Electronic component parameter array channel detection method in ocean salt mist environment

Abstract

The invention discloses an electronic component parameter array channel detection method in an ocean salt mist environment, and relates to the technical field of electronic equipment monitoring, and the method comprises the following steps: installing a plurality of sensors in the ocean salt mist environment, and continuously monitoring the data of electronic components; analyzing the preprocessed data through a deep learning model; a fault prediction mechanism is constructed, a real-time identification result is obtained based on the deep learning model, the current working state of the element is further analyzed, and whether abnormity exists or not is identified; a historical prediction result and a real-time prediction result are integrated through a cloud platform, a trend in long-term operation is found through big data analysis, and a comprehensive judgment value is calculated. Through a fault prediction mechanism based on deep learning, real-time data and historical data are combined, occurrence of component faults can be accurately predicted, the limitation of dependence on manual detection in a traditional method is avoided, preventive measures are taken in advance, and the reliability and safety of electronic components are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic equipment monitoring, and in particular to a method for detecting electronic component parameter array channels in a marine salt spray environment. Background Art

[0002] Marine salt spray environments significantly impact the long-term stability and performance of electronic components. With the widespread use of electronic equipment in marine and coastal areas, electronic components exposed to salt spray are susceptible to corrosion, leading to performance degradation or failure of components such as resistors, capacitors, diodes, and transistors. Such failures can impact the normal operation of electronic equipment, especially in high-risk sectors such as industry, military, and marine engineering. Therefore, timely detection and prediction of failures in these electronic components to ensure their reliability in harsh environments has become a pressing technical challenge.

[0003] Traditional methods for detecting electronic component faults rely primarily on manual inspections and periodic testing, typically employing visual inspections or simple electrical tests. These methods are not only inefficient but also susceptible to human interference, making them unable to detect potential faults promptly and accurately. This is particularly true in marine salt spray environments, where long-term exposure and environmental interference make traditional methods difficult to adapt to demand. Summary of the Invention

[0004] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of this application to avoid obscuring the purpose of this section, the abstract and the title of the invention, and such simplifications or omissions should not be used to limit the scope of the present invention.

[0005] In view of the problems existing in the above-mentioned existing method for detecting electronic component parameter array channels in a marine salt spray environment, the present invention is proposed.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: A method for detecting electronic component parameters in an ocean salt spray environment comprises the following steps: installing multiple sensors in an ocean salt spray environment to continuously monitor the data of electronic components such as resistors, capacitors, diodes, and transistors. , and collect data Perform denoising preprocessing; Through deep learning models For preprocessed data Perform analysis to identify different electronic component states from sensor data and determine whether there are potential problems with the components; Build a fault prediction mechanism, based on the real-time recognition results obtained by the deep learning model, further analyze the current working status of the component, identify whether there is an abnormality, and predict the fault in real time to obtain the prediction probability ; Through the cloud platform, historical prediction results With real-time prediction results Integrate and analyze big data to find long-term trends and calculate comprehensive judgment values The larger the value, the higher the required detection frequency.

[0007] As a preferred solution of the electronic component parameter array channel detection method in a marine salt spray environment described in the present invention, the expression of the deep learning model is: in, represents the output of the deep learning model, The data of the i-th sensor at time t, represents the weight coefficient of the i-th sensor data, represents the activation function, represents the weighted sum function, represents the input of hidden layer node j in the neural network, N represents the number of sensors, M represents the number of layers of the neural network, and L represents the number of nodes in the hidden layer of the neural network.

[0008] As a preferred solution of the electronic component parameter array channel detection method in a marine salt spray environment described in the present invention, the fault prediction mechanism is: based on the output of the deep learning model, the component status in the past t time is analyzed to predict future fault events, represents the failure prediction probability at time t, which is expressed as: in, represents the predicted probability of failure at time t, represents the dynamic adjustment parameter of the failure rate, Parameters for adjusting long-term aging effects, Represents the attenuation control parameter.

[0009] As a preferred solution of the electronic component parameter array channel detection method in a marine salt spray environment described in the present invention, when the fault prediction probability If the value is greater than the first threshold, the electronic component is determined to be in a faulty state, the equipment repair program is started, and the operation and maintenance personnel are notified to conduct an on-site inspection; When the failure prediction probability If the value is less than the second threshold, it is determined that the electronic component is in a normal state and no intervention is required; When the failure prediction probability When the second threshold is between the first threshold, it is determined to be a potential fault state and requires continuous monitoring and evaluation.

[0010] As a preferred solution of the electronic component parameter array channel detection method in a marine salt spray environment described in the present invention, wherein: the comprehensive judgment value The calculation process is based on a weighted average and dynamic adjustment model, and the expression is: in, represents the real-time prediction of failure probability, represents the historical failure probability, Used to adjust the impact of multi-sensor data on detection frequency, represents the attenuation parameter of the i-th sensor, represents the dynamic adjustment parameter of the i-th sensor, A larger value indicates a higher detection frequency for the component.

[0011] As a preferred solution of the electronic component parameter array channel detection method in a marine salt spray environment described in the present invention, wherein: the comprehensive judgment value Below adjustment threshold , then maintain the current detection frequency; The comprehensive judgment value Above adjustment threshold , increase the detection frequency and notify the operation and maintenance personnel to strengthen monitoring.

[0012] As a preferred solution of the method for detecting electronic component parameter array channels in a marine salt spray environment described in the present invention, real-time monitoring is continuously performed on a cloud platform, and component detection information is transmitted to a visualization device via a wireless connection. If abnormal information is found in a component, an alarm is issued and the cloud platform immediately notifies maintenance personnel.

[0013] A detection system for the above-mentioned electronic component parameter array channel detection method in a marine salt spray environment includes the following working modules: The sensor monitoring module is responsible for real-time monitoring of the working status of electronic components in the marine salt spray environment; The data acquisition and preprocessing module is responsible for receiving raw data from sensors and performing data cleaning, filtering and preprocessing operations to ensure data quality; The deep learning analysis module uses deep learning algorithms to train and analyze preprocessed data and identify the working status of electronic components from sensor data; The fault prediction and diagnosis module analyzes the current working status of electronic components based on the output of the deep learning model, determines whether a fault has occurred, and performs fault prediction; The cloud platform and data storage module is responsible for integrating and storing historical fault data and real-time monitoring data, supporting remote access and data management of the cloud platform; the detection frequency optimization module adjusts the detection frequency based on data analysis on the cloud platform and increases the detection frequency for components prone to failure.

[0014] The present invention also discloses a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned electronic component parameter array channel detection method in a marine salt spray environment when executing the computer program.

[0015] The present invention also discloses a computer-readable storage medium storing a computer program, characterized in that when the computer program is executed by a processor, the steps of the above-mentioned electronic component parameter array channel detection method in a marine salt spray environment are implemented.

[0016] Beneficial effects of the present invention: This invention uses a deep learning-based fault prediction mechanism, combined with real-time and historical data, to accurately predict the occurrence of component failures. This avoids the limitations of traditional methods that rely on manual inspection, allowing preventive measures to be taken in advance, thereby improving the reliability and safety of electronic components. This invention integrates historical and real-time prediction results through a cloud platform and employs big data analysis to identify long-term failure trends and adaptively increase the frequency of testing for components prone to failure. This mechanism ensures dynamic optimization of testing frequencies for different components, making fault detection more intelligent and precise, and minimizing maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them: Figure 1 This is a flow chart of a method for detecting electronic component parameter array channels in a marine salt spray environment proposed by the present invention. DETAILED DESCRIPTION

[0018] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0019] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0020] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0021] Reference Figure 1 , as one embodiment of the present invention, provides a method for detecting electronic component parameter array channels in a marine salt spray environment, the method comprising the following steps: Step 1: Install multiple sensors in the marine salt spray environment to continuously monitor the data of electronic components such as resistors, capacitors, diodes, and transistors , and collect data Perform denoising preprocessing; since the marine salt spray environment has different effects on different types of electronic components, installing multiple sensors can cover the status information of more components and provide comprehensive data support for subsequent data analysis.

[0022] Step 2: Based on the data obtained in step 1, it is necessary to analyze the electronic component data collected by the sensor through a deep learning algorithm to identify different electronic component states and determine whether there are potential problems with the components. To this end, a deep learning model based on a neural network was designed. ,The model considers the multidimensional characteristics of sensor data and ,the multi-layered relationships of electronic component parameters.

[0023] The expression of the deep learning model is: in, Represents the output of the deep learning model, with a value range of [0,1], The data of the i-th sensor at time t, represents the weight coefficient of the i-th sensor data, represents the activation function, represents the weighted sum function, represents the input of hidden layer node j in the neural network, N represents the number of sensors, M represents the number of layers of the neural network, and L represents the number of nodes in the hidden layer of the neural network.

[0024] According to the state value output by the model , it can be used to determine whether a component is in a potential problem state. If the output value is close to 1, it means that the component may be faulty; if it is close to 0, it means that the component is operating normally.

[0025] Step 3: Build a fault prediction mechanism. Based on the real-time recognition results obtained by the deep learning model, further analyze the current working status of the component, identify whether there is an abnormality, and predict the fault in real time to obtain the prediction probability. ; Specifically, the fault prediction mechanism is: based on the output of the deep learning model, the component status in the past t time is analyzed to predict future fault events. represents the failure prediction probability at time t, which is expressed as: in, represents the predicted probability of failure at time t, represents the dynamic adjustment parameter of the failure rate, Parameters for adjusting long-term aging effects, Represents the attenuation control parameter, the entire

[0026] When the failure prediction probability If the probability of failure is greater than the first threshold, the electronic component is judged to be in a faulty state, the equipment repair program is started, and the operation and maintenance personnel are notified to conduct on-site inspection; when the fault prediction probability is greater than the first threshold, the electronic component is judged to be in a faulty state, the equipment repair program is started, and the operation and maintenance personnel are notified to conduct on-site inspection; is less than the second threshold, the electronic component is judged to be in normal state and no intervention is required; when the fault prediction probability When the second threshold is between the first threshold, it is determined to be a potential fault state and requires continuous monitoring and evaluation.

[0027] This step provides accurate fault warnings to ensure that the system does not experience unexpected shutdowns or equipment damage due to component failures.

[0028] Step 4: Use the cloud platform to upload historical prediction results With real-time prediction results Integrate and analyze big data to find long-term trends and calculate comprehensive judgment values The larger the value, the higher the required inspection frequency. For high-risk components (e.g., those with a high probability of failure), the inspection frequency can be dynamically increased to ensure early detection of potential failures. For components with a low probability of failure, the inspection frequency can be reduced to optimize resource allocation.

[0029] Specifically, the comprehensive judgment value The calculation process is based on a weighted average and dynamic adjustment model, and the expression is: in, represents the real-time prediction of failure probability, represents the historically known probability of failure, Used to adjust the impact of multi-sensor data on detection frequency, represents the attenuation parameter of the i-th sensor, represents the dynamic adjustment parameter of the i-th sensor, The larger the value, the higher the frequency of component detection. Below adjustment threshold , then maintain the current detection frequency; comprehensive judgment value Above adjustment threshold , increase the detection frequency and notify the operation and maintenance personnel to strengthen monitoring.

[0030] Through continuous real-time monitoring on the cloud platform, component detection information is transmitted to the visualization device via wireless connection. If any abnormal information is found in a component, an alarm will be issued and the cloud platform will immediately notify the maintenance personnel.

[0031] This embodiment also provides an electronic component parameter array channel detection system in a marine salt spray environment, which is applied to the above-mentioned detection method. The system includes: a sensor monitoring module, which is responsible for real-time monitoring of the working status of electronic components in a marine salt spray environment; a data acquisition and preprocessing module, which is responsible for receiving raw data from sensors and performing data cleaning and filtering preprocessing operations to ensure data quality; and a deep learning analysis module, which uses a deep learning algorithm to train and analyze the preprocessed data and identify the working status of electronic components from the sensor data. The fault prediction and diagnosis module analyzes the current working status of electronic components based on the output of the deep learning model, determines whether a fault has occurred, and performs fault prediction; the cloud platform and data storage module is responsible for integrating and storing historical fault data with real-time monitoring data, and supports remote access and data management of the cloud platform; the detection frequency optimization module adjusts the detection frequency based on data analysis on the cloud platform and increases the detection frequency for components prone to failure.

[0032] In summary, this invention, through a deep learning-based fault prediction mechanism combined with real-time and historical data, can accurately predict the occurrence of component failures, avoiding the limitations of traditional methods that rely on manual inspections and taking preventive measures in advance, thereby improving the reliability and safety of electronic components. By integrating historical and real-time prediction results through a cloud platform and employing big data analysis, it can identify long-term failure trends and adaptively increase the detection frequency of components prone to failure. This mechanism ensures dynamic optimization of the detection frequency for different components, making fault detection more intelligent and precise, and minimizing maintenance costs.

[0033] This embodiment also provides a computer device suitable for a method for detecting electronic component parameter array channels in a marine salt spray environment, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the method for detecting electronic component parameter array channels in a marine salt spray environment proposed in the above embodiment.

[0034] The computer device may be a terminal, comprising a processor, memory, a communication interface, a display, and an input device connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores an operating system and computer programs. The internal memory provides an environment for the operating system and computer programs stored in the non-volatile storage media. The communication interface of the computer device is used to communicate with external terminals via wired or wireless communication. Wireless communication may be achieved via Wi-Fi, a carrier network, NFC (near-field communication), or other technologies. The display of the computer device may be a liquid crystal display or an electronic ink display. The input device may be a touchscreen overlay on the display, buttons, a trackball, or a touchpad on the computer device housing, or an external keyboard, touchpad, or mouse.

[0035] This embodiment also provides a storage medium having a computer program stored thereon. When the program is executed by a processor, it implements the method for detecting electronic component parameter array channels in a marine salt spray environment proposed in the above embodiment. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0036] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for detecting electronic component parameter array channels in a marine salt spray environment, characterized in that: The method comprises the following steps: Install multiple sensors in a marine salt spray environment to continuously monitor the data of electronic components , and collect data Perform denoising preprocessing; Through deep learning models For preprocessed data Perform analysis to identify different electronic component states from sensor data and determine whether there are potential problems with the components; Build a fault prediction mechanism, based on the real-time recognition results obtained by the deep learning model, further analyze the current working status of the component, identify whether there is an abnormality, and predict the fault in real time to obtain the prediction probability ; Through the cloud platform, historical prediction results With real-time prediction results Integrate and analyze big data to find long-term trends and calculate comprehensive judgment values The larger the value, the higher the required detection frequency.

2. The method for detecting electronic component parameters in an ocean salt spray environment according to claim 1, wherein: The expression of the deep learning model is: in, represents the output of the deep learning model, The data of the i-th sensor at time t, represents the weight coefficient of the i-th sensor data, represents the activation function, represents the weighted sum function, represents the input of the hidden layer node j in the neural network, N represents the number of sensors, M represents the number of layers of the neural network, and L represents the number of nodes in the hidden layer of the neural network.

3. The electronic component parameter array channel detection method under a marine salt spray environment according to claim 2, wherein: The fault prediction mechanism is: based on the output of the deep learning model, the component status in the past t time is analyzed to predict future fault events. represents the failure prediction probability at time t, which is expressed as: in, represents the predicted probability of failure at time t, represents the dynamic adjustment parameter of the failure rate, Parameters for adjusting long-term aging effects, Represents the attenuation control parameter.

4. The electronic component parameter array channel detection method under a marine salt spray environment according to claim 3, wherein: When the failure prediction probability If the value is greater than the first threshold, the electronic component is determined to be in a faulty state, the equipment repair program is started, and the operation and maintenance personnel are notified to conduct an on-site inspection; When the failure prediction probability If the value is less than the second threshold, it is determined that the electronic component is in a normal state and no intervention is required; When the failure prediction probability When the second threshold is between the first threshold, it is determined to be a potential fault state and requires continuous monitoring and evaluation.

5. The electronic component parameter array channel detection method under a marine salt spray environment according to claim 4, wherein: The comprehensive judgment value The calculation process is based on a weighted average and dynamic adjustment model, and the expression is: in, represents the real-time prediction of failure probability, represents the historical failure probability, Indicates the parameter for adjusting the influence of multi-sensor data on the detection frequency. represents the attenuation parameter of the i-th sensor, represents the dynamic adjustment parameter of the i-th sensor, A larger value indicates a higher detection frequency for the component.

6. The electronic component parameter array channel detection method under a marine salt spray environment according to claim 5, wherein: The comprehensive judgment value Below adjustment threshold , then maintain the current detection frequency; The comprehensive judgment value Above adjustment threshold , increase the detection frequency and notify the operation and maintenance personnel to strengthen monitoring.

7. The electronic component parameter array channel detection method under a marine salt spray environment according to claim 6, characterized in that: Through continuous real-time monitoring on the cloud platform, component detection information is transmitted to the visualization device via wireless connection. If any abnormal information is found in a component, an alarm will be issued and the cloud platform will immediately notify the maintenance personnel.

8. The detection system of the electronic component parameter array channel detection method under a marine salt spray environment according to claim 7, characterized in that: The system includes the following working modules: The sensor monitoring module is responsible for real-time monitoring of the working status of electronic components in the marine salt spray environment; The data acquisition and preprocessing module is responsible for receiving raw data from sensors and performing data cleaning, filtering and preprocessing operations to ensure data quality; The deep learning analysis module uses deep learning algorithms to train and analyze preprocessed data and identify the working status of electronic components from sensor data; The fault prediction and diagnosis module analyzes the current working status of electronic components based on the output of the deep learning model, determines whether a fault has occurred, and performs fault prediction; The cloud platform and data storage module is responsible for integrating and storing historical fault data and real-time monitoring data, and supports remote access and data management on the cloud platform; The detection frequency optimization module adjusts the detection frequency based on data analysis on the cloud platform and increases the detection frequency for components prone to failure.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the electronic component parameter array channel detection method in a marine salt spray environment according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the electronic component parameter array channel detection method in a marine salt spray environment according to any one of claims 1 to 7 are implemented.

Images