Electromagnetic environment detection system and method of blade server

Abstract

The invention discloses an electromagnetic environment detection system and method for a blade server. The electromagnetic environment detection system comprises a conducted interference monitoring board integrated in the server. The conducted interference monitoring board comprises an interference extraction unit, a single-chip microcomputer and a state indicating lamp. The input end of the interference extraction unit is connected with a live wire and a zero wire of a power supply filter in a server case, and extracts an electric signal representing conducted interference intensity from a power supply line; the single chip microcomputer performs digital signal processing on the electric signal, compares an obtained interference comprehensive value with a preset threshold value, and judges the state grade of electromagnetic interference; the state indicating lamp is connected with a GPIO port of the single-chip microcomputer and indicates corresponding interference states in different flicker modes. Real-time monitoring, intelligent evaluation and graded early warning of conducted interference of a power supply line are achieved, passive post-restart emergency processing is converted into active pre-interference protection, and stable operation of a blade server and continuous execution of key tasks under the maneuvering deployment condition are effectively guaranteed.

Description

Technical Field

[0001] This application relates to the field of servers, and more particularly to an electromagnetic environment detection system and method for blade servers. Background Technology

[0002] With the continuous improvement of information technology, blade servers are widely used in mobile equipment such as high-performance radar due to their advantages of high density and easy deployment. However, during mobile deployment, the variable power supply environment can introduce complex power grid conducted noise. This interference is sporadic and random, which can easily cause blade servers to experience difficult-to-reproduce failures such as abnormal startup and operation interruption.

[0003] Currently, the lack of effective real-time monitoring methods for electromagnetic interference in the server operating environment is the root cause of the difficulty in resolving the above problems. Because it is impossible to predict when the interference will occur or its intensity, operators can only take reactive restart measures after the server malfunctions. In radar monitoring tasks with extremely high real-time requirements, this reactive restart operation is highly likely to cause the loss of critical target information, leading to mission failure. Summary of the Invention

[0004] This application provides an electromagnetic environment detection system and method for blade servers, which solves the problem that critical tasks are interrupted due to the lack of real-time monitoring and early warning means for conducted interference in power supply lines, and can only be interrupted by passively restarting the server.

[0005] In a first aspect, this application provides an electromagnetic environment detection system for a blade server, comprising: Conducted interference monitoring board, integrated into the blade server, is used to monitor the intensity of conducted interference on the blade server's power supply line; the conducted interference monitoring board includes an interference extraction unit, a microcontroller, and status indicator lights; The input of the interference extraction unit is connected to the live and neutral wires of the power filter inside the blade server chassis, and is used to extract electrical signals that characterize the intensity of conducted interference from the power supply line. The microcontroller is connected to the output of the interference extraction unit to perform digital signal processing on the electrical signal and compare the comprehensive interference value obtained from the digital signal processing with a preset threshold to determine the state level of the electromagnetic interference corresponding to the intensity of conducted interference. The status indicator light is connected to the GPIO port of the microcontroller and is controlled by the microcontroller to indicate the interference status corresponding to the status level through different flashing patterns.

[0006] Secondly, this application provides a method for detecting the electromagnetic environment of a blade server, comprising: The interference extraction unit extracts electrical signals characterizing the intensity of conducted interference from the power supply lines of the blade server. The electrical signal is digitally processed by a microcontroller to determine the comprehensive interference value corresponding to the electrical signal. The overall interference value is compared with a preset threshold to determine the state level of electromagnetic interference corresponding to the intensity of conducted interference. Depending on the status level, the control status indicator lights are displayed in the corresponding visual mode.

[0007] This application provides an electromagnetic environment detection system and method for blade servers, comprising: a conducted interference monitoring board, integrated into the blade server, for monitoring the conducted interference intensity on the power supply line of the blade server; the conducted interference monitoring board includes an interference extraction unit, a microcontroller, and status indicator lights; the input terminal of the interference extraction unit is connected to the live and neutral wires of the power filter inside the blade server chassis, for extracting electrical signals characterizing the conducted interference intensity from the power supply line; the microcontroller is connected to the output terminal of the interference extraction unit, for performing digital signal processing on the electrical signals, and comparing the comprehensive interference value obtained from the digital signal processing with a preset threshold to determine the state level of electromagnetic interference corresponding to the conducted interference intensity; the status indicator lights are connected to the GPIO port of the microcontroller, and are controlled by the microcontroller to indicate the interference state corresponding to the state level with different flashing patterns. This system achieves real-time monitoring, intelligent assessment, and graded early warning of conducted interference on the power supply line, transforming passive post-event restart emergency handling into proactive pre-event interference protection, effectively ensuring the stable operation of the blade server and the continuous execution of critical tasks under mobile deployment conditions.

[0008] The further effects of the aforementioned non-conventional preferred method will be explained below in conjunction with specific embodiments. Attached Figure Description

[0009] To more clearly illustrate the embodiments of this application or the existing technical solutions, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 A schematic diagram of the structure of an electromagnetic environment detection system for a blade server provided in an embodiment of this application; Figure 2 A schematic diagram of the structure of a conducted interference monitoring board in an electromagnetic environment detection system for a blade server, provided in an embodiment of this application; Figure 3 A schematic diagram of the interference extraction unit in the conducted interference monitoring board of an electromagnetic environment detection system for a blade server, provided in an embodiment of this application; Figure 4 This is a flowchart illustrating an electromagnetic environment detection method for a blade server provided in one embodiment of this application. Detailed Implementation

[0011] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0012] With the continuous improvement of information technology, blade servers are widely used in mobile equipment such as high-performance radar due to their advantages of high density and easy deployment. However, during mobile deployment, the variable power supply environment can introduce complex power grid conducted noise. This interference is sporadic and random, which can easily cause blade servers to experience difficult-to-reproduce failures such as abnormal startup and operation interruption.

[0013] Currently, the lack of effective real-time monitoring methods for electromagnetic interference in the server operating environment is the root cause of the difficulty in resolving the above problems. Because it is impossible to predict when the interference will occur or its intensity, operators can only take reactive restart measures after the server malfunctions. In radar monitoring tasks with extremely high real-time requirements, this reactive restart operation is highly likely to cause the loss of critical target information, leading to mission failure.

[0014] To address this issue, this application proposes an electromagnetic environment detection system for blade servers. This system aims to solve the problem of critical task interruptions caused by the lack of real-time monitoring and early warning methods for conducted interference in power lines, which necessitates passive server restarts. See also... Figure 1 The image shows a specific embodiment of the electromagnetic environment detection system for a blade server provided in this application. In this embodiment, the electromagnetic environment detection system for a blade server includes: a conducted interference monitoring board 11, which is integrated into the blade server and used to monitor the conducted interference intensity on the power supply line of the blade server.

[0015] The conducted interference monitoring board 11 adopts a modular design, allowing it to be directly installed inside the blade server chassis without altering the original server's physical structure and internal layout. The conducted interference monitoring board 11 connects to the server's power supply line via a dedicated interface, enabling real-time and continuous monitoring of the power supply environment. This integrated design not only ensures the accuracy and real-time nature of the monitoring but also avoids the need for additional external devices, aligning with the highly integrated and space-efficient design philosophy of blade servers. It is particularly suitable for mobile deployment environments with limited space, such as radar shelters.

[0016] The conducted interference monitoring board 11 includes an interference extraction unit 111, a microcontroller 112, and status indicator lights 113. For example... Figure 2 The diagram shown is a schematic diagram of the structure of the conducted interference monitoring board 11 in the electromagnetic environment detection system of the blade server in this embodiment.

[0017] The interference extraction unit 111, microcontroller 112, and status indicator 113 form a complete monitoring and early warning closed loop: the interference extraction unit 111 is responsible for extracting electrical signals characterizing the interference intensity from the power supply line; the microcontroller 112 performs digital processing and intelligent analysis on the extracted signals; and the status indicator 113 presents the analysis results to the operator in an intuitive visual manner. The entire monitoring board adopts a low-power design, powered through the backplane, with a power consumption of only a few watts, having minimal impact on the overall power supply system of the server.

[0018] The input of the interference extraction unit 111 is connected to the live and neutral wires of the power filter inside the blade server chassis, and is used to extract electrical signals characterizing the intensity of conducted interference from the power supply line.

[0019] The input of the interference extraction unit 111 is connected to the live and neutral wires of the power filter inside the blade server chassis. It can directly acquire the voltage signal from the power filter's output. This location encompasses various interference components conducted from the power grid and is situated at a critical node in the server's power supply, accurately reflecting the electromagnetic environment the server faces during actual operation. By simultaneously monitoring differential-mode and common-mode interference on the live and neutral wires, the interference characteristics on the power supply line can be comprehensively understood. The interference extraction unit 111 employs a high-impedance input design, resulting in negligible impact on the power supply line. It does not alter the original electrical characteristics of the power supply system, ensuring that the server's normal operation is unaffected by the monitoring system.

[0020] The interference extraction unit 111 includes: a bridge rectifier circuit 1111, an interference extraction circuit 1112, an attenuation adjustment circuit 1113, and an emitter follower 1114; the bridge rectifier circuit 1111, the interference extraction circuit 1112, the attenuation adjustment circuit 1113, and the emitter follower 1114 are connected in sequence. Figure 3 The diagram shown is a schematic of the interference extraction unit 111 in the conducted interference monitoring board 11 of the electromagnetic environment detection system of the blade server in this embodiment.

[0021] The bridge rectifier circuit 1111, interference extraction circuit 1112, attenuation adjustment circuit 1113, and emitter follower 1114 form a complete signal processing link, with each module undertaking a specific signal conditioning function. The signal starts from the AC power supply, undergoes progressive processing and optimization, and is ultimately converted into a standard electrical signal suitable for digital sampling and analysis by the microcontroller. The entire signal link uses analog circuit design, featuring fast response speed, wide bandwidth, and low distortion. It can accurately capture various interference components ranging from power frequency to hundreds of kilohertz, providing high-quality raw data for subsequent digital signal processing.

[0022] The bridge rectifier circuit 1111 is used to convert the AC power input to the blade server into unidirectional pulsating DC power.

[0023] The bridge rectifier circuit 1111 employs four high-speed rectifier diodes to form a full-wave rectifier topology, capable of converting both the positive and negative half-cycles of a sinusoidal alternating current into pulsating direct current of the same polarity, thus preserving all interference information in the original AC signal. Compared to half-wave rectification, this full-wave rectification method not only has higher conversion efficiency but also ensures that the integrity of the interference signal is not compromised. Schottky diodes with low forward voltage drop and short reverse recovery time are selected as the rectifier diodes, enabling accurate response to high-frequency interference components and avoiding signal distortion caused by poor diode characteristics. The unidirectional pulsating direct current output after rectification contains both the fundamental frequency component of the power supply and various frequency interference harmonics, creating conditions for subsequent interference extraction.

[0024] Interference extraction circuit 1112 is used to determine high-frequency interference components from unidirectional pulsating direct current, so as to determine the corresponding interference signal based on the high-frequency interference components.

[0025] The interference extraction circuit 1112 employs a high-pass filter principle, using a combination of capacitors and resistors to selectively allow different frequency components to pass through. The capacitor presents high impedance to DC and low-frequency components, effectively blocking the power supply's fundamental frequency; while it presents low impedance to high-frequency interference components, allowing them to pass smoothly. The resistor divides the voltage across all frequency components, controlling the signal amplitude within a reasonable range. By carefully selecting the parameter values ​​of the capacitor and resistor, the cutoff frequency can be set to several kilohertz, effectively extracting the most destructive high-frequency components of conducted interference from the power grid. These high-frequency interferences are often the main cause of server malfunctions, making their focused monitoring crucial. The amplitude of the extracted interference signal is proportional to the interference intensity, providing a basis for subsequent quantitative analysis.

[0026] The attenuation adjustment circuit 1113 is used to adjust the amplitude of the interference signal so that the interference signal is adapted to the processing range of the microcontroller 112.

[0027] The attenuation adjustment circuit 1113 employs a resistor voltage divider network to achieve precise control of the signal amplitude. Through the series voltage division of two high-precision resistors, the amplitude range of the interference signal is adjusted to between 0 and 3.3V, perfectly matching the input range of the on-chip AD converter of the microcontroller 112. This attenuation adjustment must ensure that the signal amplitude does not exceed the upper voltage limit of the microcontroller 112 to avoid damage, while also ensuring that the signal amplitude is large enough to fully utilize the quantization bits of the AD converter, improving measurement accuracy and signal-to-noise ratio. Metal film resistors with low temperature coefficients and high precision are selected to ensure that the attenuation ratio remains stable under different operating temperatures.

[0028] Emitter follower 1114 is used to impedance match interference signals to generate electrical signals.

[0029] The emitter follower 1114 is built using a wideband operational amplifier and configured as a voltage follower, featuring high input impedance and low output impedance. The high input impedance ensures minimal load on the preceding attenuation adjustment circuit, maintaining the voltage division ratio and guaranteeing signal amplitude accuracy. The low output impedance provides sufficient drive capability for the subsequent ADC of the microcontroller 112, ensuring stable voltage during sampling and preventing signal degradation due to charging of the sampling capacitor. The emitter follower 1114 also acts as a buffer, effectively isolating the preceding analog signal processing circuit from the subsequent digital circuit, preventing switching noise from the digital circuit from coupling to the sensitive analog front-end through the power supply or ground, thus affecting measurement accuracy.

[0030] The microcontroller 112 is connected to the output of the interference extraction unit 111 and is used to perform digital signal processing on the electrical signal. The integrated interference value obtained by digital signal processing is compared with a preset threshold to determine the state level of electromagnetic interference corresponding to the intensity of conducted interference.

[0031] The 112 microcontroller is selected from models equipped with a high-precision AD converter. The AD converter employs a successive approximation architecture with 12-bit resolution, capable of quantizing analog voltages from 0 to 3.3V into 4096 discrete levels, enabling accurate measurement of weak interference signals. The 112 microcontroller integrates a wealth of digital signal processing peripherals, including hardware multipliers and DMA controllers, allowing for efficient execution of complex mathematical operations and data transfer processes.

[0032] The 112 microcontroller operates at a clock frequency of tens of megahertz, possessing sufficient computing power to perform real-time signal analysis tasks. Through its on-chip timer resources, the microcontroller can precisely control the timing of AD sampling, achieving a high-speed sampling rate of 500kHz to meet the requirements for capturing high-frequency interference components. The acquired raw data is stored in the microcontroller's RAM, and software algorithms perform multi-dimensional feature extraction and comprehensive evaluation, ultimately generating a quantified interference composite value. This value comprehensively reflects the quality of the current electromagnetic environment.

[0033] The electrical signal is sampled to obtain the original data corresponding to the electrical signal; the waveform average component, pulsating fundamental frequency, and waveform variance based on the pulsating fundamental frequency are calculated for the original data; the original data is analyzed in the frequency domain using the FFT algorithm to obtain the corresponding frequency domain features; based on the waveform average component, pulsating fundamental frequency, waveform variance, and frequency domain features, a comprehensive interference value is generated using a preset evaluation algorithm.

[0034] Specifically, the microcontroller 112 first continuously acquires signal data for a certain duration at a sampling rate of 500kHz, forming a data sequence containing thousands of sampling points. Then, it calculates the arithmetic mean of these sampling points to obtain the waveform average component, which reflects the DC bias level of the signal. Next, it performs fundamental frequency analysis on the raw data, extracting the 100Hz or 120Hz power frequency fundamental frequency component through digital filtering or correlation operations. This component represents the main energy of the power supply. Using the pulsating fundamental frequency as a reference, it calculates the variance of each sampling point's deviation from the fundamental frequency, obtaining the waveform variance. The waveform variance reflects the degree of waveform distortion caused by interference; a larger variance indicates more severe interference.

[0035] To obtain the spectral distribution characteristics of the interference, the microcontroller 112 performs a Fast Fourier Transform (FFT) operation on the original data, converting the time-domain signal to the frequency domain to obtain the amplitude and phase information of each frequency component. By analyzing the distribution of the frequency domain spectral lines, it is possible to identify which frequency bands contain significant interference energy, which is of great reference value for judging the source of interference and selecting a filtering scheme. Finally, the microcontroller 112 performs a weighted summation or nonlinear operation on the waveform average component, pulsating fundamental frequency, waveform variance, and frequency domain characteristics according to pre-calibrated weighting coefficients to generate a comprehensive evaluation index, namely the comprehensive interference value. This comprehensive value considers not only the magnitude of the interference but also its frequency distribution and waveform distortion characteristics, enabling a more comprehensive and accurate reflection of the electromagnetic environment quality and avoiding misjudgments that may be caused by a single index.

[0036] The conducted interference monitoring board 11 also includes a communication interface; when the electromagnetic interference is in an excessive or critical state, the microcontroller 112 sends an alarm message to the chassis management unit of the blade server through the communication interface.

[0037] The communication interface is designed according to industry standard protocols to ensure interoperability with various functional units within the server. When the microcontroller 112 detects that the overall interference value exceeds a preset critical threshold or exceedance threshold, it immediately generates an alarm data packet containing key information such as a timestamp, overall interference value, and status level code. This information is sent to the chassis management unit via the communication interface. The chassis management unit, as the central management node of the server, is responsible for summarizing the status information of each monitoring board and reporting it to the external display and control system through a higher-level network interface.

[0038] Alarm messages are typically sent using a periodic repetition mechanism, once every 5 seconds, until the electromagnetic environment returns to normal. This continuous alarm strategy ensures that operators do not miss important abnormal information due to accidental negligence. Simultaneously, the communication interface supports bidirectional communication, allowing operators to send parameter configuration commands to the monitoring board via host computer software, such as adjusting thresholds and modifying sampling frequencies, enabling flexible configuration and remote management of the monitoring system.

[0039] The communication interface is an IIC interface; the conducted interference monitoring board 11 is connected to the backplane IIC bus of the blade server via the IIC interface; the backplane IIC bus is connected to the chassis management unit; the chassis management unit is configured to forward alarm information to the radar display and control computer corresponding to the blade server via the network.

[0040] The IIC interface is a mature serial communication bus with advantages such as simple interface, few pins, and support for multiple masters and slaves, making it ideal for use in space-constrained blade server environments. The conducted interference monitoring board 11, as a slave device on the IIC bus, connects to the IIC bus on the backplane via the serial data line SDA and the serial clock line SCL. The backplane IIC bus serves as the common communication channel for all functional boards within the server. The chassis management unit, as the master device on the IIC bus, periodically polls the status of each slave device or responds to interrupt requests initiated by slave devices.

[0041] When the conducted interference monitoring board 11 has alarm information to report, it transmits the data to the chassis management unit via the IIC interface. Upon receiving the alarm information, the chassis management unit encapsulates it into UDP or TCP packets via its built-in Ethernet controller and sends them to the designated multicast or unicast address via a gigabit Ethernet port. The radar display and control computer, acting as the upper-level monitoring system, runs dedicated monitoring software to listen for alarm messages on the network in real time. Once it receives an alarm from the chassis management unit, the display and control software immediately updates the electromagnetic environment status indicator on the graphical interface, changing the green icon for normal status to yellow for critical status or red for exceeding limits, and simultaneously pops up a text prompt window to remind operators to take appropriate measures. This layered forwarding communication architecture ensures both the lightweight design of the monitoring board and the rapid uploading and visualization of alarm information, forming a complete information loop from bottom-level monitoring to top-level decision-making.

[0042] The status indicator 113 is connected to the GPIO port of the microcontroller 112 and is controlled by the microcontroller 112 to indicate the interference status corresponding to the status level in different flashing modes.

[0043] The status indicator 113 is actually a high-brightness LED, installed on the front panel of the monitoring board, making it clearly visible to operators in front of the cabinet. The anode of the LED is connected to the positive terminal of the power supply via a current-limiting resistor, and the cathode is connected to the GPIO output port of the microcontroller. The microcontroller 112 controls the LED's on / off state by controlling the output level of the GPIO port.

[0044] When the GPIO output is low, the LED is on and illuminated; when the GPIO output is high, the LED is off. The microcontroller 112 uses a software timer to precisely control the toggling timing of the GPIO port, achieving different blinking patterns with varying periods and duty cycles. This visual indication method provides operators with the most intuitive and rapid fault alarm method. Even in the event of network communication failure or host computer system malfunction, operators can still promptly detect electromagnetic environment anomalies and take emergency measures by observing the LED's blinking status.

[0045] The status indicator 113 is configured to indicate the status level through three visual modes; the status level includes normal state, critical state and excessive state, and the visual modes include: first flashing mode, second flashing mode and off mode; the first flashing mode indicates that the electromagnetic interference is in an excessive state; the second flashing mode indicates that the electromagnetic interference is in a critical state; and the off mode indicates that the electromagnetic interference is in a normal state.

[0046] This method discretizes continuously changing interference intensity into three distinct state levels, facilitating rapid judgment and decision-making by operators. The normal state indicates a good electromagnetic environment with the overall interference value below the critical threshold, allowing the server to operate safely and stably. In this state, the LED remains off, without any alarm. The critical state indicates that the electromagnetic environment is beginning to deteriorate, with the overall interference value between the critical and exceeding thresholds. Although it has not yet significantly affected the server, it is approaching a danger zone, requiring operator attention and preparedness. In this state, the LED flashes in a second-order warning mode. The exceeding-threshold state indicates a severely degraded electromagnetic environment with the overall interference value exceeding the exceeding threshold. The server may malfunction at any time, requiring immediate interference suppression measures. In this state, the LED flashes in a first-order emergency alarm mode. Through different flashing rhythms, operators can identify the current state level from several meters away without needing to approach for close observation, greatly improving the effectiveness and timeliness of the alarm.

[0047] The first flashing mode is a fast flashing mode with a duration of 200 milliseconds on and 200 milliseconds off; the second flashing mode is a slow flashing mode with a duration of 500 milliseconds on and 500 milliseconds off.

[0048] The two flashing modes present a stark contrast in rhythm. The fast flashing mode has a period of 400 milliseconds, flashing 2.5 times per second, which aligns with the psychological expectation of an emergency alarm. The slow flashing mode has a period of 1000 milliseconds, flashing once per second, which aligns with the psychological expectation of a warning. The choice of flashing period and duty cycle has been ergonomically considered, ensuring that it attracts the operator's attention in a noisy working environment while avoiding excessively frequent flashing that could cause visual fatigue or irritation.

[0049] The 200ms and 500ms on / off times fall within the range of the human eye's visual persistence effect, providing a clear flicker perception without being too fast or too slow to be difficult to identify. The frequency difference between fast and slow flickers is 2.5 times, offering significant perceptual differentiation. Operators can accurately identify the two modes with minimal training and without confusion. This concise and effective visual encoding method fully utilizes the human visual system's sensitivity to rhythmic changes, conveying the most crucial state information with minimal data.

[0050] It also includes: a pluggable high insertion loss power filter, which is detachably connected to the power supply line of the blade server; when the status indicator 113 is in the first flashing mode, the pluggable high insertion loss power filter is connected to the power supply line to suppress electromagnetic interference.

[0051] The pluggable high insertion loss power filter is an emergency interference suppression device specially designed for harsh electromagnetic environments. Its insertion loss is much higher than that of the original standard power filters in the server chassis, and it can provide stronger attenuation of power grid conducted noise.

[0052] The pluggable high insertion loss power filter adopts a multi-stage LC filter network, which includes common-mode inductors, differential-mode inductors and multiple filter capacitors with different capacitance values, forming a wide-bandwidth and high-suppression-ratio filtering characteristic, and has a good suppression effect on broadband interference ranging from power frequency harmonics to several megahertz.

[0053] Under normal electromagnetic conditions, the server does not require an external filter, maintaining its original compact layout and lightweight characteristics. Only when the monitoring system detects excessive electromagnetic interference and the LED enters a fast-flashing alarm mode should the operator connect it in series between the mains input line and the server's power input. Once connected, the filter's powerful filtering effect quickly eliminates interference components on the power supply line, restoring the electromagnetic environment to a safe range, reducing the overall interference value, clearing the LED alarm, and allowing the server to resume stable operation.

[0054] When a mission is completed and relocation is required, operators remove the external filter, restoring the server to its initial state for easy and rapid withdrawal and transport. This on-demand, plug-and-play design ensures reliable operation in harsh environments while also balancing convenience and mobility for daily use.

[0055] As can be seen from the above technical solutions, the beneficial effects of this embodiment are: This application provides an electromagnetic environment detection system for a blade server, comprising: a conducted interference monitoring board integrated into the blade server for monitoring the intensity of conducted interference on the blade server's power supply line; the conducted interference monitoring board includes an interference extraction unit, a microcontroller, and status indicator lights; the input terminal of the interference extraction unit is connected to the live and neutral wires of the power filter inside the blade server chassis, for extracting electrical signals characterizing the intensity of conducted interference from the power supply line; the microcontroller is connected to the output terminal of the interference extraction unit, for performing digital signal processing on the electrical signals, and comparing the comprehensive interference value obtained from the digital signal processing with a preset threshold to determine the state level of electromagnetic interference corresponding to the intensity of conducted interference; the status indicator lights are connected to the GPIO port of the microcontroller, and are controlled by the microcontroller to indicate the interference state corresponding to the state level with different flashing patterns. This system achieves real-time monitoring, intelligent assessment, and graded early warning of conducted interference on the power supply line, transforming passive post-event restart emergency handling into proactive pre-event interference protection, effectively ensuring the stable operation of the blade server and the continuous execution of critical tasks under mobile deployment conditions.

[0056] like Figure 4The image shows a specific embodiment of an electromagnetic environment detection method for a blade server according to this application.

[0057] In this embodiment, a method for detecting the electromagnetic environment of a blade server includes the following steps: Step 401: Extract electrical signals characterizing the intensity of conducted interference from the power supply lines of the blade server using the interference extraction unit.

[0058] The input of the interference extraction unit is directly connected to the live and neutral wires of the power filter inside the blade server chassis, monitoring the voltage waveform on the power supply line in real time. The interference extraction unit first converts the AC power into unidirectional pulsating DC power through a bridge rectifier circuit, preserving all frequency components of the original signal. Subsequently, the interference extraction circuit uses a high-pass filter to filter out the fundamental frequency component of the pulsating DC power, selectively extracting high-frequency interference components. This high-frequency interference is often conducted noise generated by various nonlinear loads, switching power supplies, and frequency converters in the power grid, and is also the most likely harmful component to interfere with the server's electronic circuitry.

[0059] The extracted high-frequency interference signal undergoes amplitude conditioning via an attenuation adjustment circuit, controlling the signal level within the range of 0 to 3.3V to ensure safe processing by the microcontroller. Finally, an emitter follower performs impedance matching and buffer isolation on the conditioned signal, outputting a low-impedance standard electrical signal. The entire extraction process is implemented using fully analog circuitry, featuring fast response, wide bandwidth, and low distortion. It can accurately capture various interference components ranging from several kilohertz to several hundred kilohertz, providing high-fidelity raw signals for subsequent digital analysis.

[0060] This method of directly extracting interference signals from the power supply line offers higher accuracy and real-time performance compared to indirect measurement methods. Because the monitoring point is located after the power filter and before the server's power input, the acquired signal accurately reflects the actual electromagnetic environment faced by the server, avoiding environmental coupling errors that may exist in external measurements. Simultaneously, the high-impedance input design ensures that the monitoring process has negligible impact on the power supply system, does not alter the original circuit's operating state, and achieves non-destructive testing.

[0061] Step 402: Perform digital signal processing on the electrical signal using a microcontroller to determine the comprehensive interference value corresponding to the electrical signal.

[0062] The electrical signal is sampled to obtain the original data corresponding to the electrical signal; the waveform average component, pulsating fundamental frequency, and waveform variance based on the pulsating fundamental frequency are calculated for the original data; the original data is analyzed in the frequency domain using the FFT algorithm to obtain the corresponding frequency domain features; based on the waveform average component, pulsating fundamental frequency, waveform variance, and frequency domain features, a comprehensive interference value is generated using a preset evaluation algorithm.

[0063] The microcontroller uses an on-chip high-precision AD converter to continuously sample the electrical signal at a sampling frequency of 500kHz, converting the analog signal into a digital quantity. The sampling process lasts for several milliseconds, acquiring a raw data sequence containing thousands of sampling points. This data completely records the variation pattern of the interference signal in the time domain. The choice of a high sampling rate is based on the Nyquist sampling theorem, ensuring accurate reconstruction of frequency components up to 250kHz in the signal, covering the frequency range of most conducted interference from the power grid.

[0064] The microcontroller first calculates the average waveform component of the raw data, which reflects the DC bias level of the signal. Then, it extracts the 100Hz or 120Hz power frequency pulsating fundamental wave component through digital filtering or correlation operations. This pulsating fundamental wave represents the main energy of the rectified power supply. Using the pulsating fundamental wave as a reference, the variance of each sampling point deviating from the fundamental wave is calculated to obtain the waveform variance. The waveform variance quantifies the degree of waveform distortion caused by interference. The larger the variance, the more severe the interference and the further the waveform deviates from the ideal state. These three time-domain parameters describe the amplitude characteristics and statistical properties of the interference signal from different perspectives, providing basic data for comprehensive evaluation.

[0065] To obtain the frequency distribution characteristics of the interference, the microcontroller performs a Fast Fourier Transform (FFT) operation on the original data, converting the time-domain signal to the frequency domain. The FFT algorithm utilizes the microcontroller's hardware multiplier to accelerate computation, enabling the analysis of thousands of spectral points within tens of milliseconds. The frequency domain results are presented as frequency-amplitude spectra, clearly showing the energy distribution of each frequency component. By analyzing the peak positions and amplitudes of the spectra, it is possible to identify which frequency bands contain significant interference energy, which is crucial for determining the source and characteristics of the interference.

[0066] Finally, the microcontroller performs weighted summation or nonlinear calculation on the four dimensions of waveform average component, pulsating fundamental frequency, waveform variance, and frequency domain characteristics according to pre-calibrated weighting coefficients to generate a comprehensive interference value. This comprehensive interference value considers not only the amplitude of the interference but also its frequency distribution and waveform distortion characteristics, providing a more comprehensive and accurate reflection of the current electromagnetic environment quality.

[0067] Step 403: Compare the comprehensive interference value with the preset threshold to determine the state level of the electromagnetic interference corresponding to the conducted interference intensity.

[0068] The preset thresholds include critical thresholds and exceedance thresholds. These two thresholds represent the safe operating boundaries of the blade server under different electromagnetic environments. The critical threshold corresponds to the interference intensity at which the server begins to experience performance degradation or occasional anomalies. At this point, although the system can still maintain operation, it is approaching the limit of reliable operation. The exceedance threshold corresponds to the interference intensity at which the server is extremely prone to serious failures such as startup failures and operational interruptions. At this point, the electromagnetic environment has deteriorated to the point where normal system operation cannot be guaranteed. The setting of these two thresholds fully considers safety margins, leaving a certain fault tolerance space to avoid frequent false alarms caused by critical judgments.

[0069] The microcontroller compares the calculated comprehensive interference value with the critical threshold and the exceeding threshold sequentially. If the comprehensive interference value is less than the critical threshold, the electromagnetic interference is considered to be in a normal state, indicating that the current power supply environment is good and the server can operate safely and stably. If the comprehensive interference value is greater than or equal to the critical threshold but less than the exceeding threshold, the electromagnetic interference is considered to be in a critical state, indicating that the electromagnetic environment is beginning to deteriorate, requiring operators to pay attention and prepare for contingencies. If the comprehensive interference value is greater than or equal to the exceeding threshold, the electromagnetic interference is considered to be in an exceeding state, indicating that the electromagnetic environment is severely degraded, and interference suppression measures must be taken immediately.

[0070] The status level determination results are not only used to control local status indicator lights, but are also reported to the chassis management unit via the IIC interface, and finally transmitted to the radar display and control computer. This hierarchical judgment and graded response mechanism ensures smooth information flow from bottom-level monitoring to top-level decision-making, providing operators with timely and accurate electromagnetic environment assessment results.

[0071] Step 404: Based on the status level, control the status indicator light to display in the corresponding visual mode.

[0072] Based on the determined state level, the microcontroller controls the on / off state of the status indicator LEDs via GPIO ports to achieve different visual display modes. When electromagnetic interference is under normal conditions, the microcontroller controls the GPIO port to continuously output a high level, keeping the LEDs off and providing no alarm indication. This off-state mode indicates that the system is working normally and requires no operator attention, avoiding unnecessary visual interference. When electromagnetic interference is at a critical level, the microcontroller controls the GPIO port to alternately output high and low levels at 1-second intervals, with each cycle lasting 500 milliseconds on and off, forming a slow flashing mode. This gentle flashing rhythm provides a sense of alertness, indicating to the operator that the current electromagnetic environment is approaching a safe boundary and vigilance is required.

[0073] When electromagnetic interference exceeds the limit, the microcontroller controls the GPIO port to rapidly alternate between high and low levels at 400-millisecond cycles, flashing for 200 milliseconds each time, creating a fast-flash mode. This rapid flashing rhythm conveys a sense of urgency and an alarm, clearly informing operators that the current electromagnetic environment is severely compromised and interference suppression measures must be taken immediately. The fast-flash and slow-flash modes differ by a factor of 2.5, providing a clear distinction in perception. Operators can quickly identify the current status level even from several meters away without needing to approach for close observation.

[0074] As can be seen from the above technical solution, the beneficial effects of this embodiment are as follows: The interference extraction unit extracts electrical signals characterizing the intensity of conducted interference from the power supply lines of the blade server; the microcontroller performs digital signal processing on the electrical signals to determine the comprehensive interference value corresponding to the electrical signals; the comprehensive interference value is compared with a preset threshold to determine the state level of the electromagnetic interference corresponding to the intensity of conducted interference; and based on the state level, the status indicator lights are controlled to display in the corresponding visual mode. This achieves real-time monitoring, intelligent assessment, and graded early warning of electromagnetic interference in the blade server's power supply environment, transforming passive post-event restarts into proactive pre-event protection, effectively avoiding server malfunctions and critical mission interruptions caused by electromagnetic interference, and significantly improving the reliability and mission success rate of the radar system under mobile deployment conditions.

[0075] Those skilled in the art will understand that the embodiments of this application can be provided as methods or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or a combination of software and hardware.

[0076] The various embodiments in this application are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0077] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0078] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. An electromagnetic environment detection system for a blade server, the system comprising: The application relates to a conductive interference monitoring board integrated in a blade server and used for monitoring the conductive interference intensity on a power supply line of the blade server. The conductive interference monitoring board comprises an interference extraction unit, a single-chip microcomputer and a state indicating lamp. The input end of the interference extraction unit is connected to the live wire and the zero wire of a power supply filter in the blade server case, and is used for extracting an electric signal representing the conductive interference intensity from the power supply line. The single-chip microcomputer is connected with the output end of the interference extraction unit, is used for carrying out digital signal processing on the electric signal, and compares an interference comprehensive value obtained by the digital signal processing with a preset threshold value to judge the state grade of the electromagnetic interference corresponding to the conductive interference intensity. The state indicating lamp is connected with the GPIO port of the single-chip microcomputer and is controlled by the single-chip microcomputer to indicate the interference state corresponding to the state grade in different flashing modes. The interference extraction unit comprises a bridge rectifier circuit, an interference extraction circuit, an attenuation adjusting circuit and an emitter follower.

2. The system of claim 1, wherein, The bridge rectifier circuit is used for converting the alternating current inputted by the blade server into unidirectional pulsating direct current. The interference extraction circuit is used for determining a high-frequency interference component from the unidirectional pulsating direct current, and determining a corresponding interference signal according to the high-frequency interference component. The attenuation adjusting circuit is used for amplitude conditioning the interference signal to make the interference signal adapt to the processing range of the single-chip microcomputer. The emitter follower is used for impedance matching the interference signal to generate the electric signal. The digital signal processing on the electric signal comprises: sampling the electric signal to obtain original data corresponding to the electric signal; 3. The system of claim 1, wherein, calculating a waveform average component, a pulsating fundamental wave and a waveform variance based on the pulsating fundamental wave corresponding to the original data; carrying out frequency domain analysis on the original data through an FFT algorithm to obtain corresponding frequency domain features; generating the interference comprehensive value through a preset evaluation algorithm based on the waveform average component, the pulsating fundamental wave, the waveform variance and the frequency domain features. The state indicating lamp is configured to indicate the state grade through three visual modes; the state grade comprises a normal state, a critical state and an over-standard state, and the visual modes comprise: a first flashing mode, a second flashing mode and an extinguishing mode; 4. The system of claim 1, wherein, the first flashing mode represents that the electromagnetic interference is in the over-standard state; the second flashing mode represents that the electromagnetic interference is in the critical state; the extinguishing mode represents that the electromagnetic interference is in the normal state. The conductive interference monitoring board further comprises a communication interface; when the electromagnetic interference is in the over-standard state or the critical state, the single-chip microcomputer sends alarm information to the case management unit of the blade server through the communication interface. The application further relates to a plug-in high insertion loss power supply filter which is detachably connected to the power supply line of the blade server.

5. The system of claim 4, wherein, ​ 6. The system of claim 4, wherein, ​ ​ When the state indicating lamp is in the first flickering mode, the plug-in high insertion loss power filter is connected to the power supply circuit to suppress the electromagnetic interference.

7. The system of claim 5, wherein, The communication interface is an IIC interface; the conduction interference monitoring board is connected with a backplane IIC bus of the blade server through the IIC interface; the backplane IIC bus is connected with a chassis management unit; and the chassis management unit is configured to forward the alarm information to a corresponding radar display and control computer of the blade server through a network.

8. The system of claim 4, wherein, The first flickering mode is a fast flashing mode with 200 milliseconds of light and 200 milliseconds of darkness; and the second flickering mode is a slow flashing mode with 500 milliseconds of light and 500 milliseconds of darkness.

9. A method for detecting the electromagnetic environment of a blade server, the method being applied to the system of any one of claims 1-8, characterized in that, The method comprises the following steps: extracting, by an interference extraction unit, an electrical signal representing a conduction interference intensity from a power supply circuit of a blade server; performing, by a single-chip microcomputer, digital signal processing on the electrical signal to determine an interference comprehensive value corresponding to the electrical signal; comparing the interference comprehensive value with a preset threshold value to determine a state level of electromagnetic interference corresponding to the conduction interference intensity; controlling a state indicating lamp to display in a corresponding visual mode according to the state level.

10. The method of claim 9, wherein, The method comprises the following steps: sampling the electrical signal to obtain original data corresponding to the electrical signal; calculating a waveform average component, a pulsating fundamental wave and a waveform variance based on the pulsating fundamental wave corresponding to the original data; performing frequency domain analysis on the original data by an FFT algorithm to obtain corresponding frequency domain features; generating the interference comprehensive value by a preset evaluation algorithm based on the waveform average component, the pulsating fundamental wave, the waveform variance and the frequency domain features.

Images