Radio frequency test equipment state monitoring and abnormal early warning method based on internet of things

Abstract

The present application belongs to the technical field of predictive maintenance, and discloses a radio frequency test equipment state monitoring and abnormal early warning method based on the Internet of Things; the method comprises the following steps: collecting radio frequency power flow data and heat dissipation data, and calculating energy transmission efficiency matrix and local entropy generation rate to obtain a current working point; for a radio frequency link, identifying critical fluctuation characteristics of transition from an efficient transmission state to an energy dissipation state; defining an optimal working point attractor domain and a performance degradation escape boundary, and combining the current working point to calculate a radio frequency performance stability margin; triggering an abnormal early warning when the radio frequency performance stability margin is lower than an adaptive threshold, determining a dominant evolution direction of equipment state deterioration, and combining the critical fluctuation characteristics to locate a dominant energy dissipation node and an impedance mismatch position to generate a link tuning strategy; the present application can effectively improve the accuracy of radio frequency test equipment state monitoring and the timeliness of early warning, and guarantee the accuracy and reliability of test results.

Description

Technical Field

[0001] This invention relates to the field of predictive maintenance technology, and more specifically, to a method for monitoring the status and providing early warning of anomalies for radio frequency test equipment based on the Internet of Things. Background Technology

[0002] Radio frequency (RF) test equipment is a core tool for performance testing and quality inspection in fields such as wireless communication, radar systems, and electronic countermeasures. Its operating status directly affects the accuracy and reliability of test results. With the rapid development of IoT technology, more and more RF test equipment is being incorporated into the industrial IoT system for network management. Through sensor networks, real-time data collection of equipment operation is achieved, enabling remote monitoring and intelligent operation and maintenance. However, RF test equipment contains a large number of precision RF modules. These modules transmit signals and couple energy through complex RF links. Their state evolution is characterized by nonlinearity, strong coupling, and gradual degradation. Traditional monitoring methods based on threshold judgment or statistical analysis are difficult to accurately capture early signs of equipment transitioning from a normal state to a fault state.

[0003] Existing methods for monitoring the status of RF test equipment have the following shortcomings: First, they mostly employ single-parameter monitoring, setting fixed thresholds for alarms only for independent indicators such as temperature and power, failing to comprehensively consider the inherent relationship between energy transfer and heat dissipation within the equipment, which can easily lead to false alarms or missed early potential problems. Second, they lack in-depth analysis of the evolution of equipment status, making it impossible to identify key characteristics of gradual performance degradation during equipment operation and difficult to provide effective early warnings before faults occur. Third, the accuracy of fault location is insufficient, only providing general anomaly alarms without specifying which module or link is causing the problem, making it difficult to provide clear repair guidance for maintenance personnel. Therefore, there is an urgent need for a method for monitoring the status and providing early warnings of anomalies in RF test equipment that can comprehensively analyze the characteristics of energy flow and heat dissipation, and achieve accurate status monitoring and intelligent early warning.

[0004] In view of this, the present invention proposes an IoT-based method for monitoring the status of radio frequency test equipment and providing early warning of anomalies to solve the above problems. Summary of the Invention

[0005] To overcome the aforementioned shortcomings of the prior art and achieve the above objectives, the present invention provides the following technical solution: a method for monitoring the status and providing early warning of anomalies in radio frequency test equipment based on the Internet of Things, comprising: Step S1: Collect RF power flow data and heat dissipation data of the RF test equipment, construct an energy transmission efficiency matrix based on the RF power flow data, calculate the local entropy generation rate of each RF module in the RF test equipment based on the heat dissipation data, and combine them to obtain the current operating point of the RF test equipment. Step S2: For the RF links formed by each RF module, the coupling evolution law of local entropy generation rate and energy transmission efficiency matrix is ​​analyzed using dissipative structure theory. The critical fluctuation characteristics of the transition from the high-efficiency transmission state to the energy dissipation state are identified, and the phase space trajectory of the RF link entropy evolution is constructed. Step S3: Define the optimal operating point attraction domain and the performance degradation escape boundary in the phase space trajectory of the RF link entropy evolution. Calculate the RF performance stability margin based on the current operating point and the performance degradation escape boundary. Calculate the deviation direction vector based on the current operating point and the optimal operating point attraction domain. Step S4: Dynamically calculate the adaptive threshold. When the RF performance stability margin is lower than the adaptive threshold, trigger an anomaly warning. Determine the dominant adaptive direction of device state deterioration based on the deviation direction vector, and locate the dominant energy dissipation node and impedance mismatch position in the RF link by combining critical fluctuation characteristics. Step S5: Generate a link tuning strategy based on the dominant energy dissipation node and impedance mismatch location.

[0006] Furthermore, methods for constructing the energy transfer efficiency matrix include: Obtain the signal transmission relationship of each RF module, and construct the RF link topology based on the signal transmission relationship; calculate the module transmission efficiency of each RF module based on the RF power flow data; construct the energy transmission efficiency matrix based on the RF link topology and the module transmission efficiency of each RF module. Methods for calculating the local entropy generation rate of each RF module include: Based on the heat dissipation data, calculate the heat dissipation power of each RF module; based on the RF power flow data and heat dissipation power, calculate the local entropy generation rate of each RF module. Methods for obtaining the current operating point of an RF test device include: The energy transfer efficiency matrix is ​​decomposed into eigenvalues ​​and eigenvectors; based on the eigenvalues, the following eigenvalues ​​are selected: eigenvectors, and The efficiency feature vector is obtained by concatenating the feature vectors; the local entropy generation rates of each RF module are combined to obtain the entropy generation rate vector; the entropy generation rate vector and the efficiency feature vector are concatenated to construct the current operating point of the RF test equipment.

[0007] Furthermore, methods for analyzing the coupled evolution of local entropy generation rate and energy transfer efficiency matrix include: A coupling relationship between local entropy generation rate and energy transfer efficiency is established to obtain the coupling degree index of each RF module. A sampling time window and sampling interval are set. Within the sampling time window, the current operating point at multiple sampling moments is continuously collected according to the sampling interval and marked as a sampling operating point. The sampling operating points at multiple sampling moments are combined to form an operating point time series. For each sampling operating point in the operating point time series, the corresponding entropy generation rate vector and efficiency feature vector are extracted. The change in the entropy generation rate vector between adjacent sampling moments is calculated to obtain the entropy generation rate change sequence. The change in the efficiency feature vector between adjacent sampling moments is calculated to obtain the efficiency feature change sequence. The entropy generation rate change sequence and the efficiency characteristic change sequence are discretized separately, dividing the continuous values ​​into multiple discrete intervals; the frequency distribution of each discrete interval is statistically analyzed, and the joint probability distribution and marginal probability distribution of the entropy generation rate change sequence and the efficiency characteristic change sequence are calculated; based on the joint probability distribution and marginal probability distribution, the mutual information value is calculated and used as the quantification result of the coupled evolution law.

[0008] Furthermore, methods for identifying the critical fluctuation characteristics of the transition from an efficient transport state to an energy dissipation state include: Define two typical operating states of RF test equipment: high-efficiency transmission state and energy dissipation state; For the operating point time series, calculate the fluctuation amplitude vector for each sampled operating point and combine them to form a fluctuation amplitude sequence; for the operating point time series, calculate the corresponding autocorrelation time vector; for the operating point time series, calculate the corresponding higher-order statistical features; normalize the fluctuation amplitude sequence, autocorrelation time vector, and higher-order statistical features respectively, and concatenate the normalized fluctuation amplitude sequence, autocorrelation time vector, and higher-order statistical features to form the critical fluctuation feature; Methods for constructing the phase space trajectory of RF link entropy evolution include: Define the RF link entropy evolution phase space, and take the current operating point as the state point in the RF link entropy evolution phase space; map each sampled operating point in the operating point time series to the RF link entropy evolution phase space in sequence to obtain the state point sequence in the RF link entropy evolution phase space; connect the state points corresponding to adjacent sampling times to form a continuous RF link entropy evolution phase space trajectory.

[0009] Furthermore, methods for defining the optimal operating point attraction domain and the performance degradation escape boundary include: Based on the phase space trajectory of the RF link entropy evolution, determine the optimal operating point of the RF test equipment; calculate the Euclidean distance between all state points in the phase space trajectory of the RF link entropy evolution and the optimal operating point, and mark them as deviation distances; calculate the standard deviation of all deviation distances to obtain the deviation standard deviation; calculate the product of the deviation standard deviation and the preset attraction field coefficient to obtain the attraction field radius; construct the optimal operating point attraction field based on the optimal operating point and the attraction field radius. Based on the phase space trajectory of the RF link entropy evolution, calculate the trajectory feature descriptor; based on the trajectory feature descriptor and the critical fluctuation characteristics, calculate the escape boundary radius; with the optimal operating point as the center and the escape boundary radius as the radius, define the performance degradation escape boundary.

[0010] Furthermore, methods for calculating the RF performance stability margin and deviation direction vector include: Obtain the current operating point of the RF test equipment, calculate the Euclidean distance between the current operating point and the optimal operating point, and mark it as the current deviation distance; calculate the RF performance stability margin based on the escape boundary radius and the current deviation distance; The current deviation distance is compared with the radius of the attraction domain to determine whether the current working point is located within the attraction domain of the optimal working point. If the current deviation distance is less than or equal to the radius of the attraction domain, the current working point is located within the attraction domain of the optimal working point, and the deviation direction vector is set to zero. If the current deviation distance is greater than the radius of the attraction domain, the vector difference between the current working point and the optimal working point is calculated to obtain the original deviation vector. The original deviation vector is then normalized to obtain the deviation direction vector.

[0011] Furthermore, methods for triggering anomaly warnings when the RF performance stability margin falls below an adaptive threshold include: Based on the current deviation distance, attraction domain radius, and escape boundary radius, the current state region of the RF test equipment is determined; the current state region includes a normal region, a sub-healthy region, and an abnormal region; a preset base threshold, critical sensitivity coefficient, and region coefficient set are established, with the region coefficient set including region coefficients corresponding to different current state regions; based on the current state region of the RF test equipment, the corresponding region coefficient is obtained from the region coefficient set and marked as the current coefficient; based on the critical fluctuation intensity index and the critical sensitivity coefficient, the critical sensitivity factor is calculated; the base threshold, the current coefficient, and the critical sensitivity factor are multiplied sequentially to obtain the adaptive threshold; The difference between the adaptive threshold and the RF performance stability margin is calculated to obtain the margin gap; the margin gap is compared with a preset set of level thresholds to determine the anomaly warning level; based on the anomaly warning level, warning information is generated, and anomaly warnings are triggered based on the warning information; wherein, the warning information includes the warning level, RF performance stability margin, adaptive threshold, and margin gap.

[0012] Furthermore, methods for determining the dominant trend of equipment deterioration include: Obtain the deviation direction vector. If the deviation direction vector is zero, there is no need to determine the dominant direction. If the deviation direction vector is not zero, take the absolute value of each component in the deviation direction vector and normalize it to obtain the absolute deviation vector. Compare the components in the absolute deviation vector, identify the component with the largest value, and mark it as the dominant component. If the dominant component is located before the absolute deviation vector... In each component, the dominant transformation direction is the entropy generation rate direction; if the dominant component is located after the absolute deviation vector... In each component, the direction of the main director's transformation is the direction of efficiency decline.

[0013] Furthermore, methods for locating the dominant energy dissipation node and impedance mismatch include: If the direction of the dominant director is the direction of entropy generation rate, then the node positioning strategy is adopted; if the direction of the dominant director is the direction of efficiency decrease, then the link positioning strategy is adopted. The node localization strategy is as follows: Construct a candidate set of dominant energy dissipation nodes and a set of high-fluctuation nodes, and obtain the intersection of the two sets. If the intersection is empty, the RF module ranked first in the candidate set of dominant energy dissipation nodes is selected as the dominant energy dissipation node. If the intersection is not empty, the RF module ranked first in the candidate set of dominant energy dissipation nodes is selected as the dominant energy dissipation node. Calculate the input and output reflection coefficients of the dominant energy dissipation node. If the input reflection coefficient is greater than a preset reflection coefficient threshold, the input port of the dominant energy dissipation node is marked as an impedance mismatch location. If the output reflection coefficient is greater than a preset reflection coefficient threshold, the output port of the dominant energy dissipation node is marked as an impedance mismatch location. The link location strategy process is as follows: calculate the path transmission efficiency of each transmission path in the RF link topology; calculate the efficiency drop of each transmission path based on the path transmission efficiency; select the transmission path with the largest efficiency drop as the efficiency bottleneck path; traverse each RF module on the efficiency bottleneck path, calculate the efficiency deviation of each RF module, and select the RF module with the largest efficiency deviation as the dominant energy dissipation node; use the same method as the node location strategy to determine the impedance mismatch location based on the dominant energy dissipation node.

[0014] Furthermore, methods for generating link tuning strategies include: Determine if there is an impedance mismatch location. If an impedance mismatch location exists, the tuning strategy type is impedance matching tuning; if there is no impedance mismatch location, the tuning strategy type is power optimization tuning. For impedance matching tuning types, an impedance matching tuning strategy is generated: if the impedance mismatch location is the input port of the dominant energy dissipation node, the impedance mismatch degree is calculated based on the input reflection coefficient; if the impedance mismatch location is the output port of the dominant energy dissipation node, the impedance mismatch degree is calculated based on the output reflection coefficient; the impedance mismatch degree is compared with a preset set of mismatch level thresholds to determine the impedance mismatch level; and a corresponding impedance matching tuning suggestion is generated based on the impedance mismatch level. For each power optimization tuning type, a power optimization tuning strategy is generated: based on the RF module corresponding to the dominant energy dissipation node, a corresponding power optimization tuning suggestion is generated, which determines the direction of power optimization; The tuning strategy type and tuning suggestion are integrated to generate the link tuning strategy.

[0015] The technical effects and advantages of the IoT-based method for monitoring the status and providing early warning of anomalies in radio frequency test equipment are as follows: By deploying an IoT sensor network in each RF module of the RF test equipment, real-time synchronous acquisition of RF power flow data and heat dissipation data is achieved, effectively overcoming the limitations of traditional methods that only monitor a single parameter independently. The innovative approach introduces non-equilibrium thermodynamics into the field of RF test equipment condition monitoring. By constructing an energy transmission efficiency matrix and calculating the local entropy generation rate, an intrinsic correlation model between RF link energy transmission and heat dissipation is established, enabling precise quantification of the energy dissipation degree and operational deviation of each RF module from a thermodynamic perspective. Furthermore, the dissipative structure theory is used to analyze the coupled evolution law of local entropy generation rate and energy transmission efficiency. Through fluctuation amplitude sequences, autocorrelation time vectors, and higher-order statistical features, the critical fluctuation characteristics of the transition from a high-efficiency transmission state to an energy dissipation state are identified. This allows for the capture of early abnormal signs before irreversible degradation of equipment performance, enabling in-depth analysis of the equipment's state evolution law. This system constructs the phase space trajectory of RF link entropy evolution and defines the optimal operating point attraction domain and performance degradation escape boundary. It scientifically divides the device's operating state into normal, sub-healthy, and abnormal regions. Combined with an adaptive threshold dynamic adjustment mechanism, it significantly improves the accuracy and sensitivity of anomaly warnings, effectively reducing false alarm and missed alarm rates. By determining the dominant evolutionary direction of device state deterioration through deviation direction vectors, and combining node and link positioning strategies, it accurately locates the dominant energy dissipation nodes and impedance mismatch positions. This overcomes the limitations of traditional methods that can only provide general anomaly alarms, clearly indicating the specific RF module or link location of the problem. It automatically generates link tuning strategies, including impedance matching tuning suggestions and power optimization tuning suggestions, providing maintenance personnel with clear repair guidance and adjustment plans, enabling rapid restoration of the RF test equipment to its optimal operating state. It enables intelligent processing across the entire chain, from data acquisition, status modeling, evolution analysis, anomaly warning, fault location to tuning guidance, thereby effectively improving the accuracy of RF test equipment status monitoring and the timeliness of warnings, reducing equipment failure rate and maintenance costs, and ultimately ensuring the accuracy and reliability of test results. Attached Figure Description

[0016] Figure 1 This is a flowchart of the IoT-based radio frequency test equipment status monitoring and anomaly early warning method according to Embodiment 1 of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Example 1:

[0018] Please see Figure 1 As shown in this embodiment, the method for monitoring the status and providing early warning of anomalies of RF test equipment based on the Internet of Things includes: Step S1: Collect RF power flow data and heat dissipation data of the RF test equipment, construct an energy transmission efficiency matrix based on the RF power flow data, calculate the local entropy generation rate of each RF module in the RF test equipment based on the heat dissipation data, and combine them to obtain the current operating point of the RF test equipment.

[0019] Methods for acquiring RF power flow data and heat dissipation data from RF test equipment include: An IoT sensor network is deployed in each RF module of the RF test equipment. The IoT sensor network includes power sensors, temperature sensors, and heat flow sensors. Among them, the power sensors are used to collect RF power flow data, and the temperature sensors and heat flow sensors are used to collect heat dissipation data. The RF modules include, but are not limited to, signal generator modules, power amplifier modules, filter modules, mixer modules, attenuator modules, and load modules. The RF power flow data of each RF module is acquired in real time using power sensors. The RF power flow data includes the input power, output power, and reflected power of each RF module. Specifically, a directional coupler and a power sensor are deployed at the input port of each RF module to acquire the input power and reflected power of the corresponding RF module; a directional coupler and a power sensor are deployed at the output port of each RF module to acquire the output power of the corresponding RF module; the input power, output power, and reflected power of each RF module are then summarized to obtain the RF power flow data of the RF test equipment. The heat dissipation data of each RF module is collected in real time using temperature and heat flux sensors. The heat dissipation data includes the surface temperature of each RF module, the ambient temperature, and the heat flux density. Specifically, a temperature sensor is deployed on the heat dissipation surface of each RF module to collect the surface temperature of the corresponding RF module; a temperature sensor is deployed inside the chassis of the RF test equipment to collect the ambient temperature of the RF test equipment; and a heat flux sensor is deployed on the main heat dissipation path of each RF module to collect the heat flux density of the corresponding RF module. The surface temperature, heat flux density of each RF module, and the ambient temperature of the RF test equipment are then combined to obtain the heat dissipation data of the RF test equipment.

[0020] Methods for constructing the energy transfer efficiency matrix include: The signal transmission relationships of each RF module within the RF test equipment are obtained, and an RF link topology is constructed based on these relationships. Specifically, each RF module is treated as a topology node, and the signal transmission paths between each RF module are determined according to their signal transmission relationships. These signal transmission paths are then treated as topology edges. The RF link topology is constructed based on the connection relationships between the topology nodes and the topology edges, which describes the transmission order and path of RF signals between the RF modules. The signal transmission relationships of each RF module are obtained by those skilled in the art through equipment design documents, experimental measurements, control interface information, or S-parameter testing. Based on the RF power flow data, the module transmission efficiency of each RF module is calculated. Specifically, for each RF module, the corresponding input power, output power, and reflected power are obtained. The difference between the input power and reflected power of each RF module is calculated to obtain the effective input power of each RF module. The ratio of the output power to the effective input power of each RF module is calculated to obtain the module transmission efficiency of each RF module. Based on the RF link topology and the module transmission efficiency of each RF module, an energy transmission efficiency matrix is ​​constructed; specifically, a matrix is ​​constructed. The energy transfer efficiency matrix, The number of RF modules; the first in the power transfer efficiency matrix. Line number Column elements , indicating from the first The radio frequency module to the first The energy transfer efficiency of the RF module; where, if the RF module's energy transfer efficiency is... The radio frequency module and the first If there are topological edges between the radio frequency modules, then equal to the The normalized transmission efficiency of each RF module; if the first... The radio frequency module and the first If there are no topological edges between the radio frequency modules, then ;like ,but equal to the Each radio frequency module corresponds to the normalized module transmission efficiency; It should be noted that the normalization process involved in this embodiment is implemented through the minimum-maximum normalization method, which is used to eliminate the dimensional differences of various data between different radio frequency modules.

[0021] Methods for calculating the local entropy generation rate of each RF module include: Based on the heat dissipation data, the heat dissipation power of each RF module is calculated. Specifically, for each RF module, the corresponding surface temperature, heat flux density, heat dissipation surface area, and ambient temperature of the RF test equipment are obtained. The heat dissipation surface area of ​​each RF module is determined by those skilled in the art based on the structural design documents or actual measurement results of each RF module. The heat dissipation power of each RF module is obtained by multiplying the heat flux density and the heat dissipation surface area of ​​each RF module. Based on the thermodynamic entropy generation theory, and using RF power flow data and heat dissipation power, the local entropy generation rate of each RF module is calculated. Specifically, the difference between the effective input power and output power of each RF module is calculated to obtain the energy dissipation power of each RF module. Based on the principle of non-equilibrium thermodynamics, the RF module is considered as an open system, and irreversible processes within the RF module (including resistance loss, dielectric loss, and radiation loss) will generate entropy increase. The specific expression for the local entropy generation rate is: ; In the formula, For the first The local entropy generation rate of each radio frequency module For the first The power dissipation of each radio frequency module For the first The surface temperature of each RF module For the first The heat dissipation power of each RF module For ambient temperature, For normalization processing; both surface temperature and ambient temperature are expressed in absolute temperature form, i.e., in Kelvin (K), which can be obtained from the corresponding Celsius temperature (i.e., the surface temperature or ambient temperature collected by the temperature sensor) by adding... Obtained through conversion; It should be understood that the local entropy generation rate consists of two parts: the part before the plus sign represents the entropy increase rate generated during the conversion of electromagnetic energy into heat energy inside the RF module; the part after the plus sign represents the entropy increase rate generated during the heat exchange between the RF module and the environment. The local entropy generation rate is used to quantify the degree of energy dissipation and thermodynamic irreversibility of the RF module. The higher the local entropy generation rate, the more severe the energy dissipation of the corresponding RF module and the further the operating state deviates from the optimal working state.

[0022] Methods for obtaining the current operating point of an RF test device include: The QR algorithm is used to perform eigenvalue decomposition on the energy transmission efficiency matrix, obtaining multiple eigenvalues ​​and eigenvectors. The ratio between each eigenvalue and the total eigenvalues ​​(the sum of all eigenvalues) is calculated to obtain the contribution rate of each eigenvalue. All eigenvalues ​​are sorted in descending order, and the cumulative contribution rate corresponding to each eigenvalue is calculated. The cumulative contribution rate is calculated by summing the contribution rate of the eigenvalue with the contribution rates of all eigenvalues ​​preceding it. All eigenvalues ​​in descending order are traversed, and the first eigenvalue with a cumulative contribution rate greater than or equal to a preset contribution threshold is found and marked as the selected value. The eigenvector corresponding to the selected value is concatenated with the eigenvectors corresponding to all eigenvalues ​​preceding the selected value to obtain the efficiency eigenvector. The efficiency eigenvector reflects the main structural features of the energy transmission efficiency matrix and can characterize the overall energy transmission efficiency distribution pattern of the RF link in a lower dimension. The local entropy generation rates of each RF module are combined to obtain an entropy generation rate vector; this vector is then concatenated with the efficiency feature vector to construct the current operating point of the RF test equipment; where the current operating point is... dimensional vector, front Each component reflects the energy dissipation and thermodynamic state of each RF module. Each component reflects the overall energy transmission efficiency characteristics of the radio frequency link. The number of eigenvectors to be spliced ​​to form an efficiency eigenvector; by fusing local entropy generation rate and energy transfer efficiency information, the current operating point can comprehensively characterize the operating state of the RF test equipment in a thermodynamic sense; It should be noted that the contribution threshold is preset by those skilled in the art based on the actual situation, and the QR algorithm is a well-known technology in the field. The specific process will not be elaborated on here.

[0023] Step S2: For the RF links formed by each RF module, the coupling evolution law of local entropy generation rate and energy transmission efficiency matrix is ​​analyzed using dissipative structure theory. The critical fluctuation characteristics of the transition from high-efficiency transmission state to energy dissipation state are identified, and the phase space trajectory of RF link entropy evolution is constructed.

[0024] An RF link refers to the complete path of RF signal transmission between various RF modules within an RF test device. It specifically describes the transmission sequence and connection relationship of RF signals from the input port through each RF module to the output port, and is determined by the aforementioned RF link topology.

[0025] Methods for analyzing the coupled evolution of local entropy generation rate and energy transfer efficiency matrix include: A coupling relationship between local entropy generation rate and energy transmission efficiency is established to obtain the coupling degree index of each radio frequency module, which is used to reflect the synergistic effect between energy dissipation and transmission efficiency reduction of radio frequency module. Specifically, for each radio frequency module, the product between local entropy generation rate and normalized module transmission efficiency is calculated, and the local entropy generation rate is subtracted from the calculation result to obtain the coupling degree index. The evolution of the local entropy generation rate and the energy transfer efficiency matrix over time is analyzed separately, constructing an entropy generation rate change sequence and an efficiency feature change sequence. Specifically, a sampling time window and sampling interval are set, both pre-defined by those skilled in the art based on the operating characteristics of the RF test equipment, and the sampling time window includes the current time. Within the sampling time window, the current operating point at multiple sampling times is continuously collected according to the sampling interval and marked as a sampling operating point. The sampling operating points at multiple sampling times are combined to form an operating point time series. For each sampling operating point in the operating point time series, the corresponding entropy generation rate vector and efficiency feature vector are extracted. The change in the entropy generation rate vector between adjacent sampling times is calculated to obtain the entropy generation rate change sequence. The change in the efficiency feature vector between adjacent sampling times is calculated to obtain the efficiency feature change sequence. Mutual information analysis is employed to calculate the mutual information value between the entropy generation rate change sequence and the efficiency characteristic change sequence. The mutual information value quantifies the nonlinear coupling strength between the local entropy generation rate and energy transfer efficiency; therefore, it is the quantification result of the coupling evolution law. Specifically, the entropy generation rate change sequence and the efficiency characteristic change sequence are discretized, dividing the continuous values ​​into multiple discrete intervals. All discrete intervals belonging to the same change sequence have the same value range. The frequency distribution of each discrete interval (i.e., the number of values ​​falling within each discrete interval) is statistically analyzed, and the joint probability distribution and marginal probability distribution of the entropy generation rate change sequence and the efficiency characteristic change sequence are calculated. Based on the joint probability distribution and marginal probability distribution, the mutual information value is calculated. The calculation methods for the joint probability distribution, marginal probability distribution, and mutual information value are standard statistical methods known in the field, and the specific calculation process will not be elaborated upon here.

[0026] Methods for identifying critical fluctuation characteristics during the transition from an efficient transport state to an energy dissipation state include: Two typical operating states of RF test equipment are defined: high-efficiency transmission state and energy dissipation state. The high-efficiency transmission state refers to the normal operating state in which the overall energy transmission efficiency of the RF link is high and the local entropy generation rate of each RF module is low. The energy dissipation state refers to the abnormal operating state in which the overall energy transmission efficiency of the RF link decreases and the local entropy generation rate of one or more RF modules increases significantly. For the operating point time series, the fluctuation amplitude vector of each sampling operating point is calculated and combined to form a fluctuation amplitude sequence. Specifically, for each sampling operating point in the operating point time series, taking the sampling time corresponding to each sampling operating point as the endpoint, a sliding window of a preset length is taken. The standard deviation and mean of each component corresponding to each sampling operating point within the sliding window are calculated separately to obtain multiple sliding standard deviations and sliding means for each component. Here, the components in the sampling operating point refer to each element in the sampling operating point, and the length of the sliding window is preset by those skilled in the art according to the actual situation. The sliding standard deviations of the same sampling operating point are integrated to obtain the fluctuation amplitude vector of each sampling operating point. The specific form of the fluctuation amplitude vector is as follows: In the formula, For the first The fluctuation amplitude vector of each sampling working point For the first The sampling work point of the first The sliding standard deviation of each component; the fluctuation amplitude vectors of each sampling working point are combined to form a fluctuation amplitude sequence; For the operating point time series, the corresponding autocorrelation time vector is calculated. Specifically, the autocorrelation function is calculated for each component in the operating point time series, obtaining the curve of the autocorrelation coefficient of each component changing with the time lag. For each component, the time lag value corresponding to the first drop of the autocorrelation coefficient below a preset correlation threshold is extracted as the autocorrelation time of the corresponding component. The autocorrelation times of each component are integrated to obtain the autocorrelation time vector. The correlation threshold is preset by those skilled in the art based on the actual situation, and is typically set to a value of [value missing]. (Approximately 0.368) or 0.5; The calculation method of the autocorrelation function is a well-known technique in this field, and the specific process will not be elaborated in detail here; For the operating point time series, calculate the corresponding higher-order statistical features; specifically, for each component in the operating point time series, calculate the corresponding skewness and kurtosis; the specific expression for skewness is: In the formula, For the first The sampling work point of the first The skewness of each component is used to describe the degree of asymmetry in the component distribution. For mathematical expectation calculation, For the first The first of the sampling work points One portion, For the first The sampling work point of the first The moving average of each component For the first The sampling work point of the first The moving standard deviation of each component; the specific expression for kurtosis is: In the formula, For the first The sampling work point of the first The kurtosis of each component is used to describe the sharpness of the component distribution; the skewness and kurtosis of each component are integrated to obtain the skewness vector and the kurtosis vector; the skewness vector and the kurtosis vector are combined to form a higher-order statistical feature. The fluctuation amplitude sequence, autocorrelation time vector, and higher-order statistical features are normalized respectively, and the normalized fluctuation amplitude sequence, autocorrelation time vector, and higher-order statistical features are combined to form the critical fluctuation feature.

[0027] Methods for constructing the phase space trajectory of RF link entropy evolution include: Define the RF link entropy evolution phase space, and take the current operating point as the state point in the RF link entropy evolution phase space; where, the RF link entropy evolution phase space is... Dimensional Euclidean space, in which the preceding The dimension corresponds to the local entropy generation rate of each RF module, and then... Each component of the efficiency eigenvector corresponds to a dimension; Based on the operating point time series, a phase space trajectory of RF link entropy evolution is constructed. Specifically, each sampling operating point in the operating point time series is sequentially mapped to the RF link entropy evolution phase space to obtain a sequence of state points in the RF link entropy evolution phase space. The state points corresponding to adjacent sampling times are connected to form a continuous RF link entropy evolution phase space trajectory, which is used to reflect the evolution of the operating state of the RF test equipment over time.

[0028] Step S3: Define the optimal operating point attraction domain and the performance degradation escape boundary in the phase space trajectory of the RF link entropy evolution. Calculate the RF performance stability margin based on the current operating point and the performance degradation escape boundary. Calculate the deviation direction vector based on the current operating point and the optimal operating point attraction domain.

[0029] Methods for defining the optimal operating point attraction region include: Based on the phase space trajectory of the RF link entropy evolution, the optimal operating point of the RF test equipment is determined. Specifically, all state points in the phase space trajectory of the RF link entropy evolution are traversed, and the comprehensive performance index corresponding to each state point is calculated. The comprehensive performance index is used to evaluate the overall operating performance of the RF test equipment in the corresponding state. The calculation method for the comprehensive performance index is as follows: the local entropy generation rate and module transmission efficiency of each RF module corresponding to the state point are normalized respectively; the local entropy generation rates of each RF module after normalization are summed sequentially to obtain the overall entropy generation rate; and the module transmission efficiency of each RF module after normalization is calculated... The mean is calculated, and the result is subtracted to obtain the average transmission loss. Performance weights are assigned to the overall entropy generation rate and the average transmission loss, respectively. Based on these performance weights, a weighted summation of the overall entropy generation rate and the average transmission loss is performed to obtain the comprehensive performance index of each state point. Each performance weight is pre-set by a person skilled in the art according to the actual situation. The comprehensive performance indices of each state point are compared, and the state point with the smallest comprehensive performance index is selected as the optimal operating point. The optimal operating point represents the ideal operating state of the RF test equipment, characterized by minimal energy dissipation and highest transmission efficiency in the RF link entropy evolution phase space. Calculate the Euclidean distance between all state points and the optimal operating point in the phase space trajectory of the RF link entropy evolution, and mark them as deviation distances; calculate the standard deviation of all deviation distances to obtain the deviation standard deviation; calculate the product of the deviation standard deviation and the preset attraction domain coefficient to obtain the attraction domain radius; wherein, the attraction domain coefficient is preset by those skilled in the art according to the actual situation; construct the optimal operating point attraction domain based on the optimal operating point and the attraction domain radius; wherein, the optimal operating point attraction domain is a hyperspherical region centered on the optimal operating point and with the attraction domain radius as its radius.

[0030] Methods for defining performance degradation escape boundaries include: Based on the RF link entropy evolution phase space trajectory, a trajectory feature descriptor is calculated, which includes the trajectory length and average curvature. Specifically, the Euclidean distance between every two adjacent state points in the RF link entropy evolution phase space trajectory is calculated and marked as the state distance. All state distances are summed to obtain the trajectory length. For each state point, the previous and next state points are obtained from the RF link entropy evolution phase space trajectory. The previous state point is subtracted from each state point to obtain the first vector of each state point. The next state point is subtracted from each state point to obtain the second vector of each state point. The angle between the first and second vectors corresponding to each state point is calculated using the vector angle formula and used as the local curvature of each state point. The average curvature is obtained by averaging the local curvatures of all state points. Among them, the trajectory length is used to reflect the degree of change in the operating state of the RF test equipment. The longer the trajectory length, the more drastic the change in the equipment state. The average curvature is used to reflect the degree of change in the evolution direction of the operating state of the RF test equipment. The larger the average curvature, the more frequent the change in the evolution direction of the RF test equipment state. The vector angle formula is a well-known technology in this field, and the specific process will not be elaborated on here.

[0031] Based on the trajectory feature descriptor and critical fluctuation features, the escape boundary radius is calculated. Specifically, each component in the critical fluctuation feature is assigned a corresponding fluctuation weight, which is pre-set by those skilled in the art based on the indicative role of each component in the critical fluctuation feature in the critical transition. The components in the critical fluctuation feature are weighted and summed based on the fluctuation weights to obtain the critical fluctuation intensity index. A set of basic boundary radii and adjustment coefficients is pre-set, including the adjustment coefficients corresponding to the trajectory length, average curvature, and critical fluctuation intensity index. Both the basic boundary radius and the set of adjustment coefficients are pre-set by those skilled in the art based on actual conditions. The trajectory length and average curvature are normalized respectively, and based on the set of adjustment coefficients, the normalized trajectory length and average curvature are weighted and summed, and the result is incremented by one to obtain the trajectory adjustment factor. The product of the critical fluctuation intensity index and the corresponding adjustment coefficient is calculated, and the result is subtracted to obtain the critical correction factor. The basic boundary radius, trajectory adjustment factor, and critical correction factor are multiplied sequentially to obtain the escape boundary radius. It should be understood that the calculation of the escape boundary radius takes into account two factors: first, the phase space trajectory dynamics reflected by the trajectory feature descriptor. When the trajectory length is long or the average curvature is large, it indicates that the system state changes drastically, and the escape boundary radius needs to be expanded to provide a greater safety margin; second, the critical fluctuation intensity index reflects the critical state of the system. When the critical fluctuation intensity index is high, it indicates that the system is close to the critical point, and the escape boundary radius needs to be contracted to improve the early warning sensitivity.

[0032] Define the performance degradation escape boundary with the optimal operating point as the center and the escape boundary radius as the radius; It should be understood that the optimal operating point attraction region refers to the region in the RF link entropy evolution phase space centered on the optimal operating point, where the RF test equipment can automatically recover to its optimal state through its own adjustment capabilities. When the current operating point of the RF test equipment is within the optimal operating point attraction region, even if subjected to a small disturbance, the RF test equipment can automatically recover to normal without external intervention. On the other hand, the performance degradation escape boundary refers to the boundary in the RF link entropy evolution phase space that separates the controllable operating region from the uncontrollable degradation region. When the current operating point of the RF test equipment crosses the performance degradation escape boundary, the RF test equipment may experience irreversible performance degradation, requiring immediate manual intervention. Therefore, the optimal operating point attraction domain and the performance degradation escape boundary divide the RF link entropy evolution phase space into three regions: the normal region, the sub-healthy region, and the abnormal region. The normal region is located within the optimal operating point attraction domain, where the RF test equipment is in good condition and can self-regulate. The sub-healthy region is located outside the optimal operating point attraction domain but inside the performance degradation escape boundary, where the RF test equipment deviates from its intended state but is still controllable and requires attention. The abnormal region is located outside the performance degradation escape boundary, where the RF test equipment is out of control and requires immediate intervention.

[0033] Methods for calculating RF performance stability margin include: Based on the current operating point and the performance degradation escape boundary, the RF performance stability margin is calculated. Specifically, the current operating point of the RF test equipment is obtained, the Euclidean distance between the current operating point and the optimal operating point is calculated and marked as the current deviation distance, the difference between the escape boundary radius and the current deviation distance is calculated, and the difference result is divided by the escape boundary radius to obtain the RF performance stability margin.

[0034] Methods for calculating the deviation direction vector include: Based on the attraction domains of the current operating point and the optimal operating point, the deviation direction vector is calculated. Specifically, the current deviation distance is compared with the radius of the attraction domain to determine whether the current operating point is located within the attraction domain of the optimal operating point. If the current deviation distance is less than or equal to the radius of the attraction domain, the current operating point is located within the attraction domain of the optimal operating point, and the deviation direction vector is set to zero. If the current deviation distance is greater than the radius of the attraction domain, the vector difference between the current operating point and the optimal operating point is calculated to obtain the original deviation vector. The original deviation vector is then normalized (i.e., the ratio between the original deviation vector and the corresponding norm is calculated) to obtain the deviation direction vector. The deviation direction vector represents the deviation direction of the current operating point relative to the optimal operating point, and each component of the deviation direction vector reflects the degree of deviation of the RF test equipment in each state dimension.

[0035] Step S4: Dynamically calculate the adaptive threshold. When the RF performance stability margin is lower than the adaptive threshold, trigger an anomaly warning. Determine the dominant adaptive direction of device state deterioration based on the deviation direction vector, and locate the dominant energy dissipation node and impedance mismatch position in the RF link by combining critical fluctuation characteristics.

[0036] Methods for triggering anomaly warnings when the RF performance stability margin falls below an adaptive threshold include: Based on the current deviation distance, the radius of the attraction domain, and the radius of the escape boundary, the current state region of the RF test equipment is determined. Specifically, if the current deviation distance is less than or equal to the radius of the attraction domain, the current operating point is in the normal region; if the current deviation distance is greater than the radius of the attraction domain but less than the radius of the escape boundary, the current operating point is in the sub-health region; if the current deviation distance is greater than or equal to the radius of the escape boundary, the current operating point is in the abnormal region. Based on the current state region and the critical fluctuation intensity index, an adaptive threshold is calculated. Specifically, a base threshold, a critical sensitivity coefficient, and a set of regional coefficients are preset. The set of regional coefficients includes regional coefficients corresponding to different current state regions. The base threshold, critical sensitivity coefficient, and set of regional coefficients are all preset by those skilled in the art according to the actual situation. Based on the current state region of the RF test equipment, the corresponding regional coefficient is obtained from the set of regional coefficients and marked as the current coefficient. The product of the critical fluctuation intensity index and the critical sensitivity coefficient is calculated, and the result is subtracted to obtain the critical sensitivity factor. The base threshold, the current coefficient, and the critical sensitivity factor are multiplied sequentially to obtain the adaptive threshold. It should be understood that the calculation of the adaptive threshold takes into account two factors: First, the influence of the current state region. When the device is in the normal region, a higher region coefficient is used to make the adaptive threshold relatively lenient and avoid false alarms. When the device is in the sub-healthy region, a lower region coefficient is used to make the adaptive threshold relatively strict and improve the sensitivity of the warning. When the device is in the abnormal region, the lowest region coefficient is used to ensure timely triggering of the warning. Second, the influence of the critical fluctuation intensity index. When the critical fluctuation intensity index is high, it indicates that the system is close to the critical transition point, and the adaptive threshold needs to be further reduced to improve the sensitivity of the warning.

[0037] When the RF performance stability margin is less than the adaptive threshold, an anomaly warning level is determined. Specifically, the difference between the adaptive threshold and the RF performance stability margin is calculated to obtain the margin gap. The margin gap is compared with a preset set of level thresholds, which includes a level 1 threshold, a level 2 threshold, and a level 3 threshold, where the level 1 threshold is less than the level 2 threshold, and the level 2 threshold is less than the level 3 threshold. The level threshold set is preset by those skilled in the art based on actual conditions. If the margin gap is greater than zero and less than or equal to the level 1 threshold, the anomaly warning level is level 1, indicating a mild anomaly. If the margin gap is greater than the level 1 threshold and less than or equal to the level 2 threshold, the anomaly warning level is level 2, indicating a moderate anomaly. If the margin gap is greater than the level 2 threshold and less than or equal to the level 3 threshold, the anomaly warning level is level 3, indicating a severe anomaly. If the margin gap is greater than the level 3 threshold, the anomaly warning level is emergency, indicating a serious anomaly. Based on the anomaly warning level, a warning message is generated. The warning message includes the warning level, RF performance stability margin, adaptive threshold, and margin gap. An anomaly warning is triggered based on the warning message, and the warning message is sent to the remote monitoring terminal through the Internet of Things network so that maintenance personnel can be informed of the abnormal status of the RF test equipment in a timely manner.

[0038] Methods for determining the dominant trend of equipment deterioration include: Obtain the deviation direction vector. If the deviation direction vector is a zero vector, it indicates that the current operating point is within the optimal operating point attraction domain, the state of the RF test equipment has not deteriorated significantly, and there is no need to determine the dominant orientation direction. If the deviation direction vector is not a zero vector, take the absolute value of each component in the deviation direction vector and normalize it to obtain the absolute deviation vector. If the component is a vector, take the absolute value of the component to calculate the norm of the corresponding vector. Compare each component in the absolute deviation vector, identify the component with the largest value, and mark it as the dominant component; if the dominant component is located at the beginning of the absolute deviation vector... In the component, the dominant evolution direction is the entropy generation rate direction, indicating that the increase in the local entropy generation rate of the corresponding RF module is the main factor leading to the deterioration of the RF test equipment state; if the dominant component is located after the absolute deviation vector Among the components, the dominant evolution direction is the direction of efficiency decline, indicating that the overall energy transmission efficiency of the RF link is reduced, which is the main factor leading to the deterioration of the equipment status.

[0039] Methods for locating dominant energy dissipation nodes and impedance mismatch locations include: Based on the dominant direction of evolution, a fault location strategy is determined. Specifically, if the dominant direction of evolution is the entropy generation rate direction, a node location strategy is adopted, focusing on analyzing the deviation of the local entropy generation rate of each RF module to locate the specific RF module with abnormal energy dissipation. If the dominant direction of evolution is the efficiency degradation direction, a link location strategy is adopted, focusing on analyzing the reasons for the overall energy transmission efficiency degradation of the RF link to locate the efficiency bottleneck node and impedance mismatch location. The node localization strategy process is as follows: extract the previous direction vector from the deviation direction vector. The entropy generation rate deviation vector is obtained by considering several components; each component in the entropy generation rate deviation vector corresponds to the degree of local entropy generation rate deviation of each RF module; the absolute values ​​of each component in the entropy generation rate deviation vector are taken and sorted in descending order; the components listed first are selected. The radio frequency modules corresponding to the components of the bit are used as the candidate set of dominant energy dissipation nodes; among them... The specific values ​​are preset by those skilled in the art based on the actual situation; Extract the fluctuation amplitude sequence from the critical fluctuation features, and obtain the fluctuation amplitude vector corresponding to the current time in the fluctuation amplitude sequence; extract the previous fluctuation amplitude vector from the fluctuation amplitude vector. The entropy generation rate fluctuation vector is obtained by considering several components; each component in the entropy generation rate fluctuation vector reflects the degree of fluctuation in the local entropy generation rate of each radio frequency module; the components in the entropy generation rate fluctuation vector are sorted in descending order, and the components with the highest order are selected. The radio frequency modules corresponding to the components of the bits are used as a set of high fluctuation nodes; Obtain the intersection of the candidate set of dominant energy dissipation nodes and the set of high fluctuation nodes. If the intersection is an empty set, the RF module ranked first in the candidate set of dominant energy dissipation nodes is taken as the dominant energy dissipation node. If the intersection is not an empty set, the RF module ranked first in the candidate set of dominant energy dissipation nodes is selected as the dominant energy dissipation node in the intersection. This is used to represent the RF module with the most severe energy dissipation in the RF link and the greatest contribution to the deterioration of the device status. The input reflection coefficient is obtained by calculating the ratio of the reflected power to the input power of the dominant energy dissipation node. The next RF module after the dominant energy dissipation node is obtained from the RF link topology and marked as a post-module. The output reflection coefficient is obtained by calculating the ratio of the reflected power of the post-module to the output power of the dominant energy dissipation node. A preset reflection coefficient threshold is established, which is set by those skilled in the art based on actual conditions. The input and output reflection coefficients are compared with the reflection coefficient threshold. If the input reflection coefficient is greater than the threshold, the input port of the dominant energy dissipation node is marked as an impedance mismatch location. If the output reflection coefficient is greater than the threshold, the output port of the dominant energy dissipation node is marked as an impedance mismatch location. If both the input and output reflection coefficients are less than or equal to the threshold, the dominant energy dissipation node does not have significant impedance mismatch, and energy dissipation is mainly caused by internal losses within the RF module. The link location strategy process is as follows: traverse each transmission path in the RF link topology, calculate the product of the module transmission efficiencies of each RF module on each transmission path to obtain the path transmission efficiency of each transmission path; preset a normal efficiency set, which includes the normal path efficiency corresponding to each transmission path and the normal module efficiency corresponding to each RF module, pre-set by those skilled in the art based on historical statistical data of the RF test equipment under normal operating conditions; wherein, the normal path efficiency is the path transmission efficiency of the transmission path under normal operating conditions, and the normal module efficiency is the module transmission efficiency of the RF module under normal operating conditions; calculate the difference between the path transmission efficiency of each transmission path and the corresponding normal path efficiency in the normal efficiency set to obtain the efficiency drop of each transmission path; select the transmission path with the largest efficiency drop as the efficiency bottleneck path. Traverse each RF module on the efficiency bottleneck path, calculate the difference between the module transmission efficiency of each RF module and the corresponding normal module efficiency in the normal efficiency set, and mark it as efficiency deviation; select the RF module with the largest efficiency deviation as the dominant energy dissipation node, which is used to represent the RF module with the most significant decrease in transmission efficiency and the greatest impact on the overall efficiency of the link; use the same method as the node positioning strategy to determine the impedance mismatch location based on the dominant energy dissipation node.

[0040] Step S5: Generate a link tuning strategy based on the dominant energy dissipation node and impedance mismatch location.

[0041] Methods for generating link tuning strategies include: Determine if there is an impedance mismatch location. If an impedance mismatch location exists, the tuning strategy type is impedance matching tuning; if there is no impedance mismatch location, the tuning strategy type is power optimization tuning. For impedance matching tuning types, an impedance matching tuning strategy is generated. Specifically, if the impedance mismatch location is at the input port of the dominant energy dissipation node, the degree of impedance mismatch is calculated based on the input reflection coefficient; if the impedance mismatch location is at the output port of the dominant energy dissipation node, the degree of impedance mismatch is calculated based on the output reflection coefficient. The calculation method for the degree of impedance mismatch is as follows: the input and output reflection coefficients are collectively referred to as reflection coefficients; the absolute value of the reflection coefficients is taken to obtain the reflection amplitude; the reflection amplitude is added to the reflection amplitude to obtain the peak standing wave voltage; the reflection amplitude is subtracted from the reflection amplitude to obtain the valley standing wave voltage; the ratio of the peak standing wave voltage to the valley standing wave voltage is calculated to obtain the degree of impedance mismatch. The impedance mismatch level is determined by comparing the degree of impedance mismatch with a preset set of mismatch level thresholds. The set of mismatch level thresholds includes a mild threshold, a moderate threshold, and a severe threshold, which are preset by those skilled in the art based on actual conditions. If the degree of impedance mismatch is less than or equal to the mild threshold, the impedance mismatch level is mild. If the degree of impedance mismatch is greater than the mild threshold but less than or equal to the moderate threshold, the impedance mismatch level is moderate. If the degree of impedance mismatch is greater than the moderate threshold but less than or equal to the severe threshold, the impedance mismatch level is severe. If the degree of impedance mismatch is greater than the severe threshold, the impedance mismatch level is critical. Based on the impedance mismatch level, corresponding impedance matching tuning recommendations are generated. For a slight mismatch, the recommendation is to fine-tune the matching network parameters, with an adjustment range of 5% to 10%. For a moderate mismatch, the recommendation is to adjust the matching network parameters, with an adjustment range of 10% to 20%. For a severe mismatch, the recommendation is to redesign the matching network and check the condition of the connectors and transmission lines. For a critical mismatch, the recommendation is to immediately shut down the system for repair and replace the matching network or related RF components. The matching network parameters refer to the adjustable circuit element parameters in the RF test equipment, such as adjustable capacitors, adjustable inductors, and transformer turns ratios. For each power optimization tuning type, a power optimization tuning strategy is generated. Specifically, based on the RF module corresponding to the dominant energy dissipation node, a corresponding power optimization tuning suggestion is generated, which determines the power optimization direction. For example, if the dominant energy dissipation node is a power amplifier module, the power optimization direction is to reduce the operating power or improve heat dissipation; if the dominant energy dissipation node is a filter module, the power optimization direction is to check the filter performance or replace the filter; if the dominant energy dissipation node is a mixer module, the power optimization direction is to adjust the local oscillator power or check the mixer operating point; if the dominant energy dissipation node is an attenuator module, the power optimization direction is to check the attenuator power capacity or replace the attenuator. By integrating tuning strategy types and tuning suggestions, a link tuning strategy is generated. This strategy is then sent to a remote monitoring terminal via an IoT network, providing maintenance personnel with accurate fault location and targeted tuning guidance. This allows maintenance personnel to perform targeted maintenance and adjustments on the RF test equipment based on the link tuning strategy, thereby quickly restoring the RF test equipment to its optimal working state and improving the equipment's operating efficiency and reliability.

[0042] This embodiment deploys an IoT sensor network in each RF module of the RF test equipment to achieve real-time synchronous acquisition of RF power flow data and heat dissipation data, effectively overcoming the limitations of traditional methods that only monitor a single parameter independently. It innovatively introduces the principle of non-equilibrium thermodynamics into the field of RF test equipment status monitoring. By constructing an energy transmission efficiency matrix and calculating the local entropy generation rate, an intrinsic correlation model between RF link energy transmission and heat dissipation is established, enabling precise quantification of the energy dissipation degree and operational deviation of each RF module from a thermodynamic perspective. Furthermore, it uses dissipative structure theory to analyze the coupled evolution law of local entropy generation rate and energy transmission efficiency. Through fluctuation amplitude sequences, autocorrelation time vectors, and higher-order statistical features, it identifies the critical fluctuation characteristics of the transition from a high-efficiency transmission state to an energy dissipation state, enabling the capture of early abnormal signs before irreversible degradation of equipment performance and achieving in-depth analysis of the equipment's state evolution law. This embodiment constructs the phase space trajectory of RF link entropy evolution and defines the optimal operating point attraction domain and performance degradation escape boundary. It scientifically divides the device's operating state into normal, sub-healthy, and abnormal regions. Combined with an adaptive threshold dynamic adjustment mechanism, it significantly improves the accuracy and sensitivity of anomaly warnings, effectively reducing false alarm and missed alarm rates. By determining the dominant evolutionary direction of device state deterioration through deviation direction vectors, and combining node and link positioning strategies, it accurately locates the dominant energy dissipation nodes and impedance mismatch positions. This overcomes the limitations of traditional methods that can only provide general anomaly alarms, clearly indicating the specific RF module or link location of the problem. It automatically generates link tuning strategies including impedance matching tuning suggestions and power optimization tuning suggestions, providing maintenance personnel with clear repair guidance and adjustment plans, enabling rapid restoration of the RF test equipment to its optimal operating state. This embodiment realizes intelligent processing across the entire chain, from data acquisition, state modeling, evolution analysis, anomaly warning, fault location to tuning guidance, thereby effectively improving the accuracy of RF test equipment status monitoring and the timeliness of warnings, reducing equipment failure rate and maintenance costs, and thus ensuring the accuracy and reliability of test results. Example 2:

[0043] This application also provides an electronic device. The electronic device may include one or more processors and one or more memories. The memories store computer-readable code, which, when executed by the one or more processors, can perform the IoT-based RF test device status monitoring and anomaly early warning method described above.

[0044] The method according to the embodiments of this application can also be implemented using the architecture of the electronic device shown in this application. The electronic device may include a bus, one or more CPUs, ROM, RAM, a communication port connected to a network, input / output, a hard disk, etc. The storage device in the electronic device, such as a ROM or hard disk, may store the IoT-based RF test equipment status monitoring and anomaly early warning method provided in this application. Furthermore, the electronic device may also include a user interface. Of course, the architecture shown in this application is merely exemplary; when implementing different devices, one or more components in the electronic device shown in this application may be omitted according to actual needs. Example 3:

[0045] Please refer to the accompanying drawings. One embodiment of this application discloses a computer-readable storage medium. The computer-readable storage medium stores computer-readable instructions. When the computer-readable instructions are executed by a processor, they can perform the IoT-based radio frequency test equipment status monitoring and anomaly early warning method according to an embodiment of this application, as described above. The storage medium includes, but is not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0046] Furthermore, according to embodiments of this application, the processes described in the above-referenced flowcharts can be implemented as computer software programs. For example, this application provides a non-transitory machine-readable storage medium storing machine-readable instructions that can be executed by a processor to perform instructions corresponding to the method steps provided in this application, such as an IoT-based method for monitoring the status and issuing early warnings for radio frequency test equipment. When this computer program is executed by a central processing unit (CPU), it performs the functions defined in the method of this application.

[0047] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0048] All formulas in this manual are dimensionless and calculated numerically. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0049] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims

1. A method for monitoring the status and providing early warning of anomalies in radio frequency test equipment based on the Internet of Things, characterized in that, include: Step S1: Collect RF power flow data and heat dissipation data of the RF test equipment, construct an energy transmission efficiency matrix based on the RF power flow data, calculate the local entropy generation rate of each RF module in the RF test equipment based on the heat dissipation data, and combine them to obtain the current operating point of the RF test equipment. Step S2: For the RF links formed by each RF module, the coupling evolution law of local entropy generation rate and energy transmission efficiency matrix is ​​analyzed using dissipative structure theory. The critical fluctuation characteristics of the transition from the high-efficiency transmission state to the energy dissipation state are identified, and the phase space trajectory of the RF link entropy evolution is constructed. Step S3: Define the optimal operating point attraction domain and the performance degradation escape boundary in the phase space trajectory of the RF link entropy evolution. Calculate the RF performance stability margin based on the current operating point and the performance degradation escape boundary. Calculate the deviation direction vector based on the current operating point and the optimal operating point attraction domain. Step S4: Dynamically calculate the adaptive threshold. When the RF performance stability margin is lower than the adaptive threshold, trigger an anomaly warning. Determine the dominant adaptive direction of device state deterioration based on the deviation direction vector, and locate the dominant energy dissipation node and impedance mismatch position in the RF link by combining critical fluctuation characteristics. Step S5: Generate a link tuning strategy based on the dominant energy dissipation node and impedance mismatch location.

2. The method for monitoring the status and providing early warning of anomalies of RF test equipment based on the Internet of Things as described in claim 1, characterized in that, Methods for constructing the energy transfer efficiency matrix include: Obtain the signal transmission relationship of each RF module, and construct the RF link topology based on the signal transmission relationship; calculate the module transmission efficiency of each RF module based on the RF power flow data; construct the energy transmission efficiency matrix based on the RF link topology and the module transmission efficiency of each RF module. Methods for calculating the local entropy generation rate of each RF module include: Based on the heat dissipation data, calculate the heat dissipation power of each RF module; based on the RF power flow data and heat dissipation power, calculate the local entropy generation rate of each RF module. Methods for obtaining the current operating point of an RF test device include: The energy transfer efficiency matrix is ​​decomposed into eigenvalues ​​and eigenvectors; based on the eigenvalues, the following eigenvalues ​​are selected: eigenvectors, and The efficiency feature vector is obtained by concatenating the feature vectors; the local entropy generation rates of each RF module are combined to obtain the entropy generation rate vector; the entropy generation rate vector and the efficiency feature vector are concatenated to construct the current operating point of the RF test equipment.

3. The method for monitoring the status and providing early warning of anomalies of RF test equipment based on the Internet of Things as described in claim 2, characterized in that, Methods for analyzing the coupled evolution of local entropy generation rate and energy transfer efficiency matrix include: A coupling relationship between local entropy generation rate and energy transfer efficiency is established to obtain the coupling degree index of each RF module. A sampling time window and sampling interval are set. Within the sampling time window, the current operating point at multiple sampling moments is continuously collected according to the sampling interval and marked as a sampling operating point. The sampling operating points at multiple sampling moments are combined to form an operating point time series. For each sampling operating point in the operating point time series, the corresponding entropy generation rate vector and efficiency feature vector are extracted. The change in the entropy generation rate vector between adjacent sampling moments is calculated to obtain the entropy generation rate change sequence. The change in the efficiency feature vector between adjacent sampling moments is calculated to obtain the efficiency feature change sequence. The entropy generation rate change sequence and the efficiency characteristic change sequence are discretized separately, dividing the continuous values ​​into multiple discrete intervals; the frequency distribution of each discrete interval is statistically analyzed, and the joint probability distribution and marginal probability distribution of the entropy generation rate change sequence and the efficiency characteristic change sequence are calculated; based on the joint probability distribution and marginal probability distribution, the mutual information value is calculated and used as the quantification result of the coupled evolution law.

4. The method for monitoring the status and providing early warning of anomalies of RF test equipment based on the Internet of Things as described in claim 3, characterized in that, Methods for identifying critical fluctuation characteristics during the transition from an efficient transport state to an energy dissipation state include: Define two typical operating states of RF test equipment: high-efficiency transmission state and energy dissipation state; For the operating point time series, calculate the fluctuation amplitude vector for each sampled operating point and combine them to form a fluctuation amplitude sequence; for the operating point time series, calculate the corresponding autocorrelation time vector; for the operating point time series, calculate the corresponding higher-order statistical features; normalize the fluctuation amplitude sequence, autocorrelation time vector, and higher-order statistical features respectively, and concatenate the normalized fluctuation amplitude sequence, autocorrelation time vector, and higher-order statistical features to form the critical fluctuation feature; Methods for constructing the phase space trajectory of RF link entropy evolution include: Define the RF link entropy evolution phase space, and take the current operating point as the state point in the RF link entropy evolution phase space; map each sampled operating point in the operating point time series to the RF link entropy evolution phase space in sequence to obtain the state point sequence in the RF link entropy evolution phase space; connect the state points corresponding to adjacent sampling times to form a continuous RF link entropy evolution phase space trajectory.

5. The method for monitoring the status and providing early warning of anomalies of RF test equipment based on the Internet of Things according to claim 4, characterized in that, Methods for defining the optimal operating point attraction domain and performance degradation escape boundary include: Based on the phase space trajectory of the RF link entropy evolution, determine the optimal operating point of the RF test equipment; calculate the Euclidean distance between all state points in the phase space trajectory of the RF link entropy evolution and the optimal operating point, and mark them as deviation distances; calculate the standard deviation of all deviation distances to obtain the deviation standard deviation; calculate the product of the deviation standard deviation and the preset attraction field coefficient to obtain the attraction field radius; construct the optimal operating point attraction field based on the optimal operating point and the attraction field radius. Based on the phase space trajectory of the RF link entropy evolution, calculate the trajectory feature descriptor; based on the trajectory feature descriptor and the critical fluctuation characteristics, calculate the escape boundary radius; with the optimal operating point as the center and the escape boundary radius as the radius, define the performance degradation escape boundary.

6. The method for monitoring the status and providing early warning of anomalies of RF test equipment based on the Internet of Things according to claim 5, characterized in that, Methods for calculating RF performance stability margin and deviation direction vector include: Obtain the current operating point of the RF test equipment, calculate the Euclidean distance between the current operating point and the optimal operating point, and mark it as the current deviation distance; calculate the RF performance stability margin based on the escape boundary radius and the current deviation distance; The current deviation distance is compared with the radius of the attraction domain to determine whether the current working point is located within the attraction domain of the optimal working point. If the current deviation distance is less than or equal to the radius of the attraction domain, the current working point is located within the attraction domain of the optimal working point, and the deviation direction vector is set to zero. If the current deviation distance is greater than the radius of the attraction domain, the vector difference between the current working point and the optimal working point is calculated to obtain the original deviation vector. The original deviation vector is then normalized to obtain the deviation direction vector.

7. The method for monitoring the status and providing early warning of anomalies of RF test equipment based on the Internet of Things according to claim 6, characterized in that, Methods for triggering anomaly warnings when the RF performance stability margin falls below an adaptive threshold include: Based on the current deviation distance, attraction domain radius, and escape boundary radius, the current state region of the RF test equipment is determined; the current state region includes a normal region, a sub-healthy region, and an abnormal region; a preset base threshold, critical sensitivity coefficient, and region coefficient set are established, with the region coefficient set including region coefficients corresponding to different current state regions; based on the current state region of the RF test equipment, the corresponding region coefficient is obtained from the region coefficient set and marked as the current coefficient; based on the critical fluctuation intensity index and the critical sensitivity coefficient, the critical sensitivity factor is calculated; the base threshold, the current coefficient, and the critical sensitivity factor are multiplied sequentially to obtain the adaptive threshold; The difference between the adaptive threshold and the RF performance stability margin is calculated to obtain the margin gap; the margin gap is compared with a preset set of level thresholds to determine the anomaly warning level; based on the anomaly warning level, warning information is generated, and anomaly warnings are triggered based on the warning information; wherein, the warning information includes the warning level, RF performance stability margin, adaptive threshold, and margin gap.

8. The method for monitoring the status and providing early warning of anomalies of RF test equipment based on the Internet of Things according to claim 7, characterized in that, Methods for determining the dominant trend of equipment deterioration include: Obtain the deviation direction vector. If the deviation direction vector is zero, there is no need to determine the dominant direction. If the deviation direction vector is not zero, take the absolute value of each component in the deviation direction vector and normalize it to obtain the absolute deviation vector. Compare the components in the absolute deviation vector, identify the component with the largest value, and mark it as the dominant component. If the dominant component is located before the absolute deviation vector... In each component, the dominant transformation direction is the entropy generation rate direction; if the dominant component is located after the absolute deviation vector... In each component, the direction of the main director's transformation is the direction of efficiency decline.

9. The method for monitoring the status and providing early warning of anomalies of RF test equipment based on the Internet of Things as described in claim 8, characterized in that, Methods for locating dominant energy dissipation nodes and impedance mismatch locations include: If the direction of the dominant director is the direction of entropy generation rate, then the node positioning strategy is adopted; if the direction of the dominant director is the direction of efficiency decrease, then the link positioning strategy is adopted. The node localization strategy is as follows: Construct a candidate set of dominant energy dissipation nodes and a set of high-fluctuation nodes, and obtain the intersection of the two sets. If the intersection is empty, the RF module ranked first in the candidate set of dominant energy dissipation nodes is selected as the dominant energy dissipation node. If the intersection is not empty, the RF module ranked first in the candidate set of dominant energy dissipation nodes is selected as the dominant energy dissipation node. Calculate the input and output reflection coefficients of the dominant energy dissipation node. If the input reflection coefficient is greater than a preset reflection coefficient threshold, the input port of the dominant energy dissipation node is marked as an impedance mismatch location. If the output reflection coefficient is greater than a preset reflection coefficient threshold, the output port of the dominant energy dissipation node is marked as an impedance mismatch location. The link location strategy process is as follows: calculate the path transmission efficiency of each transmission path in the RF link topology; calculate the efficiency drop of each transmission path based on the path transmission efficiency; select the transmission path with the largest efficiency drop as the efficiency bottleneck path; traverse each RF module on the efficiency bottleneck path, calculate the efficiency deviation of each RF module, and select the RF module with the largest efficiency deviation as the dominant energy dissipation node; use the same method as the node location strategy to determine the impedance mismatch location based on the dominant energy dissipation node.

10. The method for monitoring the status and providing early warning of anomalies of RF test equipment based on the Internet of Things according to claim 9, characterized in that, Methods for generating link tuning strategies include: Determine if there is an impedance mismatch location. If an impedance mismatch location exists, the tuning strategy type is impedance matching tuning; if there is no impedance mismatch location, the tuning strategy type is power optimization tuning. For impedance matching tuning types, an impedance matching tuning strategy is generated: if the impedance mismatch location is the input port of the dominant energy dissipation node, the impedance mismatch degree is calculated based on the input reflection coefficient; if the impedance mismatch location is the output port of the dominant energy dissipation node, the impedance mismatch degree is calculated based on the output reflection coefficient; the impedance mismatch degree is compared with a preset set of mismatch level thresholds to determine the impedance mismatch level; and a corresponding impedance matching tuning suggestion is generated based on the impedance mismatch level. For each power optimization tuning type, a power optimization tuning strategy is generated: based on the RF module corresponding to the dominant energy dissipation node, a corresponding power optimization tuning suggestion is generated, which determines the direction of power optimization; The tuning strategy type and tuning suggestion are integrated to generate the link tuning strategy.

Images