real-time data to identify potential faults. For example:

[0104] Anomaly detection uses training data to identify the difference between normal operating conditions and abnormal conditions, and detects potential faults in a timely manner.

[0105] Feature extraction, extracting features (such as temperature change rate, load fluctuation) from real-time data for fault prediction.

[0106] Set fault judgment criteria based on historical data and domain knowledge. For example, when the temperature exceeds the set threshold, it is immediately marked as a potential fault; when the voltage fluctuation exceeds a certain amplitude, it is recorded as a fault warning.

[0107] Among them, the temperature change rate, voltage fluctuation amplitude, current fluctuation amplitude and response time are extracted based on the working parameters, and the extracted features are analyzed by threshold detection, machine learning classifier or statistical method to output the fault detection value D ij , by the fault detection value D ij Construct the fault detection value set D i .

[0108] Threshold-based methods mark a parameter as faulty if it exceeds a preset threshold.

[0109] Machine learning models, such as support vector machines (SVMs) and random forests, train models based on historical data and predict failures in real time.

[0110] In one embodiment, a threshold detection method is taken as an example for explanation.

[0111] Before applying threshold detection, key features need to be extracted from sensor data. Common features include: temperature, the operating temperature of the device or module; voltage, the stability of the supply voltage; pressure, the pressure value of the hydraulic or pneumatic system; vibration, the vibration of the mechanical parts.

[0112] Feature extraction can be done through a real-time data acquisition system, and the data will be stored for subsequent analysis.

[0113] Define the threshold T. The setting of threshold T is the core part of the threshold detection algorithm. The following are the steps to set the threshold Y:

[0114] Historical data analysis:

[0115] Collect historical operating data and analyze the normal range of each characteristic.

[0116] Determine the normal range of variation of a characteristic through statistical analysis such as mean and standard deviation.

[0117] Set thresholds. According to historical data, set upper and lower thresholds. For example, assuming the normal range of temperature is [T min ,T max ], then: low threshold T min It can be set as the mean minus a certain multiple of the standard deviation, the high threshold T max Set to the mean plus a certain multiple of the standard deviation.

[0118] During real-time monitoring, the algorithm compares the extracted features with the set thresholds:

[0119] During the monitoring process, each time new sensor data (such as X ij , where i represents the module and j represents the number of detections), and compares it with the preset threshold. ij <T min or X ij >T max It is marked as a fault state. At this time, the output fault detection value D ij It can be defined as:

[0120] Output: D ij =1 means that the i-th module fails in the j-th detection; D ij =0 indicates that the i-th module operates normally in the j-th detection.

[0121] Embodiment 3

[0122] The present invention also proposes a testing device for an information monitoring system, which comprises

[0123] An initialization module, which is used to initialize various functional modules of the information monitoring system;

[0124] The test indicator acquisition module is used to obtain the test indicator A of each functional module. i ;

[0125] Functional risk value calculation module, based on the test indicator A i Calculate the functional risk value R of each functional module i ;

[0126] A ranking module is used to sort the risk value R based on the function i Perform prioritization and identify functional modules that need to be tested first;

[0127] A test frequency adjustment module is used to adjust the function risk value R based on the function risk value R i , dynamically adjust the test frequency;

[0128] Potential fault identification module, which is used to perform in-machine testing, monitor the status of each functional module in real time, and identify potential faults;

[0129] The report generation module is used to generate a test report.

[0130] Embodiment 4

[0131] An embodiment of the present disclosure provides a non-volatile computer storage medium, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions can execute the method steps described in the above embodiment.

[0132] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0133] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0134] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (AN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0135] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0136] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0137] The above introduces the preferred embodiments of the present invention, which is intended to make the spirit of the present invention clearer and easier to understand, but is not intended to limit the present invention. All modifications, substitutions, and improvements made within the spirit and principles of the present invention should be included in the scope of protection outlined by the claims attached to the present invention.

Claims

1. A testing method for an information monitoring system, characterized in that: The following steps are involved: Step S101, initializing each functional module of the information monitoring system; Step S103: Obtain the test index A of each functional module i ; Step S105: Based on the test indicator A i Calculate the functional risk value R of each functional module i ; Step S107: Based on the functional risk value R i Perform prioritization and identify functional modules that need to be tested first; Step S109: Based on the functional risk value R i , dynamically adjust the test frequency; Step S1011, perform in-machine testing, monitor the status of each functional module in real time, and identify potential faults; Step S1013: Generate a test report.

2. The method according to claim 1, characterized in that: The test index A i Defined as: A i =f(D i )+g(F impact ), where D i is the fault detection value set of the i-th module; D ij is the fault detection value of the i-th module in the j-th detection; is the variance of the fault detection value, ∈ is a very small positive number to prevent the denominator from being zero, α and β are adjustment parameters, is the fault impact function of the ith module, F impact is the fault impact parameter of the i-th module, τ is the time constant of the fault impact, δ and θ are adjustment parameters used to adjust the response speed of the function.

3. The method according to claim 2, characterized in that: The functional risk value R i The following formula is used for calculation: R i =W i ·A i , where W i is the weight of the i-th module.

4. The method according to claim 2, characterized in that: The fault detection value set D is calculated based on the collected working parameters of each functional module. i , the operating parameters include voltage, current, temperature and time.

5. The method according to claim 1, characterized in that: The priority sorting in step S107 adopts a machine learning algorithm to identify the module most likely to fail by analyzing the historical data and monitoring data of each functional module, and allocates priority testing resources to it.

6. The method according to claim 1, characterized in that: In step S109, based on the functional risk value R i By comparing with the preset threshold T, the test frequency of the corresponding functional module is adjusted.

7. The method according to claim 6, characterized in that: The functional risk value R i Compare with the preset threshold T and adjust the test frequency of the corresponding functional module, including: Set the risk preset threshold T, when R i >T, it means module i needs to be tested first; Calculate the adjustment factor K for each module i , used to determine the increase or decrease of test frequency: Set the initial test frequency F i0 , the new test frequency F i The adjustment factor is calculated using the following formula: i =F i0 ·K i , where F i0 is the initial test frequency.

8. The method according to claim 1, characterized in that: The in-machine test collects data in real time through an embedded system and performs fault detection using an improved neural network model.

9. The method according to claim 4, characterized in that: The temperature change rate, voltage fluctuation amplitude, current fluctuation amplitude and response time are extracted based on the working parameters, and the extracted features are analyzed by threshold detection, machine learning classifier or statistical method to output the fault detection value D ij , by the fault detection value D ij Construct the fault detection value set D i .

10. A testing device for an information monitoring system, comprising: An initialization module, which is used to initialize various functional modules of the information monitoring system; The test indicator acquisition module is used to obtain the test indicator A of each functional module. i ; Functional risk value calculation module, based on the test indicator A i Calculate the functional risk value R of each functional module i ; A ranking module is used to sort the risk value R based on the function i Perform prioritization and identify functional modules that need to be tested first; A test frequency adjustment module is used to adjust the function risk value R based on the function risk value R i , dynamically adjust the test frequency; Potential fault identification module, which is used to perform in-machine testing, monitor the status of each functional module in real time, and identify potential faults; The report generation module is used to generate a test report.

Images