Signal integrity analysis method, apparatus and electronic device
By converting signal data into quantum states and constructing channel models using quantum computing technology, the problem of real-time analysis of high-speed and high-frequency signals is solved, enabling accurate analysis and optimization of signal integrity and improving signal stability and equipment performance.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HEFEI LCFC INFORMATION TECH
- Filing Date
- 2024-09-14
- Publication Date
- 2026-06-12
AI Technical Summary
Existing technologies face difficulties in real-time analysis and processing of complex high-speed, high-frequency signals, especially PCIe 4.0 signals, and cannot accurately predict noise interference and signal attenuation.
Quantum computing technology is used to convert signal data into quantum state data, key features are extracted using linear discriminant analysis algorithm, and a quantum channel model is constructed through iterative training using a quantum machine learning model to analyze signal integrity.
It enables accurate analysis of high-speed and high-frequency signals, reduces the impact of noise and signal attenuation, improves signal stability and the real-time adjustment capability of equipment, and enhances user experience.
Smart Images
Figure CN119356957B_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of signal processing, and more particularly to a signal integrity analysis method, apparatus, and electronic device. Background Technology
[0002] In computing devices, signal integrity analysis is crucial for improving device performance, reducing signal interference, and enhancing user experience. Related technologies for signal integrity analysis often rely on linear system theory and digital signal processing techniques, such as eye diagrams and Fourier transforms. However, these methods have limitations when processing high-speed, high-frequency complex signals, especially those from advanced interfaces like PCIe 4.0. This is because high-speed, high-frequency signals involve massive amounts of data, making real-time analysis and processing ineffective with traditional methods. Furthermore, with increasing chip and device density, noise interference and signal attenuation become more severe, rendering traditional signal integrity analysis methods incapable of accurately analyzing and predicting signals. Summary of the Invention
[0003] This application provides a signal integrity analysis method, apparatus, and electronic device to at least solve the above-mentioned technical problems existing in the prior art.
[0004] According to a first aspect of this application, a signal integrity analysis method is provided, the method comprising:
[0005] Acquire signal data and convert the signal data into corresponding quantum state data;
[0006] The key features in the quantum state data are extracted using a linear discriminant analysis algorithm;
[0007] The quantum machine learning model is iteratively trained using the key feature values to obtain a quantum channel model; the quantum channel model is used to characterize the physical constraints and evolution laws of signals during transmission and reception.
[0008] The signal to be analyzed is input into the quantum channel model to obtain the signal integrity analysis results.
[0009] In one possible implementation, it further includes:
[0010] Based on the signal integrity analysis results, the signal to be analyzed is optimized to obtain an optimized signal.
[0011] In one possible implementation, converting the signal data into corresponding quantum state data includes:
[0012] The signal data is standardized using matrix equation calculation methods to obtain standardized data.
[0013] The standardized data is mapped onto quantum states to obtain the quantum state of at least one qubit.
[0014] In one possible implementation, the extraction of key features from the quantum state data using a linear discriminant analysis algorithm includes:
[0015] The quantum state data is classified to obtain multiple categories of quantum state data;
[0016] Calculate the first mean vector of samples in each class, and calculate the first deviation of each sample in the class from the first mean vector. Transpose the first deviation to obtain the intra-class scatter matrix.
[0017] Calculate the second mean vector of all samples, and calculate the second deviation from the first mean vector to the second mean vector in each category. Transpose the second deviation to obtain the inter-class scatter matrix.
[0018] The target projection vector is determined based on the intra-class scatter matrix and the inter-class scatter matrix; the target projection vector is used to characterize intra-class targets and inter-class targets.
[0019] The sample is projected based on the target projection vector to obtain low-dimensional key features.
[0020] In one possible implementation, the quantum machine learning model includes:
[0021] A quantum error correction mechanism is used to encode the quantum state data using error-correcting codes to obtain error-corrected quantum state data.
[0022] Quantum control mechanisms are used to manage quantum states.
[0023] In one possible implementation, the step of iteratively training the quantum machine learning model using the key feature values to obtain a quantum channel model includes:
[0024] The key feature values are input into the quantum machine learning model to obtain the prediction accuracy.
[0025] The loss value of the loss function of the quantum machine learning model is determined based on the prediction accuracy.
[0026] The target update gradient is determined based on the loss value of the loss function;
[0027] Based on the target, update the gradient, update the model parameters of the quantum machine learning model, and train until the preset convergence condition is met;
[0028] The quantum machine learning model trained to the preset convergence condition is used as the output quantum channel model.
[0029] In one possible implementation, the acquired signal data includes:
[0030] Use an appropriate network analyzer to collect signal data of signal parameters;
[0031] The signal parameters include at least one of the following: signal strength, noise level, signal loss, bit error rate, impedance value, and operating temperature.
[0032] In one possible implementation, optimizing the signal to be analyzed based on the signal integrity analysis results to obtain an optimized signal includes:
[0033] When there is signal loss in the signal to be analyzed under the target operating condition, the signal to be analyzed is optimized according to the corresponding processing rules under the target operating condition until the optimization target is achieved, and then the optimized signal is output.
[0034] According to a second aspect of this application, a signal integrity analysis apparatus is provided, the apparatus comprising:
[0035] The acquisition module is used to acquire signal data and convert the signal data into corresponding quantum state data;
[0036] The extraction module is used to extract key features from the quantum state data using a linear discriminant analysis algorithm;
[0037] The training module is used to iteratively train the quantum machine learning model using the key feature values to obtain a quantum channel model; the quantum channel model is used to characterize the physical constraints and evolution laws of signals during transmission and reception.
[0038] The analysis module is used to input the signal to be analyzed into the quantum channel model to obtain the signal integrity analysis results.
[0039] According to a third aspect of this application, an electronic device is provided, comprising:
[0040] At least one processor; and
[0041] A memory communicatively connected to the at least one processor; wherein,
[0042] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in this application.
[0043] According to a fourth aspect of this application, a non-transitory computer-readable storage medium is provided storing computer instructions for causing the computer to perform the methods described in this application.
[0044] According to a fifth aspect of this application, a computer program product is provided, comprising a computer program or instructions that, when executed by a processor, implement the method described in this application.
[0045] Using the technical solution of this application, precise quantum state calculation and analysis of a large amount of high-speed and high-frequency signal data can be achieved through quantum computing technology, effectively solving the impact of factors such as noise, signal attenuation, and reduced coherence on signal transmission.
[0046] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description
[0047] The above and other objects, features, and advantages of this disclosure will become readily apparent from the following detailed description of exemplary embodiments, taken in conjunction with the accompanying drawings. Several embodiments of this disclosure are illustrated in the drawings by way of example and not limitation, in which:
[0048] In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts.
[0049] Figure 1 This paper illustrates the implementation flow of the signal integrity analysis method in an embodiment of this application. Figure 1 ;
[0050] Figure 2 This paper illustrates the implementation flow of the signal integrity analysis method in an embodiment of this application. Figure 2 ;
[0051] Figure 3 A schematic diagram of the signal integrity analysis device in an embodiment of this application is shown;
[0052] Figure 4 A schematic diagram of the composition structure of the electronic device in an embodiment of this application is shown. Detailed Implementation
[0053] To make the objectives, features, and advantages of this disclosure more apparent and understandable, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort are within the scope of protection of this disclosure.
[0054] The following description, in conjunction with the accompanying drawings, introduces a signal integrity analysis method, apparatus, and electronic device provided in this application.
[0055] like Figure 1 As shown in the figure, this application provides a signal integrity analysis method, the method comprising:
[0056] S101, Acquire signal data and convert the signal data into corresponding quantum state data;
[0057] It is understood that the signal data in this application may be Peripheral Component Interconnect Express (PCIe) 4.0 signals, which exist in the form of slots on the computer motherboard and are used to connect various devices that need to communicate with the computer motherboard at high speed, such as graphics cards, hard drives, SSDs, wireless network cards, and sound cards. Currently, most electronic products use PCIe 4.0, with a data transfer speed of 16GT / s per LAN, which is sufficient for current consumer electronics.
[0058] In some alternative embodiments, the acquired signal data includes:
[0059] Use an appropriate network analyzer to collect signal data of signal parameters;
[0060] The signal parameters include at least one of the following: signal strength, noise level, signal loss, bit error rate, impedance value, and operating temperature.
[0061] Understandably, the signal data in this application is measured using a vector network analyzer to measure PCIe 4.0 signals. Under different operating conditions (such as temperature, voltage, power, etc.), parameters such as the signal's frequency response, phase, and group delay are monitored in real time. The signal data obtained from each measurement is recorded. This process may require long-term and continuous measurements to ensure that the collected data is substantial and covers various possible operating states.
[0062] Understandably, when collecting PCIe 4.0 signal data, it is typically necessary to focus on and collect the following types of data:
[0063] Signal strength: Signal strength directly affects the transmission quality and the recognition effect at the receiving end, so signal strength information is very important.
[0064] Noise level: Noise can also seriously affect signal quality, so it is necessary to pay attention to changes in noise level.
[0065] Channel loss: The degree of signal attenuation caused by the channel is crucial to signal integrity, therefore it is necessary to collect channel loss data.
[0066] Bit Error Rate (BER): Bit error rate is an important indicator for measuring signal integrity and needs to be collected.
[0067] Impedance value: The impedance value affects the transmission and reception of signals and needs to be taken into account.
[0068] Operating temperature: The temperature conditions of the operating environment can affect the performance of the equipment and the integrity of the signal.
[0069] These data need to be measured and recorded in real time under different operating conditions using a vector network analyzer with the appropriate capabilities. Using this data as input for training the model can improve the model's prediction accuracy and performance.
[0070] Then, this application uses quantum processing technology to convert signal data into corresponding quantum state data. It is understood that each data point is considered a qubit, and quantum superposition allows data points to exist in multiple states simultaneously. The definition and preprocessing of quantum states involves transforming conventional data into a form that can be processed by a quantum computer, i.e., a quantum state. For an n-qubit quantum system, it is typically represented in a 2n-dimensional complex vector space.
[0071] S102, use a linear discriminant analysis algorithm to extract key features from the quantum state data;
[0072] S103, The quantum machine learning model is iteratively trained using the key feature values to obtain a quantum channel model; the quantum channel model is used to characterize the physical constraints and evolution laws of signals during transmission and reception.
[0073] S104, input the signal to be analyzed into the quantum channel model to obtain the signal integrity analysis results.
[0074] The signal integrity analysis method provided in this application acquires signals and converts them into quantum state data. It then extracts key features from the quantum state data using a linear discriminant analysis algorithm. These key features are then used to iteratively train a quantum machine learning model to obtain a quantum channel model, which is then used to analyze signal integrity.
[0075] In some optional embodiments, the signal integrity analysis method provided in this application further includes:
[0076] Based on the signal integrity analysis results, the signal to be analyzed is optimized to obtain an optimized signal.
[0077] This application also enables the optimization of the signal to be analyzed after obtaining the signal integrity analysis results, thereby obtaining an optimized signal. The model can be used to predict PCIe 4.0 signal types and improve signal integrity. Since the model can predict the integrity of PCIe 4.0 signals under different operating conditions, the integrity of PCIe 4.0 signals can be improved by changing the operating conditions (such as adjusting the power supply voltage, changing the operating temperature, etc.).
[0078] In some optional embodiments, converting the signal data into corresponding quantum state data includes:
[0079] The signal data is standardized using matrix equation calculation methods to obtain standardized data.
[0080] The standardized data is mapped onto quantum states to obtain the quantum state of at least one qubit.
[0081] As a specific implementation method, quantum state processing in PCIe 4.0 signal analysis can be performed according to the following steps:
[0082] First, the signal data is standardized, specifically by performing standardization processing on the collected signal data. Using matrix computation methods, various signal parameters, such as signal strength, noise level, channel loss, bit error rate, and impedance value, are mapped to the range of 0 and 1. This makes the data adaptable to the requirements of quantum computing, since quantum states typically operate within a unit spherical space (Bloch sphere), which necessitates normalized input data.
[0083] Then, quantum state assignment is performed, specifically mapping each normalized data point to a quantum state. In quantum computing, the state of a single qubit can be represented by a complex number, according to the Pearson relation:
[0084] |ψ〉=α|0〉+β|1〉
[0085] Where α and β are complex numbers, and must satisfy...
[0086] |α| 2 +|β| 2 =1
[0087] Finally, quantum superposition state generation specifically refers to the ability, after defining a quantum state, to utilize the quantum superposition property to generate and process multiple possible signal states simultaneously. With n qubits, 2^n states can be generated concurrently. This significantly increases the efficiency of signal data processing and analysis.
[0088] like Figure 2As shown, in some optional embodiments, the extraction of key features from the quantum state data using a linear discriminant analysis algorithm includes:
[0089] S201, The quantum state data is classified to obtain multiple categories of quantum state data;
[0090] S202, calculate the first mean vector of samples in each class, and calculate the first deviation of each sample in the class from the first mean vector. Transpose the first deviation to obtain the intra-class scatter matrix.
[0091] S203, calculate the second mean vector of all samples, and calculate the second deviation from the first mean vector to the second mean vector in each category. Transpose the second deviation to obtain the inter-class scatter matrix.
[0092] S204, determine the target projection vector based on the intra-class scatter matrix and the inter-class scatter matrix; the target projection vector is used to characterize intra-class targets and inter-class targets;
[0093] S205, Project the sample based on the target projection vector to obtain low-dimensional key features.
[0094] Specifically, the signal data packets in this application contain factors such as signal strength, noise level, channel loss, and impedance. With these characteristics, a feature vector can be constructed, and LDA (Linear Discriminant Analysis) can be used to extract the feature values. The main goal of Linear Discriminant Analysis (LDA) is to make samples within a class as close as possible, while samples between classes are as far apart as possible.
[0095] After classifying the quantum state data, a linear discriminant analysis algorithm was used to extract key features from the two days' data, as follows:
[0096] Calculate the within-class scatter matrix: For each sample of class i, calculate its mean vector m. i Then, calculate the deviation of each sample from its mean vector, multiply it by its transpose, and obtain the scatter matrix for each sample. Add the scatter matrices of all samples within a class to obtain the within-class scatter matrix S. w .
[0097] S w =Σ i Σ {x∈Xi} (xm i (xm) i ) T
[0098] Among them, X iLet x represent all samples of category i, where x is one of them.
[0099] To calculate the between-class scatter matrix: First, calculate the mean vector *m* of all samples. Then, for each class, calculate the deviation of its mean vector from the mean vector of all samples, multiply it by its transpose, and obtain a scatter matrix. Summing the scatter matrices of all classes yields the between-class scatter matrix *S*. b :
[0100] S b =Σ i |X i |(m i -m)(m i -m) T
[0101] Among them, |X i | represents the number of samples in category i.
[0102] The optimization problem aims to find a projection vector w such that the projected samples satisfy the goal of being as compact within classes as possible and dispersed between classes. Therefore, the following optimization problem needs to be solved:
[0103]
[0104] The solution to this optimization problem is: The eigenvectors corresponding to the largest eigenvalues are given by S. W* is the optimal projection vector to be found, which makes the projected samples as compact as possible within classes and dispersed as possible between classes. b It is the inter-class scatter matrix, used to represent the overall scatter distribution between classes; S w This is the intra-class scatter matrix, used to represent the scatter distribution within each class. The number of values is determined by the dimensions to be reduced, and arg max... W Calculate the standard function of the quantity that maximizes the fraction.
[0105] Finally, W* is used to project the sample to obtain new properties.
[0106] Linear discriminant analysis (LDA) can extract the most discriminative low-dimensional features from the original high-dimensional features, which can then be used for subsequent model training.
[0107] In some alternative embodiments, the quantum machine learning model includes:
[0108] A quantum error correction mechanism is used to encode the quantum state data using error correction codes to obtain error-corrected quantum state data;
[0109] Quantum control mechanisms are used to manage quantum states.
[0110] Understandably, this application utilizes superquantum quantum error correction codes and quantum control to ensure signal integrity during model training, data storage, and retrieval. During training, due to system non-ideality and external perturbations, problems such as bit flips or loss of coherence may occur. To address these issues, quantum error correction and quantum control mechanisms need to be introduced into the system. For quantum error correction, the main approach is to encode each bit with an error-correcting code; commonly used quantum error correction codes include qubit flip codes and quantum phase flip codes. These codes can correct errors such as bit flips and phase flips.
[0111] Quantum error correction and quantum control are crucial steps in ensuring information fidelity during training and actual operation. In the process of converting signal data into quantum state data, after the data is defined as quantum states and quantum superposition states, these quantum states can be used in subsequent quantum computing processes. At this stage, error correction coding can be introduced to prevent qubit errors caused by noise and other environmental factors. In the construction of quantum channel models, quantum properties are taken into account in the model structure. Appropriate quantum control operations are introduced to simulate and adapt to actual channel conditions, such as channel attenuation and noise.
[0112] The purpose of quantum error correction is to correct flipped bits, while quantum control ensures that information is transmitted correctly through the channel by appropriately adjusting and controlling interference, thus guaranteeing the integrity and fidelity of data throughout the quantum computing process. The following is a detailed implementation process:
[0113] Quantum error correction: To protect quantum information in complex environments, it is encoded into special states called quantum error correction codes. The most basic of these are 3-bit qubit flip codes and quantum phase flip codes. The detailed implementation process is as follows:
[0114] 3-bit qubit flip code:
[0115] Primitive quantum state: |ψ〉=α|0〉+β|1〉
[0116] Encoded quantum state: |ψ〉=α|000〉+β|111〉
[0117] If the original quantum state encounters a bit flip during transmission (e.g., |0〉 flips to |1〉), the erroneous bit can be easily identified and corrected during the decoding process (usually by majority decision).
[0118] Quantum phase-flip code:
[0119] Primitive quantum state: |ψ〉=α|0〉+β|1〉
[0120] Encoded quantum state: |ψ〉=α|+++〉+β|---〉
[0121] This is a transpose operation on the bit-flip code. Bit flipping corresponds to the Z-gate operation, and phase flipping corresponds to the X-gate operation. In this way, the quantum state can better resist bit errors caused by environmental noise, thus ensuring the fidelity of information.
[0122] Quantum control: Used to control and manage the states of a quantum system to achieve precise quantum operations, including state preparation, quantum gate operations, and measurement.
[0123] In some embodiments, the step of iteratively training the quantum machine learning model using the key feature values to obtain a quantum channel model includes:
[0124] The key feature values are input into the quantum machine learning model to obtain the prediction accuracy.
[0125] The loss value of the loss function of the quantum machine learning model is determined based on the prediction accuracy.
[0126] The target update gradient is determined based on the loss value of the loss function;
[0127] Based on the target, update the gradient, update the model parameters of the quantum machine learning model, and train until the preset convergence condition is met;
[0128] The quantum machine learning model trained to the preset convergence condition is used as the output quantum channel model.
[0129] Specifically, in this application, the extracted features are used to train a quantum channel model using a quantum machine learning algorithm, as follows:
[0130] A quantum channel model is trained using extracted features, enabling it to predict the integrity of PCIe 4.0 signals under specific operating conditions. The basic training approach involves manipulating a series of known quantum states, observing the final output, and then training based on feedback signals to optimize the process. A quantum neural network (QNN)-based model is employed. Details are as follows:
[0131] (1) Quantum Neural Network Construction: The main structure of a quantum neural network consists of quantum gates, qubits, and parameterized rotation gates. The structure (e.g., how many layers, which gates, connection methods, etc.) and required parameters need to be determined in advance. During construction, a loss function also needs to be selected; the mean squared error loss function is used to measure the difference between the predicted value and the label.
[0132] (2) Quantum state preparation: First, the initial state needs to be prepared based on the feature extraction results. Usually, a quantum state is represented by a vector, and this state preparation can be accomplished through some rotating gates and Bloch balls.
[0133] (3) Parameterized rotating gate operation: After the quantum state is prepared, the quantum state is optimized by rotating the newly added parameters of each qubit. Each rotating gate has a parameter, which is continuously updated during the learning process.
[0134] (4) Measurement and prediction: After a series of rotating gate operations, a prediction value is obtained through measurement. Z-basis measurements are performed on specific qubits, and the loss is calculated using the measurement results (i.e., the prediction value).
[0135] (5) Parameter Update: Based on the feedback from the measurement results and the loss function, the gradient descent optimization algorithm can be used to gradually reduce the loss value and update the rotating door parameters. In quantum computers, this step can be accomplished through parameter gradient calculation methods. For example, the parameter shift method obtains the gradient estimate by changing a small amount of the parameter.
[0136] (6) Repeated iteration: The above process is repeated until a satisfactory prediction result is obtained, or the preset number of iterations is reached.
[0137] Quantum channel models simulate the transmission and evolution of signals in a channel.
[0138] In the process of constructing quantum channel models, the following factors that have a significant impact on PCIe 4.0 signal transmission are usually considered:
[0139] Weak coherence: Due to factors such as noise and signal instability, the coherence of a signal is weakened during transmission. This can be simulated by introducing appropriate coherence operations.
[0140] Attenuation: Signals will be attenuated during transmission due to various reasons, which requires the introduction of an attenuation operator to simulate.
[0141] Noise: Noise is unavoidable in actual transmission, but it can be simulated by introducing noise operators.
[0142] In quantum theory, the state of a quantum system is generally represented by a quantum state matrix ρ. A quantum channel E can be viewed as a mapping acting on ρ and is defined by the following formula:
[0143]
[0144] Among them, E k It is a Kraus operator that satisfies the normalization condition. I is the identity matrix. E(ρ) represents the state of a quantum signal after passing through a quantum channel; ρ is the initial state of a quantum channel, usually represented by a density matrix. Represents the Kraus operator E k The conjugate transpose of k: k: refers to the index of the different paths guided through the channel.
[0145] In some optional embodiments, optimizing the signal to be analyzed based on the signal integrity analysis results to obtain an optimized signal includes:
[0146] When there is signal loss in the signal to be analyzed under the target operating condition, the signal to be analyzed is optimized according to the corresponding processing rules under the target operating condition until the optimization target is achieved, and then the optimized signal is output.
[0147] In this application, after the quantum channel model is trained, it can be used to predict PCIe 4.0 signal types and improve signal integrity. Since the quantum channel model can predict the integrity of PCIe 4.0 signals under different operating conditions, the integrity of PCIe 4.0 signals can be improved by changing the operating conditions (such as adjusting the power supply voltage, changing the operating temperature, etc.). The main process of signal integrity improvement includes problem prediction, problem identification, and optimization, as detailed below:
[0148] Problem Prediction: Using a trained quantum machine learning model, the integrity of the PCIe 4.0 signal is predicted under various operating conditions. For example, the degree of loss of the PCIe 4.0 signal can be predicted at a specific power supply voltage or operating temperature. In the quantum machine learning model, the output is a "predicted value" that gives the possible degree of loss of the PCIe 4.0 signal.
[0149] Problem identification: By comparing the predicted results with the ideal state, potential problems are identified. For example, if the prediction indicates that signal loss exceeds the tolerance range under certain operating conditions, then the cause of this problem needs to be investigated. This investigation is achieved through the prediction results of a quantum machine learning model. For instance, if the model predicts that signal loss exceeds the tolerance range under certain operating conditions, then a problem can be identified. The sources of specific problems are multifaceted, such as poor operating conditions or hardware issues.
[0150] To determine whether a problem is caused by poor operating conditions, the model can be used again to predict the signal integrity after changing the operating conditions (e.g., adjusting the power supply voltage or operating temperature). If these changes significantly improve signal integrity, then the problem can be considered to originate from the operating conditions.
[0151] To determine if a problem is caused by a hardware issue, you can check the status of the hardware devices, such as whether the impedance of the transmission line is matched, and whether there are signal reflection problems. If a hardware problem is found, and the signal integrity predicted by the model improves after fixing these problems, then the problem can be considered to originate from the hardware.
[0152] Optimization and Improvement: Based on the identified problems, the signal transmission process is improved and signal integrity is enhanced by changing operating conditions or hardware optimization. A signal integrity standard or threshold is first set; if the predicted loss exceeds this threshold, a signal integrity problem is considered to exist. Problem identification is primarily based on the characteristics of the PCIe 4.0 signal and real-time conditions in the operating environment, such as at least one of the following: signal strength, noise level, channel loss, bit error rate, impedance value, and operating temperature.
[0153] The following are methods for identifying problems:
[0154] If the predicted signal loss is mainly caused by the power supply voltage, then the problem is that the power supply voltage is unstable or not within a suitable range, and the power supply voltage needs to be adjusted.
[0155] If the predicted signal loss is mainly caused by the operating temperature, then the problem is that the operating environment is too hot or too cold, and the heat dissipation system needs to be improved or the temperature of the operating environment needs to be adjusted.
[0156] If the predicted signal loss is mainly caused by channel loss, then the problem is impedance mismatch in the transmission line or signal reflection, requiring optimization of the transmission line design to improve impedance matching.
[0157] If the model predicts a high bit error rate, the problem may be that the signal is subject to significant interference during transmission or that there are performance issues with the hardware. In such cases, improvements can be made by increasing the channel protection level or optimizing the hardware.
[0158] If the predicted signal loss is mainly caused by noise level, then the problem is that the device's noise suppression capability is insufficient. In this case, noise reduction strategies can be adopted, such as using better noise suppression technology and hardware isolation.
[0159] By identifying the problems mentioned above, targeted optimizations and improvements can be made. For example, if the problem lies in the power supply voltage, then the power supply voltage needs to be adjusted or a more stable power supply device needs to be replaced; if the problem lies in the operating temperature, then the heat dissipation system needs to be improved or the operating environment of the device needs to be changed; if the problem lies in the channel loss, then the line design needs to be optimized; if the problem lies in the noise level, then better noise suppression strategies need to be adopted, and so on.
[0160] For example, the working environment can be improved by adjusting the power supply voltage and optimizing the heat dissipation system, or the hardware design can be improved, such as optimizing the transmission line design and improving impedance matching. Let the prediction function be F(V,T), where V is the power supply voltage and T is the operating temperature. We can change V and T to...
[0161] min V,TF(V,T)
[0162] Find the V and T that minimize F to obtain the optimal working environment.
[0163] After improvements, the quantum machine learning model can be used again to predict signal integrity to verify the effectiveness of the optimization. Subsequently, problem prediction and identification can continue, followed by further optimization and improvement, in a cycle until the set signal integrity target is achieved, or no further improvement can be made.
[0164] The signal integrity analysis method provided in this application collects PCIe 4.0 signal data through a vector network analyzer, preprocesses the data into quantum states for analysis, and establishes a quantum channel model of the signal based on this data to describe the physical constraints and evolution of the signal from transmission to reception, extracting key features. Over-quantum quantum error correction codes and quantum control are used to ensure signal integrity during model training, data storage, and retrieval. Furthermore, a quantum machine learning algorithm is used to train the model, and the model's prediction results are used to identify potential problems. Based on this information, the signal transmission process is optimized and improved to enhance signal integrity.
[0165] This application utilizes quantum computing technology to perform precise quantum state calculations and analysis on large amounts of high-speed, high-frequency signal data, effectively addressing the impact of noise, signal attenuation, and reduced coherence on signal transmission. By learning the characteristics and patterns of signal processing through machine learning technology, it can accurately and quickly predict and optimize signal integrity, thereby improving signal integrity. This not only enhances signal stability but also significantly reduces errors and losses, and strengthens the real-time adjustment and optimization capabilities of equipment, thus significantly improving the user experience. The technical solution provided in this application represents an AI-driven digital transformation in signal integrity analysis and is also applicable to other high-speed serial protocols, demonstrating strong versatility and practical value.
[0166] like Figure 3 As shown in the figure, this application provides a signal integrity analysis device, the device comprising:
[0167] Acquisition module 301 is used to acquire signal data and convert the signal data into corresponding quantum state data;
[0168] Extraction module 302 is used to extract key features from the quantum state data using a linear discriminant analysis algorithm;
[0169] Training module 303 is used to iteratively train the quantum machine learning model using the key feature values to obtain a quantum channel model; the quantum channel model is used to characterize the physical constraints and evolution laws of signals during transmission and reception.
[0170] The analysis module 304 is used to input the signal to be analyzed into the quantum channel model to obtain the signal integrity analysis results.
[0171] According to embodiments of this disclosure, this disclosure also provides an electronic device and a readable storage medium.
[0172] Figure 4 A schematic block diagram of an example electronic device 400 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.
[0173] like Figure 4 As shown, device 400 includes a computing unit 401, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 402 or a computer program loaded from storage unit 408 into random access memory (RAM) 403. RAM 403 may also store various programs and data required for the operation of device 400. The computing unit 401, ROM 402, and RAM 403 are interconnected via bus 404. Input / output (I / O) interface 405 is also connected to bus 404.
[0174] Multiple components in device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of monitors, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0175] The computing unit 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as signal integrity analysis methods. For example, in some embodiments, the signal integrity analysis method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the signal integrity analysis method described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform signal integrity analysis methods by any other suitable means (e.g., by means of firmware).
[0176] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0177] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0178] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0179] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).
[0180] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.
[0181] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.
[0182] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.
[0183] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means two or more, unless otherwise explicitly specified.
[0184] The above description is merely a specific embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.
Claims
1. A signal integrity analysis method, characterized by, The method includes: Acquire signal data and convert the signal data into corresponding quantum state data; The key features in the quantum state data are extracted using a linear discriminant analysis algorithm; The quantum machine learning model is iteratively trained using the key feature values to obtain a quantum channel model; the quantum channel model is used to characterize the physical constraints and evolution laws of signals during transmission and reception. The signal to be analyzed is input into the quantum channel model to obtain the signal integrity analysis results; The extraction of key features from the quantum state data using a linear discriminant analysis algorithm includes: The quantum state data is classified to obtain multiple categories of quantum state data; Calculate the first mean vector of samples in each class, and calculate the first deviation of each sample in the class from the first mean vector. Transpose the first deviation to obtain the intra-class scatter matrix. Calculate the second mean vector of all samples, and calculate the second deviation from the first mean vector to the second mean vector in each category. Transpose the second deviation to obtain the inter-class scatter matrix. The target projection vector is determined based on the intra-class scatter matrix and the inter-class scatter matrix; the target projection vector is used to characterize intra-class targets and inter-class targets. The sample is projected based on the target projection vector to obtain low-dimensional key features.
2. The method according to claim 1, further comprising: Based on the signal integrity analysis results, the signal to be analyzed is optimized to obtain an optimized signal.
3. The method according to claim 1, wherein converting the signal data into corresponding quantum state data comprises: The signal data is standardized using matrix equation calculation methods to obtain standardized data. The standardized data is mapped onto quantum states to obtain the quantum state of at least one qubit.
4. The method according to claim 1, wherein the quantum machine learning model comprises: A quantum error correction mechanism is used to encode the quantum state data using error correction codes to obtain error-corrected quantum state data; Quantum control mechanisms are used to manage quantum states.
5. The method according to claim 1, wherein iteratively training the quantum machine learning model using the key feature values to obtain a quantum channel model comprises: The key feature values are input into the quantum machine learning model to obtain the prediction accuracy. The loss value of the loss function of the quantum machine learning model is determined based on the prediction accuracy. The target update gradient is determined based on the loss value of the loss function; Based on the target, update the gradient, update the model parameters of the quantum machine learning model, and train until the preset convergence condition is met; The quantum machine learning model trained to the preset convergence condition is used as the output quantum channel model.
6. The method according to claim 2, wherein the acquired signal data includes: Use an appropriate network analyzer to collect signal data of signal parameters; The signal parameters include at least one of the following: signal strength, noise level, signal loss, bit error rate, impedance value, and operating temperature.
7. The method according to claim 2, wherein optimizing the signal to be analyzed based on the signal integrity analysis results to obtain an optimized signal includes: When there is signal loss in the signal to be analyzed under the target operating condition, the signal to be analyzed is optimized according to the corresponding processing rules under the target operating condition until the optimization target is achieved, and then the optimized signal is output.
8. A signal integrity analysis apparatus, the apparatus comprising: The acquisition module is used to acquire signal data and convert the signal data into corresponding quantum state data; The extraction module is used to extract key features from the quantum state data using a linear discriminant analysis algorithm; The training module is used to iteratively train the quantum machine learning model using the key feature values to obtain the quantum channel model; The quantum channel model is used to characterize the physical constraints and evolution of signals during transmission and reception. The analysis module is used to input the signal to be analyzed into the quantum channel model to obtain the signal integrity analysis results; The extraction module is also used to classify the quantum state data to obtain quantum state data of multiple categories; calculate the first mean vector of samples in each category, and calculate the first deviation of each sample in the category from the first mean vector, and transpose the first deviation to obtain the intra-category scatter matrix; Calculate the second mean vector of all samples, and calculate the second deviation from the first mean vector to the second mean vector in each category. Transpose the second deviation to obtain the inter-class scatter matrix. The target projection vector is determined based on the intra-class scatter matrix and the inter-class scatter matrix; The target projection vector is used to characterize intra-class and inter-class targets; the samples are projected based on the target projection vector to obtain low-dimensional key features.
9. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.