Electrical product safety intelligent detection method and system

Abstract

The invention provides an electrical product safety intelligent detection method and system. The method comprises the following steps: acquiring historical operation data and current operation data of parameters of a to-be-tested electrical product and current operation data of parameters of electrical products in the same batch as the to-be-tested electrical product; setting a dynamic safety threshold according to the historical operation data, and comparing the current operation data with the dynamic safety threshold of the parameters of the electrical products and the current data of the parameters of the electrical products of the same batch as the electrical products to be tested; and if the current data of the parameters of the to-be-tested electrical product exceed a dynamic safety threshold value or the performance score ranking of the to-be-tested electrical product is beyond the top 70%, the system triggers an early warning mechanism to prompt that performance reduction and potential safety hazards exist. By means of the method and the corresponding system, the accuracy and flexibility of electrical product parameter monitoring are improved, and potential problems can be found and processed in time.

Description

Technical Field

[0001] This invention proposes an intelligent safety testing method and system for electrical products, belonging to the field of electrical product safety testing technology. Background Technology

[0002] Electrical products refer to various devices, machines, or accessories that use electrical energy and contain electrical components. These products can range from small household appliances to large industrial equipment. They operate on electrical principles and may include components such as motors, sensors, control systems, and circuit boards. Electrical products are widely used in daily life and industry, including but not limited to lighting fixtures, power tools, household appliances, communication equipment, generators, transformers, switching equipment, and power transmission and distribution equipment. Due to the involvement of electrical and electronic technologies, the design, manufacture, and maintenance of electrical products require regular testing to ensure their safety and performance.

[0003] Traditional electrical safety testing typically relies on fixed thresholds or fixed time intervals to determine the safety of electrical products. However, the operating conditions of electrical products and the external environment may change over time, rendering fixed thresholds inapplicable or fixed time intervals unscientific. Summary of the Invention

[0004] This invention provides an intelligent safety detection method and system for electrical products to solve the problems mentioned above: This invention proposes an intelligent safety detection method for electrical products, the method comprising: Acquire historical operating data, current operating data, and current operating data of parameters of electrical products from the same batch as the electrical product under test; Based on the historical operating data, a dynamic safety threshold is set, and the current operating data is compared with the dynamic safety threshold of the electrical product's parameters and the current data of the parameters of electrical products from the same batch as the electrical product under test. If the current data of the parameters of the electrical product under test exceeds the dynamic safety threshold or the performance score of the electrical product under test is outside the top 70%, the system triggers an early warning mechanism to indicate that there is a performance degradation and safety hazard.

[0005] Furthermore, acquire historical operating data and current operating data of the parameters of the electrical product under test, as well as current operating data of the parameters of electrical products from the same batch as the electrical product under test, including: Acquire the longitudinal historical operating data of the electrical product under test since its production, including the voltage, current and temperature of the electrical product under test; Obtain the voltage, current, and temperature of electrical products manufactured in the same batch as the electrical product under test; Acquire the current data of the current, voltage, and temperature of the electrical product under test. The frequency of data acquisition is adjusted according to the following model: ; in, This is the adjusted data collection frequency. This is the current data collection frequency. This is the set minimum data collection frequency. This is the set maximum data collection frequency. It is the threshold of the rate of change. It is the change value of the parameter. The parameter in time The rate of change.

[0006] Furthermore, the threshold for the rate of change includes: The threshold formula for the rate of change is: ; Where k is a user-defined factor used to adjust the sensitivity of the threshold, n is the number of data change rate samples, and μ is the mean of the data change rate.

[0007] Furthermore, based on the historical operating data, a dynamic safety threshold is set, and the current operating data is compared with the dynamic safety threshold of the electrical product's parameters and the current data of the parameters of electrical products from the same batch as the electrical product under test, including: Set dynamic safety thresholds based on the historical operating data of the electrical product under test; Specifically, the formula for calculating the dynamic security threshold is: ; Among them, M t It is a moving average, S t It is the weighted standard deviation, and α is the safety factor. ; Among them, M t-1 It is the moving average of the previous time step, and λ is the time decay factor (0 < λ < 1), used to control the degree of influence of historical data on the current average. ; Among them, S t-1 It is the weighted standard deviation of the previous time step. The current operating data of the electrical product under test is compared with the dynamic safety threshold of the electrical product's parameters and the current data of the parameters of electrical products from the same batch as the electrical product under test.

[0008] Furthermore, the current operating data of the electrical product under test is compared with the dynamic safety threshold of the electrical product's parameters and the current data of parameters of electrical products from the same batch as the electrical product under test, including: First, compare the current operating data of the electrical product under test with the dynamic safety threshold of the electrical product's parameters; Next, the current operating data of the electrical product under test is compared with the current parameter data of electrical products from the same batch, and all products in the same batch are scored horizontally. Specifically, the horizontal scoring model is as follows: ; Where K1, K2, and K3 are weighting coefficients, Vc represents the current voltage of the electrical product, Va represents the average voltage of the current data of the same batch of electrical products, Tc represents the current temperature of the electrical product, Ta represents the average temperature of the current data of the same batch of electrical products, Ic represents the current temperature of the electrical product, and Ia represents the average current of the current data of the same batch of electrical products.

[0009] This invention proposes an intelligent safety detection system for electrical products, the system comprising: The data acquisition module is used to acquire historical operating data, current operating data, and current operating data of parameters of electrical products under test and electrical products from the same batch as the electrical product under test. The comparison module is used to set a dynamic safety threshold based on the historical operating data, and compare the current operating data with the dynamic safety threshold of the electrical product's parameters and the current data of the parameters of electrical products from the same batch as the electrical product under test; The warning module triggers a warning mechanism if the current data of the parameters of the electrical product under test exceeds the dynamic safety threshold or if the performance score of the electrical product under test is ranked outside the top 70%. This will indicate the presence of performance degradation and safety hazards.

[0010] Furthermore, the data acquisition module includes: The module for acquiring historical operating voltage, current, and temperature is used to acquire longitudinal historical operating data of the electrical product under test since its production. The parameters of the electrical product under test include the voltage, current, and temperature of the electrical product. A module for acquiring voltage, current, and temperature data of products from the same batch is used to acquire the voltage, current, and temperature of electrical products manufactured in the same batch as the electrical product under test. The current data acquisition module is used to acquire the current data of the current, voltage, and temperature of the electrical product under test. The frequency adjustment module is used to adjust the frequency of data acquisition according to the following model: ; in, This is the adjusted data collection frequency. This is the current data collection frequency. This is the set minimum data collection frequency. This is the set maximum data collection frequency. It is the threshold of the rate of change. It is the change value of the parameter. The parameter in time The rate of change.

[0011] Furthermore, the frequency adjustment module includes: The rate of change threshold calculation module is used to calculate the threshold for the rate of change. The formula for calculating the rate of change threshold is: ; Where k is a user-defined factor used to adjust the sensitivity of the threshold, n is the number of data change rate samples, and μ is the mean of the data change rate.

[0012] Furthermore, the dynamic comparison module includes: The dynamic safety threshold setting module is used to set dynamic safety thresholds based on the historical operating data of the electrical product under test. Specifically, the formula for calculating the dynamic security threshold is: ; Among them, M t It is a moving average, S t It is the weighted standard deviation, and α is the safety factor. ; Among them, M t-1 It is the moving average of the previous time step, and λ is the time decay factor (0 < λ < 1), used to control the degree of influence of historical data on the current average. ; Among them, S t-1 It is the weighted standard deviation of the previous time step. The comparison module is used to compare the current operating data of the electrical product under test with the dynamic safety threshold of the electrical product's parameters and the current data of the parameters of electrical products from the same batch as the electrical product under test.

[0013] Furthermore, the dynamic comparison module includes: The dynamic threshold comparison module is used to first compare the current operating data of the electrical product under test with the dynamic safety threshold of the electrical product's parameters; The horizontal comparison module is used to compare the current operating data of the electrical product under test with the current parameter data of electrical products in the same batch, and to perform a horizontal scoring of all products in the same batch. Specifically, the horizontal scoring model is as follows: ; Wherein, K1, K2 and K3 are weighting coefficients, V represents the current voltage of the electrical product, Vc represents the average voltage of the current data of the same batch of electrical products, T represents the current temperature of the electrical product, Tc represents the average temperature of the current data of the same batch of electrical products, I represents the current temperature of the electrical product, and Ic represents the average current of the current data of the same batch of electrical products.

[0014] The beneficial effects of this invention are as follows: By comparing dynamic safety thresholds, abnormal changes in electrical product parameters can be detected in a timely manner, thereby providing early warnings and enabling corresponding measures to avoid potential safety risks. This comparison method is highly adaptable and stable, capable of adapting to the characteristics of electrical product parameters changing over time. The horizontal scoring model provides a quantitative assessment of the performance of electrical products within the same batch, helping to understand the relative strengths and weaknesses of products within the same batch. By comparing key parameters with the average values ​​of products in the same batch, it is possible to identify which parameters the tested electrical product performs well or poorly, providing a basis for subsequent maintenance and improvement. In summary, this technical solution, through the application of dynamic safety threshold comparison and the horizontal scoring model, improves the accuracy and flexibility of electrical product parameter monitoring, helps to promptly identify and address potential problems, and provides data support for product optimization and improvement. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of an intelligent safety detection method for electrical products according to the present invention. Detailed Implementation

[0016] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0017] One embodiment of the present invention provides an intelligent safety detection method for electrical products, the method comprising: Acquire historical operating data, current operating data, and current operating data of parameters of electrical products from the same batch as the electrical product under test; Based on the historical operating data, a dynamic safety threshold is set, and the current operating data is compared with the dynamic safety threshold of the electrical product's parameters and the current data of the parameters of electrical products from the same batch as the electrical product under test. If the current data of the parameters of the electrical product under test exceeds the dynamic safety threshold or the performance score of the electrical product under test is outside the top 70%, the system triggers an early warning mechanism to indicate that there is a performance degradation and safety hazard.

[0018] The working principle of the above technical solution is as follows: Collect operating data of the electrical product under test over a period of time, including voltage, current and temperature, and obtain the current real-time operating status data of the electrical product under test; at the same time, collect the current operating data of other electrical products in the same batch as the electrical product under test; Based on historical operating data, dynamic safety thresholds are set or adjusted. These thresholds can reflect the parameter range of electrical products under normal operating conditions and can be dynamically adjusted according to changes in equipment status and operating environment. The current operating data of the electrical product under test is compared with the set dynamic safety threshold to check whether any parameters exceed the safety range. At the same time, the current operating data of the electrical product under test is compared with the current data of other electrical products in the same batch to assess whether its performance is at a low level; A performance score is calculated for the electrical product under test according to a certain scoring mechanism. The performance score of the electrical product under test is compared with the performance scores of other electrical products in the same batch to determine whether its ranking is outside the top 70%. If any parameter in the current operating data of the electrical product under test exceeds the dynamic safety threshold, or if its performance score ranks outside the top 70%, the system will trigger an early warning mechanism.

[0019] The effects of the above technical solution are as follows: This solution can monitor the operating status of the electrical product under test in real time and dynamically adjust the safety threshold based on historical data and the current status, thereby improving the real-time performance and accuracy of the early warning mechanism; by comparing with electrical products of the same batch, it can more comprehensively evaluate the performance level of the electrical product under test and promptly detect potential performance degradation and safety hazards; when the parameters of the electrical product under test exceed the safety threshold or its performance score ranks low, the triggering of the early warning mechanism can promptly remind operators or automation systems to take corresponding measures to avoid potential safety accidents or performance degradation problems; with the collection and analysis of new data, this solution can continuously optimize the dynamic safety threshold, performance scoring mechanism, and early warning mechanism to adapt to changes in the operating status and environment of electrical products.

[0020] One embodiment of the present invention provides an intelligent safety testing method for electrical products, which acquires historical operating data, current operating data, and current operating data of parameters of electrical products from the same batch as the electrical product under test, including: Acquire the longitudinal historical operating data of the electrical product under test since its production, including the voltage, current and temperature of the electrical product under test; Obtain the voltage, current, and temperature of electrical products manufactured in the same batch as the electrical product under test; Acquire the current data of the current, voltage, and temperature of the electrical product under test. The frequency of data acquisition is adjusted according to the following model: ; in, This is the adjusted data collection frequency. This is the current data collection frequency. This is the set minimum data collection frequency. This is the set maximum data collection frequency. It is the threshold of the rate of change. It is the change value of the parameter. The parameter in time The rate of change.

[0021] The working principle of the above technical solution is as follows: Historical voltage, current, and temperature data of the electrical product under test (DUT) since its production are collected. This data is arranged chronologically, providing a complete picture of the product's operation. Voltage, current, and temperature data of electrical products manufactured in the same batch as the DUT are also collected. This data is used for horizontal comparison to evaluate the performance of the DUT. Real-time current, voltage, and temperature data of the DUT are acquired to assess its current operating status. The data collection frequency adjustment model adjusts the data collection frequency based on set minimum and maximum data collection frequencies, as well as thresholds for parameter changes and rates of change. When the rate of change of parameters exceeds the threshold, it indicates a significant change in the operating status of the electrical product, requiring an increase in the data collection frequency for more accurate monitoring. Therefore, the data collection frequency will be adjusted from the minimum to the maximum frequency. When the rate of change of parameters is below the threshold, it indicates a relatively stable operating status of the electrical product, allowing for a reduction in the data collection frequency to decrease the data processing burden. Therefore, the data collection frequency will be maintained or reduced to the minimum frequency.

[0022] The beneficial effects of the above technical solution are as follows: Resource optimization: When the data change rate is low, a high data collection frequency may not be necessary. By reducing the frequency to a minimum, system resources such as processor time, memory, and storage space can be saved, which is especially important in systems that operate for long periods or are resource-constrained. Reduction of noise and redundant data: When the data change rate is low, frequent data collection may result in the collection of a large number of similar or duplicate data points, which may not contain much useful information. Reducing the data collection frequency can reduce this noise and redundant data, improving data quality. Extended equipment lifespan: For some physical equipment, frequent data collection may increase wear and tear. Reducing the data collection frequency can extend the lifespan of these devices, reducing the frequency of maintenance and replacement. Maintaining a low data collection frequency when the data change rate is low ensures that the system has sufficient responsiveness to sudden data changes. If the data change rate suddenly increases, the system can quickly increase the data collection frequency to capture these changes. This design allows the system to dynamically adjust its behavior according to the data change rate, thereby adapting to different data patterns and needs. This adaptability allows the system to remain efficient and effective under various conditions. In summary, when the data change rate is low and the current frequency is already at its maximum, choosing a design that maintains the minimum frequency helps optimize resource utilization, reduce noise data, extend equipment life, improve responsiveness, and enhance system adaptability. By collecting all historical data of the electrical product under test since its production, a comprehensive analysis of its long-term operating trends and performance changes can be conducted, helping to identify potential performance degradation and safety hazards. Dynamically adjusting the data collection frequency based on the parameter change rate and thresholds ensures that more data can be acquired in a timely manner when the operating status of the electrical product changes significantly, while reducing the data collection frequency when the operating status is stable, thereby achieving real-time and flexible data collection. By comparing data with that of electrical products in the same batch, the performance of the electrical product under test under the same conditions can be evaluated, performance differences with other products in the same batch can be identified in a timely manner, and a basis for maintenance and optimization can be provided.

[0023] In one embodiment of the present invention, an intelligent safety detection method for electrical products is provided, wherein the threshold for the rate of change includes: The threshold formula for the rate of change is: ; Where k is a user-defined factor used to adjust the sensitivity of the threshold, n is the number of data change rate samples, and μ is the mean of the data change rate. ; To calculate the threshold for the rate of change, we first need to collect a sample of the rate of change over a period of time. Assuming we have a sample set of the rate of change (Δx1 / Δt, Δx2 / Δt, ..., Δxn / Δt), we can then calculate the threshold for the rate of change.

[0024] Suppose we have the following historical data points: 0.2, 0.3, 0.25, 0.4, 0.22. First, calculate the mean μ of the historical data: mean μ = (0.2 + 0.3 + 0.25 + 0.4 + 0.22) / 5 = 1.37 / 5 = 0.274. Then, calculate the square of the difference between each of the five data points and the mean, take the average, and take the square root, resulting in 0.0714. Next, define the user-defined factor k and calculate the safety threshold T. h Assuming k=1.5, the safety threshold T h = k * 0.0714, T h = 1.5 × 0.08, T h = 0.1071 Assuming the new data point is 0.8, with a safety threshold T h This allows comparing the new data point 0.8 with the mean μ plus a safety threshold T. h The sum, mean μ plus safety threshold T h The sum = 0.274 + 0.1071 = 0.394. Since the new data point 0.8 is greater than 0.394, it can be determined that the new data point 0.8 exceeds the safety threshold. Therefore, the new data point 0.8 was not included in the historical data when calculating the safety threshold. Only historical data is used to calculate the mean μ, standard deviation σ, and safety threshold T. h Then, the new data points are compared with these values ​​derived from historical data. This ensures that the judgment is based on existing data, rather than on all data, including the new data points.

[0025] The working principle of the above technical solution is as follows: The formula reflects the volatility or dispersion of the dataset. In a production environment, if the rate of change of a product far exceeds the average rate of change, it may indicate that the product is abnormal or unqualified. By setting a threshold T... hThis method can detect products with abnormally high rates of change, allowing for further quality checks or processing. The coefficient k can be adjusted based on specific application scenarios to optimize the sensitivity and accuracy of the threshold. Based on statistical principles, this method effectively quantifies the dynamic characteristics of products and identifies potential anomalies or nonconformities. Standard deviation is a statistic that measures the dispersion of numerical distributions in a dataset. Here, it is used to quantify the difference between the rate of change of each sample and the sample mean. The consideration of time intervals, by dividing by the time interval (Δt), accounts for the rate of change. This helps distinguish between fast and slow changes, because even if two changes (Δx) are the same, their effects may differ if they occur within different time intervals. The adjustment of the constant (k), k×…, allows users to adjust the sensitivity of the threshold as needed. For example, if a more sensitive threshold is desired, the value of (k) can be increased; if a less sensitive threshold is desired, the value of (k) can be decreased.

[0026] The effects of the above technical solution are as follows: by adjusting the constant (k), users can flexibly adapt to different application scenarios and needs; by considering the time interval (Δt), the formula can distinguish changes at different rates; using standard deviation as the basis for the threshold provides statistical support for the threshold setting, making it more scientific and reliable; standard deviation is a widely used statistical quantity, so the threshold designed using this formula is intuitive for understanding and interpretation. In summary, this threshold adjustment formula is designed based on standard deviation and rate of change, aiming to provide a flexible, scientific, and intuitive way to set and adjust thresholds.

[0027] One embodiment of the present invention provides an intelligent safety detection method for electrical products, which includes setting a dynamic safety threshold based on historical operating data, comparing the current operating data with the dynamic safety threshold of the electrical product's parameters and the current data of the parameters of electrical products from the same batch as the electrical product under test, comprising: Set dynamic safety thresholds based on the historical operating data of the electrical product under test; Specifically, the formula for calculating the dynamic security threshold is: ; Among them, M t It is a moving average, S t It is the weighted standard deviation, and α is the safety factor. ; Among them, M t-1 It is the moving average of the previous time step, and λ is the time decay factor (0 < λ < 1), used to control the degree of influence of historical data on the current average. ; Among them, S t-1 It is the weighted standard deviation of the previous time step. The current operating data of the electrical product under test is compared with the dynamic safety threshold of the electrical product's parameters and the current data of the parameters of electrical products from the same batch as the electrical product under test.

[0028] The following is a specific numerical example demonstrating how to calculate a dynamic safety threshold based on a given time threshold adjustment formula and determine whether the parameter value of the current electrical product exceeds the threshold.

[0029] Suppose there is an electrical product whose current parameters are recorded at consecutive time points. For simplicity, consider only the current values ​​at the first 5 time points (t=1, 2, 3, 4, 5), and assume the historical data is as follows: t = 1, x1 = 1.0 A, t = 2, x2 = 1.1 A, t = 3, x3 = 1.2 A, t = 4, x4 = 1.15 A, t = 5, x5 = (current value to be measured). Apply the time threshold adjustment formula mentioned above to calculate the dynamic safety threshold at t=5. First, the parameter values ​​in the formula need to be determined. Assume the following parameters are chosen: time decay factor (λ = 0.9), safety factor (k = 1.5). Next, calculate step by step according to the formula: initialize the moving average (M0) and weighted standard deviation (S0) to 0. For each time point (t), start the calculation from (t=1): at t = 1, , , At t = 2, , S2 ≈ 0.44 A, t = 3, M3 ≈ 0.96 A, S3 ≈ 0.33 A, t = 4, M4 ≈ 1.00 A, S4 ≈ 0.16 A, t = 5. At t=5, the measured current value is x5. We calculate the dynamic safety threshold T5: T5 = M4 + k * S4, T5 = 1.00 + 1.5 * 0.16T5 = 1.24A. As long as the measured current value x5 does not exceed 1.24A, it is considered safe.

[0030] The working principle of the above technical solution is as follows: The dynamic safety threshold design is based on the concepts of moving average and weighted standard deviation, while introducing a time decay factor and a safety factor to adapt to the characteristics of electrical product parameters that may change over time. This design has several key reasons: the dynamic safety threshold can be adjusted as data changes, thus adapting to the actual changes in electrical product parameters. Moving average and weighted standard deviation are both statistical measures based on historical data, which can capture the trend and volatility of parameter changes; the time decay factor λ is used to control the influence of historical data on the current average and standard deviation. Over time, older data gradually loses its importance, reflecting the characteristic that electrical product parameters may change over time. By introducing the weighted standard deviation S... t The algorithm considers the deviation of parameter values ​​from the moving average, thus taking into account the data dispersion when calculating the threshold. This helps stabilize the threshold and avoids unreasonable threshold settings due to individual extreme values. By adjusting the safety factor α, the leniency of the threshold relative to the moving average can be flexibly controlled. This is very useful for different application scenarios and electrical product characteristics, as different applications may require different safety thresholds. By combining moving average, weighted standard deviation, time decay factor, and safety factor, this design can comprehensively consider historical data, data dispersion, time variation, and safety requirements, thereby effectively monitoring the operating status of electrical products.

[0031] The effects of the above technical solution are as follows: The dynamic safety threshold adjustment formula designed above combines moving average, weighted standard deviation, and time decay factor. Adaptability: The moving average and weighted standard deviation in the formula can be dynamically adjusted as the data changes, thus adapting to the actual fluctuations in electrical product parameters. This means that the threshold can more accurately reflect the normal operating range and changing trends of the product. Consideration of the impact of historical data: By introducing the time decay factor λ, the formula can consider the impact of historical data on the current threshold. This helps maintain the stability and continuity of the threshold when data changes slowly or suddenly. Flexibility: The introduction of the safety factor α makes the threshold adjustment more flexible. According to the needs of actual applications, the strictness of the threshold can be controlled by adjusting the value of α, thereby meeting the safety requirements in different scenarios. Consideration of data aging effect: The role of the time decay factor λ is to gradually weaken the impact of historical data on the current threshold, which is consistent with the actual situation of data aging over time. As time goes by, the impact of older data on the current state should gradually decrease, while newer data should have a greater weight. The calculation of the weighted standard deviation considers the deviation of each data point from the moving average, which helps to reduce the impact of outliers on the threshold calculation and improve the robustness of the threshold. This formula is based on common statistics such as moving averages and standard deviations and can be implemented using existing data processing and analysis tools without requiring complex algorithms or models. In summary, this dynamic safety threshold adjustment formula offers advantages such as adaptability, flexibility, robustness, and ease of implementation, enabling it to better adapt to actual changes in electrical product parameters and provide more accurate safety assessments.

[0032] An embodiment of the present invention provides an intelligent safety detection method for electrical products, which compares the current operating data of the electrical product under test with the dynamic safety threshold of the electrical product's parameters and the current data of the parameters of electrical products from the same batch as the electrical product under test, including: First, compare the current operating data of the electrical product under test with the dynamic safety threshold of the electrical product's parameters; Next, the current operating data of the electrical product under test is compared with the current parameter data of electrical products from the same batch, and all products in the same batch are scored horizontally. Specifically, the horizontal scoring model is as follows: ; Where K1, K2, and K3 are weighting coefficients, Vc represents the current voltage of the electrical product, Va represents the average voltage of the current data of the same batch of electrical products, Tc represents the current temperature of the electrical product, Ta represents the average temperature of the current data of the same batch of electrical products, Ic represents the current temperature of the electrical product, and Ia represents the average current of the current data of the same batch of electrical products.

[0033] To determine whether a tested electrical product falls outside the top 70%, the following steps are typically required: first, calculate the scores of all products in the same batch; then, rank them according to these scores; finally, determine the ranking of the tested product. If the tested product ranks outside the top 70%, it means its performance is relatively poor and differs significantly from most products in the same batch. It's important to note that the score is a number between 0 and 1, directly reflecting the degree of difference between the tested product and other products in the same batch. The closer the score is to 1, the smaller the difference; the closer the score is to 0, the larger the difference.

[0034] The working principle of the above technical solution is as follows: First, the current operating data of the electrical product under test is collected, including key parameters such as voltage, temperature, and current. Then, this current data is compared with the previously calculated dynamic safety threshold. The dynamic safety threshold is calculated based on the moving average and weighted standard deviation, taking into account the historical data and time-varying characteristics of the electrical product parameters. If the current data of the electrical product under test exceeds the dynamic safety threshold, an alarm mechanism is triggered, indicating that there may be a problem or abnormality in the operating status of the electrical product. After confirming that the current data of the electrical product under test does not exceed the dynamic safety threshold, it is further compared with the current data of other electrical products in the same batch. The horizontal scoring model is used to quantify the differences between the electrical product under test and other products in the same batch. It considers the differences in three key parameters: voltage, temperature, and current, and uses weighting coefficients K1, K2, and K3 to adjust the impact of each parameter on the overall score. Specifically, the model calculates the absolute differences between the current voltage, temperature, and current of the electrical product under test and the average values ​​of products in the same batch, and multiplies them by the corresponding weighting coefficients. Then, these three difference values ​​are added together and subtracted from 1 to obtain the final horizontal score. A higher score indicates that the tested electrical product performs better than other products in the same batch and has a smaller difference from the average level.

[0035] The above technical solution achieves the following effects: Through dynamic safety threshold comparison, abnormal changes in electrical product parameters can be detected promptly, enabling early warning and corresponding measures to be taken to avoid potential safety risks. This comparison method is highly adaptable and stable, capable of adapting to the changing characteristics of electrical product parameters over time. The horizontal scoring model provides a quantitative assessment of the performance of electrical products within the same batch, helping to understand the relative strengths and weaknesses of products within the same batch. By comparing key parameters with the average values ​​of products in the same batch, it is possible to identify which parameters the tested electrical product performs well or poorly, providing a basis for subsequent maintenance and improvement. In summary, this technical solution, through the application of dynamic safety threshold comparison and the horizontal scoring model, improves the accuracy and flexibility of electrical product parameter monitoring, helps to promptly identify and address potential problems, and provides data support for product optimization and improvement.

[0036] One embodiment of the present invention provides an intelligent safety detection system for electrical products, the system comprising: The data acquisition module is used to acquire historical operating data, current operating data, and current operating data of parameters of electrical products under test and electrical products from the same batch as the electrical product under test. The comparison module is used to set a dynamic safety threshold based on the historical operating data, and compare the current operating data with the dynamic safety threshold of the electrical product's parameters and the current data of the parameters of electrical products from the same batch as the electrical product under test; The warning module triggers a warning mechanism if the current data of the parameters of the electrical product under test exceeds the dynamic safety threshold or if the performance score of the electrical product under test is ranked outside the top 70%. This will indicate the presence of performance degradation and safety hazards.

[0037] The working principle of the above technical solution is as follows: Collect operating data of the electrical product under test over a period of time, including voltage, current and temperature, and obtain the current real-time operating status data of the electrical product under test; at the same time, collect the current operating data of other electrical products in the same batch as the electrical product under test; Based on historical operating data, dynamic safety thresholds are set or adjusted. These thresholds can reflect the parameter range of electrical products under normal operating conditions and can be dynamically adjusted according to changes in equipment status and operating environment. The current operating data of the electrical product under test is compared with the set dynamic safety threshold to check whether any parameters exceed the safety range. At the same time, the current operating data of the electrical product under test is compared with the current data of other electrical products in the same batch to assess whether its performance is at a low level; A performance score is calculated for the electrical product under test according to a certain scoring mechanism. The performance score of the electrical product under test is compared with the performance scores of other electrical products in the same batch to determine whether its ranking is outside the top 70%. If any parameter in the current operating data of the electrical product under test exceeds the dynamic safety threshold, or if its performance score ranks outside the top 70%, the system will trigger an early warning mechanism.

[0038] The effects of the above technical solution are as follows: This solution can monitor the operating status of the electrical product under test in real time and dynamically adjust the safety threshold based on historical data and the current status, thereby improving the real-time performance and accuracy of the early warning mechanism; by comparing with electrical products of the same batch, it can more comprehensively evaluate the performance level of the electrical product under test and promptly detect potential performance degradation and safety hazards; when the parameters of the electrical product under test exceed the safety threshold or its performance score ranks low, the triggering of the early warning mechanism can promptly remind operators or automation systems to take corresponding measures to avoid potential safety accidents or performance degradation problems; with the collection and analysis of new data, this solution can continuously optimize the dynamic safety threshold, performance scoring mechanism, and early warning mechanism to adapt to changes in the operating status and environment of electrical products.

[0039] An embodiment of the present invention provides an intelligent safety detection system for electrical products, wherein the data acquisition module includes: The module for acquiring historical operating voltage, current, and temperature is used to acquire longitudinal historical operating data of the electrical product under test since its production. The parameters of the electrical product under test include the voltage, current, and temperature of the electrical product. A module for acquiring voltage, current, and temperature data of products from the same batch is used to acquire the voltage, current, and temperature of electrical products manufactured in the same batch as the electrical product under test. The current data acquisition module is used to acquire the current data of the current, voltage, and temperature of the electrical product under test. The frequency adjustment module is used to adjust the frequency of data acquisition according to the following model: ; in, This is the adjusted data collection frequency. This is the current data collection frequency. This is the set minimum data collection frequency. This is the set maximum data collection frequency. It is the threshold of the rate of change. It is the change value of the parameter. The parameter in time The rate of change.

[0040] The working principle of the above technical solution is as follows: Historical voltage, current, and temperature data of the electrical product under test (DUT) since its production are collected. This data is arranged chronologically, providing a complete picture of the product's operation. Voltage, current, and temperature data of electrical products manufactured in the same batch as the DUT are also collected. This data is used for horizontal comparison to evaluate the performance of the DUT. Real-time current, voltage, and temperature data of the DUT are acquired to assess its current operating status. The data collection frequency adjustment model adjusts the data collection frequency based on set minimum and maximum data collection frequencies, as well as thresholds for parameter changes and rates of change. When the rate of change of parameters exceeds the threshold, it indicates a significant change in the operating status of the electrical product, requiring an increase in the data collection frequency for more accurate monitoring. Therefore, the data collection frequency will be adjusted from the minimum to the maximum frequency. When the rate of change of parameters is below the threshold, it indicates a relatively stable operating status of the electrical product, allowing for a reduction in the data collection frequency to decrease the data processing burden. Therefore, the data collection frequency will be maintained or reduced to the minimum frequency.

[0041] The beneficial effects of the above technical solution are as follows: Resource optimization: When the data change rate is low, a high data collection frequency may not be necessary. By reducing the frequency to a minimum, system resources such as processor time, memory, and storage space can be saved, which is especially important in systems that operate for long periods or are resource-constrained. Reduction of noise and redundant data: When the data change rate is low, frequent data collection may result in the collection of a large number of similar or duplicate data points, which may not contain much useful information. Reducing the data collection frequency can reduce this noise and redundant data, improving data quality. Extended equipment lifespan: For some physical equipment, frequent data collection may increase wear and tear. Reducing the data collection frequency can extend the lifespan of these devices, reducing the frequency of maintenance and replacement. Maintaining a low data collection frequency when the data change rate is low ensures that the system has sufficient responsiveness to sudden data changes. If the data change rate suddenly increases, the system can quickly increase the data collection frequency to capture these changes. This design allows the system to dynamically adjust its behavior according to the data change rate, thereby adapting to different data patterns and needs. This adaptability allows the system to remain efficient and effective under various conditions. In summary, when the data change rate is low and the current frequency is already at its maximum, choosing a design that maintains the minimum frequency helps optimize resource utilization, reduce noise data, extend equipment life, improve responsiveness, and enhance system adaptability. By collecting all historical data of the electrical product under test since its production, a comprehensive analysis of its long-term operating trends and performance changes can be conducted, helping to identify potential performance degradation and safety hazards. Dynamically adjusting the data collection frequency based on the parameter change rate and thresholds ensures that more data can be acquired in a timely manner when the operating status of the electrical product changes significantly, while reducing the data collection frequency when the operating status is stable, thereby achieving real-time and flexible data collection. By comparing data with that of electrical products in the same batch, the performance of the electrical product under test under the same conditions can be evaluated, performance differences with other products in the same batch can be identified in a timely manner, and a basis for maintenance and optimization can be provided.

[0042] One example of the present invention is an intelligent safety detection system for electrical products, characterized in that the frequency adjustment module includes: The rate of change threshold calculation module is used to calculate the threshold for the rate of change. The formula for calculating the rate of change threshold is: ; Where k is a user-defined factor used to adjust the sensitivity of the threshold, n is the number of data change rate samples, and μ is the mean of the data change rate.

[0043] The working principle of the above technical solution is as follows: Standard deviation is a statistic that measures the dispersion of numerical distributions in a dataset. Here, it is used to quantify the difference between the rate of change of each sample and the sample mean; the consideration of time intervals, by dividing by the time interval (Δt), accounts for the rate of change. This helps to distinguish between fast and slow changes, because even if two changes (Δx) are the same, their effects may be different if they occur within different time intervals; the adjustment of the constant (k), k×…, allows users to adjust the sensitivity of the threshold as needed. For example, if a more sensitive threshold to change is desired, the value of (k) can be increased; if a less sensitive threshold to change is desired, the value of (k) can be decreased.

[0044] The effects of the above technical solution are as follows: by adjusting the constant (k), users can flexibly adapt to different application scenarios and needs; by considering the time interval (Δt), the formula can distinguish changes at different rates; using standard deviation as the basis for the threshold provides statistical support for the threshold setting, making it more scientific and reliable; standard deviation is a widely used statistical quantity, so the threshold designed using this formula is intuitive for understanding and interpretation. In summary, this threshold adjustment formula is designed based on standard deviation and rate of change, aiming to provide a flexible, scientific, and intuitive way to set and adjust thresholds.

[0045] According to one embodiment of the present invention, an intelligent safety detection system for electrical products includes a comparison module comprising: The dynamic safety threshold setting module is used to set dynamic safety thresholds based on the historical operating data of the electrical product under test. Specifically, the formula for calculating the dynamic security threshold is: ; Among them, M t It is a moving average, S t It is the weighted standard deviation, and α is the safety factor. ; Among them, M t-1 It is the moving average of the previous time step, and λ is the time decay factor (0 < λ < 1), used to control the degree of influence of historical data on the current average. ; Among them, S t-1 It is the weighted standard deviation of the previous time step. The comparison module is used to compare the current operating data of the electrical product under test with the dynamic safety threshold of the electrical product's parameters and the current data of the parameters of electrical products from the same batch as the electrical product under test.

[0046] The working principle of the above technical solution is as follows: The dynamic safety threshold design is based on the concepts of moving average and weighted standard deviation, while introducing a time decay factor and a safety factor to adapt to the characteristics of electrical product parameters that may change over time. There are several key reasons for this design: the dynamic safety threshold can be adjusted as data changes, thus adapting to the actual changes in electrical product parameters. Moving average and weighted standard deviation are both statistical measures based on historical data, which can capture the trend and volatility of parameter changes; the time decay factor λ is used to control the influence of historical data on the current average and standard deviation. Over time, older data gradually loses its importance, reflecting the characteristic that electrical product parameters may change over time. By introducing the weighted standard deviation St, the algorithm considers the deviation of parameter values ​​from the moving average, thus taking into account the dispersion of data when calculating the threshold. This helps stabilize the threshold and avoid unreasonable threshold settings due to individual extreme values. By adjusting the safety factor α, the leniency of the threshold relative to the moving average can be flexibly controlled. This is very useful for different application scenarios and electrical product characteristics, as different applications may require different safety thresholds. By combining moving average, weighted standard deviation, time decay factor and safety factor, this design can comprehensively consider historical data, data dispersion, time variation and safety requirements, thereby effectively monitoring the operating status of electrical products.

[0047] The effects of the above technical solution are as follows: The dynamic safety threshold adjustment formula designed above combines moving average, weighted standard deviation, and time decay factor. Adaptability: The moving average and weighted standard deviation in the formula can be dynamically adjusted as the data changes, thus adapting to the actual fluctuations in electrical product parameters. This means that the threshold can more accurately reflect the normal operating range and changing trends of the product. Consideration of the impact of historical data: By introducing the time decay factor λ, the formula can consider the impact of historical data on the current threshold. This helps maintain the stability and continuity of the threshold when data changes slowly or suddenly. Flexibility: The introduction of the safety factor α makes the threshold adjustment more flexible. According to the needs of actual applications, the strictness of the threshold can be controlled by adjusting the value of α, thereby meeting the safety requirements in different scenarios. Consideration of data aging effect: The role of the time decay factor λ is to gradually weaken the impact of historical data on the current threshold, which is consistent with the actual situation of data aging over time. As time goes by, the impact of older data on the current state should gradually decrease, while newer data should have a greater weight. The calculation of the weighted standard deviation considers the deviation of each data point from the moving average, which helps to reduce the impact of outliers on the threshold calculation and improve the robustness of the threshold. This formula is based on common statistics such as moving averages and standard deviations and can be implemented using existing data processing and analysis tools without requiring complex algorithms or models. In summary, this dynamic safety threshold adjustment formula offers advantages such as adaptability, flexibility, robustness, and ease of implementation, enabling it to better adapt to actual changes in electrical product parameters and provide more accurate safety assessments.

[0048] According to one embodiment of the present invention, an intelligent safety detection system for electrical products includes a dynamic comparison module comprising: The dynamic threshold comparison module is used to first compare the current operating data of the electrical product under test with the dynamic safety threshold of the electrical product's parameters; The horizontal comparison module is used to compare the current operating data of the electrical product under test with the current parameter data of electrical products in the same batch, and to perform a horizontal scoring of all products in the same batch. Specifically, the horizontal scoring model is as follows: ; Where K1, K2, and K3 are weighting coefficients, Vc represents the current voltage of the electrical product, Va represents the average voltage of the current data of the same batch of electrical products, Tc represents the current temperature of the electrical product, Ta represents the average temperature of the current data of the same batch of electrical products, Ic represents the current temperature of the electrical product, and Ia represents the average current of the current data of the same batch of electrical products.

[0049] The working principle of the above technical solution is as follows: First, the current operating data of the electrical product under test is collected, including key parameters such as voltage, temperature, and current. Then, this current data is compared with the previously calculated dynamic safety threshold. The dynamic safety threshold is calculated based on the moving average and weighted standard deviation, taking into account the historical data and time-varying characteristics of the electrical product parameters. If the current data of the electrical product under test exceeds the dynamic safety threshold, an alarm mechanism is triggered, indicating that there may be a problem or abnormality in the operating status of the electrical product. After confirming that the current data of the electrical product under test does not exceed the dynamic safety threshold, it is further compared with the current data of other electrical products in the same batch. The horizontal scoring model is used to quantify the differences between the electrical product under test and other products in the same batch. It considers the differences in three key parameters: voltage, temperature, and current, and uses weighting coefficients K1, K2, and K3 to adjust the impact of each parameter on the overall score. Specifically, the model calculates the absolute differences between the current voltage, temperature, and current of the electrical product under test and the average values ​​of products in the same batch, and multiplies them by the corresponding weighting coefficients. Then, these three difference values ​​are added together and subtracted from 1 to obtain the final horizontal score. A higher score indicates that the tested electrical product performs better than other products in the same batch and has a smaller difference from the average level.

[0050] The above technical solution achieves the following effects: Through dynamic safety threshold comparison, abnormal changes in electrical product parameters can be detected promptly, enabling early warning and corresponding measures to be taken to avoid potential safety risks. This comparison method is highly adaptable and stable, capable of adapting to the changing characteristics of electrical product parameters over time. The horizontal scoring model provides a quantitative assessment of the performance of electrical products within the same batch, helping to understand the relative strengths and weaknesses of products within the same batch. By comparing key parameters with the average values ​​of products in the same batch, it is possible to identify which parameters the tested electrical product performs well or poorly, providing a basis for subsequent maintenance and improvement. In summary, this technical solution, through the application of dynamic safety threshold comparison and the horizontal scoring model, improves the accuracy and flexibility of electrical product parameter monitoring, helps to promptly identify and address potential problems, and provides data support for product optimization and improvement.

[0051] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for intelligent safety detection of electrical products, characterized in that, The method includes: Acquire historical operating data, current operating data, and current operating data of parameters of electrical products from the same batch as the electrical product under test; Based on the historical operating data, a dynamic safety threshold is set, and the current operating data is compared with the dynamic safety threshold of the electrical product's parameters and the current data of the parameters of electrical products from the same batch as the electrical product under test. If the current data of the parameters of the electrical product under test exceeds the dynamic safety threshold or the performance score of the electrical product under test is outside the top 70%, the system triggers an early warning mechanism to indicate that there is a performance degradation and safety hazard.

2. The intelligent safety detection method for electrical products according to claim 1, characterized in that, Obtain historical operating data, current operating data, and current operating data of parameters of electrical products from the same batch as the electrical product under test, including: Acquire the longitudinal historical operating data of the electrical product under test since its production, including the voltage, current and temperature of the electrical product under test; Obtain the voltage, current, and temperature of electrical products manufactured in the same batch as the electrical product under test; Acquire the current data of the current, voltage, and temperature of the electrical product under test. The frequency of data acquisition is adjusted according to the following model: ； in, This is the adjusted data collection frequency. This is the current data collection frequency. This is the set minimum data collection frequency. This is the set maximum data collection frequency. It is the threshold of the rate of change. It is the change value of the parameter. The parameter in time The rate of change.

3. The intelligent safety detection method for electrical products according to claim 2, characterized in that, The threshold for the rate of change includes: The threshold formula for the rate of change is: ； Where k is a user-defined factor used to adjust the sensitivity of the threshold, n is the number of data change rate samples, and μ is the mean of the data change rate.

4. The intelligent safety detection method for electrical products according to claim 1, characterized in that, Based on the historical operating data, a dynamic safety threshold is set, and the current operating data is compared with the dynamic safety threshold of the electrical product's parameters and the current data of the parameters of electrical products from the same batch as the electrical product under test, including: Set dynamic safety thresholds based on the historical operating data of the electrical product under test; Specifically, the formula for calculating the dynamic security threshold is as follows: ； Among them, M t It is a moving average, S t It is the weighted standard deviation, and α is the safety factor. ； Among them, M t-1 It is the moving average of the previous time step, and λ is the time decay factor (0 < λ < 1), used to control the degree of influence of historical data on the current average. ； Among them, S t-1 It is the weighted standard deviation of the previous time step. The current operating data of the electrical product under test is compared with the dynamic safety threshold of the electrical product's parameters and the current data of the parameters of electrical products from the same batch as the electrical product under test.

5. The intelligent safety detection method for electrical products according to claim 4, characterized in that, The current operating data of the electrical product under test is compared with the dynamic safety threshold of the electrical product's parameters and the current data of parameters of electrical products from the same batch as the electrical product under test, including: First, compare the current operating data of the electrical product under test with the dynamic safety threshold of the electrical product's parameters; Next, the current operating data of the electrical product under test is compared with the current parameter data of electrical products from the same batch, and all products in the same batch are scored horizontally. Specifically, the horizontal scoring model is as follows: ； Where K1, K2, and K3 are weighting coefficients, Vc represents the current voltage of the electrical product, Va represents the average voltage of the current data of the same batch of electrical products, Tc represents the current temperature of the electrical product, Ta represents the average temperature of the current data of the same batch of electrical products, Ic represents the current temperature of the electrical product, and Ia represents the average current of the current data of the same batch of electrical products.

6. An intelligent safety detection system for electrical products, characterized in that, The system includes: The data acquisition module is used to acquire historical operating data, current operating data, and current operating data of parameters of electrical products under test and electrical products from the same batch as the electrical product under test. The comparison module is used to set a dynamic safety threshold based on the historical operating data, and compare the current operating data with the dynamic safety threshold of the electrical product's parameters and the current data of the parameters of electrical products from the same batch as the electrical product under test; The warning module triggers a warning mechanism if the current data of the parameters of the electrical product under test exceeds the dynamic safety threshold or if the performance score of the electrical product under test is ranked outside the top 70%. This will indicate the presence of performance degradation and safety hazards.

7. The intelligent safety detection system for electrical products according to claim 6, characterized in that, The data acquisition module includes: The module for acquiring historical operating voltage, current, and temperature is used to acquire longitudinal historical operating data of the electrical product under test since its production. The parameters of the electrical product under test include the voltage, current, and temperature of the electrical product. A module for acquiring voltage, current, and temperature data of products from the same batch is used to acquire the voltage, current, and temperature of electrical products manufactured in the same batch as the electrical product under test. The current data acquisition module is used to acquire the current data of the current, voltage, and temperature of the electrical product under test. The frequency adjustment module is used to adjust the frequency of data acquisition according to the following model: ； in, This is the adjusted data collection frequency. This is the current data collection frequency. This is the set minimum data collection frequency. This is the set maximum data collection frequency. It is the threshold of the rate of change. It is the change value of the parameter. The parameter in time The rate of change.

8. The intelligent safety detection system for electrical products according to claim 7, characterized in that, The frequency adjustment module includes: The rate of change threshold calculation module is used to calculate the threshold for the rate of change. The formula for calculating the rate of change threshold is: ； Where k is a user-defined factor used to adjust the sensitivity of the threshold, n is the number of data change rate samples, and μ is the mean of the data change rate.

9. The intelligent safety detection system for electrical products according to claim 6, characterized in that, The comparison module includes: The dynamic safety threshold setting module is used to set dynamic safety thresholds based on the historical operating data of the electrical product under test. Specifically, the formula for calculating the dynamic security threshold is as follows: ； Among them, M t It is a moving average, S t It is the weighted standard deviation, and α is the safety factor. ； Among them, M t-1 It is the moving average of the previous time step, and λ is the time decay factor (0 < λ < 1), used to control the degree of influence of historical data on the current average. ； Among them, S t-1 It is the weighted standard deviation of the previous time step. The comparison module is used to compare the current operating data of the electrical product under test with the dynamic safety threshold of the electrical product's parameters and the current data of the parameters of electrical products from the same batch as the electrical product under test.

10. The intelligent safety detection system for electrical products according to claim 9, characterized in that, The dynamic comparison module includes: The dynamic threshold comparison module is used to first compare the current operating data of the electrical product under test with the dynamic safety threshold of the electrical product's parameters; The horizontal comparison module is used to compare the current operating data of the electrical product under test with the current parameter data of electrical products in the same batch, and to perform a horizontal scoring of all products in the same batch. Specifically, the horizontal scoring model is as follows: ； Where K1, K2, and K3 are weighting coefficients, Vc represents the current voltage of the electrical product, Va represents the average voltage of the current data of the same batch of electrical products, Tc represents the current temperature of the electrical product, Ta represents the average temperature of the current data of the same batch of electrical products, Ic represents the current temperature of the electrical product, and Ia represents the average current of the current data of the same batch of electrical products.

Images